Publications
2023
Journal Articles
Alexandros Delitzas, Kyriakos C. Chatzidimitriou and Andreas L. Symeonidis
"Calista: A deep learning-based system for understanding and evaluating website aesthetics"
International Journal of Human-Computer Studies, 175, pp. 103019, 2023 Jan
   Website aesthetics play an important role in attracting users and customers, as well as in enhancing user experience. In this work, we propose a tool that performs automatic evaluation of website aesthetics using deep learning models that display high correlation to human perception. These models were developed using two different datasets. The first dataset was created by employing a rating-based ranking approach and contains user judgments on websites in the form of an explicit numerical value on a scale. Using the first dataset, we developed models following three different approaches and managed to outperform previous works. In addition, we created a new dataset by employing a comparison-based ranking approach, which is a more reliable dataset in the sense that it follows a more “natural” data collection method. In this case, users were asked to compare two websites at a time and choose which is more attractive. Data collection was performed via a web application especially designed and developed for this purpose. In the experiments conducted, we evaluated each model and compared the two data collection methods. This work aims to illustrate the effectiveness of deep learning as a solution to the problem as well as to highlight the importance of comparison-based ranking in order to achieve reliable results. In order to further promote our work, we also developed a tool that scores the aesthetics of a website, simply by providing the website URL. We argue that such a tool will serve as a reliable guide in the hands of designers and developers during the design process. @article{DELITZAS2023103019, | |
Themistoklis Diamantopoulos, Nikolaos Saoulidis and Andreas Symeonidis
"Automated Issue Assignment using Topic Modeling on Jira Issue Tracking Data"
IET Software, pp. 1-10, 2023 May
As more and more software teams use online issue tracking systems to collaborate on software projects, the accurate assignment of new issues to the most suitable contributors may have significant impact on the success of the project. As a result, several research efforts have been directed towards automating this process to save considerable time and effort. However, most approaches focus mainly on software bugs and employ models that do not sufficiently take into account the semantics and the non-textual metadata of issues and/or produce models that may require manual tuning. A methodology that extracts both textual and non-textual features from different types of issues is designed, providing a Jira dataset that involves not only bugs but also new features, issues related to documentation, patches, etc. Moreover, the semantics of issue text are effectively captured by employing a topic modelling technique that is optimised using the assignment result. Finally, this methodology aggregates probabilities from a set of individual models to provide the final assignment. Upon evaluating this approach in an automated issue assignment setting using a dataset of Jira issues, the authors conclude that it can be effective for automated issue assignment. @article{IETSoftware2023, | |
Eleni Poptsi, Despina Moraitou, Emmanouil Tsardoulias, Andreas L. Symeonidis, Vasileios Papaliagkas and Magdalini Tsolaki
"R4Alz-Revised: A Tool Able to Strongly Discriminate ‘Subjective Cognitive Decline’ from Healthy Cognition and ‘Minor Neurocognitive Disorder’"
Diagnostics, 13, (3), pp. 338, 2023 Jan
Background: The diagnosis of the minor neurocognitive diseases in the clinical course of dementia before the clinical symptoms’ appearance is the holy grail of neuropsychological research. The R4Alz battery is a novel and valid tool that was designed to assess cognitive control in people with minor cognitive disorders. The aim of the current study is the R4Alz battery’s extension (namely R4Alz-R), enhanced by the design and administration of extra episodic memory tasks, as well as extra cognitive control tasks, towards improving the overall R4Alz discriminant validity. Methods: The study comprised 80 people: (a) 20 Healthy adults (HC), (b) 29 people with Subjective Cognitive Decline (SCD), and (c) 31 people with Mild Cognitive Impairment (MCI). The groups differed in age and educational level. Results: Updating, inhibition, attention switching, and cognitive flexibility tasks discriminated SCD from HC (p ≤ 0.003). Updating, switching, cognitive flexibility, and episodic memory tasks discriminated SCD from MCI (p ≤ 0.001). All the R4Alz-R’s tasks discriminated HC from MCI (p ≤ 0.001). The R4Alz-R was free of age and educational level effects. The battery discriminated perfectly SCD from HC and HC from MCI (100% sensitivity—95% specificity and 100% sensitivity—90% specificity, respectively), whilst it discriminated excellently SCD from MCI (90.3% sensitivity—82.8% specificity). Conclusion: SCD seems to be stage a of neurodegeneration since it can be objectively evaluated via the R4Alz-R battery, which seems to be a useful tool for early diagnosis. @article{r4alzR, |
2022
Journal Articles
Konstantinos Panayiotou, Emmanouil Tsardoulias and Andreas L. Symeonidis
"Commlib: An easy-to-use communication library for Cyber–Physical Systems"
SoftwareX, 2022 Jul
Communication and data exchange between objects is a fundamental aspect of Cyber–Physical Systems. Due to the highly distributed nature of the domain, physical and virtual objects rely on the Sense-Think-Act-Communicate model in order to provide remote interfaces for sending and receiving sensor data and actuation commands and for interconnecting processing artifacts with sensing and actuation endpoints. In order to build such interfaces, thing/object specifications must be taken into account in order to write/adapt/use their drivers and ensure appropriate connectivity; this approach is, at least cumbersome and requires hardware engineering expertise. In this paper we present Commlib, a Python library that abstracts low-level protocol-specific properties and specifications and provides a high-level API for creating and managing communication interfaces of distributed nodes over asynchronous message-driven and event-driven communication middleware, such as MQTT, AMQP, Kafka and Redis brokers. Our approach follows the Component-Port-Connector paradigm to model interconnection and intercommunication of distributed nodes via input and output ports from where messages are transferred over open connections between nodes. Commlib is easy-to-use and enables rapid development of Cyber–Physical Systems and applications, allowing users to focus on the envisioned functionality rather than the obvious connectivity/compatibility issues residing in such systems. @article{commlib, | |
Alexandros Filotheou, Anastasios Tzitzis, Emmanouil Tsardoulias, Antonis Dimitriou, Andreas Symeonidis and George Sergiadis & Loukas Petrou
"Passive Global Localisation of Mobile Robot via 2D Fourier-Mellin Invariant Matching"
Journal of Intelligent & Robotic Systems, 26, 2022 Jan
Passive global localisation is defined as locating a robot on a map, under global pose uncertainty, without prescribing motion controls. The majority of current solutions either assume structured environments or require tuning of parameters relevant to establishing correspondences between sensor measurements and segments of the map. This article advocates for a solution that dispenses with both in order to achieve greater portability and universality across disparate static environments. A single 2D panoramic LIght Detection And Ranging (LIDAR) sensor is used as the measurement device, this way reducing computational and investment costs. The proposed method disperses pose hypotheses on the map of the robot’s environment and then captures virtual scans from each of them. Subsequently, each virtual scan is matched against the one derived from the physical sensor. Angular alignment is performed via 2D Fourier-Mellin Invariant (FMI) matching; positional alignment is performed via feedback of the position estimation error. In order to deduce the robot’s pose the method sifts through hypotheses by using measures extracted from FMI. Simulations and experiments illustrate the efficacy of the proposed global localisation solution in realistic surroundings and scenarios. In addition, the proposed method is pitted against the most effective Iterative Closest Point (ICP) variant under the same task, and three conclusions are drawn. The first is that the proposed method is effective in both structured and unstructured environments. The second is that it concludes to fewer false positives. The third is that the two methods are largely equivalent in terms of pose error. @article{filotheou2022Fourier, | |
Panagiotis Antoniadis and Emmanouil Tsardoulias & Andreas Symeonidis
"A mechanism for personalized Automatic Speech Recognition for less frequently spoken languages: the Greek case"
Multimedia Tools and Applications, 2022 May
Automatic Speech Recognition (ASR) has become increasingly popular since it significantly simplifies human-computer interaction, providing a more intuitive way of communication. Building an accurate, general-purpose ASR system is a challenging task that requires a lot of data and computing power. Especially for languages not widely spoken, such as Greek, the lack of adequately large speech datasets leads to the development of ASR systems adapted to a restricted corpus and/or for specific topics. When used in specific domains, these systems can be both accurate and fast, without the need for large datasets and extended training. An interesting application domain of such narrow-scope ASR systems is the development of personalized models that can be used for dictation. In the current work we present three personalization-via-adaptation modules, that can be integrated into any ASR/dictation system and increase its accuracy. The adaptation can be applied both on the language model (based on past text samples of the user) as well as on the acoustic model (using a set of user’s narrations). To provide more precise recommendations, clustering algorithms are applied and topic-specific language models are created. Also, heterogeneous adaptation methods are combined to provide recommendations to the user. Evaluation performed on a self-created database containing 746 corpora included in messaging applications and e-mails from the same user, demonstrates that the proposed approach can achieve better results than the vanilla existing Greek models. @article{gsoc19antoniadis, | |
Nikolaos Malamas, Konstantinos Papangelou and Andreas L. Symeonidis
"Upon Improving the Performance of Localized Healthcare Virtual Assistants"
Healthcare, 10, (1), 2022 Jan
Virtual assistants are becoming popular in a variety of domains, responsible for automating repetitive tasks or allowing users to seamlessly access useful information. With the advances in Machine Learning and Natural Language Processing, there has been an increasing interest in applying such assistants in new areas and with new capabilities. In particular, their application in e-healthcare is becoming attractive and is driven by the need to access medically-related knowledge, as well as providing first-level assistance in an efficient manner. In such types of virtual assistants, localization is of utmost importance, since the general population (especially the aging population) is not familiar with the needed “healthcare vocabulary” to communicate facts properly; and state-of-practice proves relatively poor in performance when it comes to specialized virtual assistants for less frequently spoken languages. In this context, we present a Greek ML-based virtual assistant specifically designed to address some commonly occurring tasks in the healthcare domain, such as doctor’s appointments or distress (panic situations) management. We build on top of an existing open-source framework, discuss the necessary modifications needed to address the language-specific characteristics and evaluate various combinations of word embeddings and machine learning models to enhance the assistant’s behaviour. Results show that we are able to build an efficient Greek-speaking virtual assistant to support e-healthcare, while the NLP pipeline proposed can be applied in other (less frequently spoken) languages, without loss of generality. @article{malamas-healthcare, | |
Panayiotou, Konstantinos, Emmanouil Tsardoulias, Christoforos Zolotas, Andreas L. Symeonidis, and Loukas Petrou
"A Framework for Rapid Robotic Application Development for Citizen Developers"
Software, 1, (1), pp. 53-79, 2022 Mar
It is common knowledge among computer scientists and software engineers that ”building robotics systems is hard”: it includes applied and specialized knowledge from various scientific fields, such as mechanical, electrical and computer engineering, computer science and physics, among others. To expedite the development of robots, a significant number of robotics-oriented middleware solutions and frameworks exist that provide high-level functionality for the implementation of the in-robot software stack, such as ready-to-use algorithms and sensor/actuator drivers. While the aforementioned focus is on the implementation of the core functionalities and control layer of robots, these specialized tools still require extensive training, while not providing the envisaged freedom in design choices. In this paper, we discuss most of the robotics software development methodologies and frameworks, analyze the way robotics applications are built and propose a new resource-oriented architecture towards the rapid development of robot-agnostic applications. The contribution of our work is a methodology and a model-based middleware that can be used to provide remote robot-agnostic interfaces. Such interfaces may support robotics application development from citizen developers by reducing hand-coding and technical knowledge requirements. This way, non-robotics experts will be able to integrate and use robotics in a wide range of application domains, such as healthcare, home assistance, home automation and cyber–physical systems in general. @article{r4aarchitecture, | |
Konstantinos Strantzalis, Fotios Gioulekas, Panagiotis Katsaros and Andreas L. Symeonidis
"Operational State Recognition of a DC Motor Using Edge Artificial Intelligence"
Sensors, 22, (24), 2022 Dec
@article{s22249658, |
2021
Journal Articles
Maria Th. Kotouza, Alexandros-Charalampos Kyprianidis, Sotirios-Filippos Tsarouchis, Antonios C. Chrysopoulos and Pericles A. Mitkas
"Science4Fashion: an end-to-end decision support system for fashion designers"
Evolving Systems, 2021 Mar
Nowadays, the fashion clothing industry is moving towards “fast” fashion, offering a wide variety of products based on different patterns and styles, usually characterized by lower costs and ambiguous quality. The retails markets are trying to present regularly new fashion collections while trying to follow the latest fashion trends at the same time. The main reason is to remain competitive and keep up with ever-changing customer demands. Fashion designers draw inspiration from social media, e-shops, and fashion shows that set the new fashion trends. In this direction, we propose Science4Fashion, an AI end-to-end system that facilitates fashion designers by collecting and analyzing data from many different sources and suggesting products according to their needs. An overview of the system’s modules is presented, emphasizing data collection, data annotation using deep learning models, and product recommendation and user feedback processes. The experiments presented in this paper are twofold: (a) experiments regarding the evaluation of clothing attribute classification, and (b) experiments regarding product recommendation using the baseline kNN enriched by the frequency-based clustering algorithm (FBC), achieving promising results. @article{Kotouza2021, | |
Emmanouil Krasanakis and Andreas L. Symeonidis
"Defining behaviorizeable relations to enable inference in semi-automatic program synthesis"
Journal of Logical and Algebraic Methods in Programming, 123, pp. 100714, 2021 Nov
@article{krasanakis2021defining, | |
Nikolaos Malamas and Andreas Symeonidis
"Embedding Rasa in edge Devices: Capabilities and Limitations"
Procedia Computer Science, 192, pp. 109-118, 2021 Jan
Over the past few years, there has been a boost in the use of commercial virtual assistants. Obviously, these proprietary tools are well-performing, however the functionality they offer is limited, users are ”vendor-locked”, while possible user privacy issues rise. In this paper we argue that low-cost, open hardware solutions may also perform well, given the proper setup. Specifically, we perform an initial assessment of a low-cost virtual agent employing the Rasa framework integrated into a Raspberry Pi 4. We set up three different architectures, discuss their capabilities and limitations and evaluate the dialogue system against three axes: assistant comprehension, task success and assistant usability. Our experiments show that our low-cost virtual assistant performs in a satisfactory manner, even when a small-sized training dataset is used. @article{malamas2021-rasa, | |
Michail D. Papamichail and Andreas L. Symeonidis
"Data-Driven Analytics towards Software Sustainability: The Case of Open-Source Multimedia Tools on Cultural Storytelling"
Sustainability, 13, (3), pp. 1079, 2021 Jan
@article{papamichail2021data, | |
Thomas Karanikiotis, Michail D. Papamichail and Andreas L. Symeonidis
"Analyzing Static Analysis Metric Trends towards Early Identification of Non-Maintainable Software Components"
Sustainability, 13, (22), 2021 Nov
Nowadays, agile software development is considered a mainstream approach for software with fast release cycles and frequent changes in requirements. Most of the time, high velocity in software development implies poor software quality, especially when it comes to maintainability. In this work, we argue that ensuring the maintainability of a software component is not the result of a one-time only (or few-times only) set of fixes that eliminate technical debt, but the result of a continuous process across the software’s life cycle. We propose a maintainability evaluation methodology, where data residing in code hosting platforms are being used in order to identify non-maintainable software classes. Upon detecting classes that have been dropped from their project, we examine the progressing behavior of their static analysis metrics and evaluate maintainability upon the four primary source code properties: complexity, cohesion, inheritance and coupling. The evaluation of our methodology upon various axes, both qualitative and quantitative, indicates that our approach can provide actionable and interpretable maintainability evaluation at class level and identify non-maintainable components around 50% ahead of the software life cycle. Based on these results, we argue that the progressing behavior of static analysis metrics at a class level can provide valuable information about the maintainability degree of the component in time. @article{su132212848, | |
Nikolaos L. Tsakiridis, John B. Theocharis, Andreas L. Symeonidis and G.C. Zalidis
"Improving the predictions of soil properties from VNIR–SWIR spectra in an unlabeled region using semi-supervised and active learning"
Geoderma, 2021 Apr
Monitoring the status of the soil ecosystem to identify the spatio-temporal extent of the pressures exerted and mitigate the effects of climate change and land degradation necessitates the need for reliable and cost-effective solutions. To address this need, soil spectroscopy in the visible, near- and shortwave-infrared (VNIR–SWIR) has emerged as a viable alternative to traditional analytical approaches. To this end, large-scale soil spectral libraries coupled with advanced machine learning tools have been developed to infer the soil properties from the hyperspectral signatures. However, models developed from one region may exhibit diminished performance when applied to a new, unseen by the model, region due to the large and inherent soil variability (e.g. pedogenetical differences, diverse soil types etc.). Given an existing spectral library with labeled data and a new unlabeled region (i.e. where no soil samples are analytically measured) the question then becomes how to best develop a model which can more accurately predict the soil properties of the unlabeled region. In this paper, a machine learning technique leveraging on the capabilities of semi-supervised learning which exploits the predictors’ distribution of the unlabeled dataset and of active learning which expertly selects a small set of data from the unlabeled dataset as a spiking subset in order to develop a more robust model is proposed. The semi-supervised learning approach is the Laplacian Support Vector Regression following the manifold regularization framework. As far as the active learning component is concerned, the pool-based approach is utilized as it best matches with the aforementioned use-case scenario, which iteratively selects a subset of data from the unlabeled region to spike the calibration set. As a query strategy, a novel machine learning–based strategy is proposed herein to best identify the spiking subset at each iteration. The experimental analysis was conducted using data from the Land Use and Coverage Area Frame Survey of 2009 which covered most of the then member-states of the European Union, and in particular by focusing on the mineral cropland soil samples from 5 different countries. The statistical analysis conducted ascertained the efficacy of our approach when compared to the current state-of-the-art in soil spectroscopy. @article{TSAKIRIDIS2021114830, |
2020
Journal Articles
Alexandros Filotheou, Emmanouil Tsardoulias, Antonis Dimitriou, Andreas Symeonidis and Loukas Petrou
"Pose Selection and Feedback Methods in Tandem Combinations of Particle Filters with Scan-Matching for 2D Mobile Robot Localisation"
Journal of Intelligent & Robotic Systems, 100, pp. 925-944, 2020 Sep
Robot localisation is predominantly resolved via parametric or non-parametric probabilistic methods. The particle filter, the most common non-parametric approach, is a Monte Carlo Localisation (MCL) method that is extensively used in robot localisation, as it can represent arbitrary probabilistic distributions, in contrast to Kalman filters, which is the standard parametric representation. In particle filters, a weight is internally assigned to each particle, and this weight serves as an indicator of a particle’s estimation certainty. Their output, the tracked object’s pose estimate, is implicitly assumed to be the weighted average pose of all particles; however, we argue that disregarding low-weight particles from this averaging process may yield an increase in accuracy. Furthermore, we argue that scan-matching, treated as a prosthesis of (or, put differently, fit in tandem with) a particle filter, can also lead to better accuracy. Moreover, we study the effect of feeding back this improved estimate to MCL, and introduce a feedback method that outperforms current state-of-the-art feedback approaches in accuracy and robustness, while alleviating their drawbacks. In the process of formulating these hypotheses we construct a localisation pipeline that admits configurations that are a superset of state-of-the-art configurations of tandem combinations of particle filters with scan-matching. The above hypotheses are tested in two simulated environments and results support our argumentation. @article{alexPoseSelection2020, | |
D. Geromichalos, M.Azkarate, E. Tsardoulias, L. Gerdes, L. Petrou and C. Perez Del Pulgar
Journal of Field Robotics, pp. 1-18, 2020 Feb
This paper describes a novel approach to simultaneous localization and mapping (SLAM) techniques applied to the autonomous planetary rover exploration scenario to reduce both the relative and absolute localization errors, using two well‐proven techniques: particle filters and scan matching. Continuous relative localization is improved by matching high‐resolution sensor scans to the online created local map. Additionally, to avoid issues with drifting localization, absolute localization is globally corrected at discrete times, according to predefined event criteria, by matching the current local map to the orbiter's global map. The resolutions of local and global maps can be appropriately chosen for computation and accuracy purposes. Further, the online generated local map, of the form of a structured elevation grid map, can also be used to evaluate the traversability of the surrounding environment and allow for continuous navigation. The objective of this study is to support long‐range low‐supervision planetary exploration. The implemented SLAM technique has been validated with a data set acquired during a field test campaign performed at the Teide Volcano on the island of Tenerife, representative of a Mars/Moon exploration scenario. @article{etsardouEsa2020, | |
A. Tzitzis, S. Megalou, S. Siachalou, E. Tsardoulias, A. Filotheou, T. Yioultsis, and A. G. Dimitriou
IEEE Journal of Radio Frequency Identification, 2020 Jun
In this work, we present a method for 3D localization of RFID tags by a reader-equipped robot with a single antenna. The robot carries a set of sensors, which enable it to create a map of the environment and locate itself in it (Simultaneous Localization and Mapping -SLAM). Then we exploit the collected phase measurements to localize large tag populations in real-time. We show that by forcing the robot to move along non-straight trajectories, thus creating non-linear synthetic apertures, the circular ambiguity of the possible tag’s locations is eliminated and 3D localization is accomplished. A reliability metric is introduced, suitable for real-time assessment of the localization error. We investigate how the curvature of the robot’s trajectory affects the accuracy under varying multipath conditions. It is found that increasing the trajectory’s slope and number of turns improves the accuracy of the method. We introduce a phase model that accounts for the effects of multipath and derive the closed form expression of the resultant’s phase probability density function. Finally, the proposed method is extended when multiple antennas are available. Experimental results in a "multipath-rich" indoor environment demonstrate a mean 3D error of 35cm, achieved in a few seconds. @article{etsardouRfid22020, | |
Michail D. Papamichail and Andreas L. Symeonidis
"A Generic Methodology for Early Identification of Non-Maintainable Source Code Components through Analysis of Software Releases"
Information and Software Technology, 118, pp. 106218, 2020 Feb
Contemporary development approaches consider that time-to-market is of utmost importance and assume that software projects are constantly evolving, driven by the continuously changing requirements of end-users. This practically requires an iterative process where software is changing by introducing new or updating existing software/user features, while at the same time continuing to support the stable ones. In order to ensure efficient software evolution, the need to produce maintainable software is evident. In this work, we argue that non-maintainable software is not the outcome of a single change, but the consequence of a series of changes throughout the development lifecycle. To that end, we define a maintainability evaluation methodology across releases and employ various information residing in software repositories, so as to decide on the maintainability of software. Upon using the dropping of packages as a non-maintainability indicator (accompanied by a series of quality-related criteria), the proposed methodology involves using one-class-classification techniques for evaluating maintainability at a package level, on four different axes each targeting a primary source code property: complexity, cohesion, coupling, and inheritance. Given the qualitative and quantitative evaluation of our methodology, we argue that apart from providing accurate and interpretable maintainability evaluation at package level, we can also identify non-maintainable components at an early stage. This early stage is in many cases around 50% of the software package lifecycle. Based on our findings, we conclude that modeling the trending behavior of certain static analysis metrics enables the effective identification of non-maintainable software components and thus can be a valuable tool for the software engineers. @article{ISTmaintainabilityPaper, | |
Evridiki Papachristou, Antonios Chrysopoulos and Nikolaos Bilalis
"Machine learning for clothing manufacture as a mean to respond quicker and better to the demands of clothing brands: a Greek case study"
The International Journal of Advanced Manufacturing Technology, 2020 Oct
In the clothing industry, design, development and procurement teams have been affected more than any other industry and are constantly being under pressure to present more products with fewer resources in a shorter time. The diversity of garment designs created as new products is not found in any other industry and is almost independent of the size of the business. The proposed research is being applied to a Greek clothing manufacturing company with operations in two different countries and a portfolio of diverse brands and moves in two dimensions: The first dimension concerns the perfect transformation of the product design field into a field of action planning that can be supported by artificial intelligence, providing timely and valid information to the designer drawing information from a wider range of sources than today’s method. The second dimension of the research concerns the design and implementation of an intelligent and semi-autonomous decision support system for everyone involved in the sample room. This system utilizes various machine learning techniques in order to become a versatile, robust and useful “assistant”: multiple clustering and classification models are utilized for grouping and combining similar/relevant products, Computer Vision state-of-the-art algorithms are extracting meaningful attributes from images and, finally, a reinforcement learning system is used to evolve the existing models based on user’s preferences. @article{Papachristou2020, | |
Eleni Poptsi, Despina Moraitou, Emmanouil Tsardoulias, Andreas L. Symeonidis and Magda Tsolaki
"Is the Discrimination of Subjective Cognitive Decline from Cognitively Healthy Adulthood and Mild Cognitive Impairment Possible? A Pilot Study Utilizing the R4Alz Battery"
Journal of Alzheimers Disease, 77, pp. 715-732, 2020 Sep
Background: The early diagnosis of neurocognitive disorders before the symptoms' onset is the ultimate goal of the scientific community. REMEDES for Alzheimer (R4Alz) is a battery, designed for assessing cognitive control abilities in people with minor and major neurocognitive disorders. Objective: To investigate whether the R4Alz battery's tasks differentiate subjective cognitive decline (SCD) from cognitively healthy adults (CHA) and mild cognitive impairment (MCI). Methods: The R4Alz battery was administered to 175 Greek adults, categorized in five groups a) healthy young adults (HYA; n = 42), b) healthy middle-aged adults (HMaA; n = 33), c) healthy older adults (HOA; n = 14), d) community-dwelling older adults with SCD (n = 34), and e) people with MCI (n = 52). Results: Between the seven R4Alz subtasks, four showcased the best results for differentiating HOA from SCD: the working memory updating (WMCUT-S3), the inhibition and switching subtask (ICT/RST-S1&S2), the failure sets (FS) of the ICT/RST-S1&S2, and the cognitive flexibility subtask (ICT/RST-S3). The total score of the four R4Alz subtasks (R4AlzTot4) leads to an excellent discrimination among SCD and healthy adulthood, and to fare discrimination among SCD and MCI. Conclusion: The R4Alz battery is a novel approach regarding the neuropsychological assessment of people with SCD, since it can very well assist toward discriminating SCD from HOA. The R4Alz is able to measure decline of specific cognitive control abilities - namely of working memory updating, and complex executive functions - which seem to be the neuropsychological substrate of cognitive complaints in community dwelling adults of advancing age. @article{poptsiJad2020, |
2019
Journal Articles
Alexandros Filotheou, Emmanouil Tsardoulias, Antonis Dimitriou, Andreas Symeonidis and Loukas Petrou
"Quantitative and Qualitative Evaluation of ROS-Enabled Local and Global Planners in 2D Static Environments"
Journal of Intelligent & Robotic Systems, 2019 Oct
Apart from perception, one of the most fundamental aspects of an autonomous mobile robot is the ability to adequately and safely traverse the environment it operates in. This ability is called Navigation and is performed in a two- or three-dimensional fashion, except for cases where the robot is neither a ground vehicle nor articulated (e.g. robotics arms). The planning part of navigation comprises a global planner, suitable for generating a path from an initial to a target pose, and a local planner tasked with traversing the aforementioned path while dealing with environmental, sensorial and motion uncertainties. However, the task of selecting the optimal global and/or local planner combination is quite hard since no research provides insight on which is best regarding the domain and planner limitations. In this context, current work performs a comparative analysis on qualitative and quantitative aspects of the most common ROS-enabled global and local planners for robots operating in two-dimensional static environments, on the basis of mission-centered and planner-related metrics, optimality and traversability aspects, as well as non-measurable aspects, such as documentation quality, parameterisability, ease of use, etc. @article{Filotheou2019, | |
Emmanouil Krasanakis, Emmanouil Schinas, Symeon Papadopoulos, Yiannis Kompatsiaris and Andreas Symeonidis
Information Processing & Management, pp. 102053, 2019 Jun
Local community detection is an emerging topic in network analysis that aims to detect well-connected communities encompassing sets of priorly known seed nodes. In this work, we explore the similar problem of ranking network nodes based on their relevance to the communities characterized by seed nodes. However, seed nodes may not be central enough or sufficiently many to produce high quality ranks. To solve this problem, we introduce a methodology we call seed oversampling, which first runs a node ranking algorithm to discover more nodes that belong to the community and then reruns the same ranking algorithm for the new seed nodes. We formally discuss why this process improves the quality of calculated community ranks if the original set of seed nodes is small and introduce a boosting scheme that iteratively repeats seed oversampling to further improve rank quality when certain ranking algorithm properties are met. Finally, we demonstrate the effectiveness of our methods in improving community relevance ranks given only a few random seed nodes of real-world network communities. In our experiments, boosted and simple seed oversampling yielded better rank quality than the previous neighborhood inflation heuristic, which adds the neighborhoods of original seed nodes to seeds. @article{KRASANAKIS2019102053, | |
Michail Papamichail, Kyriakos Chatzidimitriou, Thomas Karanikiotis, Napoleon-Christos Oikonomou, Andreas Symeonidis and Sashi Saripalle
"BrainRun: A Behavioral Biometrics Dataset towards Continuous Implicit Authentication"
Data, 4, (2), 2019 May
The widespread use of smartphones has dictated a new paradigm, where mobile applications are the primary channel for dealing with day-to-day tasks. This paradigm is full of sensitive information, making security of utmost importance. To that end, and given the traditional authentication techniques (passwords and/or unlock patterns) which have become ineffective, several research efforts are targeted towards biometrics security, while more advanced techniques are considering continuous implicit authentication on the basis of behavioral biometrics. However, most studies in this direction are performed “in vitro” resulting in small-scale experimentation. In this context, and in an effort to create a solid information basis upon which continuous authentication models can be built, we employ the real-world application “BrainRun”, a brain-training game aiming at boosting cognitive skills of individuals. BrainRun embeds a gestures capturing tool, so that the different types of gestures that describe the swiping behavior of users are recorded and thus can be modeled. Upon releasing the application at both the “Google Play Store” and “Apple App Store”, we construct a dataset containing gestures and sensors data for more than 2000 different users and devices. The dataset is distributed under the CC0 license and can be found at the EU Zenodo repository. @article{Papamichail2019, | |
Michail D. Papamichail, Themistoklis Diamantopoulos and Andreas L. Symeonidis
"Software Reusability Dataset based on Static Analysis Metrics and Reuse Rate Information"
Data in Brief, 2019 Dec
The widely adopted component-based development paradigm considers the reuse of proper software components as a primary criterion for successful software development. As a result, various research efforts are directed towards evaluating the extent to which a software component is reusable. Prior efforts follow expert-based approaches, however the continuously increasing open-source software initiative allows the introduction of data-driven alternatives. In this context we have generated a dataset that harnesses information residing in online code hosting facilities and introduces the actual reuse rate of software components as a measure of their reusability. To do so, we have analyzed the most popular projects included in the maven registry and have computed a large number of static analysis metrics at both class and package levels using SourceMeter tool [2] that quantify six major source code properties: complexity, cohesion, coupling, inheritance, documentation and size. For these projects we additionally computed their reuse rate using our self-developed code search engine, AGORA [5]. The generated dataset contains analysis information regarding more than 24,000 classes and 2,000 packages, and can, thus, be used as the information basis towards the design and development of data-driven reusability evaluation methodologies. The dataset is related to the research article entitled "Measuring the Reusability of Software Components using Static Analysis Metrics and Reuse Rate Information @article{PAPAMICHAIL2019104687, | |
Michail D. Papamichail , Themistoklis Diamantopoulos and Andreas L. Symeonidis
Journal of Systems and Software, pp. 110423, 2019 Sep
Nowadays, the continuously evolving open-source community and the increasing demands of end users are forming a new software development paradigm; developers rely more on reusing components from online sources to minimize the time and cost of software development. An important challenge in this context is to evaluate the degree to which a software component is suitable for reuse, i.e. its reusability. Contemporary approaches assess reusability using static analysis metrics by relying on the help of experts, who usually set metric thresholds or provide ground truth values so that estimation models are built. However, even when expert help is available, it may still be subjective or case-specific. In this work, we refrain from expert-based solutions and employ the actual reuse rate of source code components as ground truth for building a reusability estimation model. We initially build a benchmark dataset, harnessing the power of online repositories to determine the number of reuse occurrences for each component in the dataset. Subsequently, we build a model based on static analysis metrics to assess reusability from five different properties: complexity, cohesion, coupling, inheritance, documentation and size. The evaluation of our methodology indicates that our system can effectively assess reusability as perceived by developers. @article{PAPAMICHAIL2019110423, | |
Eleni Poptsi, Emmanouil Tsardoulias, Despina Moraitou, Andreas Symeonidis and Magda Tsolaki
Journal of Alzheimer's Disease, pp. 1-19, 2019 Oct
Background:Subjective cognitive decline (SCD) and mild cognitive impairment (MCI) are acknowledged stages of the clinical spectrum of Alzheimer’s disease (AD), and cognitive control seems to be among the first neuropsychological predictors of cognitive decline. Existing tests are usually affected by educational level, linguistic abilities, cultural differences, and social status, constituting them error-prone when differentiating between the aforementioned stages. Creating robust neuropsychological tests is therefore prominent. Objective:The design of a novel psychometric battery for the cognitive control and attention assessment, free of demographic effects, capable to discriminate cognitively healthy aging, SCD, MCI, and mild Dementia (mD). Methods:The battery initial hypothesis was tuned using iterations of administration on random sampling healthy older adults and people with SCD, MCI, and mD, from the area of Thessaloniki, Greece. This resulted in the first release of the REflexes MEasurement DEviceS for Alzheimer battery (REMEDES for Alzheimer-R4Alz). Results:The first release lasts for almost an hour. The battery was design to assess working memory (WM) including WM storage, processing, and updating, enriched by episodic buffer recruitment. It was also designed to assess attention control abilities comprising selective, sustained, and divided attention subtasks. Finally, it comprises an inhibitory control, a task/rule switching or set-shifting, and a cognitive flexibility subtask as a combination of inhibition and task/rule switching abilities. Conclusion:The R4Alz battery is an easy to use psychometric battery with increasing difficulty levels and assumingly ecological validity, being entertaining for older adults, potentially free of demographic effects, and promising as a more accurate and early diagnosis tool of neurodegeneration. @article{poptsi2019remedes, | |
Emmanouil G. Tsardoulias, M. Protopapas, Andreas L. Symeonidis and Loukas Petrou
Journal of Intelligent & Robotic Systems, 2019 Jul
The alignment of two occupancy grid maps generated by SLAM algorithms is a quite researched problem, being an obligatory step either for unsupervised map merging techniques or for evaluation of OGMs (Occupancy Grid Maps) against a blueprint of the environment. This paper provides an overview of the existing automatic alignment techniques of two occupancy grid maps that employ pattern matching. Additionally, an alignment pipeline using local features and image descriptors is implemented, as well as a method to eliminate erroneous correspondences, aiming at producing the correct transformation between the two maps. Finally, map quality metrics are proposed and utilized, in order to quantify the produced map’s correctness. A comparative analysis was performed over a number of image processing and OGM-oriented detectors and descriptors, in order to identify the best combinations for the map evaluation problem, performed between two OGMs or between an OGM and a Blueprint map. @article{Tsardoulias2019, | |
Anastasios Tzitzis, Spyros Megalou, Stavroula Siachalou, Emmanouil Tsardoulias, Athanasios Kehagias, Traianos Yioultsis and Antonis Dimitriou
"Localization of RFID Tags by a Moving Robot, via Phase Unwrapping and Non-Linear Optimization"
IEEE Journal of Radio Frequency Identification, 3, (4), pp. 216 - 226, 2019 Aug
In this paper, we propose a new method for the localization of RFID tags, by deploying off-the-shelf RFID equipment on a robotic platform. The constructed robot is capable to perform Simultaneous Localization (of its own position) and Mapping (SLAM) of the environment and then locate the RFID tags around its path. The proposed method is based on properly treating the measured phase of the backscattered signal by each tag at the reader’s antenna, located on top of the robot. More specifically, the measured phase samples are reconstructed, such that the $2\pi $ discontinuities are eliminated (phase-unwrapping). This allows for the formation of an optimization problem, which can be solved rapidly by standard methods. The proposed method is experimentally compared against the SAR/imaging methods, which represent the accuracy benchmark in prior-art, deploying off-the-shelf equipment. It is shown that the proposed method solves exactly the same problem as holographic-imaging methods, overcoming the grid-density constraints of the latter. Furthermore, the problem, being calculations-grid-independent, is solved orders of magnitude faster, allowing for the applicability of the method in real-time inventorying and localization. It is also shown that the state-of-the-art SLAM method, which is used for the estimation of the trace of the robot, also suffers from errors, which directly affect the accuracy of the RFID localization method. Deployment of reference RFID tags at known positions, seems to significantly reduce such errors. @article{tzitzis2019localization, |
2018
Journal Articles
Christoforos Zolotas, Kyriakos C. Chatzidimitriou and Andreas L. Symeonidis
"RESTsec: a low-code platform for generating secure by design enterprise services"
Enterprise Information Systems, pp. 1-27, 2018 Mar
In the modern business world it is increasingly often that Enterprises opt to bring their business model online, in their effort to reach out to more end users and increase their customer base. While transitioning to the new model, enterprises consider securing their data of pivotal importance. In fact, many efforts have been introduced to automate this ‘webification’ process; however, they all fall short in some aspect: a) they either generate only the security infrastructure, assigning implementation to the developers, b) they embed mainstream, less powerful authorisation schemes, or c) they disregard the merits of the dominating REST architecture and adopt less suitable approaches. In this paper we present RESTsec, a Low-Code platform that supports rapid security requirements modelling for Enterprise Services, abiding by the state of the art ABAC authorisation scheme. RESTsec enables the developer to seamlessly embed the desired access control policy and generate the service, the security infrastructure and the code. Evaluation shows that our approach is valid and can help developers deliver secure by design enterprise services in a rapid and automated manner. @article{2018Zolotas, | |
George Mamalakis, Christos Diou, Andreas L. Symeonidis and Leonidas Georgiadis
"Of daemons and men: reducing false positive rate in intrusion detection systems with file system footprint analysis"
Neural Computing and Applications, 2018 May
In this work, we propose a methodology for reducing false alarms in file system intrusion detection systems, by taking into account the daemon’s file system footprint. More specifically, we experimentally show that sequences of outliers can serve as a distinguishing characteristic between true and false positives, and we show how analysing sequences of outliers can lead to lower false positive rates, while maintaining high detection rates. Based on this analysis, we developed an anomaly detection filter that learns outlier sequences using k-nearest neighbours with normalised longest common subsequence. Outlier sequences are then used as a filter to reduce false positives on the FI2DS file system intrusion detection system. This filter is evaluated on both overlapping and non-overlapping sequences of outliers. In both cases, experiments performed on three real-world web servers and a honeynet show that our approach achieves significant false positive reduction rates (up to 50 times), without any degradation of the corresponding true positive detection rates. @article{Mamalakis2018, |
2017
Journal Articles
Themistoklis Diamantopoulos, Michael Roth, Andreas Symeonidis and Ewan Klein
"Software requirements as an application domain for natural language processing"
Language Resources and Evaluation, pp. 1-30, 2017 Feb
Mapping functional requirements first to specifications and then to code is one of the most challenging tasks in software development. Since requirements are commonly written in natural language, they can be prone to ambiguity, incompleteness and inconsistency. Structured semantic representations allow requirements to be translated to formal models, which can be used to detect problems at an early stage of the development process through validation. Storing and querying such models can also facilitate software reuse. Several approaches constrain the input format of requirements to produce specifications, however they usually require considerable human effort in order to adopt domain-specific heuristics and/or controlled languages. We propose a mechanism that automates the mapping of requirements to formal representations using semantic role labeling. We describe the first publicly available dataset for this task, employ a hierarchical framework that allows requirements concepts to be annotated, and discuss how semantic role labeling can be adapted for parsing software requirements. @article{Diamantopoulos2017, | |
Themistoklis Diamantopoulos and Andreas Symeonidis
Enterprise Information Systems, pp. 1-22, 2017 Dec
Enhancing the requirements elicitation process has always been of added value to software engineers, since it expedites the software lifecycle and reduces errors in the conceptualization phase of software products. The challenge posed to the research community is to construct formal models that are capable of storing requirements from multimodal formats (text and UML diagrams) and promote easy requirements reuse, while at the same time being traceable to allow full control of the system design, as well as comprehensible to software engineers and end users. In this work, we present an approach that enhances requirements reuse while capturing the static (functional requirements, use case diagrams) and dynamic (activity diagrams) view of software projects. Our ontology-based approach allows for reasoning over the stored requirements, while the mining methodologies employed detect incomplete or missing software requirements, this way reducing the effort required for requirements elicitation at an early stage of the project lifecycle. @article{Diamantopoulos2017EIS, | |
A. Thallas, E.G. Tsardoulias and L. Petrou
"Topological Based Scan Matching – Odometry Posterior Sampling in RBPF Under Kinematic Model Failures"
Journal of Intelligent & Robotic Systems, 91, pp. 543-568, 2017 Nov
Rao-Blackwellized Particle Filters (RBPF) have been utilized to provide a solution to the SLAM problem. One of the main factors that cause RBPF failure is the potential particle impoverishment. Another popular approach to the SLAM problem are Scan Matching methods, whose good results require environments with lots of information, however fail in the lack thereof. To face these issues, in the current work techniques are presented to combine Rao-Blackwellized particle filters with a scan matching algorithm (CRSM SLAM). The particle filter maintains the correct hypothesis in environments lacking features and CRSM is employed in feature-rich environments while simultaneously reduces the particle filter dispersion. Since CRSM’s good performance is based on its high iteration frequency, a multi-threaded combination is presented which allows CRSM to operate while RBPF updates its particles. Additionally, a novel method utilizing topological information is proposed, in order to reduce the number of particle filter resamplings. Finally, we present methods to address anomalous situations where scan matching can not be performed and the vehicle displays behaviors not modeled by the kinematic model, causing the whole method to collapse. Numerous experiments are conducted to support the aforementioned methods’ advantages. @article{etsardouRbpf2017, | |
Miltiadis G. Siavvas, Kyriakos C. Chatzidimitriou and Andreas L. Symeonidis
"QATCH - An adaptive framework for software product quality assessment"
Expert Systems with Applications, 2017 May
The subjectivity that underlies the notion of quality does not allow the design and development of a universally accepted mechanism for software quality assessment. This is why contemporary research is now focused on seeking mechanisms able to produce software quality models that can be easily adjusted to custom user needs. In this context, we introduce QATCH, an integrated framework that applies static analysis to benchmark repositories in order to generate software quality models tailored to stakeholder specifications. Fuzzy multi-criteria decision-making is employed in order to model the uncertainty imposed by experts’ judgments. These judgments can be expressed into linguistic values, which makes the process more intuitive. Furthermore, a robust software quality model, the base model, is generated by the system, which is used in the experiments for QATCH system verification. The paper provides an extensive analysis of QATCH and thoroughly discusses its validity and added value in the field of software quality through a number of individual experiments. @article{Siavvas2017, | |
Athanassios M. Kintsakis, Fotis E. Psomopoulos, Andreas L. Symeonidis and Pericles A. Mitkas
"Hermes: Seamless delivery of containerized bioinformatics workflows in hybrid cloud (HTC) environments"
SoftwareX, 6, pp. 217-224, 2017 Sep
Hermes introduces a new ”describe once, run anywhere” paradigm for the execution of bioinformatics workflows in hybrid cloud environments. It combines the traditional features of parallelization-enabled workflow management systems and of distributed computing platforms in a container-based approach. It offers seamless deployment, overcoming the burden of setting up and configuring the software and network requirements. Most importantly, Hermes fosters the reproducibility of scientific workflows by supporting standardization of the software execution environment, thus leading to consistent scientific workflow results and accelerating scientific output. @article{SOFTX89, | |
Cezary Zielinski, Maciej Stefanczyk, Tomasz Kornuta, Maksym Figat, Wojciech Dudek, Wojciech Szynkiewicz, Wlodzimierz Kasprzak, Jan Figat, Marcin Szlenk, Tomasz Winiarski, Konrad Banachowicz, Teresa Zielinska, Emmanouil G. Tsardoulias, Andreas L. Symeonidis, Fotis E. Psomopoulos, Athanassios M. Kintsakis, Pericles A. Mitkas, Aristeidis Thallas, Sofia E. Reppou, George T. Karagiannis, Konstantinos Panayiotou, Vincent Prunet, Manuel Serrano, Jean-Pierre Merlet, Stratos Arampatzis, Alexandros Giokas, Lazaros Penteridis, Ilias Trochidis, David Daney and Miren Iturburu
"Variable structure robot control systems: The RAPP approach"
Robotics and Autonomous Systems, 94, pp. 226-244, 2017 May
This paper presents a method of designing variable structure control systems for robots. As the on-board robot computational resources are limited, but in some cases the demands imposed on the robot by the user are virtually limitless, the solution is to produce a variable structure system. The task dependent part has to be exchanged, however the task governs the activities of the robot. Thus not only exchange of some task-dependent modules is required, but also supervisory responsibilities have to be switched. Such control systems are necessary in the case of robot companions, where the owner of the robot may demand from it to provide many services. @article{Zielnski2017, |
2016
Journal Articles
Antonios Chrysopoulos, Christos Diou, Andreas Symeonidis and Pericles A. Mitkas
"Response modeling of small-scale energy consumers for effective demand response applications"
Electric Power Systems Research, 132, pp. 78-93, 2016 Mar
The Smart Grid paradigm can be economically and socially sustainable by engaging potential consumers through understanding, trust and clear tangible benefits. Interested consumers may assume a more active role in the energy market by claiming new energy products/services on offer and changing their consumption behavior. To this end, suppliers, aggregators and Distribution System Operators can provide monetary incentives for customer behavioral change through demand response programs, which are variable pricing schemes aiming at consumption shifting and/or reduction. However, forecasting the effect of such programs on power demand requires accurate models that can efficiently describe and predict changes in consumer activities as a response to pricing alterations. Current work proposes such a detailed bottom-up response modeling methodology, as a first step towards understanding and formulating consumer response. We build upon previous work on small-scale consumer activity modeling and provide a novel approach for describing and predicting consumer response at the level of individual activities. The proposed models are used to predict shifting of demand as a result of modified pricing policies and they incorporate consumer preferences and comfort through sensitivity factors. Experiments indicate the effectiveness of the proposed method on real-life data collected from two different pilot sites: 32 apartments of a multi-residential building in Sweden, as well as 11 shops in a large commercial center in Italy. @article{2015ChrysopoulosEPSR, | |
Pantelis Angelidis, Leslie Berman, Maria de la Luz Casas-Perez, Leo Anthony Celi, George E. Dafoulas, Alon Dagan, Braiam Escobar, Diego M. Lopez, Julieta Noguez, Juan Sebastian Osorio-Valencia, Charles Otine, Kenneth Paik, Luis Rojas-Potosi, Andreas Symeonidis and Eric Winkler
"The hackathon model to spur innovation around global mHealth"
Journal of Medical Engineering & Technology, pp. 1-8, 2016 Sep
The challenge of providing quality healthcare to underserved populations in low- and middle-income countries (LMICs) has attracted increasing attention from information and communication technology (ICT) professionals interested in providing societal impact through their work. Sana is an organisation hosted at the Institute for Medical Engineering and Science at the Massachusetts Institute of Technology that was established out of this interest. Over the past several years, Sana has developed a model of organising mobile health bootcamp and hackathon events in LMICs with the goal of encouraging increased collaboration between ICT and medical professionals and leveraging the growing prevalence of cellphones to provide health solutions in resource limited settings. Most recently, these events have been based in Colombia, Uganda, Greece and Mexico. The lessons learned from these events can provide a framework for others working to create sustainable health solutions in the developing world. @article{2016AngelidisJMET, | |
Michael Chatzidimopoulos, Fotis Psomopoulos, Emmanouil Malandrakis, Ioannis Ganopoulos, Panagiotis Madesis, Evangelos Vellios and Pavlidis Drogoudi
"Comparative Genomics of Botrytis cinerea Strains with Differential Multi-Drug Resistance"
Frontiers in Plant Science, 2016 Apr
Botrytis cinerea is a ubiquitous fungus difficult to control because it possess a variety of attack modes, diverse hosts as inoculum sources, and it can survive as mycelia and/or conidia or for extended periods as sclerotia in crop debris. For these reasons the use of any single control measure is unlikely to succeed and a combination of cultural practices with the application of site-specific synthetic compounds provide the best protection for the crops (Williamson et al., 2007). However, the chemical control has been adversely affected by the development of fungicide resistance. The selection of resistant individuals in a fungal population subjected to selective pressure due to fungicides is an evolutionary mechanism that promotes advantageous genotypes (Walker et al., 2013). High levels of resistance to site-specific fungicides are commonly associated with point mutations. For example the mutations G143A, H272R, and F412S leading to changes in the target proteins CytB, SdhB, and Erg27 are conferring resistance of the pathogen to the chemical classes of QoIs, SDHIs, and hydroxyanilides, respectively (Leroux, 2007). Multidrug resistance is another mechanism associated with resistance in B. cinerea which involves mutations leading to overexpression of individual transporters such as ABC and MFS (Kretschmer et al., 2009). This mechanism is associated with low levels of resistance to multiple fungicides including the anilinopyrimidines and phenylpyrroles. However, a subdivision of gray mold populations was found to be more tolerant to these two classes of fungicides (Leroch et al., 2013).Previous reports have clearly demonstrated that the resistance to anilinopyrimidines has a qualitative, disruptive pattern, and is monogenically controlled (Chapeland et al., 1999). In order to elucidate the mechanism of the resistance, the whole genome of three different samples (gene pools) was sequenced, each containing DNA of 10 selected strains of the same genotype regarding resistance to seven different classes of fungicides including anilinopyrimidines. This report presents the publicly available genomic data. @article{2016ChatzidimopoulosFPS, | |
Sofia E. Reppou, Emmanouil G. Tsardoulias, Athanassios M. Kintsakis, Andreas Symeonidis, Pericles A. Mitkas, Fotis E. Psomopoulos, George T. Karagiannis, Cezary Zielinski, Vincent Prunet, Jean-Pierre Merlet, Miren Iturburu and Alexandros Gkiokas
"RAPP: A robotic-oriented ecosystem for delivering smart user empowering applications for older people"
Journal of Social Robotics, pp. 15, 2016 Jun
It is a general truth that increase of age is associated with a level of mental and physical decline but unfortunately the former are often accompanied by social exclusion leading to marginalization and eventually further acceleration of the aging process. A new approach in alleviating the social exclusion of older people involves the use of assistive robots. As robots rapidly invade everyday life, the need of new software paradigms in order to address the user’s unique needs becomes critical. In this paper we present a novel architectural design, the RAPP [a software platform to deliver smart, user empowering robotic applications (RApps)] framework that attempts to address this issue. The proposed framework has been designed in a cloud-based approach, integrating robotic devices and their respective applications. We aim to facilitate seamless development of RApps compatible with a wide range of supported robots and available to the public through a unified online store. @article{2016ReppouJSR, | |
Emmanouil Tsardoulias, Aris Thallas, Andreas L. Symeonidis and Pericles A. Mitkas
"Improving multilingual interaction for consumer robots through signal enhancement in multichannel speech"
audio engineering society, 2016 Dec
Cucurbita pepo (squash, pumpkin, gourd), a worldwide-cultivated vegetable of American origin, is extremely variable in fruit characteristics. However, the information associated with genes and genetic markers for pumpkin is very limited. In order to identify new genes and to develop genetic markers, we performed a transcriptome analysis (RNA-Seq) of two contrasting pumpkin cultivars. Leaves and female flowers of cultivars, @article{2016TsardouliasAES, | |
Emmanouil Tsardoulias, Athanassios Kintsakis, Konstantinos Panayiotou, Aristeidis Thallas, Sofia Reppou, George Karagiannis, Miren Iturburu, Stratos Arampatzis, Cezary Zielinskic, Vincent Prunetg, Fotis Psomopoulos, Andreas Symeonidis and Pericles Mitkas
"Towards an integrated robotics architecture for social inclusion – The RAPP paradigm"
Cognitive Systems Research, pp. 1-8, 2016 Sep
Scientific breakthroughs have led to an increase in life expectancy, to the point where senior citizens comprise an ever increasing percentage of the general population. In this direction, the EU funded RAPP project “Robotic Applications for Delivering Smart User Empowering Applications” introduces socially interactive robots that will not only physically assist, but also serve as a companion to senior citizens. The proposed RAPP framework has been designed aiming towards a cloud-based integrated approach that enables robotic devices to seamlessly deploy robotic applications, relieving the actual robots from computational burdens. The Robotic Applications (RApps) developed according to the RAPP paradigm will empower consumer social robots, allowing them to adapt to versatile situations and materialize complex behaviors and scenarios. The RAPP pilot cases involve the development of RApps for the NAO humanoid robot and the ANG-MED rollator targeting senior citizens that (a) are technology illiterate, (b) have been diagnosed with mild cognitive impairment or (c) are in the process of hip fracture rehabilitation. Initial results establish the robustness of RAPP in addressing the needs of end users and developers, as well as its contribution in significantly increasing the quality of life of senior citizens. @article{2016TsardouliasCSR, | |
Aliki Xanthopoulou, Fotis Psomopoulos, Ioannis Ganopoulos, Maria Manioudaki, Athanasios Tsaftaris, Irini Nianiou-Obeidat and Panagiotis Madesis
"De novo transcriptome assembly of two contrasting pumpkin cultivars"
Genomics Data pp 200-201, 2016 Jan
Cucurbita pepo (squash, pumpkin, gourd), a worldwide-cultivated vegetable of American origin, is extremely variable in fruit characteristics. However, the information associated with genes and genetic markers for pumpkin is very limited. In order to identify new genes and to develop genetic markers, we performed a transcriptome analysis (RNA-Seq) of two contrasting pumpkin cultivars. Leaves and female flowers of cultivars, @article{2016XanthopoulouGD, | |
Christoforos Zolotas, Themistoklis Diamantopoulos, Kyriakos Chatzidimitriou and Andreas Symeonidis
"From requirements to source code: a Model-Driven Engineering approach for RESTful web services"
Automated Software Engineering, pp. 1-48, 2016 Sep
During the last few years, the REST architectural style has drastically changed the way web services are developed. Due to its transparent resource-oriented model, the RESTful paradigm has been incorporated into several development frameworks that allow rapid development and aspire to automate parts of the development process. However, most of the frameworks lack automation of essential web service functionality, such as authentication or database searching, while the end product is usually not fully compliant to REST. Furthermore, most frameworks rely heavily on domain specific modeling and require developers to be familiar with the employed modeling technologies. In this paper, we present a Model-Driven Engineering (MDE) engine that supports fast design and implementation of web services with advanced functionality. Our engine provides a front-end interface that allows developers to design their envisioned system through software requirements in multimodal formats. Input in the form of textual requirements and graphical storyboards is analyzed using natural language processing techniques and semantics, to semi-automatically construct the input model for the MDE engine. The engine subsequently applies model-to-model transformations to produce a RESTful, ready-to-deploy web service. The procedure is traceable, ensuring that changes in software requirements propagate to the underlying software artefacts and models. Upon assessing our methodology through a case study and measuring the effort reduction of using our tools, we conclude that our system can be effective for the fast design and implementation of web services, while it allows easy wrapping of services that have been engineered with traditional methods to the MDE realm. @article{2016ZolotasASE, | |
E.G. Tsardoulias, A. Iliakopoulou, A. Kargakos and L. Petrou
"Cost-Based Target Selection Techniques Towards Full Space Exploration and Coverage for USAR Applications in a Priori Unknown Environments"
Journal of Intelligent & Robotic Systems, 87, pp. 313-340, 2016 Oct
Full coverage and exploration of an environment is essential in robot rescue operations where victim identification is required. Three methods of target selection towards full exploration and coverage of an unknown space oriented for Urban Search and Rescue (USAR) applications have been developed. These are the Selection of the closest topological node, the Selection of the minimum cost topological node and the Selection of the minimum cost sub-graph. All methods employ a topological graph extracted from the Generalized Voronoi Diagram (GVD), in order to select the next best target during exploration. The first method utilizes a distance metric for determining the next best target whereas the Selection of the minimum cost topological node method assigns four different weights on the graph’s nodes, based on certain environmental attributes. The Selection of the minimum cost sub-graph uses a similar technique, but instead of single nodes, sets of graph nodes are examined. In addition, a modification of A* algorithm for biased path creation towards uncovered areas, aiming at a faster spatial coverage, is introduced. The proposed methods’ performance is verified by experiments conducted in two heterogeneous simulated environments. Finally, the results are compared with two common exploration methods. @article{etsardouCost2016, | |
Tsardoulias, E. G., A. Iliakopoulou, A. Kargakos, and L. Petrou
"A Review of Global Path Planning Methods for Occupancy Grid Maps Regardless of Obstacle Density"
Journal of Intelligent & Robotic Systems, 84, pp. 829-858, 2016 May
Path planning constitutes one of the most crucial abilities an autonomous robot should possess, apart from Simultaneous Localization and Mapping algorithms (SLAM) and navigation modules. Path planning is the capability to construct safe and collision free paths from a point of interest to another. Many different approaches exist, which are tightly dependent on the map representation method (metric or feature-based). In this work four path planning algorithmic families are described, that can be applied on metric Occupancy Grid Maps (OGMs): Probabilistic RoadMaps (PRMs), Visibility Graphs (VGs), Rapidly exploring Random Trees (RRTs) and Space Skeletonization. The contribution of this work includes the definition of metrics for path planning benchmarks, actual benchmarks of the most common global path planning algorithms and an educated algorithm parameterization based on a global obstacle density coefficient. @article{etsardouPp2016, |
2015
Journal Articles
Charalampos Dimoulas and Andreas Symeonidis
"Enhancing social multimedia matching and management through audio-adaptive audiovisual bimodal segmentation"
IEEE Multimedia, PP, (99), 2015 May
With the increasingly rapid growth of data in life sciences we are witnessing a major transition in the way research is conducted, from hypothesis-driven studies to data-driven simulations of whole systems. Such approaches necessitate the use of large-scale computational resources and e-infrastructures, such as the European Grid Infrastructure (EGI). EGI, one of key the enablers of the digital European Research Area, is a federation of resource providers set up to deliver sustainable, integrated and secure computing services to European researchers and their international partners. Here we aim to provide the state of the art of Grid/Cloud computing in EU research as viewed from within the field of life sciences, focusing on key infrastructures and projects within the life sciences community. Rather than focusing purely on the technical aspects underlying the currently provided solutions, we outline the design aspects and key characteristics that can be identified across major research approaches. Overall, we aim to provide significant insights into the road ahead by establishing ever-strengthening connections between EGI as a whole and the life sciences community. @article{2015DimoulasIEEEM, | |
Alfonso M Duarte, Fotis Psomopoulos, Christophe Blanchet, Alexandre M Bonvin, Manuel Corpas, Alain Franc, Rafael C Jimenez, Jesus M de Lucas, Tommi Nyrönen, Gargely Sipos and Stephanie B Suhr
"Future opportunities and trends for e-infrastructures and life sciences: going beyond the grid to enable life science data analysis"
Frontiers in Genetics, Vol. 6, No. 197 (2015), 2015 Jun
With the increasingly rapid growth of data in life sciences we are witnessing a major transition in the way research is conducted, from hypothesis-driven studies to data-driven simulations of whole systems. Such approaches necessitate the use of large-scale computational resources and e-infrastructures, such as the European Grid Infrastructure (EGI). EGI, one of key the enablers of the digital European Research Area, is a federation of resource providers set up to deliver sustainable, integrated and secure computing services to European researchers and their international partners. Here we aim to provide the state of the art of Grid/Cloud computing in EU research as viewed from within the field of life sciences, focusing on key infrastructures and projects within the life sciences community. Rather than focusing purely on the technical aspects underlying the currently provided solutions, we outline the design aspects and key characteristics that can be identified across major research approaches. Overall, we aim to provide significant insights into the road ahead by establishing ever-strengthening connections between EGI as a whole and the life sciences community. @article{2015DuarteFG, | |
Themistoklis Mavridis andAndreas Symeonidis
"Identifying valid search engine ranking factors in a Web 2.0 and Web 3.0 context for building efficient SEO mechanisms"
Engineering Applications of Artificial Intelligence (EAAI), 41, pp. 75–91, 2015 Mar
It is common knowledge that the web has been continuously evolving, from a read medium to a read/write scheme and, lately, to a read/write/infer corpus. To follow the evolution, Search Engines have been undergoing continuous updates in order to provide the user with a well-targeted, personalized and improved experience of the web. Along with this focus on content quality and user preferences, search engines have also been striving to integrate Semantic Web primitives, in order to enhance their intelligence. Current work discusses the evolution of search engine ranking factors in a Web 2.0 and Web 3.0 context. A benchmark crawler LSHrank, has been developed, which employs known search engine APIs and evaluates results against various already established metrics, in different domains and types of web content. The ultimate LSHrank objective is the development of a Search Engine Optimization (SEO) mechanism that will enrich and alter the content of a website in order to achieve its optimal ranking in search engine result pages (SERPs). @article{2015mavridisEAAI, | |
Dimitrios Vitsios, Fotis Psomopoulos, Pericles Mitkas and Christos Ouzounis
"Inference of pathway decomposition across multiple species through gene clustering"
International Journal on Artificial Intelligence Tools, 24, pp. 25, 2015 Feb
In the wake of gene-oriented data analysis in large-scale bioinformatics studies, focus in research is currently shifting towards the analysis of the functional association of genes, namely the metabolic pathways in which genes participate. The goal of this paper is to attempt to identify the core genes in a specific pathway, based on a user-defined selection of genomes. To this end, a novel algorithm has been developed that uses data from the KEGG database, and through the application of the MCL clustering algorithm, identifies clusters that correspond to different “layers” of genes, either on a phylogenetic or a functional level. The algorithm @article{2015vitsiosIJAIT, |
2014
Journal Articles
Anna A. Adamopoulou and Andreas Symeonidis
"A simulation testbed for analyzing trust and reputation mechanisms in unreliable online markets"
Electronic Commerce Research and Applications, 35, pp. 114-130, 2014 Oct
Modern online markets are becoming extremely dynamic, indirectly dictating the need for (semi-) autonomous approaches for constant monitoring and immediate action in order to satisfy one’s needs/preferences. In such open and versatile environments, software agents may be considered as a suitable metaphor for dealing with the increasing complexity of the problem. Additionally, trust and reputation have been recognized as key issues in online markets and many researchers have, in different perspectives, surveyed the related notions, mechanisms and models. Within the context of this work we present an adaptable, multivariate agent testbed for the simulation of open online markets and the study of various factors affecting the quality of the service consumed. This testbed, which we call Euphemus, is highly parameterized and can be easily customized to suit a particular application domain. It allows for building various market scenarios and analyzing interesting properties of e-commerce environments from a trust perspective. The architecture of Euphemus is presented and a number of well-known trust and reputation models are built with Euphemus, in order to show how the testbed can be used to apply and adapt models. Extensive experimentation has been performed in order to show how models behave in unreliable online markets, results are discussed and interesting conclusions are drawn. @article{2014AdamopoulouECRA, | |
Antonios Chrysopoulos, Christos Diou, A.L. Symeonidis and Pericles A. Mitkas
"Bottom-up modeling of small-scale energy consumers for effective Demand Response Applications"
EAAI, 35, pp. 299- 315, 2014 Oct
In contemporary power systems, small-scale consumers account for up to 50% of a country?s total electrical energy consumption. Nevertheless, not much has been achieved towards eliminating the problems caused by their inelastic consumption habits, namely the peaks in their daily power demand and the inability of energy suppliers to perform short-term forecasting and/or long-term portfolio management. Typical approaches applied in large-scale consumers, like providing targeted incentives for behavioral change, cannot be employed in this case due to the lack of models for everyday habits, activities and consumption patterns, as well as the inability to model consumer response based on personal comfort. Current work aspires to tackle these issues; it introduces a set of small-scale consumer models that provide statistical descriptions of electrical consumption patterns, parameterized from the analysis of real-life consumption measurements. These models allow (i) bottom-up aggregation of appliance use up to the overall installation load, (ii) simulation of various energy efficiency scenarios that involve changes at appliance and/or activity level and (iii) the assessment of change in consumer habits, and therefore the power consumption, as a result of applying different pricing policies. Furthermore, an autonomous agent architecture is introduced that adopts the proposed consumer models to perform simulation and result analysis. The conducted experiments indicate that (i) the proposed approach leads to accurate prediction of small-scale consumption (in terms of energy consumption and consumption activities) and (ii) small shifts in appliance usage times are sufficient to achieve significant peak power reduction. @article{2014chrysopoulosEAAI, | |
Themistoklis Diamantopoulos and Andreas Symeonidis
"Localizing Software Bugs using the Edit Distance of Call Traces"
International Journal On Advances in Software, 7, (1), pp. 277 - 288, 2014 Oct
Automating the localization of software bugs that do not lead to crashes is a difficult task that has drawn the attention of several researchers. Several popular methods follow the same approach; function call traces are collected and represented as graphs, which are subsequently mined using subgraph mining algorithms in order to provide a ranking of potentially buggy functions-nodes. Recent work has indicated that the scalability of state-of-the-art methods can be improved by reducing the graph dataset using tree edit distance algorithms. The call traces that are closer to each other, but belong to different sets, are the ones that are most significant in localizing bugs. In this work, we further explore the task of selecting the most significant traces, by proposing different call trace selection techniques, based on the Stable Marriage problem, and testing their effectiveness against current solutions. Upon evaluating our methods on a real-world dataset, we prove that our methodology is scalable and effective enough to be applied on dynamic bug detection scenarios. @article{2014DiamantopoulosIJAS, | |
G. Mamalakis, C. Diou, A.L. Symeonidis and L. Georgiadis
"Of daemons and men: A file system approach towards intrusion detection"
Applied Soft Computing, 25, pp. 1--14, 2014 Oct
We present FI^2DS a file system, host based anomaly detection system that monitors Basic Security Module (BSM) audit records and determines whether a web server has been compromised by comparing monitored activity generated from the web server to a normal usage profile. Additionally, we propose a set of features extracted from file system specific BSM audit records, as well as an IDS that identifies attacks based on a decision engine that employs one-class classification using a moving window on incoming data. We have used two different machine learning algorithms, Support Vector Machines (SVMs) and Gaussian Mixture Models (GMMs) and our evaluation is performed on real-world datasets collected from three web servers and a honeynet. Results are very promising, since FI^2DS detection rates range between 91% and 95.9% with corresponding false positive rates ranging between 8.1× 10^?2 % and 9.3× 10^?4 %. Comparison of FI^2DS to another state-of-the-art filesystem-based IDS, FWRAP, indicates higher effectiveness of the proposed IDS in all three datasets. Within the context of this paper FI2DS is evaluated for the web daemon user; nevertheless, it can be directly extended to model any daemon-user for both intrusion detection and postmortem analysis. @article{2014MamalakisASC, | |
Themistoklis Mavridis and Andreas Symeonidis
"Semantic analysis of web documents for the generation of optimal content"
Engineering Applications of Artificial Intelligence, 2014, 35, pp. 114-130, 2014 Oct
The Web has been under major evolution over the last decade and search engines have been trying to incorporate the changes of the web and provide the user with in terms of content. In order to evaluate the quality of a document there has been a plethora of attempts, some of which have considered the use of semantic analysis for extracting conclusions upon documents around the web. In turn, Search Engine Optimization (SEO) has been under development in order to cope with the changes of search engines and the web. SEOsss aim has been the creation of effective strategies for optimal ranking of websites and webpages in search engines. Current work probes on semantic analysis of web content. We further elaborate on LDArank, a mechanism that employs Latent Dirichlet Allocation (LDA) for the semantic analysis of web content and the generation of optimal content for given queries. We apply the new proposed mechanism, LSHrank, and explore the effect of generating web content against various SEO factors. We demonstrate LSHrank robustness to produce semantically prominent content in comparison to different semantic analysis based SEO approaches. @article{2014MavridisEAAI, |
2013
Journal Articles
Kyriakos C. Chatzidimitriou and Pericles A. Mitkas
"Adaptive reservoir computing through evolution and learning"
Neurocomputing, 103, pp. 198-209, 2013 Jan
The development of real-world, fully autonomous agents would require mechanisms that would offer generalization capabilities from experience, suitable for a large range of machine learning tasks, like those from the areas of supervised and reinforcement learning. Such capacities could be offered by parametric function approximators that could either model the environment or the agent\\'s policy. To promote autonomy, these structures should be adapted to the problem at hand with no or little human expert input. Towards this goal, we propose an adaptive function approximator method for developing appropriate neural networks in the form of reservoir computing systems through evolution and learning. Our neuro-evolution of augmenting reservoirs approach comprises of several ideas, successful on their own, in an effort to develop an algorithm that could handle a large range of problems, more efficiently. In particular, we use the neuro-evolution of augmented topologies algorithm as a meta-search method for the adaptation of echo state networks for handling problems to be encountered by autonomous entities. We test our approach on several test-beds from the realms of time series prediction and reinforcement learning. We compare our methodology against similar state-of-the-art algorithms with promising results. @article{2013ChatzidimitriouN, | |
Christos Maramis, Manolis Falelakis, Irini Lekka, Christos Diou, Pericles A. Mitkas and Anastasios Delopoulos
"Applying semantic technologies in cervical cancer research"
Data Knowl. Eng., 86, pp. 160-178, 2013 Jan
In this paper we present a research system that follows a semantic approach to facilitate medical association studies in the area of cervical cancer. Our system, named ASSIST and developed as an EU research project, assists in cervical cancer research by unifying multiple patient record repositories, physically located in different medical centers or hospitals. Semantic modeling of medical data and rules for inferring domain-specific information allow the system to (i) homogenize the information contained in the isolated repositories by translating it into the terms of a unified semantic representation, (ii) extract diagnostic information not explicitly stored in the individual repositories, and (iii) automate the process of evaluating medical hypotheses by performing case control association studies, which is the ultimate goal of the system. @article{2013MaramisDKE, | |
Fotis E. Psomopoulos, Pericles A. Mitkas and Christos A. Ouzounis
"Detection of Genomic Idiosyncrasies Using Fuzzy Phylogenetic Profile"
Plos ONE, 2013 Jan
Phylogenetic profiles express the presence or absence of genes and their homologs across a number of reference genomes. They have emerged as an elegant representation framework for comparative genomics and have been used for the genome-wide inference and discovery of functionally linked genes or metabolic pathways. As the number of reference genomes grows, there is an acute need for faster and more accurate methods for phylogenetic profile analysis with increased performance in speed and quality. We propose a novel, efficient method for the detection of genomic idiosyncrasies, i.e. sets of genes found in a specific genome with peculiar phylogenetic properties, such as intra-genome correlations or inter-genome relationships. Our algorithm is a four-step process where genome profiles are first defined as fuzzy vectors, then discretized to binary vectors, followed by a de-noising step, and finally a comparison step to generate intra- and inter-genome distances for each gene profile. The method is validated with a carefully selected benchmark set of five reference genomes, using a range of approaches regarding similarity metrics and pre-processing stages for noise reduction. We demonstrate that the fuzzy profile method consistently identifies the actual phylogenetic relationship and origin of the genes under consideration for the majority of the cases, while the detected outliers are found to be particular genes with peculiar phylogenetic patterns. The proposed method provides a time-efficient and highly scalable approach for phylogenetic stratification, with the detected groups of genes being either similar to their own genome profile or different from it, thus revealing atypical evolutionary histories. @article{2013PsomopoulosPlosOne, | |
Konstantinos N. Vavliakis, Andreas L. Symeonidis and Pericles A. Mitkas
"Event identification in web social media through named entity recognition and topic modeling"
Data & Knowledge Engineering, 88, pp. 1-24, 2013 Jan
@article{2013VavliakisDKE, | |
Tsardoulias, Emmanouil, and Loukas Petrou
"Critical Rays Scan Match SLAM"
Journal of Intelligent & Robotic Systems, 72, pp. 441-462, 2013 Feb
Scan matching is one of the oldest and simplest methods for occupancy grid based SLAM. The general idea is to find the pose of a robot and update its map simply by calculating the 2-D transformation between a laser scan and its predecessor. Due to its simplicity many solutions were proposed and used in various systems, the vast majority of which are iterative. The fact is, that although scan matching is simple in its implementation, it suffers from accumulative noise. Of course, there is certainly a trade-off between the quality of results and the execution time required. Many algorithms have been introduced, in order to achieve good quality maps in a small iteration time, so that on-line execution would be achievable. The proposed SLAM scheme performs scan matching by implementing a ray-selection method. The main idea is to reduce complexity and time needed for matching by pre-processing the scan and selecting rays that are critical for the matching process. In this paper, several different methods of ray-selection are compared. In addition matching is performed between the current scan and the global robot map, in order to minimize the accumulated errors. RRHC (Random Restart Hill Climbing) is employed for matching the scan to the map, which is a local search optimization procedure that can be easily parameterized and is much faster than a traditional genetic algorithm (GA), largely because of the low complexity of the problem. The general idea is to construct a parameterizable SLAM that can be used in an on-line system that requires low computational cost. The proposed algorithm assumes a structured civil environment, is oriented for use in the RoboCup - RoboRescue competition, and its main purpose is to construct high quality maps. @article{etsardouCritical2013, | |
Tsardoulias, E. G., A. T. Serafi, M. N. Panourgia, A. Papazoglou, and L. Petrou
"Construction of Minimized Topological Graphs on Occupancy Grid Maps Based on GVD and Sensor Coverage Information"
Journal of Intelligent & Robotic Systems, 75, pp. 457-474, 2013 Dec
One of the tasks to be carried out during the robot exploration of an unknown environment, is the construction of a complete map of the environment at bounded time interval. In order for the exploration to be efficient, a smart planning method must be implemented so that the robot can cover the space as fast as possible. One of the most important information that an intelligent agent can have, is a representation of the environment, not necessarily in the form of a map, but of a topological graph of the plane, which can be used to perform efficient planning. This work proposes a method to produce a topological graph of an Occupancy Grid Map (OGM) by using a Manhattan distance function to create the Approximate Generalized Voronoi Diagram (AGVD). Several improvements in the AGVD are made, in order to produce a crisp representation of the spaces skeleton, but in the same time to avoid the complex results of other methods. To smooth the final AGVD, morphological operations are performed. A topological graph is constructed from the AGVD, which is minimized by using sensor coverage information, aiming at planning complexity reduction. @article{etsardouTopo2013, |
2012
Journal Articles
Wolfgang Ketter and Andreas L. Symeonidis
"Competitive Benchmarking: Lessons learned from the Trading Agent Competition"
AI Magazine, 33, (2), pp. 198-209, 2012 Sep
Over the years, competitions have been important catalysts for progress in artificial intelligence. We describe the goal of the overall Trading Agent Competition and highlight particular competitions. We discuss its significance in the context of today’s global market economy as well as AI research, the ways in which it breaks away from limiting assumptions made in prior work, and some of the advances it has engendered over the past ten years. Since its introduction in 2000, TAC has attracted more than 350 entries and brought together researchers from AI and beyond. @article{2012KetterAIM, | |
Fotis Psomopoulos, Victoria Siarkou, Nikolas Papanikolaou, Ioannis Iliopoulos, Athanasios Tsaftaris, Vasilis Promponas and Christos Ouzounis
"The Chlamydiales Pangenome Revisited: Structural Stability and Functional Coherence"
Genes, Vol 3, No 2 (2012), pp. 291-319, 16, 2012 May
The entire publicly available set of 37 genome sequences from the bacterial order Chlamydiales has been subjected to comparative analysis in order to reveal the salient features of this pangenome and its evolutionary history. Over 2,000 protein families are detected across multiple species, with a distribution consistent to other studied pangenomes. Of these, there are 180 protein families with multiple members, 312 families with exactly 37 members corresponding to core genes, 428 families with peripheral genes with varying taxonomic distribution and finally 1,125 smaller families. The fact that, even for smaller genomes of Chlamydiales, core genes represent over a quarter of the average protein complement, signifies a certain degree of structural stability, given the wide range of phylogenetic relationships within the group. In addition, the propagation of a corpus of manually curated annotations within the discovered core families reveals key functional properties, reflecting a coherent repertoire of cellular capabilities for Chlamydiales. We further investigate over 2,000 genes without homologs in the pangenome and discover two new protein sequence domains. Our results, supported by the genome-based phylogeny for this group, are fully consistent with previous analyses and current knowledge, and point to future research directions towards a better understanding of the structural and functional properties of Chlamydiales. @article{2012PsomopoulosGenes, | |
Fani A. Tzima, John B. Theocharis and Pericles A. Mitkas
"Clustering-based initialization of Learning Classifier Systems. Effects on model performance, readability and induction time."
To appear in Soft Computing, 16, 2012 Jul
The present paper investigates whether an “informed” initialization process can help supervised LCS algorithms evolve rulesets with better characteristics, including greater predictive accuracy, shorter training times, and/or more compact knowledge representations. Inspired by previous research suggesting that the initialization phase of evolutionary algorithms may have a considerable impact on their convergence speed and the quality of the achieved solutions, we present an initialization method for the class of supervised Learning Classifier Systems (LCS) that extracts information about the structure of studied problems through a pre-training clustering phase and exploits this information by transforming it into rules suitable for the initialization of the learning process. The effectiveness of our approach is evaluated through an extensive experimental phase, involving a variety of real-world classification tasks. Obtained results suggest that clustering-based initialization can indeed improve the predictive accuracy, as well as the interpretability of the induced knowledge representations, and paves the way for further investigations of the potential of better-than-random initialization methods for LCS algorithms. @article{2012TzimaTASC, | |
Mingas, Grigorios, Emmanouil Tsardoulias, and Loukas Petrou
"An FPGA implementation of the SMG-SLAM algorithm"
Microprocessors and Microsystems, 36, (3), pp. 190-204, 2012 May
One of the main tasks of a mobile robot in an unknown environment is to build and update a map of the environment and simultaneously determine its location within this map. This problem is referred to as the simultaneous localization and mapping (SLAM) problem. The article introduces scan-matching genetic SLAM (SMG-SLAM), a novel SLAM algorithm. It is based on a genetic algorithm that uses scan-matching for gene fitness evaluation. The main scope of the article is to present a hardware implementation of SMG-SLAM using an field programmable gate array (FPGA). The architecture of the system is described and it is shown that it is up to 14.83 times faster compared to the software algorithm without significant loss in accuracy. The proposed implementation can be used as part of a larger system, providing efficient SLAM for autonomous robotic applications. @article{etsardouFpga2012, |
2011
Journal Articles
Fani A. Tzima, Pericles A. Mitkas, Dimitris Voukantsis and Kostas Karatzas
"Sparse episode identification in environmental datasets: the case of air quality assessment"
Expert Systems with Applications, 38, 2011 May
Sparse episode identification in environmental datasets is not only a multi-faceted and computationally challenging problem for machine learning algorithms, but also a difficult task for human-decision makers: the strict regulatory framework, in combination with the public demand for better information services, poses the need for robust, efficient and, more importantly, understandable forecasting models. Additionally, these models need to provide decision-makers with “summarized” and valuable knowledge, that has to be subjected to a thorough evaluation procedure, easily translated to services and/or actions in actual decision making situations, and integratable with existing Environmental Management Systems (EMSs). On this basis, our current study investigates the potential of various machine learning algorithms as tools for air quality (AQ) episode forecasting and assesses them – given the corresponding domain-specific requirements – using an evaluation procedure, tailored to the task at hand. Among the algorithms employed in the experimental phase, our main focus is on ZCS-DM, an evolutionary rule-induction algorithm specifically designed to tackle this class of problems – that is classification problems with skewed class distributions, where cost-sensitive model building is required. Overall, we consider this investigation successful, in terms of its aforementioned goals and constraints: obtained experimental results reveal the potential of rule-based algorithms for urban AQ forecasting, and point towards ZCS-DM as the most suitable algorithm for the target domain, providing the best trade-off between model performance and understandability. @article{2011TzimaESWA, | |
Konstantinos N. Vavliakis, Andreas L. Symeonidis, Georgios T. Karagiannis and Pericles A. Mitkas
"An integrated framework for enhancing the semantic transformation, editing and querying of relational databases"
Expert Systems with Applications, 38, (4), pp. 3844-3856, 2011 Apr
The transition from the traditional to the Semantic Web has proven much more difficult than initially expected. The volume, complexity and versatility of data of various domains, the computational limitations imposed on semantic querying and inferencing have drastically reduced the thrust semantic technologies had when initially introduced. In order for the semantic web to actually @article{2011VavliakisESWA, |
2010
Journal Articles
Giorgos Papachristoudis, Sotiris Diplaris and Pericles A. Mitkas
"SoFoCles: Feature filtering for microarray classification based on Gene Ontology"
Journal of Biomedical Informatics, 43, (1), 2010 Feb
Marker gene selection has been an important research topic in the classification analysis of gene expression data. Current methods try to reduce the \\"curse of dimensionality\\" by using statistical intra-feature set calculations, or classifiers that are based on the given dataset. In this paper, we present SoFoCles, an interactive tool that enables semantic feature filtering in microarray classification problems with the use of external, well-defined knowledge retrieved from the Gene Ontology. The notion of semantic similarity is used to derive genes that are involved in the same biological path during the microarray experiment, by enriching a feature set that has been initially produced with legacy methods. Among its other functionalities, SoFoCles offers a large repository of semantic similarity methods that are used in order to derive feature sets and marker genes. The structure and functionality of the tool are discussed in detail, as well as its ability to improve classification accuracy. Through experimental evaluation, SoFoCles is shown to outperform other classification schemes in terms of classification accuracy in two real datasets using different semantic similarity computation approaches. @article{2010Papachristoudis-JBI, | |
Fotis E. Psomopoulos and Pericles A. Mitkas
"Bioinformatics algorithm development for Grid environments"
Journal of Systems and Software, 83, (7), 2010 Jul
A Grid environment can be viewed as a virtual computing architecture that provides the ability to perform higher throughput computing by taking advantage of many computers geographically dispersed and connected by a network. Bioinformatics applications stand to gain in such a distributed environment in terms of increased availability, reliability and efficiency of computational resources. There is already considerable research in progress toward applying parallel computing techniques on bioinformatics methods, such as multiple sequence alignment, gene expression analysis and phylogenetic studies. In order to cope with the dimensionality issue, most machine learning methods either focus on specific groups of proteins or reduce the size of the original data set and/or the number of attributes involved. Grid computing could potentially provide an alternative solution to this problem, by combining multiple approaches in a seamless way. In this paper we introduce a unifying methodology coupling the strengths of the Grid with the specific needs and constraints of the major bioinformatics approaches. We also present a tool that implements this process and allows researchers to assess the computational needs for a specific task and optimize the allocation of available resources for its efficient completion. @article{2010PsomopoulosJOSAS, |
2009
Journal Articles
Theodoros Agorastos, Vassilis Koutkias, Manolis Falelakis, Irini Lekka, T. Mikos, Anastasios Delopoulos, Periklis A. Mitkas, A. Tantsis, S. Weyers, P. Coorevits, A. M. Kaufmann, R. Kurzeja and Nicos Maglaveras
"Semantic Integration of Cervical Cancer DAta Repositories to Facilitata Multicenter Associtation Studies: Tha ASSIST Approach"
Cancer Informatics Journal, Special Issue on Semantic Technologies, 8, (9), pp. 31-44, 2009 Feb
The recently proposed general molecular knotting algorithm and its associated package, MolKnot, introduce programming into certain sections of stereochemistry. This work reports the G-MolKnot procedure that was deployed over the grid infrastructure; it applies a divide-and-conquer approach to the problem by splitting the initial search space into multiple independent processes and, combining the results at the end, yields significant improvements with regards to the overall efficiency. The algorithm successfully detected the smallest ever reported alkane configured to an open-knotted shape with four crossings. @article{2009AgorastosCIJSIOST, | |
Kyriakos C. Chatzidimitriou, Konstantinos N. Vavliakis, Andreas L. Symeonidis and Pericles A. Mitkas
"Data-Mining-Enhanced Agents in Dynamic Supply-Chain-Management Environments"
Intelligent Systems, 24, (3), pp. 54-63, 2009 Jan
Special issue on Agents and Data Mining @article{2009ChatzidimitriouIS, | |
Georgios Karagiannis, Konstantinos Vavliakis, Sophia Sotiropoulou, Argirios Damtsios, Dimitrios Alexiadis and Christos Salpistis
"Using Signal Processing and Semantic Web Technologies to Analyze Byzantine Iconography"
IEEE Intelligent Systems, 24, (3), pp. 54-63, 2009 Jan
A bottom-up approach for documenting art objects processes data from innovative nondestructive analysis with signal processing and neural network techniques to provide a good estimation of the paint layer profile and pigments of artwork. The approach also uses Semantic Web technologies and maps concepts relevant to the analysis of paintings and Byzantine iconography to the Conceptual Reference Model of the International Committee for Documentation (CIDOC-CRM). This approach has introduced three main contributions: the development of an integrated nondestructive technique system combining spectroscopy and acoustic microscopy, supported by intelligent algorithms, for estimating the artworks @article{2009KaragiannisIS, | |
John M. Konstantinides, Athanasios Mademlis, Petros Daras, Pericles A. Mitkas and Michael G. Strintzis
"Blind Robust 3D-Mesh Watermarking Based on Oblate Spheroidal Harmonics"
IEEE Transactions on Multimedia, 11, (1), pp. 23-38, 2009 Jan
In this paper, a novel transform-based, blind and robust 3D mesh watermarking scheme is presented. The 3D surface of the mesh is firstly divided into a number of discrete continuous regions, each of which is successively sampled and mappedonto oblate spheroids, using a novel surface parameterization scheme. The embedding is performed in the spheroidal harmoniccoefficients of the spheroids, using a novel embedding scheme. Changes made to the transform domain are then reversed backto the spatial domain, thus forming the watermarked 3D mesh. The embedding scheme presented herein resembles, in principal,the ones using the multiplicative embedding rule (inherently providing high imperceptibility). The watermark detection isblind and by far more powerful than the various correlators typically incorporated by multiplicative schemes. Experimentalresults have shown that the proposed blind watermarking scheme is competitively robust against similarity transformations, con-nectivity attacks, mesh simplification and refinement, unbalanced re-sampling, smoothing and noise addition, even when juxtaposedto the informed ones. @article{2009KonstantinidesIEEEToM, | |
Fotis E. Psomopoulos, Pericles A. Mitkas, Christos S. Krinas and Ioannis N. Demetropoulos
"A grid-enabled algorithm yields figure-eight molecular knot"
Molecular Simulation, 35, (9), pp. 725-736, 2009 Jun
The recently proposed general molecular knotting algorithm and its associated package, MolKnot, introduce programming into certain sections of stereochemistry. This work reports the G-MolKnot procedure that was deployed over the grid infrastructure; it applies a divide-and-conquer approach to the problem by splitting the initial search space into multiple independent processes and, combining the results at the end, yields significant improvements with regards to the overall efficiency. The algorithm successfully detected the smallest ever reported alkane configured to an open-knotted shape with four crossings. @article{2009PsomopoulosMS, |
2008
Journal Articles
Pericles A. Mitkas, Vassilis Koutkias, Andreas L. Symeonidis, Manolis Falelakis, Christos Diou, Irini Lekka, Anastasios T. Delopoulos, Theodoros Agorastos and Nicos Maglaveras
"Association Studies on Cervical Cancer Facilitated by Inference and Semantic Technologes: The ASSIST Approach"
Studies in Health Technology and Informatic, 136, pp. 241-246, 2008 Jan
Cervical cancer (CxCa) is currently the second leading cause of cancer-related deaths, for women between 20 and 39 years old. As infection by the human papillomavirus (HPV) is considered as the central risk factor for CxCa, current research focuses on the role of specific genetic and environmental factors in determining HPV persistence and subsequent progression of the disease. ASSIST is an EU-funded research project that aims to facilitate the design and execution of genetic association studies on CxCa in a systematic way by adopting inference and semantic technologies. Toward this goal, ASSIST provides the means for seamless integration and virtual unification of distributed and heterogeneous CxCa data repositories, and the underlying mechanisms to undertake the entire process of expressing and statistically evaluating medical hypotheses based on the collected data in order to generate medically important associations. The ultimate goal for ASSIST is to foster the biomedical research community by providing an open, integrated and collaborative framework to facilitate genetic association studies. @article{2007MitkasSHTI, | |
Alex andros Batzios, Christos Dimou, Andreas L. Symeonidis and Pericles A. Mitkas
"BioCrawler: An intelligent crawler for the semantic web"
Expert Systems with Applications, 36, (35), 2008 Jul
Web crawling has become an important aspect of web search, as the WWW keeps getting bigger and search engines strive to index the most important and up to date content. Many experimental approaches exist, but few actually try to model the current behaviour of search engines, which is to crawl and refresh the sites they deem as important, much more frequently than others. BioCrawler mirrors this behaviour on the semantic web, by applying the learning strategies adopted in previous work on ecosystem simulation, called BioTope. BioCrawler employs the principles of BioTope @article{2008BatziosESwA, | |
Kyriakos C. Chatzidimitriou, Andreas L. Symeonidis, Ioannis Kontogounis and Pericles A. Mitkas
"Agent Mertacor: A robust design for dealing with uncertainty and variation in SCM environments"
Expert Systems with Applications, 35, (3), pp. 591-603, 2008 Jan
Supply Chain Management (SCM) has recently entered a new era, where the old-fashioned static, long-term relationships between involved actors are being replaced by new, dynamic negotiating schemas, established over virtual organizations and trading marketplaces. SCM environments now operate under strict policies that all interested parties (suppliers, manufacturers, customers) have to abide by, in order to participate. And, though such dynamic markets provide greater profit potential, they also conceal greater risks, since competition is tougher and request and demand may vary significantly in the quest for maximum benefit. The need for efficient SCM actors is thus implied, actors that may handle the deluge of (either complete or incomplete) information generated, perceive variations and exploit the full potential of the environments they inhabit. In this context, we introduce Mertacor, an agent that employs robust mechanisms for dealing with all SCM facets and for trading within dynamic and competitive SCM environments. Its efficiency has been extensively tested in one of the most challenging SCM environments, the Trading Agent Competition (TAC) SCM game. This paper provides an extensive analysis of Mertacor and its main architectural primitives, provides an overview of the TAC SCM environment, and thoroughly discusses Mertacor @article{2008ChatzidimitriouESwA, | |
Alex andros Batzios, Christos Dimou, Andreas L. Symeonidis and Pericles A. Mitkas
"An Integrated Infrastructure for Monitoring and Evaluating Agent-based Systems"
Expert Systems with Applications, 36, (4), 2008 Sep
Driven by the urging need to thoroughly identify and accentuate the merits of agent technology, we present in this paper, MEANDER, an integrated framework for evaluating the performance of agent-based systems. The proposed framework is based on the Agent Performance Evaluation (APE) methodology, which provides guidelines and representation tools for performance metrics, measurement collection and aggregation of measurements. MEANDER comprises a series of integrated software components that implement and automate various parts of the methodology and assist evaluators in their tasks. The main objective of MEANDER is to integrate performance evaluation processes into the entire development lifecycle, while clearly separating any evaluation-specific code from the application code at hand. In this paper, we describe in detail the architecture and functionality of the MEANDER components and test its applicability to an existing multi-agent system. @article{2008DimouESwA, | |
Andreas L. Symeonidis, Vivia Nikolaidou and Pericles A. Mitkas
"Sketching a methodology for efficient supply chain management agents enhanced through data mining"
International Journal of Intelligent Information and Database Systems (IJIIDS), 2, (1), 2008 Feb
Supply Chain Management (SCM) environments demand intelligent solutions, which can perceive variations and achieve maximum revenue. This highlights the importance of a commonly accepted design methodology, since most current implementations are application-specific. In this work, we present a methodology for building an intelligent trading agent and evaluating its performance at the Trading Agent Competition (TAC) SCM game. We justify architectural choices made, ranging from the adoption of specific Data Mining (DM) techniques, to the selection of the appropriate metrics for agent performance evaluation. Results indicate that our agent has proven capable of providing advanced SCM solutions in demanding SCM environments. @article{2008SymeoniidsIJIIDS, |
2007
Journal Articles
Pericles A. Mitkas, Andreas L. Symeonidis, Dionisis Kehagias and Ioannis N. Athanasiadis
"Application of Data Mining and Intelligent Agent Technologies to Concurrent Engineering"
International Journal of Product Lifecycle Management, 2, (2), pp. 1097-1111, 2007 Jan
Software agent technology has matured enough to produce intelligent agents, which can be used to control a large number of Concurrent Engineering tasks. Multi-Agent Systems (MAS) are communities of agents that exchange information and data in the form of messages. The agents @article{2007MitkasIJPLM, | |
Andreas L. Symeonidis, Kyriakos C. Chatzidimitriou, Ioannis N. Athanasiadis and Pericles A. Mitkas
"Data mining for agent reasoning: A synergy for training intelligent agents"
Engineering Applications of Artificial Intelligence, 20, (8), pp. 1097-1111, 2007 Dec
The task-oriented nature of data mining (DM) has already been dealt successfully with the employment of intelligent agent systems that distribute tasks, collaborate and synchronize in order to reach their ultimate goal, the extraction of knowledge. A number of sophisticated multi-agent systems (MAS) that perform DM have been developed, proving that agent technology can indeed be used in order to solve DM problems. Looking into the opposite direction though, knowledge extracted through DM has not yet been exploited on MASs. The inductive nature of DM imposes logic limitations and hinders the application of the extracted knowledge on such kind of deductive systems. This problem can be overcome, however, when certain conditions are satisfied a priori. In this paper, we present an approach that takes the relevant limitations and considerations into account and provides a gateway on the way DM techniques can be employed in order to augment agent intelligence. This work demonstrates how the extracted knowledge can be used for the formulation initially, and the improvement, in the long run, of agent reasoning. @article{2007SymeonidisEAAI, | |
Andreas L. Symeonidis, Ioannis N. Athanasiadis and Pericles A. Mitkas
"A retraining methodology for enhancing agent intelligence"
Knowledge-Based Systems, 20, (4), pp. 388-396, 2007 Jan
Data mining has proven a successful gateway for discovering useful knowledge and for enhancing business intelligence in a range of application fields. Incorporating this knowledge into already deployed applications, though, is highly impractical, since it requires reconfigurable software architectures, as well as human expert consulting. In an attempt to overcome this deficiency, we have developed Agent Academy, an integrated development framework that supports both design and control of multi-agent systems (MAS), as well as agent training. We define agent training as the automated incorporation of logic structures generated through data mining into the agents of the system. The increased flexibility and cooperation primitives of MAS, augmented with the training and retraining capabilities of Agent Academy, provide a powerful means for the dynamic exploitation of data mining extracted knowledge. In this paper, we present the methodology and tools for agent retraining. Through experimented results with the Agent Academy platform, we demonstrate how the extracted knowledge can be formulated and how retraining can lead to the improvement in the long run of agent intelligence. @article{2007SymeonidisKBS, | |
Andreas L. Symeonidis, Kyriakos C. Chatzidimitriou, Dionysios Kehagias and Pericles A. Mitkas
"A Multi-agent Infrastructure for Enhancing ERP system Intelligence"
Scalable Computing: Practice and Experience, 8, (1), pp. 101-114, 2007 Jan
Enterprise Resource Planning systems efficiently administer all tasks concerning real-time planning and manufacturing, material procurement and inventory monitoring, customer and supplier management. Nevertheless, the incorporation of domain knowledge and the application of adaptive decision making into such systems require extreme customization with a cost that becomes unaffordable, especially in the case of SMEs. In this paper we present an alternative approach for incorporating adaptive business intelligence into the company @article{2007SymeonidisSCPE, |
2006
Journal Articles
Sotiris Diplaris, Andreas L. Symeonidis, Pericles A. Mitkas, Georgios Banos and Z Abas
"A decision-tree-based alarming system for the validation of national genetic evaluations"
Computers and Electronics in Agriculture, 52, (1--2), pp. 21--35, 2006 Jun
The aim of this work was to explore possibilities to build an alarming system based on the results of the application of data mining (DM) techniques in genetic evaluations of dairy cattle, in order to assess and assure data quality. The technique used combined data mining using classification and decision-tree algorithms, Gaussian binned fitting functions, and hypothesis tests. Data were quarterly national genetic evaluations, computed between February 1999 and February 2003 in nine countries. Each evaluation run included 73,000-90,000 bull records complete with their genetic values and evaluation information. Milk production traits were considered. Data mining algorithms were applied separately for each country and evaluation run to search for associations across several dimensions, including bull origin, type of proof, age of bull, and number of daughters. Then, data in each node were fitted to the Gaussian function and the quality of the fit was measured, thus providing a measure of the quality of data. In order to evaluate and ultimately predict decision-tree models, the implemented architecture can compare the node probabilities between two models and decide on their similarity, using hypothesis tests for the standard deviation of their distribution. The key utility of this technique lays in its capacity to identify the exact node where anomalies occur, and to fire a focused alarm pointing to erroneous data. @article{2006DiplarisCEA, | |
Andreas L. Symeonidis, Dionisis D. Kehagias, Pericles A. Mitkas and Adamantios Koumpis
"Open Source Supply Chains"
International Journal of Advanced Manufacturing Systems (IJAMS), 9, (1), pp. 33-42, 2006 Jan
Enterprise Resource Planning (ERP) systems tend to deploy Supply Chains, in order to successfully integrate customers, suppliers, manufacturers and warehouses, and therefore minimize system-wide costs, while satisfying service level requirements. Although efficient, these systems are neither versatile nor adaptive, since newly discovered customer trends cannot be easily integrated. Furthermore, the development of such systems is subject to strict licensing, since the exploitation of such kind of software is usually proprietary. This leads to a monolithic approach and to sub-utilization of efforts from all sides. Introducing a completely new paradigm of how primitive Supply Chain Management (SCM) rules apply on ERP systems, we have developed a framework as an Open Source Multi-Agent System that introduces adaptive intelligence as a powerful add-on for ERP software customization. In this paper the SCM system developed is described, whereas the expected benefits of the open source initiative employed are illustrated. @article{2006SymeonidisIJAMS, |
2005
Journal Articles
Ioannis N. Athanasiadis, Alexandros K. Mentes, Pericles Alexandros Mitkas and Yiannis A. Mylopoulos
"A hybrid agent-based model for estimating residential water demand"
Simulation: Transactions of The Society for Modeling and Simulation International, 81, (3), pp. 175--187, 2005 Mar
The global effort toward sustainable development has initiated a transition in water management. Water utility companies use water-pricing policies as an instrument for controlling residential water demand. To support policy makers in their decisions, the authors have developed DAWN, a hybrid model for evaluating water-pricing policies. DAWN integrates an agent-based social model for the consumer with conventional econometric models and simulates the residential water demand-supply chain, enabling the evaluation of different scenarios for policy making. An agent community is assigned to behave as water consumers, while econometric and social models are incorporated into them for estimating water consumption. DAWN\\\\92s main advantage is that it supports social interaction between consumers, through an influence diffusion mechanism, implemented via inter-agent communication. Parameters affecting water consumption and associated with consumers\\\\92 social behavior can be simulated with DAWN. Real-world results of DAWN\\\\92s application for the evaluation of five water-pricing policies in Thessaloniki, Greece, are presented. @article{2005Athanasiadis-SIMULATION, | |
Ioannis N. Athanasiadis and Pericles A. Mitkas
"Social influence and water conservation: An agent-based approach"
IEEE Computing in Science and Engineering, 7, (1), pp. 175--187, 2005 Jan
Every day, consumers are exposed to advertising campaigns that attempt to influence their decisions and affect their behavior. Word-of-mouth communication-he informal channels of daily interactions among friends, relatives, coworkers, neighbors, and acquaintances-plays a much more significant role in how consumer behavior is shaped, fashion is introduced, and product reputation is built. Macrolevel simulations that include this kind of social parameter are usually limited to generalized, often simplistic assumptions. In an effort to represent the phenomenon in a semantically coherent way and model it more realistically, we developed an influence-diffusion mechanism that follows agent-based social simulation primitives. The model is realized as a multiagent software platform, which we call Dawn (for distributed agents for water simulation). @article{2005AthanasiadisIEEECSE, | |
Dionisis Kehagias, Andreas L. Symeonidis and Pericles A. Mitkas
"Designing Pricing Mechanisms for Autonomous Agents Based on Bid-Forecasting"
Electronic Markets, 15, (1), pp. 53--62, 2005 Jan
Autonomous agents that participate in the electronic market environment introduce an advanced paradigm for realizing automated deliberations over offered prices of auctioned goods. These agents represent humans and their assets, therefore it is critical for them not only to act rationally but also efficiently. By enabling agents to deploy bidding strategies and to compete with each other in a marketplace, a valuable amount of historical data is produced. An optimal dynamic forecasting of the maximum offered bid would enable more gainful behaviours by agents. In this respect, this paper presents a methodology that takes advantage of price offers generated in e-auctions, in order to provide an adequate short-term forecasting schema based on time-series analysis. The forecast is incorporated into the reasoning mechanism of a group of autonomous e-auction agents to improve their bidding behaviour. In order to test the improvement introduced by the proposed method, we set up a test-bed, on which a slightly variant version of the first-price ascending auction is simulated with many buyers and one seller, trading with each other over one item. The results of the proposed methodology are discussed and many possible extensions and improvements are advocated to ensure wide acceptance of the bid-forecasting reasoning mechanism. @article{2005KehagiasEM, | |
Pericles A. Mitkas
"Knowledge Discovery for Training Intelligent Agents: Methodology, Tools and Applications"
Lecture Notes in Artificial Intelligent, 3505, pp. 2-18, 2005 May
In this paper we address a relatively young but important area of research: the intersection of agent technology and data mining. This intersection can take two forms: a) the more mundane use of intelligent agents for improved knowledge discovery and b) the use of data mining techniques for producing smarter, more efficient agents. The paper focuses on the second approach. Knowledge, hidden in voluminous data repositories routinely created and maintained by today\\'s applications, can be extracted by data mining. The next step is to transform this knowledge into the inference mechanisms or simply the behavior of agents in multi-agent systems. We call this procedure “agent training.” We define different levels of agent training and we present a software engineering methodology that combines the application of deductive logic for generating intelligence from data with a process for transferring this knowledge into agents. We introduce Agent Academy, an integrated open-source framework, which supports data mining techniques and agent development tools. We also provide several examples of multi-agent systems developed with this approach. @article{2005MitkasLNAI, | |
Andreas L. Symeonidis, Evangelos Valtos, Serafeim Seroglou and Pericles A. Mitkas
"Biotope: an integrated framework for simulating distributed multiagent computational systems"
IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans, 35, (3), pp. 420-432, 2005 May
The study of distributed computational systems issues, such as heterogeneity, concurrency, control, and coordination, has yielded a number of models and architectures, which aspire to provide satisfying solutions to each of the above problems. One of the most intriguing and complex classes of distributed systems are computational ecosystems, which add an \\"ecological\\" perspective to these issues and introduce the characteristic of self-organization. Extending previous research work on self-organizing communities, we have developed Biotope, which is an agent simulation framework, where each one of its members is dynamic and self-maintaining. The system provides a highly configurable interface for modeling various environments as well as the \\"living\\" or computational entities that reside in them, while it introduces a series of tools for monitoring system evolution. Classifier systems and genetic algorithms have been employed for agent learning, while the dispersal distance theory has been adopted for agent replication. The framework has been used for the development of a characteristic demonstrator, where Biotope agents are engaged in well-known vital activities-nutrition, communication, growth, death-directed toward their own self-replication, just like in natural environments. This paper presents an analytical overview of the work conducted and concludes with a methodology for simulating distributed multiagent computational systems. @article{2005SymeonidisIEEETSMC, |
2003
Journal Articles
Andreas L. Symeonidis, Dionisis Kehagias and Pericles A. Mitkas
"Intelligent Policy Recommendations on Enterprise Resource Planning by the use of agent technology and data mining techniques"
Expert Systems with Applications, 25, (4), pp. 589-602, 2003 Jan
Enterprise Resource Planning systems tend to deploy Supply Chain Management and/or Customer Relationship Management techniques, in order to successfully fuse information to customers, suppliers, manufacturers and warehouses, and therefore minimize system-wide costs while satisfying service level requirements. Although efficient, these systems are neither versatile nor adaptive, since newly discovered customer trends cannot be easily integrated with existing knowledge. Advancing on the way the above mentioned techniques apply on ERP systems, we have developed a multi-agent system that introduces adaptive intelligence as a powerful add-on for ERP software customization. The system can be thought of as a recommendation engine, which takes advantage of knowledge gained through the use of data mining techniques, and incorporates it into the resulting company selling policy. The intelligent agents of the system can be periodically retrained as new information is added to the ERP. In this paper, we present the architecture and development details of the system, and demonstrate its application on a real test case. @article{2003SymeonidisESWA, |