- Serious Games, Multimodal Interaction, Serious Gaming, Machine Learning, Syntactic and Semantic Knowledge, Natural Language Processing, and 13 moreBioinformatics, Signal Processing, Mobile Computing, Data Mining, Text Mining, Computer Security, Network Security, Affective Computing, Emotional Computing, Human Computer Interaction, Kansei Engineering, Software Agents, and Artificial Intelligenceedit
- I am holding an Electrical Engineering Degree and PhD in Electrical Engineering, University of Patras, Greece. I h... moreI am holding an Electrical Engineering Degree and PhD in Electrical Engineering, University of Patras, Greece.
I have participated in several EU research projects in the role of Project Manager or Technology Manager (e.g. IST FP6: MoveON, Lab@Future, ICT FP7: e-SAVE, ARTISAN, PlayMancer, MobiServ, eInfrastructures: ENGAGE).
Previously I have been an application developer and Project Manager in a wide variety of business applications and research prototypes. I have a long standing experience in Knowledge management, System optimisation, distributed AI, data mining, environmental applications, machine learning, multi-agent and distributed problem solving systems.
I am particularly interested in Serious Games for education, training, product marketing, social networking.edit
Abstract. Feature selection is a process followed in order to improve the generalization and the performance of several classification and/or regression algorithms. Feature selection processes are divided in two categories, the filter and... more
Abstract. Feature selection is a process followed in order to improve the generalization and the performance of several classification and/or regression algorithms. Feature selection processes are divided in two categories, the filter and the wrapper approach. The formal is performed independently of the learning algorithm while the later makes use of the algorithm in an iterative way. As [1] describe, the feature weighting algorithms are divided into two categories: the filtering methods and the wrapper methods. The former is a no-feedback, pre-selection approach where the selection of the feature subset is performed independently of the learning algorithm. The later is an iterative method that encapsulates the learning algorithm in the feature selection process.
Research Interests: Emotion Regulation, Cognitive Neuroscience, Medicine, Bulimia Nervosa, Audiological Sciences, and 15 moreHumans, Complementary Therapies, Gambling, Emotion Recognition, Female, Male, Biofeedback, Mental Disorder, Mental, Clinical Sciences, Computer User Interface Design, Adult, Binge Eating Disorder, Computer Game, and Biosensing Techniques
Reviews and few non-controlled studies showed the effectiveness of several specific designed computer video-games as an additional form of treatment in several areas. However, there is a lack in the literature of specially designed... more
Reviews and few non-controlled studies showed the effectiveness of several specific designed computer video-games as an additional form of treatment in several areas. However, there is a lack in the literature of specially designed serious-games for treating mental disorders. Playmancer (ICT European initiative) aims to develop and assess a serious videogame that may help to treat underlying processes (e.g. lack of self-control strategies) in Eating and Impulse control disorders. Preliminary data will be shown.
Research Interests: Computer Science, Serious Games, Video Games, Self Control, Video Game, and 12 moreGames for Health, Serious Gaming, Health Studies, Medicine, Binge-eating Disorders, Impulsivity, Library and Information Studies, Humans, Mental Disorder, Serious Game, Pathological Gambling, and Public health systems and services research
Abstract. Serious games are about to enter the medical sector to give people with behavioural or addictive disorders the ability to use them as part of health promotion and disease prevention. The PlayMancer framework will support... more
Abstract. Serious games are about to enter the medical sector to give people with behavioural or addictive disorders the ability to use them as part of health promotion and disease prevention. The PlayMancer framework will support physical rehabilitations and psycho-education programs thru a modular multiplayer networked 3D game based on the Universally Accessible Games (UA games) guidelines. 1
In the frame of air quality monitoring of urban areas, the task of short-term prediction of key-pollutants concentrations is a daily activity of major importance. Automation of this process is desirable, but development of reliable... more
In the frame of air quality monitoring of urban areas, the task of short-term prediction of key-pollutants concentrations is a daily activity of major importance. Automation of this process is desirable, but development of reliable predictive models with good performance, to support this task in operational basis presents many difficulties. In this paper we present and discuss the NEMO prototype that has been built in order to support short-term prediction of NO2 maximum concentration levels in Athens, Greece. NEMO is based on a case-based-reasoning approach combining heuristic and statistical techniques. The process of development of the system, its architecture and its performance, are described in this paper. NEMO performance is compared with that of a back propagating neural network, and a decision tree (CART). The overall performance of NEMO makes it a good candidate to support air pollution experts in operational conditions.
Research Interests:
Research Interests:
Feature selection for air quality forecasting:
Research Interests:
In this study, results of a variety of ML algorithms are tested against artificially polluted datasets with noise. Two noise models are tested, each of these studied on a range of noise levels from 0 to 50algorithm, a linear regression... more
In this study, results of a variety of ML algorithms are tested against artificially polluted datasets with noise. Two noise models are tested, each of these studied on a range of noise levels from 0 to 50algorithm, a linear regression algorithm, a decision tree, a M5 algorithm, a decision table classifier, a voting interval scheme as well as a hyper pipes classifier. The study is based on an environmental field of application employing data from two air quality prediction problems, a toxicity classification problem and four artificially produced datasets. The results contain evaluation of classification criteria for every algorithm and noise level for the noise sensitivity study. The results suggest that the best algorithms per problem in terms of showing the lower RMS error are the decision table and the linear regression, for classification and regression problems respectively.
Research Interests:
Feature selection is a process of determining the most relevant features of a given problem in order to improve the generalization and the performance of a relevant classification or regression algorithm.This paper focuses on the... more
Feature selection is a process of determining the most relevant features of a given problem in order to improve the generalization and the performance of a relevant classification or regression algorithm.This paper focuses on the exploitation of a genetic algorithm following a wrapping iterative approach used to extract an optimal feature subset of a large database containing pollutant concentration measurements. The feature subset is fed to a machine learning algorithm in order to predict the daily maximum concentration of two air pollutants.The encoding problem of the complexity of representation of the features in the genomes is tackled. Results of the experimentation on a specific dataset of an air quality forecasting problem are presented, as well as some proposed alterations on the standard genetic algorithm that guided the process to a mature convergence and gave good solutions for this problem. A modified version of the initial algorithm is presented as well, implemented for...
Research Interests:
Feature selection is a process followed in order to improve the generalization and the performance of several classification and/or regression algorithms. Feature selection processes are divided in two categories, the filter and the... more
Feature selection is a process followed in order to improve the generalization and the performance of several classification and/or regression algorithms. Feature selection processes are divided in two categories, the filter and the wrapper approach. The formal is performed independently of the learning algorithm while the later makes use of the algorithm in an iterative way. As [1] describe, the feature weighting algorithms are divided into two categories: the filtering methods and the wrapper methods. The former is a no-feedback, pre-selection approach where the selection of the feature subset is performed independently of the learning algorithm. The later is an iterative method that encapsulates the learning algorithm in the feature selection process.
Research Interests:
Research Interests:
ABSTRACT In this paper, a novel system utilizing virtual reality for enhancing music tuition systems will be described. The proposed system operates on music notation files and produces 3D animations of virtual hands, playing a virtual... more
ABSTRACT In this paper, a novel system utilizing virtual reality for enhancing music tuition systems will be described. The proposed system operates on music notation files and produces 3D animations of virtual hands, playing a virtual recorder. The work is supported by two applications: a) the Fingering Viewer, which visualizes the animations in a 3D world and b) the Movement Authoring Tool, which provides the user with the ability to author viewing positions and comments, and store the results in a dedicated file format. The whole system provides added value to traditional multimedia music tuition systems by exploiting the efficiency of virtual reality visualization techniques.
Research Interests:
Research Interests:
Research Interests:
In this study, results of a variety of ML algorithms are tested against artificially polluted datasets with noise. Two noise models are tested, each of these studied on a range of noise levels from 0 to 50algorithm, a linear regression... more
In this study, results of a variety of ML algorithms are tested against artificially polluted datasets with noise. Two noise models are tested, each of these studied on a range of noise levels from 0 to 50algorithm, a linear regression algorithm, a decision tree, a M5 algorithm, a decision table classifier, a voting interval scheme as well as a hyper pipes classifier. The study is based on an environmental field of application employing data from two air quality prediction problems, a toxicity classification problem and four artificially produced datasets ...
Having witnessed a rapid development of the digital media literacy in the modern society due to a multitude of technological advances in the low-cost photography, cinematography and 2D/3D graphic design, there is a proliferation of high... more
Having witnessed a rapid development of the digital media literacy in the modern society due to a multitude of technological advances in the low-cost photography, cinematography and 2D/3D graphic design, there is a proliferation of high quality media content generated, ...
Research Interests:
Monitoring air quality is a necessary activity in many industrial and urban areas of our planet. Air Quality OperationalCentres (AQOCs) are established for this purpose, in areas with serious air pollution problems. The AQOCsare... more
Monitoring air quality is a necessary activity in many industrial and urban areas of our planet. Air Quality OperationalCentres (AQOCs) are established for this purpose, in areas with serious air pollution problems. The AQOCsare operational units, responsible for managing monitoring networks, processing the collected information, eventuallyproviding on-line assessment of air pollution and its short-term and long-term evolution. Great volumes of dataare collected over time in these centres. One of the prime concerns of scientists in ...
Research Interests:
Research Interests:
Feature selection is a process of determining the most relevant features of a given problem in order to improve the generalization and the performance of a relevant classification or regression algorithm. This paper focuses on the... more
Feature selection is a process of determining the most relevant features of a given problem in order to improve the generalization and the performance of a relevant classification or regression algorithm. This paper focuses on the exploitation of a genetic algorithm following a wrapping iterative approach used to extract an optimal feature subset of a large database containing pollutant concentration measurements. The feature subset is fed to a machine learning algorithm in order to predict the daily maximum concentration of two air pollutants ...
Research Interests:
Research Interests: Information Retrieval, Human Computer Interaction, Information Technology, Natural Language Processing, Machine Learning, and 33 moreData Mining, Data Analysis, Machine Translation, Pattern Recognition, Power System, Speech Recognition, Speech Processing, Intelligent Agent, Multi Agent System, System Engineering, Graphic User Interface Design, expert System, hidden Markov model, Knowledge Acquisition, Knowledge Integration, Decision Tree, Human Language Technology, Real Time, Knowledge base, Fuzzy System, Human Computer Interface, Exponential Growth, Language Model, Data Processing, Case Base Reasoning, Indexation, Concept Learning, Neural Net, Evolutionary Programming, Artificial Neural Network, Real-world Application, Knowledge Discovery In Database (kdd), and Information System
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
In this paper we propose a unified approach for integrating implicit and explicit knowledge in neurosymbolic systems as a combination of neural and neuro-fuzzy modules. In the developed hybrid system, training data set is used for... more
In this paper we propose a unified approach for integrating implicit and explicit knowledge in neurosymbolic systems as a combination of neural and neuro-fuzzy modules. In the developed hybrid system, training data set is used for building neuro-fuzzy modules, and represents implicit domain knowledge. The explicit domain knowledge on the other hand is represented by fuzzy rules, which are directly mapped into equivalent neural structures. The aim of this approach is to improve the abilities of modular neural structures, which are ...