10ᵗʰ Hellenic Conference on Artificial Intelligence 9 12 JULY Program

Transcription

1 10ᵗʰ Hellenic Conference on Artificial Intelligence 9 12 JULY 2017 Program

2 Conference Organization General Chairs: Nikos Fakotakis, Professor, University of Patras Vasileios Megalooikonomou, Professor, University of Patras General Co-Chair: Vassilis Plagianakos, Associate Professor, University of Thessaly, Greece (EETN Chairperson) Organizing Committee: Nikos Fakotakis, Professor, University of Patras Vasileios Megalooikonomou, Professor, University of Patras Ioannis Hatzilygeroudis, Professor, University of Patras Christos Makris, Associate Professor, University of Patras Konstantinos Moustakas, Associate Professor, University of Patras Kyriakos Sgarbas, Associate Professor, University of Patras Program Committee Chairs: Ioannis Hatzilygeroudis, Professor, University of Patras, Greece Christos Makris, Associate Professor, University of Patras, Greece Media Chair: Nikos Fakotakis, Professor, University of Patras, Greece Workshop Chair: Christos Makris, Associate Professor, University of Patras, Greece Tutorials Chair: Kyriakos Sgarbas, Associate Professor, University of Patras, Greece

3 Program Committee Members: Dimitris Achlioptas, Dept. of Computer Science, Univ. of California Santa Cruz Αnastasia Ailamaki, Dept. of Computer and Communication Sciences, EPFL Petros Drineas, Associate Professor, Dept. of Computer Science, Purdue University Costas Iliopoulos, Professor, King s College London Panos Ipeirotis, Associate Professor, Leonard N. Stern School of Business, New York University Prof. Myra Spiliopoulou, Fakultät für Informatik (FIN) Ioannis Tsamardinos, Computer Science Department, University of Crete Vassilios Verykios, Hellenic Open University Phivos Mylonas, National Technical University of Athens Stasinos Konstantopoulos, NCSR Demokritos Efstratios Kontopoulos, Information Technologies Institute, Centre for Research & Technology Nick Bassiliades, Aristotle University of Thessaloniki Antonis Bikakis, University College London Fotios Kokkoras, TEI of Thessaly Michael Sioutis, University of Artois Ergina Kavallieratou, University of the Aegean Ioannis Katakis, University of Athens Konstantinos, Blekas University of Ioannina Kostas Stefanidis, University of Tampere Pavlos Peppas, University of Technology Sydney Grigorios Tsoumakas, Aristotle University of Thessaloniki Christos-Nikolaos Anagnostopoulos, University of the Aegean Manolis Maragoudakis, University of the Aegean Dimitris Kalles, Hellenic Open University Anastasios Tefas, Aristotle University of Thessaloniki Stefanos Kollias, National Technical University Giorgos Flouris, FORTH-ICS Iosif Mporas, University of Hertfordshire Basilis Gatos, Institute of Informatics and Telecommunications, NCSR Demokritos Michalis Titsias, AUEB Camelia Pintea, Technical University of Cluj-Napoca, North University Center at Baia Mare Grigoris Antoniou, University of Huddersfield Vangelis Karkaletsis, NCSR Demokritos Manolis Koubarakis, National and Kapodistrian University of Athens Todor Ganchev, Technical University of Varna Konstantinos Parsopoulos, University of Ioannina Dimitris Vrakas, Aristotle University of Thessaloniki Isidoros Perikos, University of Patras, Department of Computer Engineering & Informatics Dimitris Iakovidis, Technological Educational Institute of Lamia Ioannis Partalas, Expedia LPS Nikos Fazakis, University of Patras Efstathios Stamatatos, University of the Aegean George Magoulas, Birkbeck College Ion Androutsopoulos, Athens University of Economics and Business (AUEB) Sotiris Batsakis, University of Huddersfield Spiros Likothanassis, University of Patras Georgios Paliouras, Institute of Informatics & Telecommunications, NCSR Demokritos Antonios Gasteratos, Democritus University of Thrace Ilias Maglogiannis, University of Piraeus

4 Michael Loizos, Open University of Cyprus George Tsihrintzis, University of Piraeus Jim Prentzas, Democritus University of Thrace Dimitrios Vogiatzis, NCSR Demokritos Ioannis Vlahavas, Aristotle University of Thessaloniki Foteini Grivokostopoulou, University of Patras Andreas Symeonidis, Aristotle University of Thessaloniki Christophoros Nikou, University of Ioannina Aristidis Likas, University of Ioannina Christos Papatheodorou, Department of Archives and Library Science, Ionian University, Corfu, Greece Petros Stefaneas, National Technical University of Athens Kostas Stergiou, University of Western Macedonia Elpida Keravnou-Papailiou, Professor of Computer Science Dimitris Plexousakis, Institute of Computer Science, FORTH George Vouros, University of Piraeus Georgios Dounias, Associate Professor, University of the Aegean Georgios Chalkiadakis, Technical University of Crete Vassilis Plagianakos, University of Thessaly Sotiris Kotsiantis, Univerisity of Patras Athanasios Tsadiras, Aristotle University of Thessaloniki Vasile Palade, Coventry University Manolis Gergatsoulis, Associate Professor, Department of Archive and Library Sciences Spyros Vosinakis, University of the Aegean, Department of Product and Systems Design Engineering Ioannis Refanidis, University of Macedonia, Dept. of Applied Informatics Nikos Nikolaidis, Aristotle University of Thessaloniki Nikos Aspragathos, University of Patras Antonis Kakas, University of Cyprus ordinary Antonios Tzes, Abu Dabi New York University Plamen Angelov, Lancaster University

5 Invited Talks A Holistic Approach to Automatic Deep Understanding of Technical Documents by Dr. Nikolaos Bourbakis, IEEE Fellow Director, CART-WSU, BAIF ABSTRACT Most of the technical documents are composed by several modalities, like diagrams, tables, formulas, functions, algorithms, graphics, pictures and natural language text. Each of these modalities and their associations significantly contribute to the overall deep understanding of the technical document and the knowledge represented in it. Here, for us all these modalities, except NL text, are considered as images. Thus, each technical document mainly is composed by NL text sentences and images. Thus, in this talk we present a holistic approach, where all these modalities can be expressed into the same two modalities (natural languages text sentences and SPN graphs) for better associations and deeper understanding of a technical document. This deeper understanding will come from two different novel contributions. The first unique contribution will be an enrichment of the NL text part with additional NL text sentences extracted from the images of the technical document. The second unique contribution will come from the SPN models of these images that enrich the main block diagram s functionality by generating a simulator for the system described in that technical document. Graph degeneracy and applications to social networks and text mining by Michalis Vazirgiannis, Professor at LIX, Ecole Polytechnique in France ABSTRACT Graph degeneracy is a popular method to approximate the densest subgraph in almost linear complexity time. In our research work we extended this method to weighted and directed graphs and capitalizing on them to investigate its potential in different graph and text mining cases. One of the cases is k-core based community evaluation specifically metrics that integrates authority and collaboration a properties not captured by the single node metrics or by the established community evaluation metrics. Based on the k-core, which essentially measure the robustness of a community under degeneracy, we extend it to weighted graphs. We further extend introduce novel metrics for evaluating the collaborative nature of directed graphs and define a novel D-core metric, extending the classic graph-theoretic notion of k-cores for undirected graphs to directed ones.. We applied the D-core approach on large real-world graphs such as Wikipedia and Aminer.org citation data and report interesting results. The D- core metric has been adopted by Aminer as part of its reported metrics see an example here. We also investigate to issue of influence maximization in graphs using degeneracy as means to select the optimal spreaders. The results are promising and show that starting an epidemic from the densest k-truss. We also investigate thoroughly the issue of graph similarity via novel graph kernels and embedding schemes with applications to graph classification in chemo-informatics, social networks and text mining.

6 At the level of Text mining, we capitalize on the Graph-of Words (GoW) model, that capitalizes on a graph representation of documents and captures inherently the words order and distances in the document, apart from the frequency, to capture document similarity. We applied graph-of-word in various tasks such as ad-hoc Information Retrieval, Single-Document Keyword Extraction, Text Categorization and Sub-event Detection in Textual Streams (i.e. twitter) and document summarization. In all cases the graph of word approach, assisted by degeneracy at times, outperforms the state of the art base lines in all cases. We are currently investigating the potential of the GoW as input to deep learning architectures for text mining tasks. Deep learning for collaborative control of mobile robots for area coverage by Anthony Tzes, Professor at NYU in Abu Dhabi ABSTRACT Collaborative control of mobile robots demand the mutual exchange of information related to their position. This is used for the construction of the region of responsibility of each robot corresponding to its Voronoi cell. These cells are disjoint and their union comprise the overall area to be sensed. Rather than relying on gradient-search based collaborative control algorithms, a deep learning algorithm is suggested that adapts the heading and velocity of each robot while maximizing the combined sensed area. Simulation studies are provided to indicate the efficiency of the deep-learning based distributed controller. Time-aware Multi-agent Symbiosis by Panos Trahanias, Professor at Department of Computer Science, University of Crete ABSTRACT Contemporary research in human-machine symbiosis has mainly concentrated on enhancing relevant sensory, perceptual and motor capacities, assuming short-term and nearly momentary interaction between the two ends. Still, human-machine confluence encompasses an inherent temporal dimension that is typically overlooked by current research endeavors. In the current keynote we present a novel approach aiming at bridging the fundamental gap of time perception in multi-agent interaction by shifting the focus of human-machine coexistence on the temporal and long-lasting aspects of symbiosis. We put forward the concept of entimed cognition postulating that intelligent thinking is largely determined by the temporal properties of the cognitive processes and real-world phenomena. According to entimed cognition, artificial partners acquire capacities that are inherently existent in humans, such as being able to dynamically allocate cognitive resources, to shift attention in the past and future, to recall experiences, to make associations between asynchronous events and more. We examine the role of time in multi-agent systems, considering particularly the case of symbiotic human-robot interaction (shri). The proposed research computationally models time perception and replicates relevant processes in-silico, adopting a rigorous research approach that involves modeling, integration on actual robotic platforms and real-world experiments.

7 Special Sessions Tutorials - Contests Special Sessions 1. Natural Language Processing for Social Media Analysis Organising committee, Iosif Mporas, University of Hertfordshire, UK Vasiliki Simaki, Lancaster University, UK Carita Paradis, Lund University, Sweden Andreas Kerren, Linnaeus University, Sweden Michael Paraskevas, CTI Diophantus, Greece ABSTRACT The exploitation of natural language from social media data is an intriguing task in the fields of text mining and natural language processing (NLP), with plenty of applications in social sciences and social media analytics. In this special session, we call for research papers in the broader field of NLP techniques for social media analysis. The topics of interest include (but are not limited to): sentiment analysis in social media and beyond (e.g. stance identification, sarcasm detection, opinion mining), computational sociolinguistics (e.g., identification of demographic information such as gender, age), and NLP tools for social media mining (e.g., topic modelling for social media data, text categorization and clustering for social media, social media visual analytics). More info: 2. Intelligent Biomedical Systems and Applications Organising committee, Konstantinos Moustakas, Associate Professor, University of Patras Vasileios Megalooikonomou, Professor, University of Patras Christos Makris, Associate Professor, University of Patras ABSTRACT Recent advances in computing, archiving and communication technologies have resulted in an outbreak of available biomedical data of multiple heterogeneous sources. Processing, data mining and rendering of meaningful information has become a challenge of interdisciplinary nature. Moreover, the significant advances in computational medicine add one more dimension of information to be analyzed, related to the simulated evaluation of deterministic or stochastic computational models. The scope of the special session is to provide a platform for new ideas, achievements and implementations in the field of intelligent biomedical systems and applications. Researchers are invited to submit their work following the same schedule as for the main SETN 2018 conference. More info:

8 3. Special Session on Quantum Artificial Intelligence (QAI) Organising committee, Organising committee, Kyriakos Sgarbas, University of Patras, Nikos Konofaos, Aristotle University of Thessaloniki, Ioannis Karafyllidis, Democritus University of Thrace, ABSTRACT The recent developments in quantum computing hardware have inspired several researchers to focus in the creation of new quantum algorithms to address complex problems that were difficult to confront via classical computation. Artificial Intelligence is a huge compedium of such complex problems. A great deal of classical AI algorithms are handicaped by the "combinatorial explosion" effect and until now were used only in combination with problemspecific heuristics, in order to reduce the amount of computation. On the other hand, recent quantum computing architectures have indicated great potential, especially in the areas of optimization, constraint satisfaction and machine learning. It is now more than evident that quantum computing and artificial intelligence can merge in a new scientific and technological domain, i.e. Quantum Artificial Intelligence, thus several research laboratories with this name have begun to emerge worldwide. The purpose of this Special Session is to present recent research in quantum computing and especially quantum architectures and quantum algorithms for artificial intelligence, machine learning, constraint satisfaction, optimization, and related areas. More info: Tutorials 1. Deep Learning for Computational Biology Tutor, Thrasyvoulos Karydis, MIT Media Lab ABSTRACT The field of computational biology has seen dramatic growth over the past few years, principally due to the advent of high-throughput experimental technologies producing Petabytes of data across different biological scales. As part of this transition, the traditional, systems-based and theory-based, approaches to understand and engineer biology have given place to high-capacity, data-driven deep-learning methods. The goal of this session is to stimulate discussion on how to build, train and interpret data-driven models for biological data, in light of the current experimental work in the field. This session comprises two parts: a talk to present current research problems in computational biology on which deep learning has had a significant impact, with a focus on the presenter s work on protein biology and a technical tutorial to provide hands-on experience with the standard tools in deep learning and their applications to molecular biology datasets. More info:

9 Contests 1. Contest in Robotics Organisers, Kavallieratou Ergina, University of the Aegean Dimitris Chatzis, University of the Aegean Balafoutis Athanasios, University of the Aegean Ioanna Bakali, University of the Aegean Anestis Vovos DESCRIPTION In the context of STEN2018, a PanHellenic competition in educational robotics is organized. The competition will be held on July 2018 in the university of Patras establishments. DETAILS You can participate in the following contests: Sumo Line Follower Free Style Each team consists of a coach and four (4) members at most. The contests outlines are as follows: Sumo Two robots compete in a head-to-head match following the basic system of traditional human sumo matches. The sole purpose is a pushing match between the two robots to force the other out of the arena. Multiple weight and dimension classes are allowed. The robots compete each other on a Dohyo (sumo ring). The size of the arena depends on robot class. The match consists of three rounds. Every match lasts 3 minutes. The match ends when a contestant earns two Yuhkoh points. Yuhkoh point shall be given when a robot forces the body of the opposing robot to touch the space outside the ring. There is no age limit. A more through description of the trial, the rules and the limitations you can find in the rules brochure. Line Follower Is one of the most famous robotic contests. The objective is to follow a black line on a white background, without losing the line and navigating through several turns and obstacles. The robot has to complete the course in the shortest period of time while accurately tracking the course line from start to finish. The faster and more accurate robot wins. The line following course will traverse a white paper rectangle, 120cm x 250cm. The line will be a black approx. 15mm wide line, traversing the arena from end to end with many sharp turns. Robots must be in constant contact with the line. Any robot that loses the line course must reacquire the line at the point where it was lost or at any earlier, already traversed, point. Robot that loses the line course and fails to reacquire it, will be allowed a single reattempt from the beginning. If any part of the robot goes out of the arena it will be disqualified. There may be some obstacles on the track. There is a maximum of 3 minutes for a robot to complete the course. There is no age limit. A more through description of the trial, the rules and the limitations you can find in the rules brochure.

10 Free Style Robots can perform any function. Within the framework of the free style category, simple automation can be demonstrated. The exhibits are rated by a board of judges, on a scale from Some of the categories to which they are rated are: Originality: Is this robot unique? Are there any others like it? Functionality: Does this robot complete a function that could be readily useful? Usability: Can the robot feature be exploitable in the near future? Aesthetics: Does it look cool? Autonomy: How long and how far can it go on a single power charge? The Free Style competition is distinguished into three age categories: Primary Education for primary school students Secondary Education for junior & senior high school students Higher Education for graduate and under-graduate students There is no limit in the participation concerning the materials. A more through description of the trial, the rules and the limitations you can find in the rules brochure. More info Contest website: Registration form:

11 Program Brief Sunday, July, 8 th 16:00-19:00 Registration Monday, July, 9 th 8:30-9:00 Registration 9:00-9:30 Opening Ceremony: Welcome address by the chairs Keynote 1: A Holistic Approach to Automatic Deep Understanding of Technical Documents 9:30-10:30 Dr. Nikolaos Bourbakis, IEEE Fellow, Director, CART-WSU, BAIF Chair:.. 10:30-11:30 Session O1: Deep Learning (55min) Chair. Neural Architecture Search with Synchronous Advantage Actor-Critic Methods and Partial Training 10:30-10:50 George Kyriakides and Konstantinos G. Margaritis Convolutional Neural Networks for Toxic Comment Classification 10:50-11:10 Spiros V. Georgakopoulos, Sotiris K. Tasoulis, Aristidis G. Vrahatis and Vassilis P. Plagianakos. Speaker Verification based on extraction of Deep Features (S) 11:10-11:30 Evangelos Mitsianis, Evaggelos Spyrou and Theodore Giannakopoulos 11:30-12:00 Coffee Break Session O2: Data Mining (1h+55min) 12:00-14:00 Chair:. Fully Unsupervised Convolutional Learning for Fast Image Retrieval 12:00-12:20 Maria Tzelepi and Anastasios Tefas Multiagent Reinforcement Learning Methods to Resolve Demand Capacity Balance Problems 12:20-12:40 Christos Spatharis, Theocharis Kravaris, George Vouros, Konstantinos Blekas, Georgios Chalkiadakis, Jose Manuel Cordero and Esther Calvo Fernandez Recurrent attention for deep neural object detection 12:40-13:00 Georgios Symeonidis and Anastasios Tefas Deep Sparse Autoencoders for Football Match and Bet Prediction 13:00-13:20 Konstantinos Tsampazis and Anastasios Tefas Data-Driven Audio Feature Selection for Audio Quality Recognition in Broadcast News 13:20-13:40 Theodoros Theodorou, Iosif Mporas, Ilyas Potamitis and Nikos Fakotakis A Semi-supervised regressor based on model trees 13:40-14:00 Nikos Fazakis, Stamatis Karlos, Sotiris Kotsiantis and Kyriakos Sgarbas 14:00-15:30 Lunch 15:30-17:30 15:30-15:50 15:50-16:10 16:10-16:30 Session O3: Machine Learning I (2h) Chair:. Evaluation of Sensitive Data Hiding Techniques for Transaction Databases Christos Makris and Panagiotis Markovits On Using Linear Diophantine Equations for Efficient Hiding of Decision Tree Rules Georgios Feretzakis, Dimitris Kalles and Vassilios Verykios Generalized Adaptive Possibilistic C-Means Clustering Algorithm Spyridoula Xenaki, Konstantinos Koutroumbas and Athanasios Rontogiannis

12 The Projected Dip-means Clustering Algorithm 16:30-16:50 Theofilos Chamalis and Aristidis Likas Generating Recommendations by Graph Traversal in Social Rating Networks 16:50-17:10 Flora Sakketou, Nicholas Ampazis and Dimosthenis Drivaliaris Several MapReduce Implementations for Privacy Preserving Record Linkage (S) 17:10-17:30 Dimitris Boussis, Elias Dritsas, Andreas Kanavos, Spyros Sioutas and Vassilios Verykios 17:30-18:00 Coffee Break Session O4: Machine Learning IΙ (1h+10min) Poster Session PS1: 18:00-19:00 Chair: Chair. 18:00-18:20 18:20-18:40 18:40-18:50 18:50-19:00 Sliding Window Approach for Online Energy Disaggregation Using Artificial Neural Networks Odysseas Krystalakos, Christoforos Nalmpantis and Dimitris Vrakas Identifying Retweetable Tweets with a Personalized Global Classifier Michail Vougioukas, Ion Androutsopoulos and Georgios Paliouras A Parallel Algorithm for Tracking Dynamic Communities based on Apache Flink (S) Georgios Kechagias, Grigorios Tzortzis, Dimitrios Vogiatzis and Georgios Paliouras Deep learned features for image retrieval (S) Evangelos Mitsianis, Evaggelos Spyrou, Theodore Giannakopoulos, Stavros Niafas and Stavros Perantonis Design of a vision substitution vibrotactile vest for the visually impaired. Dimitris Kalampalikis and Konstantinos Moustakas 3-Class Prediction of Asthma Control Status Using a Gaussian Mixture Model Approach. Gerasimos Arvanitis, Otilia Kocsis, Aris Lalos, Stavros Nousias, Konstantinos Moustakas and Nikos Fakotakis A gaming ecosystem as a tool for research and education in Artificial Intelligence. Kyriakos Giagtzoglou and Dimitris Kalles Travel Companion: A mobile system for trip assistance relying on Artificial Intelligence and Augmented Reality. Prodromos Lilitsis, Theodore Patkos, Giorgos Flouris and Dimitris Plexousakis Sports and Nutrition Data Science using Gradient Boosting Machines. Antonios Pantazopoulos and Manolis Maragoudakis Classification of occluded 2D objects using deep learning of 3D shape surfaces. Vasileios Tzitzilonis, Vassilios Kappatos, Evangelos Dermatas and George Apostolopoulos El Greco: a 3d-printed humanoid that anybody can afford. Pavlos Skoupras, Shubham Khandelwal, Jaideep Upadhyay, Konstantinos Paraskevas, Georgios Zervas, Nikolaos Fourtounis, Michail Chartomatsidis, Dimitris Katsios, Georgios Papamichalakis and Ergina Kavallieratou Control a robot via internet using a block programming platform for educational purposes Ioanna Bakali, Dimitris Chatzis, Nikolaos Fourtounis, Maria Soulountsi, Nikolaos Mavropoulos, Aristotelis Theodoulidis, Nikolaos Manos, Panagiotis Papanastasiou and Ergina Kavallieratou 19:00-21:00 Welcome Reception 9:00-10:00 10:00-11:00 Tuesday, July, 10 th Keynote 2: Graph degeneracy and applications to social networks and text mining Dr. Michalis Vazirgiannis, Professor at LIX, Ecole Polytechnique in France Chair:. Session O5: Text Mining and Analysis (70min) Chair:...

13 Intrinsic Author Verification Using Topic Modeling 10:00-10:20 Nektaria Potha and Efstathios Stamatatos Real Time Location Based Sentiment Analysis on Twitter - The AirSent System (S) 10:20-10:30 Dimitrios Michailidis, Nikolaos Stylianou and Ioannis Vlahavas Energy profile representation in vector space (S) 10:30-10:40 Christoforos Nalmpantis, Odysseas Krystalakos and Dimitris Vrakas Energy profile representation in vector space (S) 10:40-10:50 Christoforos Nalmpantis, Odysseas Krystalakos and Dimitris Vrakas Diversifying Search Engine Results (S) 10:50-11:00 Christos Klavdianos and Christos Makris 11:00-11:30 Coffee Break Session O6: Knowledge Representation and 11:30-13:30 Reasoning (1h+55min) Chair: Towards Multipolicy Argumentation 11:30-11:50 Nick Bassiliades, Nikolaos Spanoudakis and Antonis Kakas Correlations of Neural Activity with Behavioral Kinematics during Active Tactile Decision Making 11:50-12:10 Ioannis Delis, Jacek Dmochowski, Paul Sajda and Qi Wang Iterated Belief Revision and Dalal's Operator (S) 12:10-12:25 Theofanis Aravanis, Pavlos Peppas and Mary- Anne Williams Towards Human Activity Reasoning with Computational Logic and Deep Learning (S) 12:25-12:45 Ioannis Prapas, Georgios Paliouras, Alexandros Artikis and Nicolas Baskiotis Local weighted Averaged 2-Dependence Estimator(S) 12:45-13:00 Stamatis Karlos, Αikaterinι Karanikola, Vangjel Kazllarof and Sotiris Kotsiantis Composite Event Patterns for Maritime Monitorin(S) Manos Pitsikalis, Ioannis Kontopoulos, Alexander Artikis, Elias Alevizos, Paul Delaunay, 13:00-13:15 Jules-Edouard Pouessel, Richard Dreo, Cyril Ray, Elena Camossi, Anne-Laure Jousselme and Melita Hadzagic An Aggregation Operator for Evaluating 13:15-13:30 Unbounded Positive Evidence (S) Ilias Kotinas and Fakotakis Nikos 13:30-15:00 Lunch Session SS1: Special Session (IBSA) (1h+55min) 15:00-17:00 Chair: Dr. Konstantinos Moustakas 15:00-15:20 15:20-15:40 15:40-16:00 16:00-16:20 16:20-16:40 16:40-17:00 Tutorial " Deep Learning for Computational Biology" Part A: Talk "Deep representation learning for protein analysis, search and design" Tutor: Thrasyvoulos Karydis, MIT Media Lab Tutorial " Deep Learning for Computational Biology" Part B: "Hands-on Deep Learning Tutorial for Computational Biology" Tutor: Thrasyvoulos Karydis, MIT Media Lab 11:30-12:00 Technical Presentation on Deep Learning with Applications in Biology 12:00-12:15 Installation of Jupyter notebooks on participants' laptops 12:15-13:30 Coding session - introduction - language translation - molecular properties prediction - protein properties prediction Global vs local classification models for multi-sensor data fusion Evangelia Pippa, Evangelia I. Zacharaki, Ahmet Turan Özdemir, Billur Barshan and Vasileios Megalooikonomou Characterization of whole-body muscle activity during reaching movements using space-by-time modularity and functional similarity analysis Ioannis Delis, Pauline Hilt, Thierry Pozzo, Stefano Panzeri and Bastien Berret Exploring machine learning for monitoring and predicting severe asthma exacerbations Aggeliki Anastasiou, Otilia Kocsis and Konstantinos Moustakas Pathway analysis using XGBoost classification in Biomedical Data Georgios Dimitrakopoulos, Aristidis Vrahatis, Vassilis Plagianakos and Kyriakos Sgarbas Mining Free-Text Medical Notes for Suicide Risk Assessment Marios Adamou, Grigoris Antoniou, Elissavet Greasidou, Vincenzo Lagani, Paulos Charonyktakis and Ioannis Tsamardinos Towards visualizing primary Sjögren's Syndrome data from heterogeneous cohorts (S) Eleftheria Polychronidou, Ilias Kalamaras, Kostantinos Votis and Dimitrios Tzovaras 17:00-17:30 Coffee Break Session O7: Evolutionary and Nature 17:30-18:30 Inspired Methods (1h) Chair:. A novel Nature Inspired metaheuristic for Optimal 17:30-17:50 Leveling of Resources in Project Management (F) Alexandros Tzanetos, Georgios Dounias, Christos Session O8: Agent-Based Systems (55min) Chair:. Detecting and Measuring Human Walking in Laser Scans (F)

14 17:50-18:10 18:10-18:30 20:00-23:30 Banquet Kyriklidis, Apostolis Dimoulakis and Anastasia Papamichail Acquisition of approximate throughput formulas for serial production lines with parallel machines using intelligent techniques (F) Konstantinos Boulas, Alexandros Tzanetos and Georgios Dounias A Hybrid Evolutionary Algorithm for Maximizing Satisfiability in Temporal or Spatial Qualitative Constraints (F) Ali Mensi, Jean-François Condotta, Issam Nouaouri, Michael Sioutis and Lamjed Ben Saïd Katerina Zamani, Georgios Stavrinos and Stasinos Konstantopoulos Game theoretic optimal position computation of collaborating agents for visual area coverage (F) Sotiris Papatheodorou, Michalis Smyrnakis, Tembine Hamidou and Anthony Tzes DRAMa: An IoT-enabled Distributed Reputation Agent Model Kalliopi Kravari, Maria Ustyantseva and Nick Bassiliades Wednesday, July, 11 th Keynote 3: Deep learning for collaborative control of mobile robots for area coverage 9:00-10:00 Dr. Anthony Tzes, professor, NYU Abu Dhabi Chair: Keynote 4: Time-aware Multi-agent Symbiosis 10:00-11:00 Dr. Panos Trahanias, professor, Department of Computer Science, University of Crete Chair: 11:00-11:30 Coffee Break Session SS2: Special Session (NLP4SMA) 1,5 11:30-13:30 Chair: Iosif Mporas Controversy and Sentiment: An Exploratory Study 11:30-11:50 Christopher Leberknight, Kateryna Kaplun and Anna Feldman Detection of Stance-related Characteristics in Social Media Text 11:50-12:10 Vasiliki Simaki, Panagiotis Simakis, Carita Paradis and Andreas Kerren Text analysis for decision making under adversarial 12:10-12:30 environments Ilias Kotinas and Nikos Fakotakis WAMBy: An information retrieval approach to webbased question answering 12:30-12:50 Christos Samarinas and Grigorios Tsoumakas Detecting Censorable Content on SinaWeibo: A Pilot Study (S) 12:50-13:10 Kei Yin Ng, Anna Feldman and Christopher Leberknight Evaluation of an Educational Training Platform Using Text Mining (S) 13:10-13:30 Nikolaos Spatiotis, Isidoros Perikos, Iosif Mporas and Michael Paraskevas 13:30-15:00 Lunch 15:00-16:00 Session SS3: Special Session (QAI) (50min) Chair: Kyriakos Sgarbas Application of Quantum Gradient Descent as a 15:00-15:20 Learning Algorithm for Factorization Machine Narges Alavi Samani and Hossein Aghababa Improving the Sequence Alignment Method by 15:20-15:40 Quantum Multi-Pattern Recognition (S) Konstantinos Prousalis and Nikos Konofaos Knock Detection Improvement Applying Quantum Signal Processing Method in Automotive System (S) 15:40-16:00 Amirhossein Moshrefi, Narges Alavi and Hossein Aghababa 16:00-16:30 Coffee Break 16:30-17:00 Awards 17:00-18:00 EETN General Assembly - SETN conclusion by the chairs Session RC1: Robotics Competition Chair: Ergina Kavallieratou

15 09:00-15:00 Tour Thursday, July, 12 th

16 Sponsors & Supporters