Software agent technologies reached a certain level of maturity that allows development of applications spanning from lab prototypes to mature real-life systems,
in domains that could have not been imagined before. Furthermore, software agent technologies proved their usefulness in synergy with methods of intelligent computing and
artificial intelligence.
The aim of the WASA series of workshops is to contribute to the advancement of technologies and applications of software agents' with a special interest in intelligent computing
including, but not limited to reasoning, semantics, pattern recognition, learning and cognition, etc. See the Topics section for more information on the web page for WASA:
https://perun.pmf.uns.ac.rs/events/wasa2019
Organizers:
Mirjana Ivanovic, University of Novi Sad, Serbia
Maria Ganzha, Technical University of Warsaw, Poland
Marcin Paprzycki, IBS PAN and WSM, Poland
Costin Badica, University of Craiova, Romania
The provision of large amounts of data from various sources (the Web, Social Media, Application Logs, Data Warehouses, Sensors, Mobiles,
Open Data, etc.) is now emerging into the collection and processing of "Big Data". While Big Data notion is adopted by both academic and enterprise
communities, there is currently a wide gap between its potential and its realization. Variety, velocity, scale, complexity, interpretation and security
problems with Big Data raise challenges at all phases of the pipeline that can extract information and knowledge from it. The Semantic Web can offer a
well-studied toolbox that can address Big Data requirements and contribute towards their meaningful analysis. Still, there are often issues that need to
be tackled with like bootstrapping, efficiency and standardized business processes for semantic analytics to achieve satisfactory results. To this end,
machine- and deep-learning techniques, have been shown to have considerable contributions towards Big Data analytics and to overcome Semantic Web inherent
limitations. Also, there is currently a shift from computational-intensive, server-side deployments, to efficient client implementations, as an effort to
give everyday browsing tasks a blend of intelligence.
Thus, there is a natural interest in using these data and technology assets to improve a variety of applications, especially in a Web environment. It is
very interesting to explore how researchers utilize data-driven strategies and discover what disciplines will change because of the advent of data. With
the vast amount of data now available, modern businesses are facing the challenges of storage, management, analysis, privacy, visualization, security and
data integration.
The aim of this workshop is to serve as an interdisciplinary forum for bringing together specialists from the scientific areas of Computer & Web Engineering,
Data Science, Semantic Computing, Bioinformatics-Personalized Medicine, Finance and Operational Research. The focus of this workshop is on current
technological advances and challenges about the development of big data-driven algorithms, methods and tools; furthermore, to investigate how semantics-aware
applications can contribute towards Big Data analysis on the Web.
Following the success of the previous four MT4BD (MT4BD2014, MT4BD2015, MT4BD2016, and MT4BD2018) aims to further promote the formation of a community
around the topic and gather an increased number of researchers and practitioners.
Organizers:
Professor Spiros Likothanassis
Professor Spyros Sioutas
Program Committee:
Tzovaras Dimitrios, CERTH/ITI, GR
Koutsomitropoulos Dimitrios, University of Patras, GR
Georgopoulos Efstratios, Technological Institute of Kalamata, GR
Votis Konstantinos, CERTH/ITI, GR
Tsolis Dimitrios, Universityof Patras, GR
Alexakos Christos, Industrial Systems Institute/ATHENA Reseach Center, GR
Kalogeras Athanasios, Industrial Systems Institute/ATHENA Reseach Center, GR
Makris Christos, University of Patras, GR
Vonitsanos Gerasimos, University of Patras, GR
Kanavos Andreas, University of Patras, GR
Savvopoulos Alkiviadis, University of Patras, GR
Drakopoulos George, Ionian University, GR
Karydis Ioannis, Ionian University, GR
Mylonas Phivos, Ionian University, GR
Livieris Ioannis, University of Patras, GR
| Big Data Analytics: | Semantic Analytics: | Tools and Applications: | Big Data Architectures and Frameworks: |
|---|---|---|---|
| • Business intelligence and analytics; • Interactive Visualization Technologies and Visual Analytics; • Personalization; • Data mining; • Human Collaboration (crowdsourcing); • Smart Manufacturing Analytics; • Internet of Things Data Analysis; |
• Ontologies for Big Data; • Reasoning approaches for knowledge extraction; • Ontology learning and topic modeling; • NLP and word embedding; • Semantic lakes and blockchain; • Data science and semantics; • Evaluation techniques; • Semantic deep learning; ◽ Ontologies as training sets; ◽ Ontology evolution and learning feedback; |
• E-commerce; • E-learning; • Smart Health and Wellbeing; • Smart Cities; • Sensors Networks; • Industrial Automation; • Systems Biology and Bioinformatics; • Network-based and Personalized Medicine; • Geoinformatics; • Financial Forecasting and Trading; • Security; |
• Cloud computing; • Grid computing; • Decentralized and P2P Computing; • Distributed Infrastructures and P2P Overlays; • High Performance Computing with Map-Reduce Programming; • High Performance Computing with Tensor-Flow Programming; • Deep Learning; • Large-scale triple stores; • OBDA approaches for big data access; • Reasoning over streaming data; • Data storage and processing frameworks; • Security and privacy; |
Reservoir Computing (RC) denotes a class of approaches for designing Recurrent Neural Networks
aiming at very fast learning in the context of temporal data processing. Essentially, while training is limited to a simple output layer, the dynamical
recurrent component is left untrained after initialization. The resulting RC methodology is nowadays widespread in the Neural Networks community, and
opens many intriguing exploring possibilities under both application and theoretical viewpoints.
This session aims at providing an ideal context for exchange of ideas and for cross-fertilization among interdisciplinary research areas that
might benefit from the RC approach. This special session calls for contributions in the area of RC, ranging from application-oriented to theoretical,
and from consolidated models applications to novel breakthrough pioneering results.
The topics covered by this special session include, but are not limited to, the following:
• Echo State Networks and Liquid State Machines
• Challenging applications of Reservoir Computing, including Big Data, embeddable systems, and industrial processes
• Novel Reservoir Computing models
• Theoretical analysis of Reservoir Computing
• Novel efficient training algorithms for Reservoir Computing
• Deep Reservoir Computing models
Organizers:
Petia Koprinkova-Hristova (Bulgarian Academy of Sciences, Bulgaria)
Claudio Gallicchio (University of Pisa, Italy)
Alessio Micheli (University of Pisa, Italy)
Artificial Intelligence (AI) has been applied successfully to many fields such as data analysis, finance, multimedia, signal and image processing, web
technologies, robotics, and automations, etc. Machine learning, as a major technology behind AI, is changing the world rapidly by deploying varied algorithms. For example,
artificial neural networks, especially those for deep learning, are implemented in real world such as the GPU computations owing to the maturity of high-speed and parallel
architecture. The latter is also becoming a promising research field for further explorations. Many researches of machine learning are inspired by the developments of computational
intelligence. How machine learning can be contributed to varied applications related to intelligence is the main focus of this special session. The methodologies of machine
learning may include mathematical or statistical foundations, algorithms, architectures, and uncertainty issues. As for applications of machine learning, we look forward to
including researches or implementations in varied fields that are emerged to intelligence and automation. For future trends of machine learning, we encourage authors to propose
their innovative ideas and concepts. We offer an opportunity for researchers and practitioners to identify new promising research directions as well as to publish recent advances
in this area.
The scope of the MLMAT 2019 includes, but is not limited to the following topics:
• Algorithms of machine learning
• Mathematical foundations of machine learning
• Machine learning based on probability and statistics
• Classifications based on machine learning
• Supervised learning and non-supervised learning
• Machine learning based on rough sets or fuzzy set theory
• Methodologies of computational intelligence
• GPU-based parallel computation and deep learning implementations
• Big data and machine learning
• IoT and machine learning
• Decision making by machine learnings
• FinTech and machine learning
• Intelligent systems with machine learning
Organizers:
Prof. Chung-Ming Ou