Invited Speakers
S1: Prof. Arturas Kaklauskas, Vilnius Gediminas Technical University, Lithuania
S2: Prof. Patrick Siarry, Université Paris-Est Créteil, Paris. France
S3: Prof. Yukio Ohsawa, University of Tokyo, Japan
S4: Prof. Laura García-Hernández. University of Cordoba, Spain
S5: Dr. Kingsley Okoye, Tecnologico de Monterrey, Writing Lab, TecLabs, Mexico
S6: Prof. Ladislav Zjavka, ENET Centre, VsB-Technical University of Ostrava, Czech Republic
 |
Prof. Arturas Kaklauskas Member of the Research Council of Lithuania Member of the Lithuanian Academy of Science Vilnius Gediminas Technical University Sauletekio al. 11, LT-10223 Vilnius, Lithuania |
Abstract: TBA
Biography: Ph.D Dr.Sc Arturas Kaklauskas is a professor at Vilnius Gediminas Technical University, in Lithuania; Head of the Department of Construction Management and Property; laureate of the Lithuanian Science Prize; member of the Lithuanian Academy of Sciences, editor of Engineering Applications of Artificial Intelligence, an international journal and associate editor of journal “Ecological Indicators”. He contributed to nine Framework and five Horizon 2020 programmes projects and participated in over 30 other projects in the EU, US, Africa and Asia. The Belarusian State Technological University (Minsk, Belarus) awarded him an Honorary Doctorate in 2014. His publications include nine books and 143 papers in Web of Science Journals. Fifteen PhD students successfully defended their theses under his supervision. The Web of Science H-Index of Prof. A. Kaklauskas is 27. Web of Science Journals have cited him 2471 times and average citations per article - 17.28. His areas of interest include affective computing, intelligent tutoring systems; affective intelligent tutoring systems; Massive open online courses (MOOCS); affective Internet of Things; smart built environment; intelligent event prediction, opinion mining, intelligent decision support systems, life cycle analyses of built environments, energy, climate change, resilience management, healthy houses, sustainable built environments, big data and text analytics, intelligent library, internet of things, etc.
S2: Title: Some contributions to the adaptation of discrete metaheuristics for continuous optimization
| Prof. Dr. Patrick SIARRY Université Paris-Est Créteil, Paris France |
Abstract: In this talk, we firstly present the general frame of "hard" continuous optimization: after a short description of a few typical applications, we point out the difficulties peculiar to continuous problems. Then we describe some pitfalls of adapting metaheuristics to continuous variable problems. In a second part, we present, as an illustration, the methods that we have proposed to adapt some metaheuristics: simulated annealing, tabu search, genetic algorithms and ant colony algorithms. We outline some perspectives or works in progress, particularly dealing with particle swarm optimization. Lastly, we show, as an example, an application in the field of biomedical engineering of a continuous ant
colony algorithm: the registration of retinal angiograms.
Biography: Patrick Siarry is an engineer graduated from Ecole Supérieure d’Electricité (Supélec, France) in 1977. He then received the PhD degree from the University Paris 6, in 1986 and the Doctorate of Sciences (Habilitation) from the University Paris 11, in 1994. He was first involved in the development of analog and digital models of nuclear power plants at Electricité de France (E.D.F.). Since 1995 he is a professor in automatics and operations research at the University Paris-Est Créteil (UPEC), France. He is head of the team “Signal and Image Processing” of the “Signals, Images & Intelligent Systems” laboratory of UPEC. His main research interests are the development of methods for solving “hard” optimization problems occurring in real-life engineering design projects. He is particularly interested in “metaheuristic” approaches, such as simulated annealing, evolutionary algorithms, ant colonies, and particle swarms. His main contributions are related to the adaptation of discrete metaheuristics for solving continuous optimization problems. The methods developed in the team have been applied in various fields: image processing, computer-aided design of electronic circuits, fitting of process models to experimental data, learning of fuzzy rule bases and neural networks, etc.
S3: Title: Data Jackets as Communicable Metadata for Potential Innovators
Prof. Yukio Ohsawa, |
Abstract: Data Jackets are human-made metadata for each dataset, reflecting peoples' subjective or potential interests. Via visualizing relevances between DJs, participants in the market of data think and talk about why and how they should combine the corresponding datasets. Even if the owners of data may hesitate to open their data to the public, they can present the DJs in the data marketplace that can be regarded as a platform for data-driven innovations. In this market, the participants communicate to find ideas to combine/use data and find future collaborators. Furthermore, explicitly or implicitly required data can be searched by use of tools such as DJ Store and Variable Quest, created on DJs, which enabled analogical inventions of data analysis methods. As a result, the innovators' marketplace on DJs turned out to be the birthplace of fruits in business and science.
Biography: Yukio Ohsawa is a professor of Systems Innovation in the School of Engineering, The University of Tokyo. He received BE, ME, and PhD in from the School of Engineering, The University of Tokyo (1995). Then worked for the School of Engineering Science in Osaka University (research associate, 1995-1999), Graduate School of Business Sciences in University of Tsukuba (associate professor, 1999-2005), and moved back to The Univ. of Tokyo. He started researches from non-linear optics, and, via artificial intelligence, created a new domain chance discovery meaning to discover events of significant impact on decision making, since year 2000. About chance discovery he gave keynote talks in conferences such as International Symposium on Knowledge and Systems Sciences, Intl Conf. on Rough Sets and Fuzzy Sets, Joint Conf. on Information Sciences, Knowledge-Based Intelligent Information and Engineering Systems, etc. Chance discovery came to be embodied as innovators? marketplace, a methodology for innovation borrowing principles of the dynamics of markets. Then he, when biking from his job in a business school, invented the basic idea of Data Jackets. Since then, he is introducing the method presented in this book to sciences, educations, and businesses. His original concepts and technologies have been published as books and monographs from global publishers such as Springer Verlag, Taylor & Francis, etc. Two most important books among them are, Chance Discovery (2003 Springer, foreword given by Eric von Hippel), Innovators Marketplace: Using Games to Activate and Train Innovators? (2012 Springer, foreword given by Larry Leifer). He edited special issues as guest editors for journals, mainly relevant to chance discovery, such as Intelligent Decision Technologies (2016), Information Sciences (2009), New Generation Computing (2003), Journal of Contingencies and Crisis Management (2002), etc.As the program chair of the Annual Conference of The Japanese Society on Artificial Intelligence, he came to be the first to change this domestic conference into an international conference from June 2019.
S4: Title: Optimization in Facility Layout Problems: new trends in bio-inspired algorithms
Prof. Laura García-Hernández |
Abstract: Facility Layout Design is considered as an extremely relevant issue for manufacturing due to it directly impacts over the efficiency and effectiveness of the production system. A satisfactory facility design can significantly reduce the manufacturing cost and it involves contemplating the flow of material, information, and work as well as taking into account the needs of employees. Focusing on this main objective, it seems that it is crucial to consider not only quantitative criteria but also the integration of the decision maker's knowledge and experience, for facility design. Meta-heuristics evolutionary algorithms have been widely applied to deal with Facility Layout Problems owing to complexity and NP-hard problems. This fact makes it impossible to readily solve these problems by means of analytical models. Recently, Coral Reefs Optimization Algorithm and has achieved excellent performance addressing problems in areas such as Structural Engineering, Energy, Bio-Medical Applications, etc. This new evolutionary-type algorithm and its updated versions guide their evolution by simulating the real coral reef operations such as reproduction, the fight for space or survival from predators. This lecture will offer more technical aspects about this bio-inspired algorithm and its improved versions and future research directions with a focus on Facility Layout Problems.
Biography: Dr. Laura García-Hernández is Assistant Professor in the Area of Project Management at the University of Córdoba (Spain). She received M.Sc. in Computer Science in 2007 from Universitat Oberta de Catalunya (Spain) and European Ph.D. in the field of Engineering in 2011 from the University of Córdoba (Spain) and Institut Français de Mécanique Avancée (Clermont-Ferrand, France).
Dr. García-Hernández primary areas of research are engineering design optimization, intelligent systems, machine learning, user adaptive systems, interactive evolutionary computation, project management, risk prevention in automatic systems and educational technology. In these fields she has authored/coauthored more than 50 research publications. She has given several invited talks in different countries. Considering her research, she has won the Young Researcher Award granted by the Spanish Association of Engineering Projects (IPMA Spain) in 2015. Additionally, she has won two times the General Council of Official Colleges Award at prestigious International Conference on Project Management and Engineering both 2017 and 2018 editions. She has realized several post-doc internships in different countries with a total duration of more that 2 years. She has been invited Prof. during a semester in the Institut Français de Mécanique Avancée (Clermont-Ferrand, France). She won the prestigious National Government Research Grant “José Castillejo” for supporting their post-doc research during 6 moths in the University of Algarve (Portugal) in 2018.
Dr. García-Hernández has been investigator principal in two Spanish research projects and she has been investigator collaborator in some research contracts and projects. She is a expert member of ISO/TC 184/SC working team and National Standards Institute of Spain (UNE). Moreover, she is a member of Spanish Association of Engineering Projects (IPMA Spain). She is the Co-editor-in-Chief of Journal of Information Assurance and Security and is the Program Chair of 19th International Conference on Hybrid Intelligent Systems (HIS 2019) and the 11th World Congress on Nature and Biologically Inspired Computing (NaBIC 2019). Dr. García-Hernández is a regular reviewer for more that 15 International Journals indexed by Thomson ISI and is actively involved in the committee program of several international conferences.
S5: Title: Learning Analytics for Educational Innovation: Early Indicators and Success Factors
Dr. Kingsley Okoye |
Abstract:Today, Learning Analytics (LA) which implies measurement, collection, analysis, and reporting of data about progress of the stakeholders (e.g. learners) and contexts in which the learning takes place is of importance towards achieving the goals of the modern educational models, processes, and innovation. On the one hand, there is a growing need for educators to adopt the modern technologies in support of the different activities that constitute the educational processes; ranging from the changing educational labour market to the rapidly renovation of the information system and tools used to support the learners and the context in which they learn. On the other hand, the education community is expected to include a more proactive and creative learning strategies and experiences for the said stakeholders.
Why is Learning Analytics important in this aspect? Perhaps, by leveraging the unprecedented increase in amount of datasets that are recorded and stored about the different learners activities and digital footprints during and/or within the learning execution environments; we trust that learning analytics and its associated technologies can take us further than traditional methods or mechanisms utilized by the educators to support the various learning platforms and decision-making strategies in diaspora. Thus, modern institutions could consider the introduction and adoption of a suitable learning analytics system in their different operational processes. Technically, the learning analytics methods benefit by drawing upon the existing databases, statistics and machine learning, data visualization and pattern recognition, to optimization, high-performance and soft computing, etc.
Implications of the early signals and anticipated success: Although learning analytics is still at a relatively early stage of its development and application within the modern educational settings, there is convincing evidence from the early researches that the concept is capable of improving the higher education processes and innovation. Besides, every educational institution has an interest in ensuring that the learners are learning effectively, and in turn, learning analytics has been seen as a suitable technology to help address and manage those problems of high amounts and growth of student ’s activities and curricula. Indeed, despite the existing efforts and challenges, the true proof and usefulness of the learning analytics frameworks will be their wider usage within the educational research and innovation; be it either with regards to the main fundamental features of the methods (learning analytics) to the personalized adapted formats, or the institutional-driven educational innovation and undertakings. For example, this work notes some implications of the early signals and application of the learning analytics methods to include: Educational process innovation and monitoring, Recommendation and guidance, Personalized and adaptive learning, e-Content and curriculum design, etc. Moreover, lessons learned from the early studies have shown that learning analytics and its methods are capable of improving the quality of teaching, support the early identification of constraints or bottlenecks, and/or students who are struggling to meet with the learning processes in question. Thereby, enabling flexibility as to how, when, and where learning occurs, as well as, allowing students to take control of their own learning.
In summary, the users (e.g. students) are leaving an unprecedented huge amount of data and/or digital footprints behind with regards to the different learning processes. Perhaps, those footprints which today are recorded and stored as (big) data within the various IT systems; tell us about the learning patterns and experiences of the learners across and during the time of their study at the different institutions. This research shows that the educators and/or process innovators can make use of the readily available datasets to understand, for instance, how the students learn and to provide support if required to enhance the students' experience. To this end, the work proposes a Learning Analytics Educational Process Innovation (LAEPI) model that leverages the ever-increasing amount of data that are recorded and stored about the different learning activities and digital footprints of the users; to provide a method that proves useful towards maintaining a continuous improvement and monitoring of the educational processes, digital learning platforms, and innovation. This is called Learning Analytics.
Biography: Kingsley received his Ph.D. in Software Engineering from the School of Architecture Computing and Engineering, College of Arts Technologies and Innovation, University of East London, UK in 2017. He also completed a MSc in Technology Management in 2011 and a BSc (Hons) in Computer Science in 2007. He is a MIET member at the Institution of Engineering and Technology, UK and a Graduate Member in the Institute of Electrical and Electronics Engineers, IEEE. He is a devoted researcher to Industry and Academia in operational, hardware and software fields of computing in areas such as Data Science, Machine Learning, Artificial Intelligence, Big Data and Advanced Analytics, Software Development and Programming, and Business Process Management. Therefore, Kingsley has had the opportunity to do case studies and work in interdisciplinary and cross-cultural teams of various business and academic units that serve multiple industries. This includes serving as a software programming lab tutor for undergraduate students. He also serves as editorial board member and reviewer in reputable journals and conferences and has contributed to research and project outcomes by assessing and evaluating their impacts upon the scientific and industrial communities. It is Kingsley's personal mission to foster sustainable technical research and provide solutions through critical thinking, creative problem solving and cross-functional collaboration. He has also served as principal organizer and participated in organizing special session workshops, presentations, research methods, and statistical analysis topics in several conferences and workshops. The outcomes of his research have been published as Journal Articles, Authored and Edited Books, Book Chapters, Conference Proceedings in high index and reputable Journals, Publishers, and Conferences in the areas of Computer Science and Educational Innovation. His Research interests include: Process Mining, Business Process Modelling and Automation, Learning Analytics and Machine Learning, Semantic Web Technologies, Knowledge Management, Big Data Analysis and Process Querying, Internet Applications and Ontology. Kingsley is a Data Architect in the Writing Lab of Tecnologico de Monterrey. He is also a Member of the Machine Intelligence Research Lab (MIRLabs), USA, and a Member of the IEEE SMCS Technical Committee on Soft Computing.
S6: Title: Differential Network: Biologically inspired unconventional derivative neuro-computing - principles and applications
 |
Prof. Ladislav Zjavka ENET Centre, VsB-Technical University of Ostrava, Czech Republic |
Abstract: Differential Neural Networks (DNN) are a new class of novel computing networks based on analogues with brain pulse processing. DNN develops progressively a Polynomial Neural Network (PNN) or Complex Neural Network (CNN) structure, adding layer by layer with the nodes, to produce applicable sum PDE model components in blocks of the selected 2-input nodes. DNN decomposes the n-variable linear Partial Differential Equation (PDE) into node converted 2nd order sub-PDEs (i.e. neurons in this context) according to Operational Calculus (OC). This OC polynomial conversion of 2-variable 2nd order PDEs, based on the analogous ODE conversion of OC, results in pure rational or periodic terms which represent the Laplace images of unknown node functions. The inverse Laplace transformation is applied to them to obtain the originals whose sum gives the complete PDE model of a searched n-variable separable output function. The DNN structure is dynamically extended/changed in each iteration cycle, i.e. some of its nodes (forming the active PDE components) can be added/removed or the inputs changed. The optimal sum PDE model is gradually expanded (starting empty) by applicable node sub-PDE solutions (components), one by one, according to Goedel's Incompleteness theorem, to minimize DNN output errors. Composite PDE node solutions (terms) are the products of the selected neurons, produced in the actual and back-connected node blocks in previous layers, according to the composite function partial derivation rules. The gradient method optimizes the parameters of node blocks, which are shared by the selected neurons used single or in the products of composite terms. DNN can use the phases and amplitudes of input data instead of the real values (analogous to CNN). Its operating principles correspond to the dynamic computing of brain time-delayed pulses which seem to represent analogous sum model components. DNN can efficiently select from dozens of input variables (analogous to GMDH) to model complex dynamic systems or data patterns without reducing significantly the data dimensionality (as regression or computing techniques do).
Biography: Ladislav ZJAVKA is a Full-time researcher of the ENET Centre, VŠB-Technical University of Ostrava, Czech Republic. His scientific research is focusing on novel approaches to modelling complex dynamic systems and patterns combining neural networks with Operational calculus to decompose and solve partial differential equations (biologically inspired unconventional computing methods). He investigates in addition to simulation of neural structures and questions related with human brain learning.
