Keynote Speaker I
Prof. Yonghong Peng
The University of Sunderland, UK
Speech Title:The Science of Data: to empower the next generation of Artificial Intelligence
Data is now becoming an incredibly driving power for technological innovations. With aim for making machine to be with intelligence including for “problem-solving” and “learning”, the discipline of Artificial intelligence grown-up from symbol manipulation, computational logic, knowledge-base/expert systems, neural network to hybrid intelligence, during the past 60 years. In the big data era, AI has been empowered by the advance of machine learning and particularly by the popularity of deep learning, and is now becoming a buzzword to industries.
This talk will first present an overview on the framework of emerging discipline of data science, as driven by the big data. Thought we have seen the boom of AI and technology innovation, industries still struggle to transfer data from operational systems to analytical systems, thus have difficulty to catch the opportunities in data economy. In this talk, Prof Peng will present an ecosystem where machine learning empowers the big data analytics and big data drives the AI technology innovation. This talk will also explore the development of a new data intelligence platform (DIP) to empower the next generation of AI.
Prof Yonghong Peng is aProfessor of Data Science at the University of Sunderland, United Kingdom.His research in data science includesmachine learning/deep learning and artificial Intelligence, with application tohealth and genome data analytics. His research group has developed multiple leadingapproaches for the integrated analytics of genome data.Prof Peng is an associate editor for IEEE Transaction onBig Data, and an academic editor of PeerJ and PeerJ Computer Science. Prof Pengis the Chair for Big Data Task Force (BDTF) of IEEE computational intelligencesociety (CIS), and a member of Data Mining and Big Data AnalyticsTechnical Committee of IEEE CIS. He is a founding member of the TechnicalCommittee on Big Data (TCBD) of IEEE Communications, and a member of Big DataTask Force of China Information Industry Association (CIIA). He is also anadvisory board member for IEEE Special Interest Group (SIG)on Big Data for Cybersecurity and privacy.
Prof.Leszek S. Czarnecki
ALFREDO LOPEZ DISTINGUISHED PROFESSOR
IEEE Life Fellow
Louisiana State University, USA
Power electronics, nonsinusoidal systems, network analysis and synthesis.
Speech Title:Degradation of the Energy Transfer Effectiveness Described in Terms of Currents’ Physical Components (CPC)-based Power Theory
Abstract: The Key Note would be focused on physical phenomena that degrade the effectiveness of the electric energy transfer in electrical systems when voltages and currents are nonsinusoidal and asymmetrical. The Currents’ Physical Components (CPC) – based power theory, developed by L.S. Czarnecki, provides theoretical fundamentals for the analysis of the electric energy flow. This analysis identifies in electrical systems seven distinctive physical phenomena that affect this flow. Seven current components are associated with these phenomena in the CPC-base power theory concept. Only one of them contributes to the useful transfer of energy. Remaining six components only degrade the effectiveness of this transfer. They could be reduced by various compensators and the CPC-based power theory provides fundamentals for their synthesis and control. The results presented in the Key Note are valid for electrical systems of any complexity, meaning for single- and for three-phase systems and for any loads, meaning for linear and for nonlinear loads. A draft of the history of the CPC –power theory development will be presented as well. The Key Note will provide numerical examples that will illustrate the presentation.
Prof. Hartmut Hinz
University of Applied Sciences, Frankfurt, Germany
Speech Title: Overview of wind energy: Technology, currents status and outlook scenarios
Abstract: Most estimates predict that the global energy requirements will double by the year 2050. However global greenhouse gas emissions need to be stabilized until 2030 and reduced by the mid-century to less than half of the level of 1990. Therefor in the long term fossil fuels are unable to meet the rising demands for energy. Consequently a transition towards a decarbonized economy is mandatory. A substantial growth of renewables led by wind is indispensable.
The keynote speech first shows the state of the art of wind power systems. Subsequently an overview of the global status of wind power is presented. The development of the installed capacities is discussed for the markets Europe, North America, Latin America, Asia, Africa and the Pacific region. Finally a market forecast is given for the years 2017 - 2020.
Prof. H. Hinz was born in Düren, Germany. He received the diploma degree in electrical engineering from the University of Applied Sciences, Aachen and the Ruhr University, Bochum in Germany in the years 1990 and 1994 respectively. He received the Ph.D. degree from the Technical University, Darmstadt in Germany in 2000.
From 1999 to 2009 he worked for General Motors Europe in the research department for fuel cell vehicles. In 2009 he was appointed as a Professor in power electronics at the Frankfurt University of Applied Sciences, Germany. Since 2011 he is the academic leader of the study program Energy efficiency and renewable energy. Since 2010 he is a visiting Professor at the Vietnamese-German University in Ho-Chi-Minh City, Vietnam. His research interests are in the areas power electronics and decentralized power generation.
Dr. Ahmed Chemori
Tenured research scientist in Automatic control and Robotics for the French National Center for Scientific Research (CNRS), France
Speech Title: Control of High-Speed Parallel Robots for Automated Food Packaging
Abstract: Serial robot manipulators consist of a set of sequentially connected links, forming an open kinematic chain. These robots are mainly characterized by their large workspace and their high dexterity. However, in order to perform tasks requiring high speeds/accelerations and high precision; such robots are not always recommended because of their lack of stiffness and accuracy. Indeed, parallel kinematic manipulators (PKMs) are more suitable for such tasks. The main idea of their mechanical structure consists in using at least two kinematic chains linking the fixed base to the travelling plate, where each of these chains contains at least one actuator. This allows for a distribution of the load between the chains. PKMs have important advantages with respect to their serial counterparts in terms of stiffness, speed, accuracy and payload. However, these robots are characterized by their highly nonlinear dynamics, actuation redundancy, kinematic redundancy, uncertainties, singularities, etc. Besides, when interested in high speed robotized repetitive applications, such as food packaging tasks, the key idea relies in looking for short cycle times. This means obviously to look for short, motion and stabilization, times while guaranteeing the robustness and performance with respect to disturbances and changes in operational conditions. Consequently, when we are interested in control of such robots, all these issues should be taken into account, which makes it a challenging task.
This talk will give an overview of some proposed advanced control solutions for high-speed applications of PKMs in food packaging tasks. The proposed solutions are mainly based on nonlinear adaptive control techniques and have been validated through real-time experiments on different prototypes.
Videos of experiments : https://www.youtube.com/channel/UC870Se7GH9x3xmO_GFRAlOg
Research Interest: Nonlinear predictive and adaptive control and their applications in robotic systems (Parallel Kinematic Manipulators, underwater robots, under-actuated mechanical systems, humanoid robots and exoskeletons).
Ahmed CHEMORI. wa born in Constantine. He received his B.Sc. and M.Sc. degrees in electronics from the university of Mentouri - Constantine, in 1998 and 2000. He received his M.Sc. and Ph.D. degrees, both in automatic control from Politechnical Institute of Grenoble, France, in 2001 and 2005 respectively. During the year 2004/2005 he has been a Research and Teaching assistant at Laboratoire de Signaux et Systèmes (Centrale Supelec) and University Paris 11. Then he joined Gipsa-Lab (Former LAG) as a CNRS postdoctoral researcher. He is currently a tenured research scientist in Automatic control and Robotics for the French National Center for Scientific Research (CNRS), at the Montpellier Laboratory of Computer Science, Robotics and Microelectronics (LIRMM). His research interests include nonlinear (adaptive and predictive) control with special emphasis on their real-time application in robotics (underactuated mechanical systems, parallel Kinematic Manipulators, underwater vehicles, exoskeletons and humanoids). He is the author of more than 85 scientific publications, including international journals, patents, book chapters and international conferences. He co-supervised 13 PhD theses (including 6 defended) and more than 35 MSc theses. He served as a TPC/IPC member or associate editor for different international conferences and he organized different scientific events (e.g. PKM 2016 summer school and WIR 2017 workshop). In April 2017 he has been visiting Huazhong University of Science & Technology in China, as an invited researcher/lecturer. He has been as invited plenary/keynote lecturer for various international conferences.
Prof.Angel Pasqual del Pobil
Jaume I University,Spain
Angel P. del Pobil is a professor at Jaume I University (Spain), where he was the founding director of the UJI Robotic Intelligence Laboratory. He has been Co-Chair of two Technical Committees of the IEEE Robotics and Automation Society and is a member of the Governing Board of the Intelligent Autonomous Systems (IAS) Society (2012-present) and EURON (European Robotics Research Network of Excellence, 2001-2009). He has over 250 publications, including 13 books, the last three published recently by Springer. Prof. del Pobil was co-organizer of some 50 workshops and tutorials including: five at ICRA (1996, 2000, 2010-2012), ten at IROS (2000, 2004-2013), three at RSS (2008-2010, 2012), ECAI'04, ICAR'05 and ACM/IEEE HRI 2010. He was Program Co-Chair of the 11th International Conference on Industrial and Engineering Applications of Artificial Intelligence, and General Chair of the 13th International Conference on Adaptive Behaviour (SAB 2014) and of five editions of the International Conference on Artificial Intelligence and Soft Computing (2004-2008). He is Associate Editor for ICRA (2009-2015) and IROS (2007-2016) and has served on the program committees of over 130 international conferences, such as IJCAI, ICPR, ICRA, IROS, EUROS, IAS, ICAR, CIRA, etc. The UJI Robotic Intelligence Lab has organized 12 consecutive editions of IURS, the International UJI Robotics School. He has been General Chair for IURS 2005 on Robotics and Neuroscience, IURS 2006 on Humanoid Robots, IURS 2009 on Visuomotor Coordination, IURS 2012 on Perceptual Robotics and the 2015 IEEE-RAS Summer School on Experimental Methodology, Performance Evaluation and Benchmarking in Robotics. He has been involved in robotics research for the last 30 years. Professor del Pobil has been invited speaker of 63 tutorials, plenary talks, and seminars in 14 countries. He serves as associate or guest editor for 12 journals, and as expert for research evaluation at the European Commission, the US National Science Foundation and the Spain Ministry of Science. He has supervised 16 Ph.D. Thesis, including winner and finalists of the Georges Giralt EURON PhD Award and the Robotdalen Scientific Award Honorary Mention. He has been Principal Investigator of 30 research projects. Del Pobil is an active member of the IEEE Robotics and Automation Society and a lifetime member of the Association of the Advancement of Artificial Intelligence (AAAI).
Dr. Vasco Amaral
Universidade Nova de Lisboa,Portugal
Current Interest Research Topics: Model-Driven Development, Domain-Specific Languages, Language Engineering, Model Checking and Model-Based Testing, Experimental Validation, Software Quality, Rapid Prototyping, Big Data.
Instituto Politecnico Nacional de Mexico (Mexico-city)
Speech Title:3D Visualization Based on Robust Methods for Disparity Map Reconstruction
Abstract:Estimation of disparity maps (DM) has been a hot topic during more than a decade. The main reason is the wide range of applications where the generation of 3D content is important. Among such applications there are: computer vision areas, medical imaging, automated systems, artificial intelligence, etc.
A variety of solutions have been proposed with the aim to design a robust, faster and reliable technique for specific needs or requirements. Different frameworks that are used for DM estimation can be divided in two groups, where the first group methods are focused in better time processing performance, and the second group techniques are directed in better quality performance. The first group methods employ mainly the local search for the disparity estimation, and as a result, they lose in quality of DM reconstructed, especially in real scenarios (different resolutions, exposures, light conditions, presence of noise, etc.). Second group techniques can guarantee good quality and acceptable results in most of real scenarios, but the processing time can be an inconvenient for practical applications.
The trade-off between execution time and quality of the matching must be handled with care and is a difficult task. Novel approach for sparse and dense disparity maps (DM) estimation is introduced in this study to reduce the distance between two important performances: processing time and DM quality using implementation in sequential and parallel architectures with minor modifications, maintaining the same quality results. To enable both accurate and fast real time stereovision in embedded systems, we propose several implementations using CPU multicore and GPU hardware.
In simulation experiments, to evaluate the performance of the proposed approach, novel techniques were compared with better state-of-the-art methods using the synthetic images taken from Middlebury Stereo Vision website] and Tsukuba dataset. The Structural Proposed scheme has been implemented using CPU and GPU hardware reducing time values via parallel processing. Numerous experiments have demonstrated competitive and robust property of novel techniques against state-of-the-art methods. Similarity Index Measure and the Percentage of Bad Pixels in objective quality evaluation as well as subjective perception via human visual system have shown better performance in maintaining fine features in DM that is crucial in 3D visualization.
Volodymyr Ponomaryov attained his Ph.D. in 1974, Doctor of Sciences in 1981 and has been a Full Professor(1984). He is working as Professor at Instituto Politecnico Nacional de Mexico (Mexico-city). He is a referee for more than 20 international scientific journals, and a member of the editorial board of international journals and conferences. He was the lead guest editor of a special issue on Image and Video Quality Improvement Techniques for Emerging Applications in EURASIP Journal on Advances in Signal Processing (2011). Dr. Ponomaryov served and currently serves as Associate Editor in Journal of Real Time Image Processing. His current research interests include signal/image and video processing, denoising, intelligent pattern recognition, real-time filtering, 3D reconstruction, medical sensors, remote sensing, etc. Over the years he has also been a promoter of 41 Ph.D. on his scientific areas of interests. He has authored or co-authored more than 200 scientific papersin international referred
journals, 350 international conference papers, and also 23 patents of ex USSR, Russia and Mexico, 18 author certificates, and five scientific books published in international editorials.
Invited Speaker II
Prof. Ismail Rakip Karas
Professor of Computer Engineering Department at Karabuk University, Turkey
Speech Title: NETWORK ANALYSES IN 3D GIS FOR INDOOR BASED ON USER CENTRIC INTELLIGENT EVACUATION SYSTEM
ABSTRACT: The number of buildings, which are very tall, complex and located on wider areas, has been increasing in today’s modern cities. Having dozens of floors, hundreds of corridors, and rooms, and passages, these buildings are almost like a city in terms of their complexity and number of people accommodated. Due to size and complexity of buildings, there are many new problems to be addressed. Evacuation of the buildings quickly and seamlessly is the leading problem in case of emergency. Fire, power outage, terrorism (explosions, bomb threat, hostage-taking incidents), chemical spills, earthquake, flood, etc., are some of the extraordinary occasions that may be encountered or affect indoors. In such kind of cases, formation of panic, crowd, congestion, crush, unable to reach exit, etc. are frequently encountered.
In this talk, 3D Network Analyses and Interactive Human Navigation System for indoor which consists of three components will be presented. The first component is used to extract the geometrical and 3D topological vector data automatically from architectural raster floor plans. The second component is used for network analysis and simulations. It generates and presents the optimum path in a 3D modeled building, and provides 3D visualization and simulation. And the third component is used to carry out the generation of the guiding expressions and it also provides that information for the mobile devices such as PDA’s, laptops etc via Internet.
In addition, an Intelligent Evacuation Model for Smart Buildings will be introduced in this presentation. The model dynamically takes into account environmental (smoke, fire, etc.) and human-induced (age, disability, etc.) factors and generates personalized evacuation route by performing network analysis interactively and in real-time. Intelligent Control Techniques (Feed-Forward Artificial Neural Networks) has been used in the design of the model.
BIBS of Prof. Ismail Rakip Karas:
Dr Ismail Rakip Karas is a Professor of Computer Engineering Department at Karabuk University, Turkey. He received his BSc degree from Selcuk University, MSc degree from Gebze Institute of Technology, and PhD degree from GIS/RS program of Yildiz Technical University, in 1997, 2001 and 2007 respectively, three of them from Geomatics Engineering Department. In 2002, he involved in a GIS project as a Graduate Student Intern at Forest Engineering Department, Oregon State University, USA. During the summer of 2014, and summer of 2010 he was a Visiting Researcher in 3D GIS Research Lab, Faculty of Geoinformation Science and Engineering, Universiti Teknologi Malaysia. Between 2000-2009, he was a Research Assistant at Geomatics Engineering Department of Gebze Institute of Technology. Since 2009, he has been in Karabuk University and taught undergraduate and graduate classes in Geoinformation and Computer Sciences. He has also been carrying out as Head of Computer Science Division of Department and Director of Safranbolu Vocational School of Karabuk University.
Dr. Ismail Rakip Karas is the author of many international and Turkish publications and papers on various areas of Geoinformation Science. He is in the editorial board of International Geoinformatics Research and Development Journal, American Journal of Geographic Information System, and some others. Also reviewer of some international journals such as Sensors, Turkish Journal of Electrical Engineering & Computer Sciences, and International Journal of Environmental Research. He is also committee member of some of conferences such as “Int’l Conference on Digital Image Processing” and “3D GeoInformation Conference”. He has involved in several projects and been supervisor and examiner of many Msc and PhD students. His research interests include Geographic Information Systems, 3D GIS, 2D and 3D Network Analyses on GIS, Software Development for GIS, Web based GIS, Geo-Databases, Computer Graphics, Computational Geometry, Digital Image Processing, and Graph Theory.
Ms. Tiya T. Deng
Spet.21, 2018: Registration + icebreaker reception
Spet.22, 2018: Opening Ceremony+KN Speech+Technical Sessions
Spet.23, 2018: One day tour or Technical Sessions+ half day tour/lab tours
All the papers will be peer-reviewed by 2-3 conference experts. Registered and presented papers will be published in the Conference Proceeding, indexed by Ei compendex, Scopus etc.Selected papers will be recommended to publish in international journals.
Prospective authors and participants are invited to submit the full manuscript /abstract to IARCE2017!
Full Paper Submission Deadline:Feb. 20, 2018
Notification of Acceptance/ Rejection: within 2 weeks
Registration Deadline: Before April. 20, 2018
Conference Dates: Sep. 21-23, 2018
Stockholm is the capital of Sweden and the most populous city in the Nordic countries;942,370 people live in the municipality,approximately 1.5 million in the urban area,and 2.3 million in the metropolitan area.The city stretches across fourteen islands where Lake Mälaren flows into the Baltic Sea. Just outside the city and along the coast is the island chain of the Stockholm archipelago.
Best Paper Awards
The best paper is selected by scores compiled by the at least 2 session chairs from those papers that have received the highest review scores and/or highest number of best paper award nominations.
Mr. Florian Voigtländer
Technische Universität München, Germany
Paper Title:5G for Robotics: Ultra-Low Latency Control of Distributed Robotic Systems
Mr. Shenlu Jiang,
Paper Title:An Adaptive 2D Tracking Approach for Person Following Robot