Title
New Challenges in Machine Learning:
Multiclass-Classification for Risk Predictions in Health Care Applications

Abstract
Discovering patterns from big data attracts a lot of attention due to its importance in discovering accurate patterns and features that are used in predictions of decision making.
The challenges in big data analytics are the high dimensionality and complexity in data representation analytics especially for on-line feature selection. Granular computing and feature selection on data streams are among the challenge to deal with big data analytics that is used for Decision making. We will discuss these challenges in this talk and provide new projection on ensemble deep learning techniques for on-line health care risk prediction. Different type of data (time series, linguistic values, interval data, etc.) imposes some difficulties to data analytics due to preprocessing and normalization processes which are expensive and difficult when data sets are raw, or imbalanced. We will highlight these issues through project applied to health-care for elderly, by merging heterogeneous metrics from multi-sensing environment providing health care predictions assisting active aging at home. We have utilized ensemble learning as multi-classification techniques on multi-data streams using incremental learning to update data change “concept drift“
Subjectivity (i.e., service personalization) would be examined based on correlations between different contextual structures that are reflecting the framework of personal context, for example in nearest neighbor based correlation analysis fashion. Some of the attributes incompleteness also may lead to affect the approximation accuracy. I present deep learning feature selection in medical application early predictions (heart diseases and others). We outline issues on Virtual Doctor Systems, and highlights its innovation in interactions with elderly patients, also discuss these challenges in multiclass classification and decision support systems research domains.　In this talk I will present the current state of art and focus it on health care risk analysis applications with examples from our experiments.

Biodata
He is professor at Iwate Prefectural University (IPU), Iwate, Japan, as a director of Intelligent Software Systems. He is the Editor-in-Chief of Knowledge-Based Systems, Elsevier of impact factor (4.528) for 2016. He received Doctor Honoris Causa from O’buda University in 2013 and also from Timisoara Technical University in 2018, and a title of Honorary Professor from O’buda University, Budapest, Hungary in 2011. He received honorary scholar award from University of Technology Sydney, Australia on 2012. He is Adjunct professor to Stockholm University, Sweden, University of Technology Sydney, National Taiwan Ocean University and others. He has supervised PhD students jointly with University of Laval, Quebec, Canada; University of Technology, Sydney, Australia; Oregon State University (Corvallis), University of Paris 1 Pantheon-Sorbonne, France and University of Genoa, Italy. He has four international Patents in Software System and Several research projects with Japanese industry and partners. He is vice president of International Society of Applied Intelligence, and Co-Editor in Chief of Applied Intelligence Journal, (Springer). He has given many keynotes in many prestigious international conferences on intelligent system and subjective intelligence. He headed a number of projects including Intelligent HCI, a project related to Mental Cloning as an intelligent user interface between human user and computers and SCOPE project on Virtual Doctor Systems for medical applications.

Title
Learning from imbalanced data - recent trends and challenges

Abstract
Imbalanced data problem occurs whenever there is a significant disproportion among the number of instances in considered classes. It may pose a serious difficulty, often requiring the specially designed methods. In such cases, the most important consideration is often to properly detect minority examples, but at the same time, the performance on majority class cannot be neglected. It is, however, important to note that imbalance ratio (even if it is high) usually does not pose a problem by itself. Only when combined with other data difficulty factors it negatively affects the minority class classification. Defining and understanding such factors is, therefore, a crucial task when designing new methods for dealing with imbalanced data.
Notwithstanding, the problem of imbalanced data analysis is the focus of intense research, but many open problems remain still unsolved in this domain.
The talk will focus on the main approaches related to the imbalanced data classification and the open challenges in this domain, as multiclass imbalanced data classification, imbalanced stream learning.

Biodata
Michał Woźniak is a professor of computer science at the Department of Systems and Computer Networks, Wroclaw University of Science and Technology, Poland. His research focuses on machine learning, compound classification methods, classifier ensembles, data stream mining, and imbalanced data processing. Prof. Woźniak has been involved in research projects related to the topics mentioned above and has been a consultant for several commercial projects for well-known Polish companies and public administration. He has published over 300 papers and three books. He was awarded numerous prestigious awards for his scientific achievements as IBM Smarter Planet Faculty Innovation Award (twice) or IEEE Outstanding Leadership Award, and several best paper awards of the prestigious conferences. He serves as program committee chairs and the member for the numerous scientific events and prepared several special issues as the guest editor. He is the member of the editorial board of the high ranked journals as Information Fusion (Elsevier), Applied Soft Computing (Elsevier), and Engineering Applications of Artificial Intelligence (Elsevier).

Title
Robot Brains and the Development of Artificial Intelligence in Robot Soccer

Abstract
What would be more challenging, to develop a self-driving car, or a robot that can play soccer autonomously? Most people would be familiar with some of the challenges the autonomous car industry is facing, while soccer-playing robots would more likely be associated with simple toys and next-generation futuristic technology at the same time. This keynote will look at an autonomous Humanoid robot soccer team that competes at the international robot soccer worldcup, RoboCup. Development of the robots includes an efficient software framework using algorithms for vision, localisation, motion control and behaviour, and the integration of suitable hardware. In the Humanoid league only human-like sensors are allowed, and video captured with a camera with a maximum field of view of 180 degrees is the primary source for object detection and localisation. For many years the high computational cost of traditional computer vision methods put severe limitations on what such robots could see and do. A significant advancement in object detection was recently achieved by new deep neural networks that can run with very high frame-rates on low-powered devices. This provided an important step towards the goal of RoboCup which is to develop a robot soccer team which beats the human world champion team by 2050. The evolution of the soccer robots’ brain-like control systems over the past years may also allow to predict when these autonomous humanoid robots would be capable of leaving the soccer field or lab environment and securely perform tasks in the real world such as driving a car.

Biodata
Associate Professor Stephan Chalup is the Head of the Discipline of Computing and Information Technology at the University of Newcastle and leader of the Newcastle Robotics Lab. He obtained his Ph.D. in Computing Science in 2002 at the Machine Learning Research Centre at Queensland University of Technology. Before he came to Australia he studied mathematics with neuroscience at the University of Heidelberg in Germany. Stephan is an expert in neural networks and has authored or co-authored over 100 refereed articles in areas such as deep neural networks, autonomous intelligent agents, manifold learning and various aspects of pattern recognition and data analytics. He worked on a variety of projects in academia and with industry where his largest collaborations were with architecture (2005-2014) and with transport safety in the rail industry (2016 to date). During his career, Stephan has successfully educated over twelve PhD students and served on the editorial boards of several academic journals.

Title
Deep Learning Accelerator: Challenges and Solutions for Setting-up Model Optimization for On-Device AI

Abstract
Designing an efficient deep neural network inference on a heterogeneous mobile device is still challenging. Performance and energy consumption limitations make the execution of such computationally intensive algorithms on mobile devices prohibitive. Current industry level abstraction such as Google’s TensorFlow-Lite only supports CPU accelerator for inference. Based on several experiments showed that the new fully-connected layer kernel performs up to 4x faster than TensorFlow-Lite original kernel on large enough input, while the new convolution layer kernel can perform up to 6x faster with same input dataset. Since AI technologies truly understand our needs, with a whole series of sensors and monitors connected to our mobile device, which essentially becomes our personal edge server, the AI capabilities will have massive amounts of data to analyze for our benefit and react to issues far faster than we can manually. It will bring an increasingly complex interaction environment down to something that is manageable. Positively, that would be a very good thing. Based on;
- Disruptive Evolution on AI
- AI based Market Environment
- On-Device Inference Model Trends
- SRIN Deep Learning Accelerator Modeling and Use Cases

Biodata
Dr. Alfred Boediman is an experienced senior management who has implemented changes to answer business and technology needs across a number of areas in the Software Research and Telecommunication sectors. Dr. Alfred also an Adjunct Professor in University of Chicago Graduate School of Business, he holds degrees from University of Indonesia, Vrije Universiteit Brussel, Rochester Institute of Technology and University of Chicago - Booth School of Business. His postdoctoral research focuses on examining the neuro-statisical approach in derivatives financial exchange with combination of multi layered market sentiment. Dr. Alfred’s interest and training in technology research for cognitive socio-behavior, machine learning and on-device AI modeling area. While, he is also an advisor for Polsky Center of Entrepreneurship in the University of Chicago, and enjoying other activities like riding Vespa, archery and cooking in his free times.

Title
Towards Practical Cyber-Physical Environments in Consensus Formation

Abstract
Nowadays, a lot of types of communication system to make consensus among people are provided. We can utilize these kinds of systems, such as Social network system, e-mail, and instant messenger system, to make a decision and determination through online discussion. In the next decade, we can forecast a lot of types of consensus formation systems are provided and we may find new communication systems integrating between cyber and physical environment. In this talk, I introduce our conducted experiments using cyber-physical discussion environment in the panel discussion session in the conference. In the session, facilitator asks question to panelists about issues on the discussion and attendees can also do as well by their voice. Each attendee also can post and declare his/her opinions and suggestions through the online discussion system during the session. One or two facilitators facilitate the discussion in the online system as well as real discussion. We found out a lot of interesting results of attendees survey taken in before/after the experiments. I also introduce the environment to provide useful information for attendees by the digital signage system in the conference venue. This digital signage system is connected to the attendees location capture system and conference registration system. These integrations between cyber and physical environments and data enable to make better consensus formation between all sorts of people.

Biodata
Dr. Tokuro Matsuo is a full professor at Advanced Institute of Industrial Technology since 2012. He received his Ph.D. in computer science from Nagoya Institute of Technology in 2006. He then joined the faculty of the Yamagata University, where he is an Associate Professor of Informatics until 2012. Currently, he is a Guest Professor at Bina Nusantara University, Indonesia; the Project Professor of Collective Intelligence Research Center at Nagoya Institute of Technology, Japan; a Research Fellow of SEITI in Central Michigan University, USA. He was a Visiting Professor at University of Nevada, Las Vegas, USA from 2016-2017; a Visiting Researcher at University of California at Irvine, USA from 2010-2011; was a Research Fellow at Shanghai University, China from 2010 to 2013; and was the Project Professor of Green Computing Research Center at Nagoya Institute of Technology, Japan from 2011 to 2014. His current research interests include electronic commerce and business, service science and marketing, business management, artificial intelligence, material informatics, tourism informatics, convention and event management research, and incentive design on e-services. Some of his researches are presented in the top international conferences on AAAI, IEEE CEC, AAMAS, and WWW. He is a founder of IEEE International Conference on Agents in 2016 and International Congress on Advanced Applied Informatics in 2012. He also chaired a lot of international conferences over 50, such as IEEE/ACIS SNPD 2009, 2012 and 2014, IEEE TENSYMP 2016, IEEE/ACIS ICIS 2010 and 2013, IEEE IWEA 2007-2012, ACAN 2005-2012, IEEE ICA 2016-2017, AAI 2012-2019. He served several academic services including Editor in chief of International Journal of Computer and Information Science, and Managing Editor of International Journal of Information Engineering Express, International Journal of Smart Computing and Artificial Intelligence, International Journal of Institutional Research and Management, and International Journal of Service and Knowledge Management. He gave over 100 keynotes and invited talk at international conferences, symposia, and seminars in two decades. He also received over 20 awards and 30 research grants from research foundations, company and government. He was/is also commissioned as the Vice President of International Association for Computer and Information Technology, USA; Vice President of Software Engineering Research Foundation, USA; Executive Director of International Institute of Applied Informatics, Japan; Japan Conference Ambassador; Kumamoto City MICE Ambassador; and Adviser of Information Promotion of Japan.