Keynote Speakers










Jason J. Jung 

Yeungnam University, Republic of Korea

Jason J. Jung is an associate professor of Computer Engineering Department at Yeungnam University, Korea. He was a postdoctoral researcher in INRIA Rhone-Alpes, France in 2006, and a visiting scientist in Fraunhofer Institute (FIRST) in Berlin, Germany in 2004. He received the B.Eng. in Computer Science and Mechanical Engineering from Inha University in 1999. He received M.S. and Ph.D. degrees in Computer and Information Engineering from Inha University in 2002 and 2005, respectively. His research topics are knowledge engineering on social networks by using machine learning, semantic Web mining, and ambient intelligence. He has about 25 international journal articles published in Knowledge-Based Systems, Information Retrieval, Information Processing & Management, Knowledge and Information Systems, and Expert Systems with Applications. Also, he is an editorial member of Journal of Universal Computer Science and International Journal of Intelligent Information and Database Systems. Moreover, he has been editing 10 special issues in Information Sciences, Journal of Network and Computer Applications, Computing and Informatics and so on.

Keynote Talk: Social Big Data: Challenges
We are now facing a new IT paradigm called “Big Data.” In particular, social networking services are strongly related to the “Big Data” issues. As we have various types of feasible information from “Big Data” sources, e.g., medical records, bioinformatics, and social media, it is becoming increasingly more difficult to efficiently develop social networking services. Efficient information management remains a challenge in many research areas, e.g., knowledge acquisition, reuse evaluation as well as integration. In this talk, the speaker will introduce and discuss diverse information system architectures that are involved in these areas. He will present how to exploit relevant solutions to support a number of intelligent services (e.g., knowledge management and decision making).





University of Malaya

Palaiahnakote Shivakumara is a Senior Lecturer in Faculty of Computer Science and Information Technology, University of Malaya. From 2005-2012 he is a Research Fellow in the Department of Computer Science, School of Computing, National University of Singapore. He received B.Sc., M.Sc., M.Sc Technology by research and Ph.D degrees in computer science respectively in 1995, 1999, 2001 and 2005 from University of Mysore, Mysore, Karnataka, India. In addition to this, he has obtained educational degree (B.Ed) in 1996 from Bangalore University, Bangalore, India. From 1999 to 2005, he was Project Associate in the Department of Studies in Computer Science, University of Mysore, where he conducted research on document image analysis, including document image mosaicing, character recognition, skew detection, face detection and face recognition. He worked as a Research Fellow in the field of image processing and multimedia in the Department of Computer Science, School of Computing, National University of Singapore, from 2005‐2007. He also worked as a Research Consultant in Nanyang Technological University, Singapore for a period of 6 months on image classification in 2007. He has published more than 90 research papers in national, international conferences and journals. He has been reviewer for several conferences and journals. His research interests are in the area of image processing, pattern recognition, including text extraction from video, document image processing, biometric applications and automatic writer identification.

Keynote Talk: Multi-Oriented Text Extraction from Video

Text detection and extraction in video is an emerging area for the researchers in the field of image processing, pattern recognition and multimedia processing because it helps in bridging gap between low level and high level features, which is essential for labeling video events. In addition, conventional content based image retrieval methods (CBIR) may not be good enough to handle the problem of event labeling or retrieving based on semantics of the video content. Besides, undesirable characteristics of text (graphics/scene) in video, such as variation in resolution, contrast, background, fonts, font size, color, orientation of text makes the problem more complex and challenging.

In this talk, I try to address one of the major issues of multi-orientation of text in video as it is not easy as extraction of horizontal text in video. Since video may contain low resolution text, we propose new combination of Sobel and Laplacian to enhance the low resolution text information. As classification of text and non-text pixels is two class problem, we propose Bayesian classifier to separate text from the non-text without assuming priori probability. The probable matrices are obtained based on different ways of clustering of text and non-text pixels with the help of k-means clustering algorithm on the enhanced image. The method proposes Boundary growing procedure to traverse multi-oriented text. However, this method gives poor accuracy because of inherent problems of the enhancement method and the boundary growing method. To overcome this problem, we propose one more method based on wavelet and median moments with angle projection boundary growing to achieve better accuracy. Wavelet and median moments are computed at block level to identify text candidates and then text information is restored from the Sobel edge map of the input image if text is missing, which we call text representatives. From the text representatives, we present angle projection boundary growing which fixes bounding box for multi-oriented text lines based on nearest neighbor criteria and angle projection. 



Xiuqin Ma

Xiuqin Ma received the B.Sc. degree in computer science from Central South University, Changsha, China and M.Sc. degree in computer science from Northwest Normal University, Lanzhou, China, and the Ph.D. degree in computer science from the Faculty of Computer Systems and Software Engineering, Universiti Malaysia Pahang, Pahang, Malaysia.

Currently, she is a senior Lecturer with the Faculty of Computer Systems and Software Engineering, Universiti Malaysia Pahang, Pahang, Malaysia. She has published 6 articles in famous international journals such as IEEE TRANSACTIONS ON FUZZY SYSTEMS, Computers and Mathematics with applications, Knowledge-Based Systems and more than 20 articles in conference proceedings. She acts as a reviewer for many journals and conferences. She has also served as a program committee member and co-organizer for numerous international conferences/workshops. Her research interests include soft set theory, rough set theory, data mining, and decision support system.

Tutorial Talk: The Parameterization Reduction and Decision Making of the Interval-Valued Fuzzy Soft Sets (IVFSS)

There has been a rapid growth of interest in developing approaches that are capable of dealing with imprecision and uncertainty. Generally soft set theory which was initiated by Russian mathematician D. Molodtsov in 1999 is applied to deal with uncertainties. A soft set is parameterized family of the subsets of a universal set. It can be said that soft sets are neighborhood systems, and that they are a special case of context-dependent fuzzy sets. Presently, research on soft sets has been very active and many important results have been achieved.

It is the most worthwhile to mention that the concept of the interval-valued fuzzy soft set (IVFSS) by combining soft set with interval-valued fuzzy set has been proposed. To this end, an IVFSS has been employed to handle imprecision and uncertainty in applications such as decision-making problems. However, there has been little focus on parameter reduction of the interval-valued fuzzy soft sets, which is significant in decision-making problems.

In this tutorial, I introduce four different definitions of parameter reduction in interval-valued fuzzy soft sets to satisfy different the needs of decision makers. I presents four heuristic algorithms of parameter reduction. Finally, the algorithms are compared and summarized from the aspects of easy degree of finding reduction, applicability, reduction result, exact level for reduction, multi-usability, applied situation, and computational complexity. The results of the experiment show that the methods reduce the redundant parameters while preserving certain decision abilities.