More about HKUST
Soft Computing Techniques for Constructing Intelligent Information System
Speaker: Professor Rolly Intan, Dr.Eng. Department of Informatics Petra Christian University, Indonesia Title: "Soft Computing Techniques for Constructing Intelligent Information System" Date: Thursday, 6 September 2018 Time: 4:00pm - 5:00pm Venue: Rm2303 (via lift 17/18), HKUST Abstract: We live in an uncertain world that means uncertainty cannot be avoided in our real world application. Uncertainty has already influenced many theories and concepts in modern science as a great utility in solving many real world problems essentially. Living in uncertain world is also represented in human communication that usually uses perception-based information. Therefore, it is necessary to construct a computer-based information system called "Intelligent Information System" that is able to process perception-based information. In the future through the Intelligent Information System, humans are able to communicate with computers in the level of perception-based information. Here, perception is defined as a process of translating sensory stimulation into an organized experience. Perception is an intrinsic aspect in human-based information. In the perception-based information, the information might be incomplete, imprecise, fragmentary, vague, contradictory, etc. All characteristics of information are considered as various types of uncertainty. They need a hybrid soft computing techniques to construct the intelligent information system. As proposed by L. A. Zadeh in 1990, unlike hard (conventional) computing, soft computing is tolerant of imprecision, uncertainty, partial truth, and approximation to achieve tractability, robustness and low solution cost. Soft Computing is a human mind-based computing. The human mind, unlike present day computers, possesses a remarkable ability to store and process information which is pervasively imprecise, uncertain and lacking in category. Some principal constituents of soft computing are Fuzzy Systems, Probabilistic Reasoning, Granular Computing, Belief Network, Neural Networks, Evolutionary Computation, Machine Learning, Chaos, DNA Computing, etc. The principal constituent methodologies in soft computing are complementary rather than competitive. Soft computing is a partnership in which each of the partners contributes a distinct methodology for addressing problems in its domain. Soft computing may be viewed as a foundation component for the emerging field of conceptual intelligence. The employment of soft computing techniques leads to systems which have high MIQ (Machine Intelligence Quotient). A simple example of hybrid soft computing techniques is given by a complementary among fuzziness, roughness and probability. It is clear that probability and fuzziness work in different areas of uncertainty. Here, fuzzy event in the presence of probability theory provides probability of fuzzy event in which fuzzy event could be regarded as a generalization of crisp event. Moreover, in rough set theory, a rough event is proposed representing two approximate events, namely lower approximate event and upper approximate event. Similarly, in the presence of probability theory, rough event can be extended to be probability of rough event. ********************** Biography: Prof. Rolly Intan, Dr.Eng. is currently a full professor in Informatics Department of Petra Christian University, Surabaya, Indonesia. He was the rector (president) of Petra Christian University from 2009 to 2017. His Doctor of Engineering degree was obtained in 2003 from Meiji University, Tokyo, Japan. He also received his Doctor honoris causa in Business Administration from Dongseo University, Busan, South Korea. Prof. Rolly Intan has research interests in how to apply Computational Intelligence and Soft Computing methods especially Fuzzy Sets Theory, Rough Sets Theory and Granular Computing in constructing Intelligent Information System. He has already published more than 80's papers in international journals and reputable international conference proceedings.