主题:   A new intelligent pattern classifier based on the logic in human thinking

Abstract：Inthis talk, a new intelligent pattern classifier is proposed based on humanbeing's thinking logic. It is shown that, in order to identify the digitpatterns from a database，the initial patternclusters can be built up in terms of the dot product operation between two datavectors. Then，the developed pattern clusters are used to form the first layer of theclassifier. The second layer will play the role of extracting advanced statisticalfeatures and then output those extracted high-level feature vectors to theoutput layer of the classifier, where logic pattern classification mechanism isused to make the classification decisions. The advantages of the proposedclassifier are that the development of the input layer, the extraction of theadvanced features and the logic decision making for pattern classification are simplybased on the logic in human thinking. Moreover, there is no need to use mathematicaloptimization algorithm to determine the classifier parameters, and thus boththe classifier design and pattern classification process are greatlysimplified.

Bio：Zhihong Man received his B.Eng degree from Shanghai Jiaotong University, China, in 1982,M.Sc degree from Chinese Academy of Sciences in 1987, and PhD degree from theUniversity of Melbourne, Australia, in 1994. From 1994 to 1996, Zhihong was theLecturer in the Department of Computer and Communication Engineering at EdithCowan University, Perth, Australia. From 1996 to 2001, he was the Lecturer andthen Senior Lecturer in the School of Engineering at The University ofTasmania, Australia. In 2001, he was the Visiting Senior Fellow in the Schoolof Computer Engineering at Nanyang Technological University (NTU), Singapore.From 2002 to 2007, he was the Associate Professor of Computer Engineering atNTU. From 2007 to 2008, Zhihong was with Monash University Sunway Campus(Malaysia), where he served as the Professor and Head of Electrical andComputer Systems Engineering, the Chair of the Research Committee of the Schoolof Engineering, and the Chair of the Monash Sunway Campus Research Committee.Zhihong is currently the Professor of Robotics and Mechatronics in the Facultyof Science, Engineering and Technology at Swinburne University of Technology,Melbourne, Australia. 

Zhihong Man’s research interests are in nonlinear control, signal processing, robotics,neural networks, fuzzy systems, engineering optimization, diagnosis ofindustrial systems, vehicle dynamics and control. He has published more than200 papers in refereed international journals and refereed international conferencesproceedings. Since 1994, Zhihong was the Guest Editor of 6 Special Issues onneural networks, diagnosis of industrial systems and nonlinear control,published in ISCI and ERA journals. Zhihong has been involved in manyinternational conferences in control, robotics, signal processing, neuralnetworks and industrial electronics as General Chair, Program Committee Chair,Track Chair, Session Chair, and the International Advisory Committee andTechnical Committees member, including the Chair of the Technical Committee ofthe third IEEE International Conference on Industrial Electronics andApplications (ICIEA 2008) and the co–Chair of the Program Committee of theFourth IEEE International Conference on Industrial Electronics and Applications(ICIEA 2009).

Language：English