讲座题目：Evolutionary Feature Reduction and Applications

主讲人：Dr. Xue Bing  (Victoria University of Wellington, VUW)

时间： 2015年6月15日（周一）14:30-16:30

地点： 文科楼H3-400 MBA专用教室

主持人：牛奔 副教授 管理科学系主任

主讲人简介：

Bing Xue is currently a Lecturer in Evolutionary Computation Research Group, Victoria University of Wellington (VUW), New Zealand. Her research focuses mainly on evolutionary computation, feature selection, feature construction, dimension reduction, multi-objective optimisation, symbolic regression, image processing, data mining and machine learning. Dr Xue is leading the strategic research direction on evolutionary feature selection and construction at VUW.

Bing is the Chair of Task force in Evolutionary Feature Selection and Construction in IEEE Computational Intelligence Society (CIS), Program Chair of the 7th International Conference on Soft Computing and Pattern Recognition (2015), Guest Editor of Special Issue on Evolutionary Optimisation, Feature Reduction and Learning, Soft Computing (Journal), Chair of Symposium on Computational Intelligence in Feature Analysis, Selection, and Learning in Image and Pattern Recognition in IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2016), Chair of Special session Evolutionary Feature Selection and Construction in IEEE Congress on Evolutionary Computation, WCCI 2016 /CEC2016 and CEC2015,  and in international conference on Simulated Evolution And Learning (SEAL) 2014.  She is also a member of Evolutionary Computation Technical Committee in IEEE CIS. Dr Xue is serving as a reviewer for 17 international journals and a program committee member for over 30 international conferences. She is also serving as the Director of Women in Engineering for the IEEE New Zealand Central Section.

讲座内容简介：Many real-world problems often involve a large number of features/attributes. However, not all the features are essential (or important) since many of them are redundant or even irrelevant, which may even reduce the performance of a machine learning or data mining algorithm. Feature reduction mainly feature selection can solve this problem by selecting only a small subset of relevant features.  However, feature selection is a challenging task due mainly to the large search space. Evolutionary computation techniques have recently gained much attention and shown some success. This talk will discuss the state-of-the-art work on evolutionary computation for feature selection and different applications of evolutionary feature selection methods. In addition, current issues and challenges will also be discussed to identify promising areas for future research.

欢迎感兴趣的师生参加！

　　　　　　　　　　　　　　　深圳大学 管理学院 管理科学系

　　　　　　　　　　　　　　　　　　　　2015年6月10日