报告题目：Computation Efficient Gene Expression Programming for Big Data Analytics
报告人：Maozhen Li 教授，Brunel University London
Gene expression programming (GEP) is a data driven evolutionary technique that well suits for correlation mining of big data. This talk starts with a brief introduction to GEP and its application in mining the correlations of the parameter settings of Hadoop MapReduce for big data analytics. MapReduce is a major computing model in dealing with data intensive applications, and Hadoop has been widely taken up by the community due to its open source implementation of MapReduce. This talk then elaborates the computation nature of GEP in evolution based on an analysis of GEP schema theory, and as a result it presents a parallel GEP for computation speedup. The parallel GEP is evaluated on two data sets with complementary features. One data set has complex but loosely-coupled data samples in that each sample has a large number of input factors. The other data set has strongly correlated data samples but each sample has a small number of input factors. The computation complexity of the parallel GEP is further analyzed to demonstrate the high scalability of the parallel GEP in dealing with potential big data using a large number of CPU nodes. This work has recently been accepted for publication in IEEE Transactions on Evolutionary Computation with an impact factor of 10.629.
About the Speaker
Professor Maozhen Li received his PhD from the Institute of Software, Chinese Academy of Sciences in 1997. He did his post-doc research in the Dept. of Computer Science at Cardiff University, UK in 1999-2002. He is now a full Professor in the Department of Electronic and Computer Engineering at Brunel University London, UK. His research interests are in the areas of high performance computing technologies including grid computing and cloud computing, big data analytics, and intelligent systems. He has over 150 scientific publications in these areas including 3 books and 70 peer reviewed journal papers. He has served over 30 IEEE conferences. He was the Chair of the TPC of FSKD’16, FSKD’14 and FSKD’12 respectively and he is on the Editorial Boards of a number of journals. His collaborative research with Tongji University, China on Intelligent Transportation Systems was nominated by the Institution of Engineering and Technology (IET) for its Innovation Award in November 2015. Currently he is organizing a Special Issue on High Performance Deep Learning Techniques for
Big Data Analytics for journal of Concurrency and Computation: Practice and Experience, looking at the research challenges in empowering large scale deep neural networks with high performance computing technologies. He is a Fellow of the British Computer Society.