Time: June 20, 2017, 9:00 am
Venue: Small Conference Room, Department of Biotechnology
Lecturer: Prof. HE Zengyou, School of Software Technology Dalian University of Technology
Prof. Zengyou He, Doctor of Engineering, professor and Ph. D supervisor of School of Software Technology, Dalian University of Technology. He obtained his bachelor degree, master degree and Ph. D degree in 2000, 2002 and 2006 respectively from School of Software Technology, Harbin Institute of Technology. From 2007 to 2010, he carried out postdoctoral study in Department of electronic and computer engineering, Hong Kong University of Science & Technology. From 2010 to now, he worked in School of Software Technology, Dalian University of Technology. His research is focused on the area of data mining and machine learning algorithms and their applications in bioinformatics. He presided over two national natural science research projects, wrote one academic book in English and published more than 40 international scientific papers, which were cited more than 2800 times. He has obtained three provincial and ministerial level awards including: the second prize of natural science of Heilongjiang province (2008, rank 3), the third prize of natural science of Liaoning province (2014, rank 3), the second prize of ministry of education (2016, rank 2).
Machine learning and data mining methods have been widely used for solving real bioinformatics problems. However, such a data analysis process is not trivial. It consists of many steps: problem definition, data collection, data preprocessing, modeling and validation. For each step, different techniques may be applied. Due to the complexity of data mining process and data mining methods, people cannot easily use data mining tools to solve their bioinformatics problems. In this talk, I will use an example-based method to illustrate how to apply data mining techniques to solving real bioinformatics problems. More precisely, I will use several bioinformatics problems in proteomics as examples for illustration purpose. For each example, I will describe the entire data mining process, ranging from data preprocessing to modeling and result validation. In addition, I will also describe how to use different data mining methods to solve the same bioinformatics problem in some examples.
Contact：Group 1810 Prof. ZHANG Lihua