2018年1月19日学术报告（Jacky Keung City University of Hong Kong ）
报告题目1：Making Sense of Data in Software Engineering Data Analytics
报告人： Jacky Keung Assistant Professor
报告人单位： Department of Computer Science, City University of Hong Kong
Dr. Jacky Keung received his B.Sc. (Hons) in Computer Science from the University of Sydney, Australia and his Ph.D. in Software Engineering from the University of New South Wales, Australia. He is Assistant Professor in the Department of Computer Science, City University of Hong Kong. He has substantial research experience in experimental software engineering, including software effort estimation, data analytics, statistical analysis, and the empirical evaluation of software engineering theories and methodologies. His main research area is in software effort and cost estimation, empirical modelling and evaluation of complex systems, and intensive data mining for software engineering datasets, as well as his latest work in deep-learning and blockchain for a FinTech Project. He has published many papers in prestigious journals including IEEE-TSE, IEEE-SOFTWARE, EMSE, IST, JSS as well as in many other leading journals and international conferences.
Software Engineering has been shifting its primary focus from traditional software development techniques to utilizing a diverse range of techniques such as machine learning and statistics to understand and making sense of software data observed, in order to making and communicating decisions from data. In this seminar, we are focusing on our predictive analytics in software defect predictions on the class imbalance issue and its effects of resampling approaches, as well as their significant effects on defect prioritization and classification problems. Furthermore, we show new experimentations on utilizing Convolutional Neural Network CNN on Deep Learning to improve bug localization as well as its applications to future directions in software engineering.