报告人简介：

张吉，现为澳大利亚南昆士兰大学计算机科学终身教授职位，博士生导师。曾任南昆士兰大学信息技术中心首席研究顾问, IEEE高级会员，ACM会员，澳大利亚奋进学者，昆士兰学者，加拿大Killam学者，第3届世界智能大会特邀专家，美国密歇根州立大学、新加坡南洋理工大学和日本筑波大学访问客座教授。张吉教授获2011年度南昆士兰大学杰出研究奖和澳大利亚奋进奖。张吉教授的主要研究方向为大数据分析, 数据挖掘, 信息隐私保护及安全，计算智能等，张吉教授已在国际主要期刊和国际会议中发表研究论文150余篇，其中包括国际重要的学术期刊和国际会议如TKDD, TDSC, Information Sciences, KAIS, PRL, WWW Journal, JIIS, Bioinformatics and top international conferences such as VLDB, ACM CIKM, ACM SIGKDD, IEEE ICDE, IEEE ICDM, WWW Conference, PAKDD, DASFAA 和DEXA等，并撰写个人专著1部及专著论文7篇。

报告简介：

In this talk, I will present some of our recent work on outlier detection. I will first talk about SPOT, a technique for detecting outliers from large high-dimensional data streams. Computational Intelligence method based on Genetic Algorithm is developed to achieve efficient high-dimensional subspace search. Innovative fast convergence technique is also proposed to significant speed up the detection process. I will then introduce DISTROD, a technique for detecting outliers from multiple large distributed databases. It is able to effectively detect the so-called global outliers from distributed databases that are consistent with those produced by the centralized detection paradigm.