报告题目:   Application of Deep Learning in Spatio-temporal Data Management

报告人：    郑凯 教授  电子科技大学

主持人：    程鹏

报告时间：2019年6月6日  周四14:00-15:00

报告地点：中北校区数学馆201

报告摘要：
Recently, with the great success of deep learning models and techniques in multimedia areas such as audio/video analysis, they have been replacing the traditional machine learning models and become the mainstream tools for data analysis in numerous products and applications. In contrast, it is still in very early stage for deep learning techniques dealing with many other kinds of data, leaving lots of open problems to investigate. On the other hand, as an important extension of relational data, spatio-temporal data management has drawn increasing attention from both academia and industry, due to its wide application in critical domains such as transportations, meteorology, urban planning, homeland resources, etc. In this talk, I will introduce the challenges and opportunities when applying deep learning techniques in spatio-temporal data management, by relating to its source, taxonomy and features. Moreover, I will share some application cases of spatio-temporal predication with deep learning techniques.

报告人简介：
郑凯，电子科技大学教授，博士生导师。2012年于澳大利亚昆士兰大学获计算机科学博士学位，2012至2017年在澳大利亚昆士兰大学先后担任博士后研究员和讲师。近年来的主要研究方向涵盖了时空数据管理、不确定数据管理、内存数据管理、图数据管理以及区块链数据管理等领域的理论基础与技术应用。在数据库和数据挖掘等领域的重要会议和期刊发表论文120余篇，谷歌学术引用2700余次。曾获得澳大利亚优秀青年基金（2013），两次获得数据库顶级会议ICDE最佳论文奖（2015和2019），国际会议APWeb-WAIM和WISE最佳论文奖（2017）。担任数据库国际会议APWeb2016的程序主席和DASFAA2017的大会执行主席，担任国际SCI期刊Distributed and Parallel Databases和DKE的编委，WWW Journal、Geoinformatica、Frontier of Computer Science客座编委，担任数十个大数据与人工智能领域顶级会议的程序委员(TPC member)。