（一）

时间：2013年5月12日（周日）14:30-15:40
地点：逸夫楼501
主题： Mining and Exploring Data in Service Computing
主讲：吴建

报告人简介：

       吴健，副教授/硕导，1998年在浙江大学计算机系获学士学位，2004年在浙江大学计算机应用专业获博士学位，2006年晋升为浙江大学计算机学院副教授。浙江大学电子服务研究中心副主任，中国计算机学会青工委委员，中国计算机学会服务计算专委会委员，中国计算机学会计算机应用专委会委员，浙江省151人才，科技部重点领域创新团队成员，曾任CCF YOCSEF杭州主席，浙江省计算机学会青工委主任。担任PAKDD2013/2014、ICESS2013、ADMA2013等国际学术会议程序委员会委员，TKDE、KAIS、TSMC、TSC、JWSR等学术期刊的审稿专家。研究兴趣集中在服务计算、数据挖掘等方面。近年来承担国家科技支撑项目1项，国家自然科学基金项目3项，浙江省自然科学基金1项，863计划3项，浙江省重大科技攻关1项。先后在IEEE Intelligent Systems、IEEE TKDE、IEEE TSMC、KAIS等国内外期刊会议发表SCI/EI收录论文70余篇，获得2008和2009年度中国百篇最具影响力国内文章。2007年获得教育部科技进步一等奖。2008年获得浙江省科技进步一等奖，2010年获国家科技进步二等奖。

报告提要：

     The development of cloud computing and mobile computing poses a lot of opportunities to service oriented computing. In particular, the knowledge hidden in the explosive growth of service related data provides a chance to handle some difficult problems in service computing. In this talk, we will focus on the problem of service recommendation, and utilize two kinds of service related data to improve its performance. In the first scenario, we propose to improve the recall performance of service recommendation by using a Web service clustering framework named WSTCluster, in which WSDL documents and social tagging data are employed. To handle the spam tags and cold-start problem, a tag relevance measurement Mechanism, i.e. WS-TRM, is proposed. In the second scenario, considering the user knowledge and behavior information hidden in service historical execution records, we employ a bayes theorem based approach on the historical data to estimate the probabilities of candidate services for the purpose of facilitating service recommendation. A graph-mining based approach is also proposed to model and explore the historical service composition records. Finally, we will summary a series of work of our group in service discovery and recommendation.

（二）

时间：2013年5月12日（周日）15:50-17:00
地点：逸夫楼501
主题：QoS Management of Service Computing
主讲：郑子彬

报告人简介：

　　郑子彬，香港中文大学深圳研究院副研究员，主要研究方向为服务计算、分布式系统、及软件可靠性。近五年共发表期刊及会议论文50余篇，被SCI收录16篇，出版Springer英文著作1部，论文总共被引用602次。2011年获得香港中文大学杰出博士毕业论文奖；2010年获得软件工程领域旗舰会议国际软件工程大会（ICSE）ACM SIGSOFT Distinguished Paper Award；2010年获得IEEE Web服务大会（ICWS）最佳学生论文奖；2010年被评为IBM Ph.D. Fellow；2009年被英国剑桥名人传记中心评为该年度2000名杰出青年科学家之一。担任International Journal on Advances in Networks and Services、International Journal on Intelligent Systems等多个国际期刊的编委，担任IEEE ICWS、IEEE SCC、IEEE CLOUD、IEEE SOSE、ICSOC等多个国际学术会议的PC Member。

报告提要：

        Web service is becoming a major technique for building loosely-coupled distributed systems. Quality-of-Service (QoS) is usually employed for describing the non-functional characteristics of Web services and employed as an important differentiating point of different Web services. With the prevalence of Web services on the Internet, Web service QoS management is becoming more and more important. In this talk, we will first propose a distributed QoS evaluation framework for Web services, named WS-DREAM. Inspired by the recent success of Web 2.0, our evaluation framework employs the concept of user-collaboration. Since Web service evaluation is time and resource consuming, and in some scenarios, Web service evaluation may not be possible (e.g., the Web service invocation is charged, too many service candidate, etc.). Therefore, Web service QoS prediction approaches are becoming more and more attractive. In order to prediction the Web service QoS as accurate as possible, we propose three prediction methods. Finally, based on the predicted QoS values, we propose two methods for building fault tolerance Web services. 

计算机学院研究生分会
2013年5月9日