News (2013)

News (2013)

IEEE Cloud-Link

Dr. Carson K. Leung serves as an Assistant Editor for the Cloud-Link, which is a joint collaboration between the IEEE Cloud Computing Initiative (CCI) and the IEEE Computer Society Cloud Computing Special Technical Community (STC).

CASoN 2013

On Tuesday, August 13, 2013, Richard Kyle MacKinnon presented a refereed paper titled "Finding groups of friends who are significant across multiple domains in social networks", which he co-authored with his academic supervisor (Dr. Carson K. Leung) and his fellow lab members (Dr. Syed K. Tanbeer, Fan Jiang, and Irish J.M. Medina), in CASoN 2013 held in Fargo, ND, USA. The paper was published by the IEEE Press.

WAIM 2013

On Saturday, June 15, 2013, Fan Jiang presented a refereed paper titled "Mining frequent itemsets from sparse data streams in limited memory environments", which he co-authored with his academic supervisor (Dr. Carson K. Leung), his fellow lab member (Juan J. Cameron), and their international collaborator (Dr. Alfredo Cuzzocrea from Italian National Research Council), in WAIM 2013 held in Beidaihe (北戴河) (a district in the city of Qinhuangdao in Hebei province), China. The paper was published by the Springer.

USRA 2013

Three lab members won undergraduate student research awards:

• • Mr. Richard Kyle MacKinnon, who just completed his B.C.Sc.(Hons.) degree program with First Class Honours, won a Faculty of Science Undergraduate Student Research Award (USRA) to conduct a full-time 16-week research project in the area of data mining under the academic supervision of Dr. Carson K. Leung.

  • Fourth-year undergraduate student Ms. Irish J.M. Medina, who is enrolled in the B.C.Sc.(Hons.) degree program, won a UofM Vice-President (Research and International) Undergraduate Research Award (URA) the second time to conduct a full-time 16-week research project in the area of data mining (social network mining) under the academic supervision of Dr. Carson K. Leung. Among ~23,000 undergraduate students across the campus, she was one of 82 winners of this award.

  • Third-year undergraduate student Ms. Wenzhu Tong (童文竹), from Wuhan University (武汉大学), won a MITACS Globalink award to conduct a full-time 12-week research project on "Mining useful information from social network" in the area of data mining (social network mining) under the academic supervision of Dr. Carson K. Leung. She was one of the 10 Globalink Research Interns in the entire UofM campus, but the only Globalink Research Intern in UofM Department of Computer Science.

MITACS Globalink 2013

Mining useful information from social networks

Program: Globalink Research Internship

University: University of Manitoba

Department: Computer Science

Faculty Supervisor: Carson Leung

Research within the Database and Data Mining Laboratory in Department of Computer Science at University of Manitoba mainly focuses on databases and data mining, which includes efficient and effective management of, knowledge discovery from, as well as analysis of, large amounts of data (such as transactional, uncertain, social media, Web, and/or streams of data). Current research programs focus on data mining, data warehousing and OLAP (on-line analytical processing), data visualization and visual analytics, as well as applications of database and data mining technologies to areas such as social computing and social network mining. Over the past few years, members in my lab (both undergraduate and graduate, international and local, students including USRA award recipients) have actively designed algorithms that efficiently and effectively find frequently occurring patterns (say, merchandise items frequently purchased together by customers) as well as detected exceptional or abnormal items (say, detect malfunction devices). The resulting algorithms have been applied to various real-life applications.

The research project for Globalink 2013 falls within the scope of the aforementioned research programs. Specifically, we focus on social network mining in this project. Over the past few years, the rapid growth and the exponential use of social digital media has led to an increase in popularity of social networks and social computing. In general, social networks are structures made of social entities (e.g., individuals) that are linked by some specific types of interdependency relationship such as friendship, kinship, or partnership. The emergence of Web-based communities and hosted services such as social networking sites (e.g., Facebook, Google+, LinkedIn, Renren, Sina Weibo, Tencent Weibo, Twitter) has facilitated collaboration and knowledge sharing between users. Most users of social media have many linkages in terms of friends, connections, and/or followers. Among all these linkages, some of them are more important than others. For instance, some friends of a user may be casual ones who acquaintances met him at some points in time, whereas some others may be friends that care about him in such a way that they frequently post on his wall, view his updated profile, send him messages, invite him for events, and/or follow his tweets. In this project, students will apply the knowledge and skills they acquired in their undergraduate database courses to build a database for capturing relevant data from a social network. They will then develop a business intelligence solution that applies data mining techniques to social networks so as to help users of the social digital media to discover implicit, previously unknown, and useful knowledge from the social networks.

Specialization: My specialized research area in computer science relates to data management. In particular, I focus on data mining. The student participates in this Globalink 2013 project will learn data mining techniques to provide a business intelligence solution for knowledge discovery from social network data.

Skills Required: While the very specific details of the Globalink 2013 project will be further determined by the supervisor and the student, we expect that the student to complete a small concrete component (that is suitable and manageable for an undergraduate student) during the internship. In general, international student participating in this research project will be asked to implement a data mining component in C/C++ and/or a visualization component in C# or .Net.

Student Role: The Database and Data Mining Lab in Department of Computer Science at University of Manitoba is a multi-cultural environment. Current and previous lab members include students from Asia (e.g., China, Korea, India, Bangladesh, Malaysia), Central and South Americas (e.g., Paraguay). The international undergraduate student participating in the MITACS Globalink 2013 project will work under the academic supervision of Dr. Carson Leung for an approximate 12-week research internship in the summer of 2013. In addition, the student will also work closely with a senior lab member (who will serve as a mentor) and will contribute a small concrete component of the project suitable at the level for the undergraduate students.

Celebration of Excellence 2013

Congratulation to B.C.Sc.(Hons.) student Irish Medina, who was recognized as a winner of the UofM Vice-President (Research and International) Undergraduate Student Research Award (USRA) 2012 at the Celebration of Excellence organized by UofM Faculty of Science held Tuesday, February 5, 2013. Among all full-time UofM undergraduate students, only 80 of them won this award in 2012. Out of the 13 award winners from the Faculty of Science, Medina was the only female award winner from Computer Science.

SMM-SNA (2013)

Guandong Xu, Lin Li (Eds.):

Social Media Mining and Social Network Analysis: Emerging Research

(January 2013)

ISBN 978-1-4666-2806-9

Detailed Table of Contents (pp. vii-xii)

The emergence of Web-based communities and social networking sites has led to a vast volume of social media data, embedded in which are rich sets of meaningful knowledge about the social networks. Social media mining and social network analysis help to find a systematic method or process for examining social networks and for identifying, extracting, representing, and exploiting meaningful knowledge—such as interdependency relationships among social entities in the networks—from the social media. This chapter presents a system for analyzing the social networks to mine important groups of friends in the networks. Such a system uses a tree-based mining approach to discover important friend groups of each social entity and to discover friend groups that are important to social entities in the entire social network.

Preface (pp. xv-xviii) [igi]

Chapter 6 analyzes social networks to mine important friends among many users in social media. In particular, this chapter theoretically investigates, from a frequent pattern mining prospective, the research problem of distinguishing close friends who post messages on your wall from those acquaintances. Theoretical concepts of both ego-centric and socio-centric groups of friends are also implemented and materialized into a tree-based social media mining system that discovers important ego-centric groups of friends of any individual social media user as well as important socio-centric groups of friends in the social networks. A step-by-step illustrative example is given to demonstrate how relevant social network information is capturing in a tree structure, from which important groups of friends can be mined.

About the Contributors (pp. 245-251) [igi]

Carson K.-S. Leung received his B.Sc. (Hons.), M.Sc., and Ph.D. degrees, all in Computer Science, from the University of British Columbia, Canada. Currently, he is an Associate Professor in Department of Computer Science at University of Manitoba, Canada. His research interests include the areas of databases, data mining, social media mining, social network analysis, and social computing. His work has been published in refereed international journals and conferences such as ACM Transactions on Database Systems, IEEE International Conference on Data Engineering (ICDE), IEEE International Conference on Data Mining (ICDM), and Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD). In the past few years, he has served as a Program Chair for International C* Conference on Computer Science and Software Engineering (C³S²E) 2009-2010, an organizing committee member of ACM SIGMOD 2008 and IEEE ICDM 2011, and a PC member of numerous international conferences including ACM KDD, CIKM, and ECML/PKDD.

Irish J. M. Medina is pursuing her B.C.Sc. (Hons.) degree in Computer Science with a minor in Mathematics. During her current undergraduate degree studies, she has received several awards and honours including a few institutional scholarships as well as recognitions to be on the University 1 Honour List and the Dean's Honour List. Moreover, she has also received the University of Manitoba Undergraduate Summer Research Award for her summer academic research in the Database and Data Mining Lab, led by Prof. Carson K.-S. Leung, in Department of Computer Science at University of Manitoba, Canada. Ms. Medina is interested in databases and data mining.

Syed K. Tanbeer received his B.S. degree in Applied Physics and Electronics in 1996 and his M.S. degree in Computer Science in 1998, both from University of Dhaka, Bangladesh. He then worked as a faculty member in Department of Computer Science and Information Technology at IUT-OIC, Dhaka, Bangladesh. He received his Ph.D. degree in Computer Engineering in 2010 from Kyung Hee University, South Korea. Currently, he is a Post-Doctoral Fellow in the Database and Data Mining Lab, led by Prof. Carson K.-S. Leung, in Department of Computer Science at University of Manitoba, Canada. Dr. Tanbeer's research areas are data mining, parallel and distributed mining, and knowledge discovery from social network.

Tanbeer's Teaching

Dr. Syed K. Tanbeer, a post-doctoral fellow in our lab, teaches:

• • lecture-based COMP 1260 A01 (Introductory Computer Usage 1) in Winter 2013 on every Monday, Wednesday & Friday at 11:30am-12:20pm in Isbister 231 from January 07 to April 10, 2013; and

  • distance & online education-based COMP 1260 (D01) in Summer 2013 from May 06 to August 02, 2013.

By the end of Summer 2013, Tanbeer has taught COMP 1260 eight times (three lecture-based and five distance & online education-based).

TLDKS VIII (2013)

Alfredo Cuzzocrea, Ueshwar Dayal:

Preface.

LNCS Transactions on Large-Scale Data- and Knowledge-Centered Systems (TLDKS) VIII (LNCS 7790),

special issue on advances in data warehousing and knowledge discovery:

V-IX (December 2012)

Finally, the eighth paper, titled "Discovering Frequent Patterns from Uncertain Data Streams with Time-Fading and Landmark Models", by Carson Kai-Sang Leung, Alfredo Cuzzocrea, and Fan Jiang, proposes novel techniques for discovering frequent patterns from uncertain data streams that exploit the time-fading model and the landmark model, respectively. Indeed, as authors recognize, streams of data can be continuously generated by sensors in various real-life applications such as environment surveillance. Partially due to the inherited limitation of the sensors, data in these streams can be uncertain. To discover useful knowledge in the form of frequent patterns from streams of uncertain data, a few algorithms have been developed. They mostly use the sliding window model for processing and mining data streams. However, for some applications, other stream processing models such as the time-fading model and the landmark model are more appropriate. On the basis of this main assumption, authors provide mining algorithms that use these two latter models to discover frequent patterns from streams of uncertain data, by completing with an extensive experimental assessment and analysis on both synthetic and real-life data stream sets.