Shan-Hung Wu

Among the well-known "V"s of big data, it’s arguably the "Variety" and "Veracity" that bother most practitioners. While not everybody has the huge problems of "Volume" and "Velocity" that a Facebook or a high frequency trader has, even the smallest business has multiple data sources they can benefit from the integration of various data sources and from appropriate pre-processing. In this talk, I will share my experience in coping with the variety and veracity of big network data when performing some common data mining/machine learning tasks, including classification and clustering. Our results show that innovative access to a broad variety of data is a key part of a learning task for driving better understanding.

Shan-Hung Wu is an associate professor at the Department of Computer Science, National Tsing Hua University (NTHU). Before joining NTHU, he was a senior research scientist at Telcordia Technologies (formerly Bellcore). He received the Ph.D. degree in Electrical Engineering from the National Taiwan University, in 2009. His research interests include wireless networking, machine learning/data mining, mobile data management, and databases/distributed systems. Prof Wu has published many papers in top-tier journals such as IEEE/ACM Tans. on Networking (TON), IEEE Selected Areas in Communications (JSAC), IEEE Trans. on Knowledge and Data Engineering (TKDE), and IEEE Trans. on Mobile Computing (TMC), and top-tier conferences such as MobiHoc, INFOCOM, KDD, and ICML.