Special Session Proposal for IDEAL2017
Learning from Big Data, Streaming Data and Heterogeneous Multi-Source Data: Algorithms, Models and ApplicationsOrganizers:
Prof. Ming Yang, Nanjing Normal University, China. Email: firstname.lastname@example.org
Prof. Yang Gao, Nanjing University, China. Email: email@example.com
Prof. Wensheng Zhang, Institute of Automation of Chinese Academy of Sciences, China. Email: firstname.lastname@example.org
Dr. Wanqi Yang, Nanjing Normal University, China. Email: email@example.comIntroduction:
In our real life, big data are usually continuously collected from various sources (e.g., websites, devices, databases, etc). Thus, they are in form of streaming and heterogeneous multi-source data. The learning and mining techniques to obtain the valuable information from such big data, are becoming more and more significant, which can help improve our life. However, the state-of-the-art techniques are undesirable to deal with the issue. Recently, related learning theories and techniques of big data analysis have attracted much attention from both academic and industrial communities. Several existing methods have been successfully presented in many applications, e.g., social network, e-business, information retrieve, multimedia analysis, etc. The special session on “learning from big data, streaming data and heterogeneous multi-source data: algorithms, models and applications” will focus on the latest developments about learning theories and techniques to deal with streaming data and heterogeneous multi-source data. Specifically, it is welcome to discuss about several novel methods to address (1) efficient learning algorithms for heterogeneous multi-source data, (2) fast online learning algorithms for streaming data and (3) their applications in computer vision (e.g., medical image analysis, face recognition, person re-identification, etc).