On-line Monitoring of High-dimensional Data Streams

Abstract

[evdate 2013-12-19] HKUST International Forum on Probability and Statistics. Talk no.7.

Title from opening screen.

The Second HKUST International Forum on Probability and Statistics (2013), held 19 December, 2013, at the Hong Kong University of Science and Technology. Co-sponsored by the HKUST Jockey Club Institute for Advanced Study and the Center for Statistical Science.

'This talk is based on joint works with Changliang Zou and Zhaojun Wang.'

Abstract: Monitoring high-dimensional data streams has become increasingly important for real-time detection of abnormal activities in many data-rich applications. The speaker is interested in detecting an occurring event as soon as possible, but we do not know which subset of data streams is affected by the event. By connecting to the problem of detecting heterogeneous mixtures, a new control chart scheme is developed based on a powerful goodness-of-fit test of the local cumulative sum statistics from each data stream. Both (asymptotically) theoretical analysis and numerical results show that the proposed method is able to balance the detection of various fractions of affected streams, and generally outperforms existing methods.

Duration: 28 min.