When: Thursday 10th May 2018, 13:00-14:00.
Included in meeting:
The fortnightly BRAG meeting will be held tomorrow, 10/5/2018, Thursday at 1.00 pm in Y801. This week we will have talks from Dilini and Miles.
Title: Anomaly Detection in Nonstationary Streaming Temporal Data
Abstract : This work develops a framework for detecting anomalous series within a large collection of time series in the context of non-stationary streaming data. We define an anomaly as an observation that is very unlikely given the forecast distribution for the corresponding time period. In this work we make two fundamental contributions. First, we propose a framework that provides early detection of anomalous behaviour within a large collection of streaming time series data. The proposed framework first forecast a boundary for the systems typical behavior and then a sliding window is used to test for anomalous series within the newly arrived collection of series. An approach based on extreme value theory is used for the boundary prediction process. Second, we propose a method for early detection of non-stationarity (also called concept drift in the machine learning literature.) The proposed algorithm uses time series features as inputs, and a density-based comparison to detect any significant change in the distribution of the features.
Title: Making an Impact with Software Publishing
Abstract: Lessons learned from the R community about how to publish software people will not only love, but more importantly cite.
Looking forward to see you all!
Farzana and Trish