Burst-Based Event Classification on Weakly Labeled Time Series Data of Sensors


Detecting events on time series data generated by sensors has received a great amount of attention with increasingly deployment of variable sensors. In this paper, we propose a novel framework for classifying events upon sensors data called BEC. Given long raw time series and event labels on fuzzy time points, BEC extracts burst-based features to represent… (More)
DOI: 10.1109/BigDataCongress.2017.66


8 Figures and Tables