Time Series Segmentation through Automatic Feature Learning
This work addresses the need for scalable automatic labeling in IoT applications, such as energy monitoring and health tracking, by improving breakpoint detection, though it is incremental as it builds on deep learning methods for a known bottleneck.
The paper tackles the problem of detecting subtle breakpoints in time series data, which traditional statistical methods miss, by proposing an unsupervised deep learning approach that achieves high accuracy and outperforms existing techniques on real-world datasets like human-activity sensing and EEG traces.
Internet of things (IoT) applications have become increasingly popular in recent years, with applications ranging from building energy monitoring to personal health tracking and activity recognition. In order to leverage these data, automatic knowledge extraction - whereby we map from observations to interpretable states and transitions - must be done at scale. As such, we have seen many recent IoT data sets include annotations with a human expert specifying states, recorded as a set of boundaries and associated labels in a data sequence. These data can be used to build automatic labeling algorithms that produce labels as an expert would. Here, we refer to human-specified boundaries as breakpoints. Traditional changepoint detection methods only look for statistically-detectable boundaries that are defined as abrupt variations in the generative parameters of a data sequence. However, we observe that breakpoints occur on more subtle boundaries that are non-trivial to detect with these statistical methods. In this work, we propose a new unsupervised approach, based on deep learning, that outperforms existing techniques and learns the more subtle, breakpoint boundaries with a high accuracy. Through extensive experiments on various real-world data sets - including human-activity sensing data, speech signals, and electroencephalogram (EEG) activity traces - we demonstrate the effectiveness of our algorithm for practical applications. Furthermore, we show that our approach achieves significantly better performance than previous methods.