Latent Space Unsupervised Semantic Segmentation
This work addresses the need for efficient segmentation of biosignals from wearable sensors, which is incremental as it improves upon existing change-point detection methods.
The paper tackles the problem of unsupervised segmentation of multidimensional time series, such as biosignals, by proposing LS-USS, which overcomes limitations of traditional change-point detection methods by handling both online and batch data. It shows that LS-USS achieves on par or better performance compared to state-of-the-art algorithms in offline and real-time settings.
The development of compact and energy-efficient wearable sensors has led to an increase in the availability of biosignals. To analyze these continuously recorded, and often multidimensional, time series at scale, being able to conduct meaningful unsupervised data segmentation is an auspicious target. A common way to achieve this is to identify change-points within the time series as the segmentation basis. However, traditional change-point detection algorithms often come with drawbacks, limiting their real-world applicability. Notably, they generally rely on the complete time series to be available and thus cannot be used for real-time applications. Another common limitation is that they poorly (or cannot) handle the segmentation of multidimensional time series. Consequently, the main contribution of this work is to propose a novel unsupervised segmentation algorithm for multidimensional time series named Latent Space Unsupervised Semantic Segmentation (LS-USS), which was designed to work easily with both online and batch data. When comparing LS-USS against other state-of-the-art change-point detection algorithms on a variety of real-world datasets, in both the offline and real-time setting, LS-USS systematically achieves on par or better performances.