Detecting Anomalies within Time Series using Local Neural Transformations
This addresses the challenge of anomaly detection in time series for applications like self-driving cars and medical diagnosis, but it is incremental as it adapts existing self-supervised techniques to a new domain.
The paper tackled the problem of detecting anomalies in time series by developing Local Neural Transformations (LNT), a self-supervised deep learning method that learns local transformations from data, resulting in improved detection of anomalies in speech segments and cyber-physical systems compared to previous work.
We develop a new method to detect anomalies within time series, which is essential in many application domains, reaching from self-driving cars, finance, and marketing to medical diagnosis and epidemiology. The method is based on self-supervised deep learning that has played a key role in facilitating deep anomaly detection on images, where powerful image transformations are available. However, such transformations are widely unavailable for time series. Addressing this, we develop Local Neural Transformations(LNT), a method learning local transformations of time series from data. The method produces an anomaly score for each time step and thus can be used to detect anomalies within time series. We prove in a theoretical analysis that our novel training objective is more suitable for transformation learning than previous deep Anomaly detection(AD) methods. Our experiments demonstrate that LNT can find anomalies in speech segments from the LibriSpeech data set and better detect interruptions to cyber-physical systems than previous work. Visualization of the learned transformations gives insight into the type of transformations that LNT learns.