Unsupervised anomaly detection by densely contrastive learning for time series data.

Time series data continuously collected by different sensors play an essential role in monitoring and predicting events in many real-world applications, and anomaly detection for time series has received increasing attention during the past decades. In this paper, we propose an anomaly detection method by densely contrasting the whole time series with its sub-sequences at different timestamps in a latent space. Our approach leverages the locality property of convolutional neural networks (CNN) and integrates position embedding to effectively capture local features for sub-sequences. Simultaneously, we employ an attention mechanism to extract global features from the entire time series. By combining these local and global features, our model is trained using both instance-level contrastive learning loss and distribution-level alignment loss. Furthermore, we introduce a reconstruction loss applied to the extracted global features to prevent the potential loss of information. To validate the efficacy of our proposed technique, we conduct experiments on publicly available time-series datasets for anomaly detection. Additionally, we evaluate our method on an in-house mobile phone dataset aimed at monitoring the status of Parkinson's disease, all within an unsupervised learning framework. Our results demonstrate the effectiveness and potential of the proposed approach in tackling anomaly detection in time series data, offering promising applications in real-world scenarios. • We propose Densely Contrastive Anomaly Detection (DCAD) by contrasting the whole time series and its subsequences in a latent space. • We jointly utilize a contrastive learning loss, a distribution alignment loss, and a reconstruction loss to train our model. • We conduct experiments on publicly available datasets for anomaly detection and an in-house mobile phone dataset for PD to thoroughly validate the effectiveness of our method. [ABSTRACT FROM AUTHOR]