udCATS: A Comprehensive Unsupervised Deep Learning Framework for Detecting Collective Anomalies in Time Series

Abstract

Anomaly detection has recently gained enormous attention from the research community. It is widely applied in many industrial areas, such as information security, financing, banking, and insurance. The data in these fields can mainly be represented as time series data, the corollary being that time series anomaly detection plays an essential role in these applications. Therefore, many authors have tried to solve the problem of collective anomaly detection in time series. They have proposed several approaches, from classical methods such as Isolation Forests to modern deep learning networks such as Autoencoders. However, a comprehensive framework for handling this problem is still lacking. In this work, firstly, we propose using an Attention-based Bidirectional LSTM Autoencoder (Att-BiLSTM-AE) as an anomaly detection model. Furthermore, in the essential part of this paper, we developed a comprehensive unsupervised deep learning framework, udCATS, to solve the problem of detecting collective anomalies in time series. Our experiments show that the Att-BiLSTM-AE outperforms other detection models, and using it within the udCATS framework increases the detection accuracy.

Frugal Heart Rate Correction Method for Scalable Health and Safety Monitoring in Construction Sites

“…This paradigm shift consists of moving away from the traditional methods for carrying out collective risk assessments for specific groups of workers to assessment methods that allow for the determination of the level of risk individually for each worker. Furthermore, the existing periodical risk assessment approaches are replaced by the continuous monitoring of hazards in the work environment, in real or near-real time [ 11 ], and facilitate the application of time-series-oriented anomaly detection methods to monitor dangerous events [ 12 ].…”