Ensemble Denoising Autoencoders Based on Broad Learning System for Time-Series Anomaly Detection

Time-series anomaly detection has gained considerable prominence in numerous practical applications across various domains. Nonetheless, the scarcity of labels leads to the neglect of anomalous patterns in data, as well as the inherent complexities and variances in the definitions of temporal anomalies, pose significant challenges for insufficient recognition of anomaly patterns. In addition, real-time anomaly detection poses high demands on low computational cost and model robustness, presenting substantial obstacles for unsupervised time-series anomaly detection. In this article, we propose the data-driven spontaneous perturbation based on the sequence-image strategy and temporal anomaly knowledge enhancement strategy based on artificial anomalous data pairs to enhance the cognition of abnormal knowledge in unsupervised scenarios. On this basis, we propose the denoising autoencoder based on the broad learning system (DBLS-AE), which sufficiently learns the anomalous patterns, achieving efficient anomaly detection with low computational costs. To enhance the robustness in handling complex and diverse temporal anomalies, we further propose the progressive diversity denoising autoencoders based on the broad learning system (PddBLS-AE), which gradually prioritizes challenging samples and constructs a diverse ensemble of DBLS-AEs, markedly improving both performance and robustness. By innovatively utilizing the broad learning system (BLS), PddBLS-AE achieves accelerated training compared with advanced deep learning models. Comprehensive evaluations across multiple datasets robustly substantiate the efficacy of PddBLS-AE.