Attention and Autoencoder Hybrid Model for Unsupervised Online Anomaly Detection
This addresses anomaly detection in time series data, which is incremental as it combines existing attention and autoencoder techniques in a novel way for this domain.
The paper tackles unsupervised online anomaly detection in time series by proposing a hybrid attention and autoencoder model that captures both local patterns and long-term features, achieving improved accuracy on benchmark datasets.
This paper introduces a hybrid attention and autoencoder (AE) model for unsupervised online anomaly detection in time series. The autoencoder captures local structural patterns in short embeddings, while the attention model learns long-term features, facilitating parallel computing with positional encoding. Unique in its approach, our proposed hybrid model combines attention and autoencoder for the first time in time series anomaly detection. It employs an attention-based mechanism, akin to the deep transformer model, with key architectural modifications for predicting the next time step window in the autoencoder's latent space. The model utilizes a threshold from the validation dataset for anomaly detection and introduces an alternative method based on analyzing the first statistical moment of error, improving accuracy without dependence on a validation dataset. Evaluation on diverse real-world benchmark datasets and comparing with other well-established models, confirms the effectiveness of our proposed model in anomaly detection.