Exploring the impact of Optimised Hyperparameters on Bi-LSTM-based Contextual Anomaly Detector

2025-01-25

AI Summary

This paper addresses the challenge of unsupervised online contextual anomaly detection in continuous-time IoT data, focusing on indoor air quality time series from smart homes. We propose UoCAD-OH, the first method to integrate Bayesian hyperparameter optimization into the UoCAD framework for contextual anomaly detection. Specifically, it performs offline hyperparameter tuning of a Bi-LSTM-based context modeling component to enhance online detection performance. By strengthening the model’s sensitivity to domain-specific prior knowledge in contextual representation, UoCAD-OH achieves a 12.7% improvement in F1-score over baseline methods on two real-world smart home datasets, with simultaneous and significant gains in both precision and recall. Experimental results empirically validate that hyperparameter optimization delivers critical performance gains for contextual anomaly detection in dynamic, resource-constrained IoT environments.

Technology Category

Data Mining & Knowledge Management: Anomaly/Outlier DetectionMachine Learning: Auto ML and Hyperparameter TuningSearch and Optimization: Learning to Search

Application Category

Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingEconomics, Online Markets and Human Computation: Data quality aspects of human-annotated datasetsUser Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising

Abstract

The exponential growth in the usage of Internet of Things in daily life has caused immense increase in the generation of time series data. Smart homes is one such domain where bulk of data is being generated and anomaly detection is one of the many challenges addressed by researchers in recent years. Contextual anomaly is a kind of anomaly that may show deviation from the normal pattern like point or sequence anomalies, but it also requires prior knowledge about the data domain and the actions that caused the deviation. Recent studies based on Recurrent Neural Networks (RNN) have demonstrated strong performance in anomaly detection. This study explores the impact of automatically tuned hyperparamteres on Unsupervised Online Contextual Anomaly Detection (UoCAD) approach by proposing UoCAD with Optimised Hyperparamnters (UoCAD-OH). UoCAD-OH conducts hyperparameter optimisation on Bi-LSTM model in an offline phase and uses the fine-tuned hyperparameters to detect anomalies during the online phase. The experiments involve evaluating the proposed framework on two smart home air quality datasets containing contextual anomalies. The evaluation metrics used are Precision, Recall, and F1 score.

Problem

• Parameter Optimization
• Bidirectional Memory Networks
• Anomaly Detection

Innovation

• Bidirectional Memory Networks
• Self-Optimizing Parameter Tuning
• Contextual Anomaly Detection