Improving Security in IoT-Based Human Activity Recognition: A Correlation-Based Anomaly Detection Approach

Anomaly detection in Human Activity Recognition (HAR) is a critical subfield that leverages data from the Internet of Things (IoT) to monitor human activities and detect errors or abnormal events. Conventional rule-based approaches often fail to capture the intricate relationships between sensor values, while machine learning-based methods tend to lack the ability to provide explainability and actionable context for the detected anomalies. In this paper, we introduce a novel correlation-based anomaly detection framework designed to improve the security and reliability of IoT-enabled HAR systems. Our proposed scheme utilizes a context-aware deep learning architecture to predict sensor values by leveraging the interdependencies between coexisting sensors in the deployment environment. Experimental results demonstrate that our model achieves a best anomaly prediction accuracy of 99.76% on individual sensors and outperforms other baseline models, consistently maintaining high F1 scores with a minimum of 0.866 on various sensors, even when the training dataset is reduced. Furthermore, we propose an AI-Generated Content (AIGC)-based visualization method for reporting anomalies, offering clear insights into the context and severity of detected anomalies and their potential system impact.