Clara: Context-Aware RAG-LLM Framework for Anomaly Detection in Mobile Device Sensors

Mobile devices are equipped with various sensors that continuously gather data about user activity and environmental conditions. Detecting anomalies in this sensor data is crucial for both health monitoring applications and technical quality control. This paper presents a novel framework, namely CLARA, that leverages Retrieval-Augmented Generation (RAG) with Large Language Models (LLMs) to detect anomalies in mobile device sensor data. Using the ExtraSensory dataset, which contains labeled sensor data from smartphones and smartwatches, we demonstrate how RAG enhances LLM-based anomaly detection by retrieving relevant historical patterns and domain knowledge to provide context-rich analysis. Our framework serves dual purposes: (1) providing health and lifestyle insights to end-users through anomaly detection in their daily activities and (2) offering manufacturers a tool for identifying technical sensor malfunctions during quality control processes. The framework delivers rich, contextual explanations of detected anomalies, making the results actionable for end-users and technical teams, addressing key industry challenges in sensor data analysis.