Research Article
AIHardMon: An AI-Driven Hardware Monitoring System for Anomaly Detection and Performance Analysis
@INPROCEEDINGS{10.4108/eai.28-4-2025.2358082, author={K. Sri Harsha and K Vishweshwar Reddy and P. Sai Ranga and N. Malarvizhi}, title={AIHardMon: An AI-Driven Hardware Monitoring System for Anomaly Detection and Performance Analysis}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part II}, publisher={EAI}, proceedings_a={ICITSM PART II}, year={2025}, month={10}, keywords={artificial intelligence computer hardware anomaly detection diagnostic systems preventive maintenance machine learning temperature analysis}, doi={10.4108/eai.28-4-2025.2358082} }- K. Sri Harsha
K Vishweshwar Reddy
P. Sai Ranga
N. Malarvizhi
Year: 2025
AIHardMon: An AI-Driven Hardware Monitoring System for Anomaly Detection and Performance Analysis
ICITSM PART II
EAI
DOI: 10.4108/eai.28-4-2025.2358082
Abstract
Conventional hardware monitoring systems frequently suffer from false alarm rate (FAR) issues and lack prediction and contextual information. In this paper, we present AIHardMon, an AI-based hardware monitoring technique aiming to resolve these drawbacks. By utilizing machine learning methods such as Isolation Forest algorithms and considering context fan monitoring, AI-HardMon can provide proactive anomaly detection and advance the health control of such systems. Our experimental results demonstrate that AIHardMon effectively improves system reliability by reducing false positive alerts while accurately detecting genuine hardware anomalies. This is a smarter, more efficient and more predictable way of monitoring hardware health.
