Anomaly Detection in Industrial IoT Sensor Data Using SVC and Random Forest A Review

The Internet of Things IoT has transformed the way we interact with our surroundings by enabling large scale connectivity among billions of devices. These connected devices continuously exchange data, resulting in massive and rapidly growing data volumes. However, this expansion also brings a major concern ensuring the reliability and security of IoT generated data. Detecting data anomalies is essential for identifying unusual patterns, system deviations, and potential cyber threats within IoT environments. This paper reviews the latest developments, commonly used approaches, and ongoing challenges in IoT data anomaly detection. We examine the advantages and limitations of different detection techniques, including statistical models, machine learning approaches, and deep learning methods. The discussion also highlights the unique characteristics of IoT data—such as heterogeneity, scalability requirements, real time processing demands, and privacy issues—that make anomaly detection particularly complex. By addressing these factors, this review aims to provide a comprehensive understanding of the difficulties involved and guide the development of more accurate and efficient anomaly detection solutions for IoT systems. Somoshi Kavita M. | Bansode Rahul S. "Anomaly Detection in Industrial IoT Sensor Data Using SVC and Random Forest: A Review" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-9 | Issue-6 , December 2025, URL: https://www.ijtsrd.com/papers/ijtsrd99872.pdf Paper URL: https://www.ijtsrd.com/engineering/electronics-and-communication-engineering/99872/anomaly-detection-in-industrial-iot-sensor-data-using-svc-and-random-forest-a-review/somoshi-kavita-m