3D Histogram-Based Anomaly Detection for Categorical Sensor Data in Internet of Things
Publication Date: 9/9/2022
Event: VLIoT 2022 – Very Large Internet of Things 2022 (virtual conference)
Reference: pp. 22-43, 2022
Authors: Peng Yuan, NEC Laboratories America, Inc.; Lu-An Tang, NEC Laboratories America, Inc.; Haifeng Chen, NEC Laboratories America, Inc.; Moto Sato, NEC Laboratories America, Inc.; Kevin Woodward, Lockheed Martin
Abstract: The applications of Internet-of-things (IoT) deploy massive number of sensors to monitor the system and environment. Anomaly detection on streaming sensor data is an important task for IoT maintenance and operation. In real IoT applications, many sensors report categorical values rather than numerical readings. Unfortunately, most existing anomaly detection methods are designed only for numerical sensor data. They cannot be used to monitor the categorical sensor data. In this study, we design and develop a 3D Histogram based Categorical Anomaly Detection (HCAD) solution to monitor categorical sensor data in IoT. HCAD constructs the histogram model by three dimensions: categorical value, event duration, and frequency. The histogram models are used to profile normal working states of IoT devices. HCAD automatically determines the range of normal data and anomaly threshold. It only requires very limit parameter setting and can be applied to a wide variety of different IoT devices. We implement HCAD and integrate it into an online monitoring system. We test the proposed solution on real IoT datasets such as telemetry data from satellite sensors, air quality data from chemical sensors, and transportation data from traffic sensors. The results of extensive experiments show that HCAD achieves higher detecting accuracy and efficiency than state-of-the-art methods.
Publication Link: https://www.ronpub.com/ojiot/OJIOT_2022v8i1n04_Yuan.html