Discretized-Isolation Forest: Memory- and Compute-Efficient Unsupervised Anomaly Detection for Resource-Constrained Internet of Things Edge Devices
Eduardo Ortega, Fei Su, Rita Chattopadhyay, Krishnendu Chakrabarty · IEEE Internet of Things Journal · 2024
Memory and compute constraints make anomaly detection model training infeasible on Internet of Things (IoT) resource-limited edge devices. Many solutions train anomaly detection models (e.g., deep neural networks or DNNs) on the cloud and deploy them on IoT edge devices for inferencing. However, cloud-based training does not address overall communication latency and potential data leakage. Moreover, because anomalies rarely occur, using labels to define anomalies is impractical. Hence, supervised learning mechanisms are unsuitable for anomaly detection. There is a need for effective unsupervised anomaly detection for resource-constrained edge devices. We present the discretized isolation Forest (DIF) to address memory- and compute-efficient unsupervised anomaly detection for resource-constrained edge devices. We also present a discretization function, based on information entropy, to inform the growth of the isolation Forest (IF) ensemble to create the DIF. The DIF reduces the training time (memory usage) of the original IF by$79.38\times (166.66\times)$. We test the DIF against general anomaly detection benchmarks and edge-anomaly detection benchmarks. The edge-anomaly detection benchmarks were curated from the built-in iPhone edge sensors. Across all the edge-sensor anomaly detection datasets and against all the other considered models, the discretized isolation resulted in the lowest training time, lowest memory usage, preserved anomaly detection performance, and highest inference speeds. In addition, across all general anomaly detection benchmarks and against all considered models, DIF incurs lower training time and memory usage while retaining competitive inferencing execution time and anomaly detection performance.