Real-Time Machine Learning for Embedded Anomaly Detection

TL;DR

This paper surveys machine-learning techniques for real-time anomaly detection on resource-constrained embedded IoT devices, emphasizing trade-offs between accuracy and efficiency under strict hardware limitations.

Contribution

It provides a comprehensive comparison of lightweight algorithms, practical recommendations, and insights into hardware-aware algorithm selection for embedded anomaly detection.

Findings

Lightweight algorithms vary in accuracy and efficiency.

Hardware constraints significantly influence algorithm choice.

The survey offers a strategic roadmap for edge anomaly detection deployment.

Abstract

The spread of a resource-constrained Internet of Things (IoT) environment and embedded devices has put pressure on the real-time detection of anomalies occurring at the edge. This survey presents an overview of machine-learning methods aimed specifically at on-device anomaly detection with extremely strict constraints for latency, memory, and power consumption. Lightweight algorithms such as Isolation Forest, One-Class SVM, recurrent architectures, and statistical techniques are compared here according to the realities of embedded implementation. Our survey brings out significant trade-offs of accuracy and computational efficiency of detection, as well as how hardware constraints end up fundamentally redefining algorithm choice. The survey is completed with a set of practical recommendations on the choice of the algorithm depending on the equipment profiles and new trends in TinyML, which can help close the gap between detection capabilities and embedded reality. The paper serves as a strategic roadmap for engineers deploying anomaly detection in edge environments that are constrained by bandwidth and may be safety-critical.