Wireless Sensor Networks anomaly detection using Machine Learning: A Survey
It provides an overview for researchers and practitioners in WSN domains, but is incremental as it summarizes existing work without novel contributions.
This survey paper reviews machine learning techniques for detecting anomalies in Wireless Sensor Networks data, addressing challenges like noise and unreliability, but does not present new experimental results or concrete numbers.
Wireless Sensor Networks (WSNs) have become increasingly valuable in various civil/military applications like industrial process control, civil engineering applications such as buildings structural strength monitoring, environmental monitoring, border intrusion, IoT (Internet of Things), and healthcare. However, the sensed data generated by WSNs is often noisy and unreliable, making it a challenge to detect and diagnose anomalies. Machine learning (ML) techniques have been widely used to address this problem by detecting and identifying unusual patterns in the sensed data. This survey paper provides an overview of the state of the art applications of ML techniques for data anomaly detection in WSN domains. We first introduce the characteristics of WSNs and the challenges of anomaly detection in WSNs. Then, we review various ML techniques such as supervised, unsupervised, and semi-supervised learning that have been applied to WSN data anomaly detection. We also compare different ML-based approaches and their performance evaluation metrics. Finally, we discuss open research challenges and future directions for applying ML techniques in WSNs sensed data anomaly detection.