A Study on Machine Learning Based Anomaly Detection Approaches in Wireless Sensor Network

Wireless sensor networks (WSN) became very popular in last few years. They are deployed in distributed manner for collecting variety of data. There are a lot of research issues and challenges in WSN viz; energy efficiency, security, localization etc. Outlier or anomaly detection is one of such area to prevent malicious attacks or reducing the errors and noisy data in millions of wireless sensor networks. Outlier detection models should not compromise with quality of data. We have to identify the anomalies in offline mode or online mode with accuracy, better performance and intake of minimal resources in the network. There are various machine learning techniques which have been used by several researchers these days to detect outliers. This paper presents a survey on outlier detection in WSN data using various machine learning techniques.