ABSTRACT
This chapter covers various outlier detection techniques applicable to wireless sensor networks. Noise, errors, and malicious attacks are the outliers on the network. To filter noisy data, to find faulty nodes and to discover interesting events, outlier detection techniques are used. Over the recent years, the term ‘deep learning’ has been considered as one of the primary choices for handling huge amount of data. Having deeper hidden layers, it surpasses classical methods for detection of outliers in a wireless sensor network. The convolutional neural network (CNN) is a biologically inspired computational model which is one of the most popular deep learning approaches. It comprises neurons that self-optimize through learning. EEG, generally known as electroencephalography, is a tool used for investigation of brain function, and the EEG signal gives time-series data as output. In this chapter, we propose a state-of-the-art technique designed by processing the time-series data generated by the sensor nodes stored in a large data set into discrete one-second frames, and these frames are projected onto 2D map images. A CNN is then trained to classify these frames. The result improves detection accuracy.
