Improved KPCA for outlier detection in Wireless Sensor Networks

Abstract

In Wireless Sensor Networks (WSNs), the accuracy of sensor readings is without a doubt one of the most important measures to evaluate the quality of a sensor and its network. For this case, the task amounts to create a useful model based on KPCA to recognize data as normal or outliers. Over the last years, Principal component analysis (PCA) has shown to be a good unsupervised feature extraction. But, this method only focuses on second orders statistics. Recently, Kernel Principal component analysis (KPCA) has used for nonlinear case which can extract higher order statistics. Kernel PCA (KPCA) mapping the data onto another feature space and using nonlinear function. So, we propose an improved KPCA method based on Mahalanobis kernel as a preprocessing step to extract relevant feature for classification and to prevent from the abnormal events. All computation are done in the original space, thus saving computing time using Mahalanobis Kernel (MKPCA). Then the classification was done on real hyperspectral Intel Berkeley data from urban area. Results were positively compared to a version of a standard KPCA specially designed to be use with wireless sensor networks (WSNs).