Classification with missing data in a wireless sensor network

Abstract

We have developed a novel method to estimate missing observations in wireless sensor networks. We use a hierarchical unsupervised fuzzy ART neural network to represent the data cluster prototypes and describe missing input patterns based on the network. We then estimate missing inputs by a spatial-temporal imputation technique. Our experimental results show that our proposed approach performs better than nine other missing data imputation techniques including moving average and Expectation-Maximization (EM) imputation.