Distributed and efficient classifiers for wireless audio-sensor networks

This paper presents schemes to generate effective feature vectors of low dimension, and also presents a cluster-based algorithm, where sensors form clusters on-demand for the sake of running a classification task based on the produced feature vectors. The features generated through our proposed schemes are evaluated using k-nearest neighbor (k-NN) and maximum likelihood (ML) classifiers. The proposed schemes are effective in terms of classification accuracy, and can even outperform previously proposed approaches, but, in addition, they are also efficient in terms of communication overhead.