Application of wavelet neural-networks in wireless sensor networks

Abstract

Most of the current in-network data processing algorithms are modified regression techniques like multidimensional data series analysis. In our opinion, some of the algorithms developed within the artificial neural-networks tradition can be easily adopted to wireless sensor network platforms and will meet the requirements for sensor networks like: simple parallel distributed computation, distributed storage, data robustness and auto-classification of sensor readings. As a result of the dimensionality reduction obtained simply from the outputs of the neural-networks clustering algorithms, lower communication costs and energy savings can also be obtained. In this paper we will present two different data aggregation architectures with algorithms using artificial neural-networks which use unsupervised learning methods for categorization of the sensory inputs. They are tested on a data obtained from a set of several motes, equipped with several sensors each. Results from simulations of purposefully faulty sensors show the data robustness of these architectures. These architectures are further developed adding one pre-processing level which will use wavelets for initial data-processing of the sensory inputs at different resolutions and later introduced into the artificial neural-networks. The effects of this additional wavelet pre-processing are given for the two above mentioned architectures.