Embedding a Neural Network into WSN furniture

Wireless Sensor Networks (WSN) is an emerging technology that is developed with a large number of useful applications. On the other hand, Artificial Neural Networks (ANN) have found many successful applications in nonlinear system and control, digital communication, pattern recognition, pattern classification, etc. There are many similarities between WSN and ANN. For example, the sensor node itself can be seen as a neuron since the WSN application show characteristics such as distributed processing, massive parallelism, adaptively, inherent contextual information processing, fault tolerance and low computation. This paper examines the possibility of embedding ANN and WSN into a Smart Table. Prototypal results have shown that ANN models are good candidates for using it deployed into low cost System-on-a-Chip (SoC).