Intelligent Wireless Sensor Nodes for Human Footstep Sound Classification for Security Application

Sensor nodes present in a wireless sensor network (WSN) for security surveillance applications should preferably be small, energy-efficient and inexpensive with on-sensor computational abilities. An appropriate data processing scheme in the sensor node can help in reducing the power dissipation of the transceiver through compression of information to be communicated. In this paper, authors have attempted a simulation-based study of human footstep sound classification in natural surroundings using simple time-domain features. We used a spiking neural network (SNN), a computationally low weight classifier, derived from an artificial neural network (ANN), for classification. A classification accuracy greater than 85% is achieved using an SNN, degradation of ~5% as compared to ANN. The SNN scheme, along with the required feature extraction scheme, can be amenable to low power sub-threshold analog implementation. Results show that all analog implementation of the proposed SNN scheme can achieve significant power savings over the digital implementation of the same computing scheme and also over other conventional digital architectures using frequency-domain feature extraction and ANN-based classification.