Robust Forecasting for Energy Efficiency of Wireless Multimedia Sensor Networks

An important criterion of wireless sensor network is the energy efficiency in specified applications. In this wireless multimedia sensor network, the observations are derived from acoustic sensors. Focused on the energy problem of target tracking, this paper proposes a robust forecasting method to enhance the energy efficiency of wireless multimedia sensor networks. Target motion information is acquired by acoustic sensor nodes while a distributed network with honeycomb configuration is constructed. Thereby, target localization is performed by multiple sensor nodes collaboratively through acoustic signal processing. A novel method, combining autoregressive moving average (ARMA) model and radial basis function networks (RBFNs), is exploited to perform robust target position forecasting during target tracking. Then sensor nodes around the target are awakened according to the forecasted target position. With committee decision of sensor nodes, target localization is performed in a distributed manner and the uncertainty of detection is reduced. Moreover, a sensor-to-observer routing approach of the honeycomb mesh network is investigated to solve the data reporting considering the residual energy of sensor nodes. Target localization and forecasting are implemented in experiments. Meanwhile, sensor node awakening and dynamic routing are evaluated. Experimental results verify that energy efficiency of wireless multimedia sensor network is enhanced by the proposed target tracking method.