Boosting incremental Nelder-Mead simplex for distributed regression over wireless sensor networks

Wireless sensor networks (WSNs) have attracted much interest in recent years. The main goal of a WSN is data collection. As the amount of the collected data increases, it would be essential to analyze them. However, restricted power supply of small sensors makes it a serious problem to transmit all the data to a fusion center for a centralized analysis. This is why the role of in-network processing seems crucial. In this paper, we propose an in-network optimization algorithm based on Nelder-Mead simplex to incrementally do regression analysis over distributed data. Then, we improve the resulted regressor by the application of boosting concept. Simulation results show that the proposed algorithm increases accuracy and is more efficient in terms of communication compared to its counterparts.