A hybrid fuzzy weighted centroid and extreme learning machine with crow‐particle optimization approach for solving localization problem in wireless sensor networks

Abstract

SummaryThe sensor nodes localization is very advantageous in wireless sensor network (WSN). This allows effective data transfer between the sensor node networks. Therefore, it saves energy and prolongs network life. Here, a hybrid FWCELM‐CPO method is proposed for solving the sensor node localization problem in WSN. The proposed hybrid method is executed in MATLAB, and the performance is analyzed with different existing algorithms like centroid, fuzzy centroid, and ELM. The simulation results show that the proposed FWCELM‐CPO method attains the higher detection rate of 14.117%, 5.435%, and 11.494%, higher segmentation accuracy of 9.556%, 26.41%, and 16%, lower execution time of 66.667%, 75%, and 70.37%, higher segmented region of 65.957%, 20%, and 44.444%, and higher precision of 34.72%, 18.29%, and 8.78% compared to the existing algorithms. The simulation results demonstrate that the proposed method can be able to find the optimal global solutions efficiently with accurately.