Optimized Forward Consecutive Mean Excision Algorithm for Adaptive Threshold Estimation in the Energy Detector

Abstract

In this paper, we provide a new model for optimizing the parameters of the Forward Consecutive Mean Excision (FCME) algorithm for autonomous threshold estimation in Cogntive Radio (CR). Our new model ensures that the FCME algorithm is made capable of autonomously adjusting it’s parameter values based on the Cuckoo Search Optimization (CSO) algorithm. The between-class variance function of the Otsu’s algorithm was used as the objective function in the CSO algorithm towards ensuring optimal FCME parameter values. The new optimized FCME algorithm was tested using both simulated and real datasets. The comparative results obtained between the optimized and non-optimized FCME algorithm showed better threshold values been estimated via the optimized than the unoptimized algorithms leading to improved detection and false alarm probabilities.