Abstract:As we all know, the parameter optimization of Mamdani model has a defect of easily falling into local optimum. To solve this problem, we propose a new algorithm by constructing Mamdani Fuzzy neural networks. This new scheme uses fuzzy clustering based on particle swarm optimization(PSO) algorithm to determine initial parameter of Mamdani Fuzzy neural networks. Then it adopts PSO algorithm to optimize model's parameters. At the end, we use gradient descent method to make a further optimization for parameters. T… Show more
“…Because the existing ABC algorithms [11][12][13] have the defect of restricting the escape of precocious individual [13]. We deign a new escape scouter strategy.…”
“…Because the existing ABC algorithms [11][12][13] have the defect of restricting the escape of precocious individual [13]. We deign a new escape scouter strategy.…”
“…Therefore, we compare TVAC with our new method (EM-CMLSQN), and the simulation results show that EM-CMLSQN has a better convergence rate and performance of jumping out of local solution than PSO and TVAC method. We also apply EMCMLSQN algorithm into path planning problem, and the results represent that EM-CMLSQN algorithm can search the optimal path more precisely and can be better applied into solving discrete domain problems than genetic algorithm and PSO algorithm [10,11]. The basic EM algorithm is composed of initialization, local search, resultant force calculation, particle displacement and judgment terminated.…”
“…The accuracy of speaker recognition is needed by system recognition, where the recognition system must be able to perform an accurate response in accordance with data from the human speech [2]. Artificial intelligent approaches have been used to increase accuracy in speaker recognition; one of the methods in the artificial intelligent approach is the fuzzy Mamdani method [3]. The Mamdani method can be used to identify a non-linear system such as speaker recognition [4].…”
The purpose of this research is to measure the speaker recognition accuracy in Content-Based Image Retrieval. To support research in speaker recognition accuracy, we use two approaches for recognition system: identification and verification, an identification using fuzzy Mamdani, a verification using Manhattan distance. The test results in this research. The best of distance mean is size 32x32. The best of the verification for distance rate is 965, and the speaker recognition system has a standard error of 5% and the system accuracy is 95%. From these results, we find that there is an increase in accuracy of almost 2.5%. This is due to a combination of two approaches so the system can add to the accuracy of speaker recognition.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.