intelligent algorithms

In this paper, the effect of using various intelligent algorithms to optimize the adaptive neuro-fuzzy disturbance observer has been investigated .First, a model reference adaptive control is designed for the spacecraft simulator. Then, in order to reduce the disturbance effect, an adaptive neuro-fuzzy disturbance observer is used. In this paper, the fuzzy system is optimized using Intelligent Genetic Algorithm, Particle Swarm Optimization, Imperialist Competitive Algorithm, Bee Colony, Ant Colony Optimization, and especially Policy Gradient Particle Swarm Algorithm, which speeds up and optimizes the response. The Policy Gradient Particle Swarm algorithm is a combination of gradient policy reinforcement learning and particle swarming ideas and is a hybrid optimization method to control a nonlinear complex system with many applications in the real world. In this method, influenced by reinforcement idea, the policy gradient for a non-fossilized system is calculated, and in the optimization of particle swarm relations, optimization is performed in addition to the factors included in the congestion methods in the direction of the policy gradient. It is intended to optimize the fuzzy neuro system parameters and input and output data in the cost function. Finally, the neuro-fuzzy systems optimized by these algorithms are compared and it is shown that the gradient particle swarm algorithm performs better than the particle swarm algorithm.

The goal of this paper is improvement of the operation of networked control systems using optimized fuzzy logic controlled communication. Network traffic is reduced with optimal kalman filter estimator and fuzzy logic. It should be explained, there is no need to send information on the network continuously and the measurements are processed locally before sending. In this paper, population based optimization algorithms are used to set the parameters of fuzzy system for control the communication logic. The performance of regulated controllers are compared by the results of Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Biogeography Based Optimization (BBO), Imperialist Competitive Algorithm (ICA) and Ant Colony Optimization with continuous domain (ACOR) algorithms. The proposed method is simulated on two overhead cranes over a network with nonlinear features. Simulation results prove the validation of the proposed solution. While the results of all algorithms are reasonable but PSO algorithm has best result in reducing tracking error and fitness function point of view. Simulation results illustrate the effectiveness of proposed control system in coordination of two cranes over the network in moving heavy loads.

Feature selection is one of the most important preprocessing steps for pattern recognition,data mining and machine learning. The objective of feature selection is selecting the most effectivefeature subset of original features set. So that in addition to dimension reduction of feature space,the recognition accuracy is improved. In this paper, feature selection process is the global search inthe space of all features using the wrapper approach. In this paper, the binary harmony searchalgorithm as intelligent algorithm is used to feature selection. Also, the one versus all method isused to classify and evaluate the selected feature subset.The performance of proposed approach is assessed on 6 datasets all of which are from UCI dataset.Numerous and Various experiments carried out on dataset reveal the superiority of the proposedmethod compared to similar approaches.