No abstract

This paper proposed an optimization algorithm in order to improve path maintaining of swarm of two wheel mobile robots with presence of external disturbance. The three robots forms use the leaderfollower strategy, the best path for leader is determined using A* algorithm ,the other two robots follow the leader path. Two PID controller are used in each robot to control the angular and velocity torque of wheel. Each PID controller is tuned using intelligent optimization control method which are Particle swarm optimization ,random occurring distributed time delay particle swarm optimization and hybrid particle swarm optimization and genetic after that the proposed algorithm is used for tuning. The new algorithm is the contribution of this article. It is built by combine the random occurring distributed time delayed and genetic algorithm .The combination of these two algorithms takes the advantage of them by using the historical best global position of particles in random occurring distributed time delayed particle swarm optimization algorithm to update velocity of new population generated by genetic algorithm. The integral absolute error (IAE) is computed for system in each algorithm for comparison between them. The performance of intelligent control systems for controlling the three robots path is tested with presence of external disturbance in environment .Two type of external disturbance is tested, these are constant external disturbance and dynamic external disturbance. The performance of the same optimization algorithm is tested in pure environments. From the obtained result ,the new combination method is the best in both disturbance environments (constant or dynamic) and pure.

This paper introduces an effective method of fingerprint classification based on discriminative feature gathering from orientation field. A nonlinear support vector machines (SVMs) is adopted for the classification. The orientation field is estimated through a pixel-Wise gradient descent method and the percentage of directional block classes is estimated. These percentages are classified into four-dimensional vector considered as a good feature that can be combined with an accurate singular point to classify the fingerprint into one of five classes. This method shows high classification accuracy relative to other spatial domain classifiers.

No abstract

No abstract