JOURNAL OF ARTIFICIAL INTELLIGENCE IN ELECTRICAL ENGINEERING
Year:2013 | Volume:1 | Issue:4|Papers Count:8

In this paper, a faster method for embedding cryptographic information in the image is presented by expressing the concept of latent prints (Steganography). Data is encrypted by two methods before embedding to increase reliability. Then they are embedded into the image by a button, a method has been expressed to reduce potential noise impact on the way information is encoded.

In this approach, the Left ventricular assist pump for patients with left ventricular failure is used. The failure of the left ventricle is the most common heart disease during these days. In this article, a State feedback controller method is used to optimize the efficiency of a sampling pump current. Particle Swarm Algorithm, which is a set of rules to update the position and velocity, is applied to find the optimal State feedback controller parameters for the first time. In comparison to other optimization algorithms, including genetic algorithm, PSO has higher convergence speed. As it is shown in the simulation part in the same number of iterations, the PSO algorithm decreases the cost function, which leads to desired transient and stability response of the system more effectively. In addition, in this work we propose a new structure for the cost function which includes the dynamical equations of current sampling pump in combination with penalty sentences which decrease the speed and output fluctuations. In this article, the system model and the system controlling parameters are set in such a way that the proposed cost function can be optimized. The efficiency of the method is illustrated in simulation part.

This paper addresses the dynamic path planning for two mobile robots in unknown environment with obstacle avoidance and moving target tracking. These robots must form a triangle with moving target. The algorithm is composed of two parts. The first part of the algorithm used for formation planning of the robots and a moving target. It generates the desired position for the robots for the next step. The second part is designed as the path planning for mobile robots. In this part desired trajectory of the robots for reaching the desired position of formation is generated. The potential field method is used to path planning for the robots. This method enables the robot to achieve these tasks: to avoid obstacles, and to make ones way toward its new position. Finally, the effectiveness of the proposed algorithm is demonstrated through simulations.

The rapid advancement in wireless over wired has augmented the need for improving the Quality of Service (QoS) over such wireless links. However, the wireless ad hoc networks have too low bandwidth, and establishing a QoS in these networks is a difficult issue. So, support of quality of service in ad hoc networks is the topical issue among the network science researchers. In this research we are going to evaluate the performances of DSACC (Distributed Scheduling algorithm with Collision Control) and QPART (QoS protocol for Ad hoc Real Time Traffic) algorithms in different conditions. These two algorithms are able to support quality of service in ad hoc networks. It should be noted that we have used ns-2 simulator software to compare these two algorithms.

Switching supervisory is the most important section of a feedback control process in MIMO hybrid systems. By choosing a non-compatible controller, system may go to unstable mode or high overshoot response. In this paper, a new method of switching for selecting MBC controllers is discussed. Results of the simulation show the MIMO (2-in 2-out) linear hybrid system can be switched stable and low overshooting in switching time. This method can be expanded to nonlinear MIMO systems.

In this paper the real time operation of an automatic teller machine (ATM) is analyzed using a Timed Petri Net (TPN) model. In the modeling, the probability of arrivals, the speed and attentiveness of customers (clients) are taken to account. Different parameters are based on the statistical data. The model is simulated for 24 hours. The diagrams of number of succeeded customers, failed references to ATM, idle times of ATM and wait times of customers are the outputs of TPN model.

In the several past years, Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) have became basic algorithm for state-variables and parameters estimation of discrete nonlinear systems. The UKF has consistently outperformed for estimation. Sometimes least estimation error doesn't yield with UKF for the most nonlinear systems. In this paper, we use a new approach for a two variable state nonlinear systems which it is called Rotated UKF (R_UKF). R_UKF can be reduced estimation error and reached for least error in state estimation.

A number of algorithms based on the evolutionary processing have been proposed for communication networks backbone such as Genetic Algorithm (GA). However, there has been little work on the SWARM optimization algorithms such as Particle Swarm Optimization (PSO) for backbone topology design. In this paper, the performance of PSO on GA is discussed and a new algorithm as PSOGA is proposed for the network topology design. The simulations for specific examples show that the performance of the new algorithm is better than other common methods.