Journal of Artificial Intelligence in Electrical Engineering
Volume:4 Issue: 13, Spring 2015

In this paper، kinematic characteristics of writing are compared in 5 patient with writer’s cramp who performed a set of standardized writing task. The kinematic characteristics thumb and forefinger force before and during cramp. The effect of writing on different inclined supporting surfaces is also investigated. Our results indicate that inclined surfaces aspects of writing discomfort in writer’s cramp subjects. Although the change in arm joint angles and fingers/hand pressure is not generalizable between patients، such kinematic evaluations seem to be a key factor in the outcome of any personalized treatment or rehabilitation strategy.

Today, due to qualitative growth and scientific advances, energy, especially electricity is increasingly needed by human society. One of the almost endless and pure energy which have been paid attention over the years is the solar energy. Solar cells directly convert solar energy into electrical energy and are one of the main blocks of photovoltaic systems. Significant improvement has been made in the performance of solar cells since their introduction. Improvement of parameters such as cell efficiency, solar spectrum absorption and manufacturing costs which are key parameters in the process of cell development. The crystalline type is commonly used to achieve a lower recombination and higher absorption coefficient, and other types of silicon that have high recombination and low absorption coefficient, leading to a sharp drop in cell efficiency are not used as much. Different kinds of light trapping techniques and effective photons trapping using some fibered structures and various types of reflecting structures and light scattering, etc., have been proposed. In this paper, distributed Bragg reflector structure and also diffraction grating structure are used. In both structures, determination of the optimum material and also geometric properties to achieve maximum improvement in efficiency have taken into consideration.

In this paper we intend to generate some set of optimal trajectories according to the number of control points has been applied for parameterizing those using B-spline curves. The trajectories are used to generate an optimal locomotion gait in a crawling worm-like robot. Due to gait design considerations it is desired to minimize the required torques in a cycle of gait. Similar to caterpillars, progress in our crawling robot is achieved by propagating a trapezoidal wave from tail to head in the vertical plane. According to this model, the optimization problem has been solved via parameterization of joint trajectories, and consequently cost function, using cubic B-spline curves versus variant numbers of control points (CPs) needed in building those. Indeed, it is tried to find the best number of the CPs, of which the cost function obtains a minimum dynamical effort. To this end, the Genetic Algorithm is employed to find the minimal cost value once a nominated number of CPs is considered. Furthermore, since a complete period of this locomotion gait is composed of separated stages called sub-motions, thus the optimal trajectories for each sub-motion is examined independently. The results show choosing the number of CPs between 8 to 12 points constructs the optimized trajectories that reduce the dynamical effort of crawl in comparison with ones are reported by previous researches.

In this paper, a novel approach for control of the DC-DC buck converter in high-power and low-voltage applications is proposed. Designed method is developed according to state feedback linearization based controller, which is able to stabilize output voltage in a wide range of operation. It is clear that in high-power applications, parasitic elements of the converter may become comparable with load value and hence, in this paper all of the converter parasitic elements are modeled during development of the controller and the state feedback coefficients, are optimized using the optimal control theory. In order to evaluate the accuracy and effectiveness of the proposed method, designed controller is simulated using MATLAB/Simulink toolbox. Presented simulation result proves that the developed controller has acceptable dynamic and steady-state responses. The controller is robust to the load variation and variety of parameters.

This paper demonstrates design and fabrication of a mechatronic system for human drowsiness detection. This system can be used in multiple places. For example, in factories, it is used on some dangerous machinery and in cars in order to prevent the operator or driver from falling asleep. This system is composed of three parts: (1) mechanical, (2) electrical and (3) image processing system. After processing the input image and eye position detection, the system investigates the state of the eye, and in the case of drowsiness, the system activates the alarm. It also has the ability to track the eyes.

This paper is based on a combination of the principal component analysis (PCA), eigenface and support vector machines. Using N-fold method and with respect to the value of N, any person’s face images are divided into two sections. As a result, vectors of training features and test features are obtained. Classification precision and accuracy was examined with three different types of kernel and appropriate number of face features was considered and the best function for system identification rate. Then, face features were fed into the support vector machine (SVM) with one vs. all classification. At first, 2-Fold method was examined for images of training and test system. The results indicated that the rotation of the sets in identical classifications had no impact on the efficiency of radial basis function (RBF). It was observed that the precision increased in the 5-Fold method. Then, 10-Fold method was examined which indicated that the average recognition rate further increased when compared with 2-Fold and 10-Fold methods. The results revealed that as the rotation number increases, the precision and efficiency of the proposed method for face recognition increases.