Journal of Advances in Computer Research
Volume:5 Issue: 3, Summer 2014

Anti-lock Braking System (ABS) which is a nonlinear and time variant system may not be easily controlled by classic control methods. This is due to the fact that classic linear controllers are just capable of controlling a specific plant in small region of state space. To overcome this problem, a more powerful control technique must be employed for complex nonlinear plants. Fuzzy controllers are potential candidates for the control of such systems, while they have an intrinsic ability to control a complex set of dynamics like ABS in an appropriate wider region in the state space.This paper introduces a new zero order Takagi-Sugeno fuzzy controller. The input membership functions of the proposed controller have been optimized such that the ABS performance enhances over different braking situations. Simulation shows the effectiveness of the proposed controller under various road conditions. The optimization is done by using DARLA, a powerful heuristic technique.

According to this fact that wind is now a part of global energy portfolio and due to unreliable and discontinuous production of wind energy; prediction of wind power value is proposed as a main necessity. In recent years, various methods have been proposed for wind power prediction. In this paper the prediction structure involves feature selection and use of Artificial Neural Network (ANN). In this paper, feature selection tool is applied in filtering of inappropriate and irrelevant inputs of neural network and is performed on the biases of mutual information. After determining appropriate inputs, the wind power value for the next 24-hours is predicted using neural network in which BP algorithm and PSO and ICA evolutionary algorithms are used as training algorithm. With investigation and compare numerical results, better performance of PSO and ICA evolutionary algorithm is deduced with respect to BP algorithm. More accurate survey will result in more proper efficiency of imperialist competitive algorithm (ICA) in comparison to swarm particle algorithm. Thus, in this paper; accuracy of the wind power prediction for the next 24-hours is improved considerably using mutual information and providing an irrelevancy filter for reducing the input dimension by eliminating the irrelevant candidates and more effectively using Imperialist competitive evolutionary algorithm for training the neural network.

Identification based on faces is still a useful method for many applications and face recognition developing is an active research Field. In this paper, a novel face identification method is proposed. The proposed method (Bridle Path on Gabor Phase (BPGP)) is based on extracting texture patterns from phases of the Gabor wavelet. Also, in order to describe the textures, a novel texture descriptor method (Bridle Path) is proposed to extract the features from textures. The Bridle Path method inspired by LBP method and brings some advantages such as lower feature vector length and higher texture description capability in comparison with LBP. Experimental results shows that, Bridle Path texture descriptor is a powerful tool for describing textures and consequently proposed face recognition method (BPGP) yields high identification performance compared to other methods.

In this paper a new strategy is proposed to design a fixed-structure robust controller for a flexible beam. Robust controller designed by the conventional loop­ shaping method is not appropriate for a beam because of its high order and complicated form. Fixed-structure loop shaping control in conjunction with particle swarm optimization (PSO)algorithm is used to overcome this drawback. The performance and robust stability conditions of the loop shaping controller are formulated as the cost function in the optimization problem. PSO is adopted to optimize the parameters and cost function. The proposed control design and loop shaping method are successfully applied on the flexible beam, and results of the two approaches are compared. Simulation results show the superiorities of the proposed controller in terms of having a lower order and simple structure; besides the beam stability and robust performance are retained as well. Also in comparison to the solutions based on genetic algorithms, the use of PSO shows better efficiency in terms of computational time.

Nowadays, economic load dispatch between generation units with least cost involved is one of the most important issues in utilizing power systems. In this paper, a new method i.e. Water Cycle Algorithm (WCA) which is similar to other intelligent algorithm and is based on swarm, is employed in order to solve the economic load dispatch problem between power plants. WCA is used to solve complicated problems including non-linear cost functions such as the constraint for input steam valve, constraint for loss, ramp rate of generators and prohibited operating zones of generators’ production. This algorithm is employed on a system with 3 units and load demand of 850 MW and on a system with 15 units and load demand of 2630 MW with and without considering the constraints. The results of the paper comparing to the results of the other valid papers show that the proposed algorithm can be used to solve in any kind of economic dispatch problems with proper results.

With regard to the society’s need for complicated software and high level of expenses on its development, it is necessary to take all stakeholders’ requirements and the demands into consideration, before any investments and put on the design and utilization stages. Software architecture is a technical description of a software system that indicates components and their relationships between them. In fact architecture style is a set of principles used by a software architect to design software architecture. Nowadays, this is a common behavior among the software architects in designing any software. As “Performance” is the most important qualitative features chosen for the assessment, the main objective of this research is studying the effect of various styles on its non-functional requirements, using Markov model, so that the architect can choose a suitable style based on qualitative and precise criteria. In this paper with regards to the results obtained based on homogeneous style, an algorithm has been presented to generalize the assessment method for the heterogeneous styles. Finally, to represent the correctness of the proposed algorithm, an illustrative example has been presented.

Recommender Systems (RS) provide personalized recommendation according to user need by analyzing behavior of users and gathering their information. One of the algorithms used in recommender systems is user-based Collaborative Filtering (CF) method. The idea is that if users have similar preferences in the past, they will probably have similar preferences in the future. The important part of collaborative filtering algorithms is allocated to determine similarity between objects. Similarities between objects are classified to user-based similarity and item-based similarity. The most popular used similarity metrics in recommender systems are Pearson correlation coefficient, Spearman rank correlation, and Cosine similarity measure. Until now, little computation has been made for optimal similarity in collaborative filtering by researchers.For this reason, in thisresearch, weproposean optimal similaritymeasure via a simple linear combination of values and ratio of ratings for user-based collaborative filtering by use ofFireflyalgorithm; and we compare our experimental results with Pearson traditional similarity measure and optimal similarity measure based on genetic algorithm. Experimental results on real datasets show that proposed method not only improves recommendation accuracy significantly but also increases quality of prediction and recommendation performance.

Nowadays, wireless sensor network has been of interest to investigators and the greatest challenge in this part is the limited energy of sensors. Sensors usually are in the harsh environments and transit in these environments is hard and impossible and moreover the nodes use non- replaceable batteries. Because of this, saving energy is very important. In this paper we tried to decrease hard and complex computing with using soft computing such as fuzzy logic and we used it in cluster head selection part. Hard and complex computing can waist energy, because of this, we used some techniques to solve this problem. Minimum cost tree (MCT) helps to find minimum path, so we used this technique for intra cluster routing and again more over we used distributed source coding (DSC) technique for aggregating data. Finally all of methods could reduce energy consumption and increased network lifetime. Proposed algorithm is called FCMCT and simulation and results show improvement.