JOURNAL OF SOFT COMPUTING AND INFORMATION TECHNOLOGY (JSCIT)
Year:2017 | Volume:5 | Issue:4 |Papers Count:8

Todays, various heuristic optimization methods have been developed. Many of these algorithms are inspired from physical processes or swarm behaviors in nature. Gravitational Search Algorithm (GSA) is an optimization algorithm based on the law of gravity and mass interactions. In the proposed algorithm, the search agents are a collection of masses. In this paper, mentioned algorithm is used to solve of the Frequency Assignment Problem (FAP). For ability test of the algorithm, CALMA benchmarks are used and results are good.

A novel method for future event prediction is proposed in textual environment. Proposed method is able to produce an event prediction model through generalization of cause events and then predict the effect events by using causal rules. First, the events of interest are extracted from domain-specific texts via an event representation model at semantic level, and are stored in the form of a graphical model in ontology as a posteriori (dynamic) knowledge. Then, a set of domain-specific causal rules in first-order logic (FOL) are fed into the machine as a priori (common-sense) knowledge. In addition to this common-sense knowledge, several large-scale ontologies containing DBpedia, VerbNet and WordNet are used for modeling contextual (static) knowledge and generalizing events. Finally, all types of these knowledge are integrated in a standard Web ontology Language (OWL) to perform causal inference. Empirical evaluation on real news articles showed that our method was better than the baselines.

In this paper a new method has been proposed to solve Combined Heat and Power Economic Dispatch (CHPED) based on Modified Shuffled Frog Leaping Algorithm (MSFLA). Difficulty on complexity of the problem is related to its constraints. This algorithm can satisfy constraints simply. This optimization algorithm has a wide spread search space and this characteristic helps to achieve optimum solutions. Application of MSFLA in CHPED problem has been simulated on two test cases. Numerical results show that MSFLA has proposed better solutions in comparison with other existing methods.

Wireless sensor networks have been used for monitoring of events and environment for a long time. The networks are used in numerous applications such as monitoring of battle fields, traffic, forest firing, tracking of an object and so on. Successful performance of WSNs depends on appropriate coverage of the environment. Coverage has a severe dependence on the infrastructure including the numbers and the places of sensors. So, a substantial step in designing networks is to specify the deployment strategy of nodes. Most of the deployment algorithms have been focused in minimizing network constraints and optimizing sensor coverage in recent years. The purpose of this study is to accommodate the physical form of environments in deployment problem which have not been investigated in previous works. Indeed our goal is to advantage from the ability of GIS in sensors deployment problems in order to make the problem closer to reality. As a result, the Minimax algorithm based on Voronoi diagram is used for optimizing sensor coverage in an urban and a natural area. This method resulted in 12 and 19 percent increase in sensor coverage respectively.

Cell planning is a complex problem. In this project we take advantage of Genetic Algorithms to find the optimum location of a cellular network base station, and to optimally determine other parameters such as power, height and tilt of each base station antenna, as well.The main goal is to maximize the network coverage and simultaneously to minimize the downlink interference in the Azadshahr region of Mashhad. In order to study the performance of the proposed method in a realistic way, the Urban Signal Propagation Simulator computer software (USPS) is used. The results indicate that our method has a very good performance in real situations.

Nowadays, given the ever-increasing growth of the industry, the optimal use of electrical energy is of particular importance. On the other hand, due to the fact that the increase in the voltage of electric energy transmission lines is almost saturated to increase the power transmission capacity, the need to find new solutions for this purpose is very necessary. One of the solutions that is considered today for optimal utilization of electrical power sources is multi-phase transmission networks. Multiphase transmission networks are networks of 6, 9 and 12 phases, which are among the preferred 6-phase networks and are known as a useful way to increase transmission power against increasing energy demand. The most important factors affecting the choice of optimal conversion (suitable alternative) of transmission lines can be the system losses and the acceptable range for the voltage of all the bus. But since there are a lot of nonlinear loads in the power systems, and this generates harmonics across the network, it is necessary to consider network harmonics and power quality indices. In this paper, a method is proposed to find the best arrangement of lines with the aim of optimizing power quality indices, which is carried out using multi-objective optimization based on non-post ranking (NSGA_II). The results have been performed on a 400 kV network in south of Iran.

In this paper a new method has been proposed for control of AVR system. For this purpose Fuzzy-PID controller has been employed. This controller has four parameters that their values have been obtained with optimization and imperialist competitive algorithm due to its high speed and accuracy. By using of proposed controller it is possible to control the system more effective. To illustrate good performance of proposed Fuzzy-PID, simulations have been carried out in MATLAB environment and results have been compared with PID and FOPID controllers. Results of simulations show good performance of suggested controller.

Visual servoing system controls a robot by visual feedback so that robot moves from any arbitrary start position to the target positions. The coordinates of points in three dimensions is needed in 3D space. In this paper, a Kinect camera is used to collect RGB images as well as workspace’s depth matrix. The control law is obtained using Jacobian matrix. Since, the mathematical model of robot and workspace, is unknown, artificial neural networks is applied to approximate inverse of Jacobian matrix by gathering data. The approximated neural models are used in control law directly. For each degree of freedom of the robot manipulator, a two-layer feed forward neural network is considered. The distance between end-effector and target in 3D space, and the shoulder joint coordinates are inputs of each of the networks and outputs are the fraction of the related robot joint changes to the image features changes (the elements of inverse of Jacobian matrix). The proposed method has been implemented on an industrial robot manipulator. The experimental results show that the proposed control system can move the end-effector to different target positions in workspace with good accuracy and fewer steps in comparision with the previous method.