فصلنامه هوش محاسباتی در مهندسی برق
سال ششم شماره 1 (بهار 1394)

In this paper، we propose a computer aided diagnosis (CAD) system based on hierarchical convolutional neural networks (HCNNs) to discriminate between malignant and benign tumors in breast DCE-MRIs. A HCNN is a hierarchical neural network that operates on two-dimensional images. A HCNN integrates feature extraction and classification processes into one single and fully adaptive structure. It can extract two-dimensional key features automatically، and it is relatively tolerant to geometric and local distortions in input images. We evaluate CNN implementation learning and testing processes based on gradient descent (GD) and resilient back-propagation (RPROP) approaches. We show that، proposed HCNN with RPROP learning approach provide an effective and robust neural structure to design a CAD base system for breast MRI، and has potential as a mechanism for the evaluation of different types of abnormalities in medical images.

This paper proposes a multi-objective based framework to capacitor placement within distribution networks. A bidding strategy is introduced considering customers reliability of service; moreover، effects of such strategy are evaluated on risk assessment and profitability of the privatized distribution utility. Afterwards، multi-objective Genetic Algorithm (NSGAII) is conducted to solve the capacitor placement problem to simultaneously minimize total costs and risk of profitability. Finally، effectiveness of the proposed method is investigated on several scenarios conducted on the IEEE 34-Bus test system، followed by a discussion on results.

The rapid advance of technology and the subsequent reduction size of the MOSFET transistors has led to different behavior of the transistors in electronic circuits. In recent decades، many models are presented to estimate the behavior of short-channel MOSFET transistors. In This paper، a new model is proposed to predict the short-channel MOSFET transistor behavior. This model، increases the accuracy and reduces the error rate of the “nth-power law MOS” against the original one. parameters of the proposed model is optimized and compared with the actual Characteristic BSIM3 at 130nm technology and TSMC_CM018RF at 180nm technology. These devices have Many applications in electronic circuits، especially high-frequency circuits. In order to increase the accuracy of the proposed model، its parameters are optimized by a heuristic optimization algorithm. To this، three algorithms including genetic algorithm، particle swarm optimization and gravitational search algorithm are compared. The experimental results indicate that for the proposed model، gravitational search algorithm has got better parameters.

Reconfiguration is one of low expense and easy ways for better operation of distribution electricity networks. So far، reconfiguration problem in presence of distributed generation resources with the purpose of reliability improvement has not been fully investigated. In the reconfiguration problems، different configuration are evaluated، thus، reliability calculation algorithm should be generalized and usable for all configurations. In this paper، firstly، for the reconfiguration problem in the presence of distributed generation resources، a procedure of reliability calculation is developed using an analytical method. The objective functions of this multi-objective optimization problem in the proposed method، are energy not supplied (ENS) and active power losses. Then reconfiguration problem is implemented using genetic algorithm based on edge window decoder. Finally، the proposed method is simulated on the Baran 33-Bus test system in the MATLAB software environment.. The simulation results shows the capability of the proposed method in finding the best configuration based on the objective function of the paper.

Optimal energy management in systems based on multiple Microgrids (MG) is a vital component to ensure the economic dispatch of generation resources. Energy management system (EMS) can be employed to achieve the optimum utilization of resources، to reach the operational performance targets in the MGs as well as to control exchange power among them and with grid as well. In this regard، a double-layer control scheme (DLCS) equipped with primary and secondary controllers are proposed in this paper. In primary control level، EMS is operating separately for each MG by considering the problem constraints and uncertainty of renewable resources by using Taguchi’s approach، power set-points of generation resources and possible shortage or surplus of power generation in the MGs. Then، the shortage or surplus generation of the MGs should be submitted to a central energy management system (CEMS) at the secondary layer. In order to validate the proposed control structure، a case study including two MGs and a lumped load is simulated and optimized based on multi-period imperialist competition (MICA) algorithm. Different scenarios are applied to evaluate the performance of the proposed DLCS. The obtained results clearly show that the proposed DLCS is effective for achieving optimal dispatch of generation resources in systems with multiple MGs. Furthermore، the proposed DLCS is able to control the performance of the MGs in interaction with the grid and with each other as well.

Sensors have a great role in industry and science. Thus fault detection and mitigation in sensors is of special importance. In this paper، a network of temperature sensors is considered to measure the temperature of an area. The weighted average of sensors is considered as the final output for more reliability. Some of sensors are considered to provide redundancy for fault mitigation. Kalman filter detects fault and Genetic algorithm changes system such that the fault is mitigated. In this paper، bias fault، scaling fault، high noise fault and hard fault are considered and this system is resistant and effective for a variety of faults.

Nowadays considering many advantages of air traveling، we notice that traffic congestion has significantly increased in airspace of countries، and it is expected that this growth rate، increases even more in the forthcoming years. This growth rate and different limitations posed on developing some airports led to the problem of landing airplanes to become one of the most important issues formed in the field of aviation. In this paper، in the form of a new approach based on CPSO algorithm for intelligent landing planning، determining optimal landing times، optimal allocation of runways، and at last the order of successive landings of planes has been done in a way that appropriately fulfills the main goal of the problem (minimizing the total flights delays); thus helping significantly to controlling air traffic congestion in airports approaches. The simulation results show that compared to the last presented methods، including methods based on genetic algorithms، GLS and Bionomic، has decreased the total amounts of flight delays considerably. Getting zero for total amount of flight delays for the two problems with real data of DFW airport in Texas، United States، confirms the more capability of CPSO algorithm compared to the other intelligent methods for obtaining optimal solutions to the problem.

Due to the increase in the number of organizations that want to create data warehouses in order to use its business benefits، an approach for decision making is required. Relational، multi dimensional and tabular models addresses this goal by supporting a broad range of reporting and analysis. The difference between the aforementioned model specifications and operations makes decision making difficult when choosing a data warehouse model. One of the reasons that organizations have not been successful in creating a data warehouse and have spent much time and money for its generation is that they have yet to fully appreciate the need of an appropriate model. The contribution of this paper is using a fuzzy multi-criteria decision making approach for choosing a model for data warehouse creation based on requirements of organizations، features of implementation، data model، business logic، data access and storage، and security. Based on a case study conducted in this paper، and with analysis and identification of the most important criteria and when compared with an Analytical Hierarchy Process method، the proposed framework is shown to reduce both cost and time of data warehouse creation due to proper decision making based on organizations requirements.