COMPUTATIONAL INTELLIGENCE IN ELECTRICAL ENGINEERING (INTELLIGENT SYSTEMS IN ELECTRICAL ENGINEERING)
Year:2013 | Volume:3 | Issue:4|Papers Count:6

This study presents a dynamically adapted bacterial foraging algorithm (BFA) to solve the economic dispatch (ED) problem considering valve-point effects and power losses. In addition, wind power is included in the problem formulation. Renewable sources and wind energy in particular have recently been getting more interest because of various environmental and economical considerations. The original BFA is a recently developed evolutionary optimisation technique inspired by the foraging behaviour of the Escherichia coli bacteria. The basic BFA has been successfully implemented to solve small optimisation problems; however, it shows poor convergence characteristics for larger constrained problems. To deal with the complexity and high dimensioned search space of the ED problem, essential modifications are introduced to enhance the performance of the algorithm. The basic chemotactic step is adjusted to have a dynamic non-linear behavior in order to improve balancing the global and local search. The stopping criterion of the original BFA is also modified to be adaptive depending on the solution improvement instead of the preset maximum number of iterations. The proposed algorithm is validated using several test systems. The results are compared with those obtained by other algorithms previously applied to solve the problem considering valve-point effects and power losses in addition to wind power.

Despite the significant decline in coronary artery disease (CAD) mortality in the second half of the 20th century, sudden cardiac death (SCD) continues to claim 250 000 to 300 000 US lives annually. Even in the presence of advanced first responder systems for resuscitation of out-of-hospital cardiac arrest, the overall survival rate in a recent North American analysis was 4.6%. If there are existed suitable ways to predict sudden cardiac death, doctors can make better decisions for patients at risk. In this paper, we investigate a way to predict sudden cardiac death. To do this, after the extraction of the HRV signal from ECG signal, some nonlinear and time-frequency features have been extracted from HRV signal. Then, the dimension of the feature space is reduced by applying the feature selection and PCA. Finally, healthy people and people at risk of SCD are classified using an MLP neural network. To evaluate the capabilities of analytical methods in classification, we have compared the classification rates for nonlinear and TF features, separately and in combination. The results show that there are features in the HRV signal of SCD patients just near the occurrence of SCD, which is quite different from normal people. Also, results show that the combination of time-frequency and nonlinear features have a greater ability to detect this difference. It has also been investigated that there are precious information in four minutes before the incident of SCD to predict the death; and this is enough time to save the patient by doctors or medical centers.

In this paper, we study the description and the representation of carpet’s flowers. The available carpet’s flowers set are classified in 14 classes. Since flowers have rotation, scale change and transition, the desirable descriptor should be invariant to this change. In this research we use wavelet descriptor and Fourier-Mellin descriptor. In wavelet descriptor uses the standard deviation of sub-bands. We recognize flowers to evaluate the used descriptors. The nearest neighbor method was used for the recognition and that highest recognition rate was obtained by the manhattan distance criterion. Some flowers segregated with inner details and considered in this research. For a method that is done according to the flower’s Contour and Fourier descriptor, the reported recognition rate is 69.4%, but in Fourier-Mellin method that considers the inner details also, the recognition rate is 81.5%.

Power-system dynamic stability improvement by a static synchronous series compensator (SSSC) based damping controller is thoroughly investigated in this paper. In order to design the optimal parameters of the controller, Imperialist Competitive Algorithm (ICA) is employed to search for the optimal controller parameters. Both local and remote signals are considered in the present study and the performance of the proposed controllers with variations in the signal transmission delays has been investigated. The performances of the proposed controllers are evaluated under different disturbances for both single-machine-infinite-bus and multi-machine power systems. Finally, the results of ICA method are compared with the results of Genetic Algorithm (GA).

Increasing demand for the amount and the value of electricity consumption in recent decades, communication, security and continuity to the electric grid has a great significance. Transmission networks as the main element in the power network has an important role in covering consumer’s needs. Various indices for evaluating the transmission network are defined and among them TTC is evaluated to determine the ability of the network in different economic conditions. In this paper, the probabilistic assessment of TTC is done and by solving a multi-objective optimization problem different values of TTC are obtained for different risks. Objectives that considered in this optimization are increasing TTC and reducing the risk. In probability assessment of TTC the uncertainty of generators and transmission lines are considered. To select contingencies, the probability of outage and the amount of TTC are considered. The IEEE reliability test system is used to demonstrate the effectiveness of the approach.

According to many medical and biometric applications of retinal images, the automatic and accurate extraction of the retinal blood vessels is very important. In this paper, an effective method is introduced to extract the blood vessels from the background of colored images of retina. In this algorithm, by applying the equalizer function on the retinal images, the brightness of the images is considerably uniformed. Because of high ability of Curvelet transform in introducing image borders in various scale and directions, borders and, consequently the contrast of retinal images can be enhanced. Therefore, the enhanced retinal image can be prepared for the extraction of blood vessels by improving Curvelet coefficients of the retinal images, adaptively and locally. Since the blood vessels in retinal images are distributed in various directions, we use the adaptive weighted morphology operators to extract the blood vessels from retinal images. Morphology operators based on reconstruction are used to refine the appeared frills with the size of smaller than arterioles in images properly. Finally, by analyzing the connected component in the images and applying adaptive filter on the components locally, all residual frills are refined from the images. The proposed algorithm in this paper has been evaluated by the images in the DRIVE database. The results how that the blood vessels are extracted from background of the retinal images of DRIVE database with the high accuracy of 96.15%, which in turn shows the high ability of the proposed algorithm in extracting the retinal blood vessels.