Volume 1 Issue 2
Authors: Ahmad Farid Bin Abidin; Azah Mohamed; Hussein Shareef
Abstract: An intelligent approach is developed to discriminate a fault, stable swing and unstable swing for correct distance relay operation by using the S-transform and the probabilistic neural network (PNN). To illustrate the effectiveness of the proposed techniques, simulations were carried out on the IEEE 39 bus and a practical test system using the PSS/E and MATLAB software. Test results show that the PNN gives an overall classification accuracy of 97.33% in which it performs better than MLPNN in detecting and classifying unstable swing, stable swing, fault, fault clearance and post fault events. Such fast and accurate intelligent detection schemes are useful for preventing distance relay from tripping during power swing.
Keywords: Unstable Swing; Stable Swing; S-transform; Probabilistic Neural Network (PNN); Multi Layer Perceptron Neural Network (MLPNN)
Authors: Amir Bahador Bayat
Abstract: Automatic recognition of handwritten characters has long been a goal of many research efforts in the pattern recognition field. This paper investigates the design of a high efficient system for recognition of handwritten digits. First it proposes an efficient system that includes two main modules: the feature extraction module and the classifier module. In the feature extraction module, seven sets of discriminative features are extracted and used in the recognition system. In the classifier module, as the first time in this area, the adaptive neuro-fuzzy inference system (ANFIS) is investigated. Experimental results show that the proposed system has good Recognition Accuracy (RA). However, the results show that in ANFIS training, the vector of radius has very important role for its recognition accuracy. At the second fold, it proposes an intelligence system in which a novel optimization module, i.e., improved bees algorithm (IBA) is proposed for finding the best parameters of the classifier. In test stage, 3-fold cross validation method was applied to the MNIST handwritten numeral database to evaluate the proposed system performances. Simulation results show that the proposed system has high recognition accuracy.
Keywords: Handwritten Digits; ANFIS; MNIST; IBA; Optimization
Authors: Guoqing Liu; Qianjin Feng
Abstract: We propose a volume rendering method that is capable of highlighting the region of interest and preserving contextual information so as to assist in accurate location and diagnosis on medical imaging data. The region of interest was marked, followed by recording spatial location of the first contour surface along the ray direction. According to the distance between sampling point and the point of interest, and the angle of ray and the connecting line of sampling point and point of interest, attenuation function was created by using Gauss function, which acted on opacity transfer function to control ray synthesis. The experimental result from head CT scan indicates the proposed method can highlight region of interest under the premise of preserving a clear tissue contour.
Keywords: Volume Rendering; Iso-surface; Gaussian Function; Opacity