Journal of Advances in Computer Research
Volume:6 Issue: 3, Summer 2015

The license plate edge detection is the most important step of the process of plate identification. Plate recognition system is an automated system that captures vehicle location, vehicle license plate accurately on various vehicles at different times of day and night sets. In this paper the issue of searching the exact location of the license plate from the input images using Sobel operator for edge detection and image processing and histogram analyzing techniques for candidate areas restriction has been examined.The proposed method is tested on the database containing 250 different input images with different background, size and angles in different lighting condition and during different times of the day on different kinds of vehicles (cars, vans and trucks and etc). And the rate of the correct extraction of the exact location of the license plate was 88.4%. The response time and the processing speed of the proposed method is faster in Comparewith existing works.

The aim of this study is to evaluate how far Lempel-Ziv complexity (LZC) of the binary symbolic sequences resulting from static or dynamic transformation (partitioning first-order difference) of the short-term electrocardiogram (ECG) signals (only 2 seconds duration) has the potential in discriminating normal and ventricular tachycardia/ventricular fibrillation (VT/VF) subjects. The statistical analyses show that LZC from either transformation is sufficient to distinguish between normal and VT/VF subjects. Between the two, LZC of dynamic transformation is found to outperform LZC of static transformation. The receiver operating characteristic curve analysis confirms the robustness of this new approach which exhibits an average sensitivity of about 99.1% (100.0%), specificity of about 100.0% (100.0%), precision of around 98.9% (100.0%), and accuracy of about 99.5% (100.0%), with LZCto distinguish between normal and VT (VF) subjects. The presented method is simple, computationally efficient, and well suited for real time implementation in automatic external or implantable cardioverter-defibrillators.

One of the major problems that may occur in the differential protection systems of power transformers is mal-operation of the protection relays in sake of internal fault detection, because of similarity between this current and inrush current. This paper presents a novel approach for discriminating inrush current from internal fault in power transformers based on Improved Gravitational Search Algorithm (IGSA). For this purpose, an Artificial Neural Network (ANN) which is trained by IGSA has been applied to discrete sample data of internal fault and inrush currents in the transformers. Results show that, the used approach can discriminate between these two kinds of phenomenon, very well and also, has high accuracy and excellent reliability, in addition, it has less computational burden and complexity.

Secure Electronic Transaction (SET) protocol is an open protocol, which has the potential to emerge as a powerful tool in securing of electronic transactions. The quality of a design of an Ecommerce protocols has a great influence on achieving non-functional requirements (NFRs) to the system. An increasingly important non-functional attribute of complex software systems is adaptability. Software for adaptive software systems should be flexible enough to allow components to change their behaviors depending upon the environmental and stakeholders'' changes and goals of the system. Evaluating adaptability at software to identify the weaknesses of the software and further to improve adaptability of their, are very important tasks. This paper presents a method based on the use of Colored Petri Nets for evaluating Adaptability in SET protocol. We try to see how we can apply the way formalize CPN in terms of quality attributes to evaluate some of them, on the SET protocol

Customers are the most valuable asset of an organization. Due to high contest in the business field, it is necessary to regard the Customer Relationship Management (CRM) of the enterprise. Data Mining and Machine Learning methods been utilized by businesses in recent years in order to improve CRM. CRM is the strategy for building, managing, and strengthening loyal and long lasting customer relationship. Data mining is the knowledge discovery process by analyzing the large volumes of data from various perspectives and summarizing it into useful information. Data mining have a several techniques in CRM but in this article we present the basic classification and clustering techniques that used. The target of this survey is to provide extensive review of different classification and clustering techniques in customer segmentation.

In this paper, a new method is presented for the detection of defects in random textures. In the training stage, the feature vectors of the normal textures’ images are extracted by using the optimal response of Gabor wavelet filters, and their probability density is estimated by means of the Gaussian Mixture Model (GMM). In the testing stage, similar to the previous stage,at first, the feature vectors corresponding to local neighborhoods of each pixel of the image under inspection are extracted. Then, by computing the likelihood of the test image’s feature vectors’ belonging to the parameters of the GMM, they are compared with a threshold value. Finally, the defective regions are localized in a defect map. The proposed algorithm was evaluated on a set of grayscale ceramic tile images with random textures. The simulations indicate that in comparison with the previous methods, the proposed algorithm enjoys an acceptable computational volume and accuracy in the detection of texture defects.

In order to the enhancement of the quality of speech corrupted by additive noise, a speech enhancement method has been put forward based on the combination of spectral subtraction and binary masking. Spectral subtraction is a powerful method for removing noise from speech and binary masking provides essential elements to be used in monaural speech segregation. In the proposed combined method, first, spectral subtraction is used for reduction of noise in noisy speech and then binary masking is used for monaural speech segregation from musical noise introduced by spectral subtraction. The binary masking method, isolates the basic principle of target voice from other signals by using time frequency decomposition, energy masking and unites grouping. This masking is like what the human ear does in noisy environment. In our implementation for binary masking, an auditory filter (Gamma-tone) is divided into different frequency sub-bands. From these sub-band channels, channels 1,2,4,8,16,32,64,128 have been used from this bank of 128 Gamma-tone filter for implementing the binary masking. Evaluations show that the proposed combined method can improve the signal to noise ratio from 5 to 19 db for experimented signals and have better performance than binary masking or spectral subtraction in most situations, especially when noise and speech have not similar power spectrum.

This paper addresses a nonlinear observer based control scheme to synchronize chaotic systems subject to uncertainties and external disturbances. It is assumed that the dynamic of slave system is not completely known. In order to compensate for the system perturbation resulting from parameter variations and mismodeling phenomena, an adaptive neural network observer is employed to handle this problem. A nonlinear observer for a class of nonlinear systems is proposed based on a generalized dynamic recurrent neural network. The weights of the proposed neural network in the observer are tuned on-line with no off-line learning phase required. Also, no exact information of the nonlinear term of the system is required and this important characteristic compensates considerable part of uncertainty. To realize control purpose, two controllers are considered. At first, PID controller is combined with proposed observer and then 2nd order sliding mode controller called twisting algorithm is applied to synchronize systems. This method is implemented on the Duffing chaotic systems and simulation results confirm the effectiveness of the proposed method.

Coverage improvement is one of the main problems in wireless sensor networks. Given a finite number of sensors, improvement of the sensor deployment will provide sufficient sensor coverage and save cost of sensors for locating in grid points. For achieving good coverage, the sensors should be placed in adequate places. This paper uses the genetic and learning automata as intelligent methods for solving the blanket sensor placement. In this paper an NP-complete problem for arbitrary sensor fields is described which is one of the most important issues in the research fields, so the proposed algorithm is going to solve this problem by considering two factors: first, the complete coverage and second, the minimum used sensors. The proposed method is examined in different areas using MATLAB. The results confirm the successes of using this new method in sensor placement; also they show that the new method is more efficient than other methods like FAPBIL and MDPSO in large areas

Nowadays diabetes disease is one of the main problems of health domain and it’s known as the fourth factor of death in the world. The main problem with this dangerous disease is the late or weak diagnosis. The reason of weak diagnosis is because sometimes doctors aren’t able to select the right patterns or they can’t use the standard patterns very well, so the outcome is that the disease will be diagnosed by the patients when it has become late for controlling or curing it. Therefore, implementing a method which can help each person to have an authentic diagnosis of being or not being affected to this disease; can be an important step for prevention and controlling this special disease at the beginning of it. In this paper, a new method is presented for diagnosing diabetes disease which is able to extract the proper knowledge by helping to cluster and analyze the training patterns, after that in recognition phase it can diagnose diabetes disease precisely and fast via a fuzzy reward-penalty mechanism. For evaluating the proposed method, PIMA dataset has been used. The experimental results show that the proposed method has a better performance compared to other existing methods.