International Journal of Advances in Applied Sciences
Not a member yet
668 research outputs found
Sort by
Writer Identity Recognition and Confirmation Using Persian Handwritten Texts
Get PDFThere are many ways to recognize the identity of individuals and authenticate them and the modern world still is looking for unique biometric features of humans. The recognition and authentication of individuals with the help of their handwriting is regarded as a research topic in recent years. It is widely used in the field of security, legal, access control to systems and financial activities. This thesis tries to examines the identification and authentication of individuals in Persian (Farsi) handwritten texts so that the identity of the author can be determined with a handwritten text, and in the authentication problem, with having two handwritten texts, it is determined that whether both manuscripts belong to a specific person or not. The proposed system for recognizing the identity of the author in this study can be divided into two main parts: one part is intended for training and the other for testing. To assess the performance of introduced characteristics, the Hidden Markov Model (HMM) is used as the classifier; thus, a model is defined for each angular characteristic. The defined angular models are connected by a specific chain network to form a comprehensive database for classification. This database is then used to determine and authenticate the author
Hybrid Photovoltaic and Wind Power System with Battery Management System using Fuzzy Logic Controller
Get PDFIn recent year, the development of hybrid renewable energy sources has the important role of power generation. This paper focused on design of hybrid PV / Wind power system and its battery management system. The fuzzy logic control based battery management system has been designed for effective power utilization. The proposed control to operate the battery charging and discharging mode during non-linear power generation. The battery will charge whenever the renewable energy power is greater than to consumer load power as well as the battery will discharge whenever the renewable energy power is lesser than to consumer load power. The proposed model will be simulated using Matlab environment and analysis the proposed system results. Finally, simulation results are evaluated and validating the effectiveness of the proposed controller
Fault Identification in Sub-Station by Using Neuro-Fuzzy Technique
Get PDFFault identification and its diagnosis is an important issue in present scenario of power system, as huge amount of electric power is utilized. Random types of faults occur in substation, which leads to irregular and discontinue supply of power from generating to consumer point. Fault detection is an important concept of power system which is to be studied and new method has to develop for fault detection and removal of it. This paper proposed on-line fault detection and identification of fault-type by using Neuro-Fuzzy method in substation. Combination of Artificial Neural Network (ANN) and Fuzzy Logic (FL), results in gaining learning capabilities of fuzzy logic. Variation of current according to fault is used for identification. Fuzzy controller display output condition in form of (0,1).Here, single line-to ground (LG) fault, line-to-line (LL) fault, double line-to ground (LLG)/ LLL fault are considered
Highly effective Security Techniques in OSN Based on Genetic Programming Approach
Get PDFAssurance is one of the grinding centers that enhances when trades get mediated in Online Community Techniques (Online Social Networks). Diverse gatherings of utilization innovation specialists have limited the 'OSN security issue' as one of surveillance, institutional or open security. In taking care of these issues they have moreover overseen them just as they were person. We adapt that the elite security issues are caught and that evaluation on genuine feelings of serenity in Online Social Networks would advantage from a more exhaustive method. Nowadays, points of interest systems mean a critical piece of relationship; by losing security, these organizations will decrease a ton of pleasant areas to see as well. The inside motivation behind subtle elements security (Information Security) is risk control. There are a great deal of discovering works and exercises in security danger control (ISRM, for example, NIST 800-30 and ISO/IEC 27005. Regardless, only few works of appraisal focus on Information Security danger diminishment, while the signs depict normal determinations and suggestions. They don't give any use ideas concerning ISRM; truth be told diminishing the Information Security dangers in questionable conditions is cautious. Subsequently, this papers joined an acquired counts (GA) for Information Security danger loss of weaknesses. Finally, the parity of the associated system was broke down through a reflection
Classification of Heart Rate Data Using BFO-KFCM Clustering and Improved Extreme Learning Machine Classifier
Get PDFAn Electrocardiogram or ECG is an electrical recording of the heart and is used in the investigation of heart disease. The heart rate varies not only in relation to the cardiac demand but is also affected by the presence of cardiac disease and diabetes. Furthermore, it has been shown that Heart Rate Variability (HRV) may be used as an early indicator of cardiac disease susceptibility and the presence of diabetes. Therefore, the heart rate variability may be used for early clinical screening of these diseases. The generalization performance of the SVM classifier is not sufficient for the correct classification of heart rate data. To overcome this problem the Improved Extreme Learning Machine (IELM) classifier is used which works by searching for the best value of the parameters, and upstream by looking for the best subset of features using Bacterial Foraging Optimization (BFO) that feed the classifier. In this work, nine linear and nonlinear features are extracted from the HRV signals. After the preprocessing, feature extraction is done along with feature selection using BFO for data reduction. Then, proposed a scheme to integrate Kernel Fuzzy C-Means (KFCM) clustering and Classifier to improve the accuracy result for ECG beat classification. The results show that the proposed method is effective for classification of heart rate data, with an acceptable high accuracy
Self-Tuning VGPI Controller Based on ACO Method Applied for WTGS system
Get PDFThe stability and the fast response are two parameters to evaluate the efficiency of any system, and the acknowledgement of the mathematic model studied and its parameters are strongly required. In order to build the regulation and the control of the system, different methods are used. Some are traditional (PI, PD, PID…); whereas, others are modern (Fuzzy logic, neural networks, statistical algorithms, genetic algorithms, VGPI and so on…).In this paper, we focused on the presentation of a new method which we call the scheduling regulation based on a particle swarm optimization. A stochastic diffusion search method that takes inspiration from the social behaviors of real ants with their environment. Ant colony optimization algorithms (ACO) presents a promising performance which is a self-organized regulation system with no need to the acknowledgment of both the mathematic model and the parameters of the systems from a side, and it can insure the stability and the fast response of the system from another side
Review of Machine Vision Based Insulator Inspection Systems for Overhead Power Distribution System
Get PDFThe necessity to have reliable and quality power distribution is increasing, and hence there is great scope for research on automation of distribution system. There are signs of increased research in the work on condition monitoring of insulators during the last few decades. The possible failures can be predicted before they actually occur by using the condition monitoring of cables or any electrical equipment on-line. Those assets such as towers, conductors and insulators which are on the threshold of failure have to be replaced or repaired, so that forced outages reduce. Traditionally the workers who inspect these lines check them in close proximity by going for foot-patrolling and pole-climbing. With an incredible expansion of power distribution network even to remote areas, previously mentioned methods do not seem to be viable. In developed countries aerial patrolling has been adopted to monitor the insulators as an alternative. The development of an efficient method of condition monitoring by using image processing followed by machine learning techniques is found to be a suitable method and thus emerging as a feasible option for real-time implementation. This review paper covers overall aspects of automatic detection of defects of insulator systems of electric power lines and classification into different classes by using vision-based techniques
Design of Converters for PV System Under Partial Shading Conditions
Get PDFThis paper presents a maximum power generation with the interconnection of photovoltaic modules under partially shaded and/or mismatching conditions. The partial shading condition reduces power level of each module. The reduction in power due to the partial shading will be compensated by the bidirectional converter. The proposed system consisting of two and three PV modules connected in series under partial shading conditions which are capable of increasing the power levels up to 50% compared to conventional by-pass diode structure. In general ‘n’ number of modules connected in series so that the maximum power gain will be expected to (100/n) %. This is achieved by developing the new control strategy in which the correct adjustment of converter duty ratio under partially shading conditions. The novel control scheme is developed by using analysis of the power converters. The proposed scheme was verified in MATLAB/SIMULINK
Comparative Study of Various Neural Network Architectures for MPEG-4 Video Traffic Prediction
Get PDFNetwork traffic as it is VBR in nature exhibits strong correlations which make it suitable for prediction. Real-time forecasting of network traffic load accurately and in a computationally efficient manner is the key element of proactive network management and congestion control. This paper comments on the MPEG-4 video traffic predictions evaluated by different types of neural network architectures and compares the performance of the same in terms of mean square error for the same video frames. For that three types of neural architectures are used namely Feed forward, Cascaded Feed forward and Time Delay Neural Network. The results show that cascade feed forward network produces minimum error as compared to other networks. This paper also compares the results of traditional prediction method of averaging of frames for future frame prediction with neural based methods. The experimental results show that nonlinear prediction based on NNs is better suited for traffic prediction purposes than linear forecasting models
An Open Source Contact-Free Palm Vein Recognition System
Get PDFIn this document, we propose a novel palm vein recognition system using open source hardware and software. We have developed an alternative preprocessing and feature extraction technique. The proposed system is built on Raspberry Pi using OpenCV 2.4.12. The palm vein image is cropped to Region of Interest(ROI) to reduce the computational time in real time systems and then preprocessed to enhance the vein pattern visibility and to extract more number of key points using SIFT algorithm. Then the descriptors are stored in a dictionary like codebook file during training. Later the descriptors are tested with unknown patterns. The clustering is based on K-means algorithm and classification is done using Support Vector Machines (SVM)