Main Menu
NEWS & VIEWS
| 
| 
Previous issue | Next issue | Archive
Volume 3 (2); Aug 2014
|
Research Title/ Graphical Abstract |
Article Information / Abstract |
Download |
|
PII: S232251141400006-3 Comparison of Bayesian Networks and Lazy Model Algorithms in Intrusion Detection Systems Based on Data Mining |
Original Research, C6 Fazli-Maghsoudi H. and Momeni H. J. World. Elect. Eng. Tech., 3(2): 47-52, 2014. ABSTRACT: By development of information technology, network security is considered as one of the main issues and great challenges. Intrusion detection systems are a major component of a secure network. Traditional intrusion detection systems cannot adapt themselves to new attacks thus today's Intrusion detection systems have been introduced based on data mining. Identifying patterns in large volumes of data, is a great help to us. Data mining techniques by identifying a binary label (normal packet, abnormal packet) and specifying attributes by classification algorithms can recognize the abnormal data Therefore, the precision and accuracy of intrusion detection systems will increase, thereby increasing network security. In this paper, we compare the performance of the different lazy model-based algorithms and Bayesian networks on their data sets. Obtained results show that the HNB algorithm has the highest precision of 83.29% for the intrusion detection system. Key words: Intrusion detection, data mining, lazy model, normal, abnormal, Bayesian networks. |
|
|
PII: S232251141400007-3 Comparison of Fuzzy Clustering Algorithms in Intrusion Detection System |
Original Research, C7 ABSTRACT: According to the growth of the Internet technology, there is a need to develop strategies in order to maintain security of system. One of the most effective techniques is Intrusion Detection System (IDS). Clustering which is commonly used to detect possible attacks is one of the branches of unsupervised learning. Fuzzy clustering algorithms play an important role to reduce spurious alarms and Intrusion detection, which have uncertain quality. This paper Compare and Review fuzzy c-means and Gath-Geva and Gustafson-Kessel algorithms in order to Intrusion detection in system. Key words: FCM, Gath-Geva, Gustafson-Kessel, IDS, Security |
|
|
PII: S232251141400008-3 Graph Coloring Problem based on Discrete Social Based Algorithm |
Original Research, C8 ABSTRACT: A new and popular technique for combinatorial optimization is to embed local search into the framework of evolutionary algorithms. In this article we propose a discrete hybrid evolutionary algorithm of the traditional genetic algorithm followed by the new Imperialist Competitive Algorithm (Social Based Algorithm) to solve the graph-coloring problem. A good selection for graph coloring is a function of vertices of graph into a set of colors such that both neighbor vertices of the graph have different colors. Using the Social Based Algorithm makes a new technique with a high accuracy in both exploration and exploitation in the search space for coloring the graph. The algorithm is tested toward different standard benchmark tests while limiting the number of usable colors to the known chromatic numbers. Results prove the superiority of the proposed method in comparison with other algorithms and even in terms of the minimum number of colors required for graph coloring problems. |
|
|
PII: S232251141400009-3 Design of Slotless BLDC Motor for Eliminating Cogging Torque |
Original Research, C9 ABSTRACT: Design of a cogging torque free motor is presented in this paper. Cogging torque is a disturbing phenomenon in electrical machines that causes certain problems in performance of them. This unwanted component in output torque could be reduced or eliminated by some methods i.e. skewing the stator slot, skewing the permanent magnets (PMs) of rotor, employing fractional pitch winding and building slotless motor. In this paper, firstly these ethods are discussed and then the effect of skewing PMs is investigated which is distinguished by a design parameter i.e. offset. After that, slotless structure of a brushless DC motor (BLDC) is considered. In a slotless BLDC motor, cogging torque would be eliminated and there is no major component of cogging torque in slotless structure of a BLDC motor. These types of motors are very convenient due to excellent features such as zero-cogging torque, minimal vibration, high speed capability, excellent power-to-weight ratio, compact design, light weight and etc. At the end, finite element analysis (FEA) is employed to validate the topics. |
|
|
PII: S232251141400010-3 Identifying and locating connection fault of layer winding turn in distribution transformer
|
Original Research, C10 ABSTRACT:Transformers are considered as the most important and expensive distribution and transfer networks of electrical energy. Among different fault identifying in transformers, identifying winding fault is not easily recognizable because of lower domain effect in terminal voltages and currents. In this article, frequency response analysis method is used as an efficient method to recognize turn’s connection fault. By comparing frequency response in fault and intact conditions, fault recognizing in winding becomes possible. In order to determine frequency response, the described winding model is used. Analyzing the model is done by MATLAB software. The accuracy of this model is very dependent on determining its parameters. In order to exact calculation of parameters of described winding model, Finite Element Method based on winding design information is used and in order to increase accuracy, parameter dependency to frequency is considered. Finally, the effect of turn’s connection fault and its location on layer winding of a distribution transformer is evaluated. |
|
|
PII: S232251141400011-3 Comparison of LQR and Pole Placement Design Controllers for Controlling the Inverted Pendulum
|
Original Research, C11 ABSTRACT:A new algorithm for skin segmentation in color images is presented in this paper based on semi-supervised discriminant analysis (SDA). At first, input RGB space input image is transferred to YCbCr and CIE Lab color space in which skin pixels are more similar to each other and different from pixels of other objects. Some components of new color spaces are treated as features of pixels and construct feature vectors. Feature vectors are given to SDA algorithm to decrease the inter-class distances and increase between-class distances. Finally, projected vectors are given to the K-nearest neighbor (KNN) classifier to separate skin pixels from non-skin pixels. Simulation results show that proposed approach has considerable efficiency in skin pixel detection. |
|
|
PII: S232251141400012-3 Semi-supervised Discriminant Analysis for Skin Detection in Color Images |
Original Research, C12 Key words: KNN, Lab, SDA, skin, YCbCr |
|
|
PII: S232251141400013-3 Implementation of an Optimum Model for Hybrid Electric Vehicles |
Original Research, C13 ABSTRACT: Nowadays hybrid electric vehicles are the most efficient technology in transportation industry. They have demonstrated the capability of reducing the energy consumption while maintaining vehicle performance. The main focus of this paper is on simulation of a hybrid electric vehicle based on the information provided by HONDA Company for Insight vehicle. This vehicle is a parallel hybrid vehicle that utilizes IMA system and an engine with 66 pound force power. IMA system uses a DC brushless motor with permanent magnet that is placed between engine and transmission system. The IMA system uses engine as the main source of power while the electric motor is used for acceleration. In this article a model has been developed in MATLAB and dynamic systems has been modelled with ADAMS. This model utilized the Honda Insight with IMA (integrated motor assist) that its characteristics have been published by the company [1]. The accuracy of the MATLAB/ADAMS model has been verified using ADVISOR software. All drive cycles and information used in MATLAB/ADAMS model has been built according to defined model in ADVISOR. |
|
