Articles
93 Documents
Search results for
, issue
"Vol 11, No 10: October 2013"
:
93 Documents
clear
Weighted Multi-Scale Image Matching Based on Harris-Sift Descriptor
Can Sun;
Jin-ge Wang;
Zaixin Liu;
Junmin Li
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 10: October 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
According to the rotational invariance of Harris corner detectorand the robustness of Sift descriptor. An improved Harris-Sift corner descriptor was proposed. At first, the algorithm given multi-scale strategy to Harris corner, improved corner counting method and removed redundant points at the same time, then, the corner was directly applied to low-pass Gaussian filter image. Based on the histogram of Sift feature descriptor, generates a new 128-dimensional feature vector descriptor by multi-scale Gauss weighted.Through the above, Harris corner detectorand Sift descriptorwas normalizedin the scale layer and gradient features. The experiment results indicated that, the improved corner descriptorcomprised both advantage of Harris corner detection and Sift feature descriptor. The method reduced the computation time and the false match rate, which could be validly applied to the robotstereo vision matching andthree-dimensional reconstruction. DOI: http://dx.doi.org/10.11591/telkomnika.v11i10.3429
An Application of Six Sigma for Improving the Efficiency of Power Supply
Chang-Hsien Hsu;
Pei-Shih Chen;
Chun-Ming Yang
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 10: October 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Implementing the Six Sigma control method is to use define, measure, analyze, improve and control (DMAIC) framework to improve the process from the beginning, emphasize the process management, reduce the process time, eliminate the defects, and increase the passing rate. The aims of this study is to apply Six Sigma control method with DMAIC framework to shorten the power supply over time in order to enhance the power supply efficiency in T. power company (TPC). The result showed that the power supply over time was reduced from 66% to 30% in the Construction Work Second Section.DOI: http://dx.doi.org/10.11591/telkomnika.v11i10.2910
A Modified Particle Swarm Optimization Algorithm
Jie He;
Hui Guo
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 10: October 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
In optimizing the particle swarm optimization (PSO) that inevitable existence problem of prematurity and the local convergence, this paper base on this aspects is put forward a kind of modified particle swarm optimization algorithm, take the gradient descent method (BP algorithm) as a particle swarm operator embedded in particle swarm algorithm, and at the same time use to attenuation wall (Damping) approach to make fly off the search area of the particles of size remain unchanged and avoid the local optimal solution, with three input XOR problem to testing the improvement of the particle swarm optimization algorithm and the results showed that the improved algorithm not only increase global optimization ability, but also avoid the prematurity, convergence problem. DOI: http://dx.doi.org/10.11591/telkomnika.v11i10.2947
A Comparison of Improved Artificial Bee Colony Algorithms Based on Differential Evolution
Jianfeng Qiu;
Jiwen Wang;
Dan Yang;
Juan Xie
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 10: October 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
The Artificial Bee Colony (ABC) algorithm is an active field of optimization based on swarm intelligence in recent years. Inspired by the mutation strategies used in Differential Evolution (DE) algorithm, this paper introduced three types strategies (“rand”,” best”, and “current-to-best”) and one or two numbers of disturbance vectors to ABC algorithm. Although individual mutation strategies in DE have been used in ABC algorithm by some researchers in different occasions, there have not a comprehensive application and comparison of the mutation strategies used in ABC algorithm. In this paper, these improved ABC algorithms can be analyzed by a set of testing functions including the rapidity of the convergence. The results show that those improvements based on DE achieve better performance in the whole than basic ABC algorithm. DOI: http://dx.doi.org/10.11591/telkomnika.v11i10.3343
Parametric Matching of Drivetrain For Parallel Hybrid Electric Vehicle
Zhang Zhongwei;
Yu Hao;
Li Yingli
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 10: October 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Based on the software ADVISOR2002, the simulation modal of the assembly power and vehicle of the Parallel Hybrid Electric Vehicle(PHEV)has been set up.With the control targets for power characteristic and for fuel characteristic, this paper still considers the state of charge meanwhile; this thesis presents a simulation analysis of the PHEV and the influence on vehicle characteristic by component parameters of drivetrain, and studies the parametric choice and proper parametric matching among drivetrain component. DOI: http://dx.doi.org/10.11591/telkomnika.v11i10.3408
Audio Sensing Aid based Wireless Microphone Emulation Attacks Detection
Wang Shan-shan;
Luo Xing-guo;
Li Bai-nan
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 10: October 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
The wireless microphone network is an important PU network for CRN, but there is no effective technology to solve the problem of microphone evaluation attacks. Therefore, this paper propose ASA algorithm, which utilizes three devices to detect MUs, and they are loudspeaker audio sensor (LAS), environment audio sensor (EAS), and radio frequency fingerprint detector (RFFD). LASs are installed near loudspeakers, which have two main effects: One is to sense loudspeakers’ output, and the other is to broadcast warning information to all SUs through the common control channel when detecting valid output. EASs are pocket voice captures provided to SU, and utilized to sense loudspeaker sound at SU’s location. Utilizing EASs and energy detections in SU can detect primary user emulation attack (PUEA) fast. But to acquire the information of attacked channels, we need explore RFFDs to analyze the features of PU transmitters. The results show that the proposed algorithm can detect PUEA well. DOI: http://dx.doi.org/10.11591/telkomnika.v11i10.3424
Region of Interest Coding Based on Support Vector Machine in Transmission System
Li Zhu;
Xiaoguang Wu;
Rong Li
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 10: October 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
The development of network technology and multimedia technology has promoted the development of the integration, digitalization and individualization of communication technology, and has realized multiple functions based on wireless channel network, including voice, data and image. On the basis of classification by Support Vector Machine (SVM), this paper has proposed a low bit-rate coding method for segmenting the Regions of Interest (ROI) of objects through reasonably selecting initial class center and dynamically adjusting the number of categories, and designs its 3-dimension model method. In low bit-rate coding, the ROI is coded first using SPIHT algorithm, and then the background or the regions insensitive are coded using H.264 code, analyzing the experimental data and designing the structure, we can get the relation among related parameters under conditions of different permanent-magnet thickness and air gaps. It is proved that this method can achieve a better recognition effect, greatly improve the coding efficiency and satisfy the visual effects of human eyes, which can provide criteria in theory and application for designing on new driving principle, control system. DOI: http://dx.doi.org/10.11591/telkomnika.v11i10.3463
Weighted K-Nearest Neighbor Classification Algorithm Based on Genetic Algorithm
Xuesong Yan
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 10: October 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
K-Nearest Neighbor (KNN) is one of the most popular algorithms for data classification. Many researchers have found that the KNN algorithm accomplishes very good performance in their experiments on different datasets. The traditional KNN text classification algorithm has limitations: calculation complexity, the performance is solely dependent on the training set, and so on. To overcome these limitations, an improved version of KNN is proposed in this paper, we use genetic algorithm combined with weighted KNN to improve its classification performance. and the experiment results shown that our proposed algorithm outperforms the KNN with greater accuracy. DOI: http://dx.doi.org/10.11591/telkomnika.v11i10.2534
A Moving Object Detection Algorithm Based On Multiple Judgments
Mengxin Li;
Jingjing Fan;
Ying Zhang;
Rui Zhang;
Weijing Xu;
Dingding Hou
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 10: October 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
In the field of moving object detection, the traditional background subtraction method is used broadly, which seems more sensitive to light and shows poor anti-interference performance. Background modeling is the key step of background subtraction method. The Local Binary Pattern (LBP) algorithm is considered to put texture information into the background model, combining color and texture information and an improved background subtraction method proposed. In addition, a new method is proposed combining the inter-frame difference method with improved background subtraction method in this paper. It can overcome traditional methods only using the pixel gray value changes for moving targets detection. The method makes use of dual-threshold to detect moving targets and makes multiple judgments. It not only uses the change of pixel gray value to detect moving targets, but also takes advantage of the number of changed pixels to detect moving targets which we are interested in. The experiments show that the algorithm proposed is adopted to detect the moving target accurately and can resist interferences brought about by the slow slight movements in the scene with better robustness. DOI: http://dx.doi.org/10.11591/telkomnika.v11i10.3338
A Curve-fitting Calibration Method applied for Ultrasonic Flow-meter
Yong Luo;
Rangding Wang;
Ling Yao
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 10: October 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
As the influence of fluid distribution in the internal pipe, the measurement characteristics of theory and practice exist significant differences in Ultrasonic Flow-meter(USF). Through analysis of fluid state, the method of curve-fitting is applied for the calibration of USF. Experimental results show that the USF can achieve level-1 accuracy with just a correction of 5 flow points, and this method performs a low computational complexity and strong practicality. DOI: http://dx.doi.org/10.11591/telkomnika.v11i10.3392