Articles
102 Documents
Search results for
, issue
"Vol 12, No 1: January 2014"
:
102 Documents
clear
Target Tracking Feature Selection Algorithm Based on Adaboost
Chen Yi
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: January 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
With the development of image processing technology and popularization of computer technology, intelligent machine vision technology has a wide range of application in the medical, military, industrial and other fields. Target tracking feature selection algorithm is one of research focuses in the machine intelligent vision technology. Therefore, to design the target tracking feature selection algorithm with high accuracy and good stability is extremely necessary. This paper presents a target tracking feature selection algorithm based on Adaboost. It includes Adaboost algorithm’s principle and Adaboost algorithm's application in video object tracking. Experimental results show that the proposed algorithm has the characteristics of real-time, accuracy and stability. DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3688
Research on Web Service Composition Algorithm Using Description Logic
Yuemin Wang
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: January 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
This paper presents a dynamic Web service composition algorithm based on description logic. Firstly, each input or output of the Web service request is regarded as a concept of description logic and according to the semantic similarity between concepts given the five types of description logic, we study on the dynamic composition algorithm based on service. Because the factors of service semantics and quality of service composition are considered, the algorithm can automatically implement dynamic composition according to the user's service request. Because of using the expression ability of semantic description logic, when Web service is combined the algorithm can determine whether the service can be combined according to thesemantic relationship between concepts, thus the probability of successful combination can be improved. DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3536
Design of LCL-Filter Based Three-level Active Power Filter
Nianchang Yu;
Jiaqiang Yang;
Shilan Chen;
Ming Ye
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: January 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
This paper proposes an improved design of LCL-Filters for Three-Level Shunt Active power filters (APF). Available design principles are presented to achieve high compensation bandwidth and low switching frequency current. Then, affecitons of different parameters are taken into consideration of constraints on LCL-Filter design with detail analysis of ripple current. A simple and practical design procedure of LCL-Filter for Three-Level APF is subsequently proposed. The first step is to choose the resonant frequency of LCL-Filter according to the highest order harmonic needed to be compensated. Then it is aim to optimize the parameters of the LCL-Filter based on the design principles and constraints. The simulation results verify the effectiveness of the proposed method. DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3441
Assembly Quality Prediction Based on Back-propagation Artificial Neural Network
Zhang Jian-zhong;
He Yong-yi;
Li Jun
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: January 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Because of the severe geometrical distortion induced by the optical system and the limited kinetic accuracy of mechanical system in the vision-based mobile-phone lens’s assembly system, the nonlinear, perspective distortion errors and the kinematics errors generally exist in the assembly process of the mobile-phone lens. It is necessary to predict the assembly quality of the vision-based mobile-phone lens’s pick-and-place system so as to eliminate the immediate effect on the assembling process before extracting quantitative assembling. Comparison with current research methods, the back-propagation artificial neural network is applied to predict the assembly quality of the vision-based mobile-phone lens’s pick-and-place system. Firstly, the mobile-phone lens’s assembly quality characteristics are defined and sampled; Secondly, a back-propagation artificial neural network of the mobile-phone lens’s assembly quality prediction is presented; Finally apply some training samples obtained from the experiments to train and test this back-propagation artificial neural network. The results show that the proposed method is effective to predict the assembly quality of the vision-based mobile-phone lens’s pick-and-place system with high accuracy and high reliability. DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3906
Precipitation’s Level Prediction Based on Tree Augmented Naïve Bayes model
Xue Shengjun;
Chen Jingyi;
Xu Xiaolong;
Li Mengying
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: January 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
At present, most of the precipitation’s level predictions use the laws of nature to build the mathematical model which contains one or more series level to carry out the numerical simulation, as thus to analyze the causes and consequences of the evolution. Bayesian model is one kind of the foregoing said. In the Bayesian classification model, Naive Bayes model is known for its stability and easy to operate, but the established precedent assumption tends to be inadmissible. So here the article proposed a new precipitation’s level prediction model based on the tree Augmented Naïve Bayes(we called TAN model for short hereafter), which improve the original Naïve Bayes model defects and increase the association between the leaf nodes on the basis of the original model. And we use the Dongtai station, Jiangsu province meteorology data to test the new precipitation model. The results show that the new precipitation prediction model’s performance is superior to the traditional Naive Bayes model. DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3997
Remote Monitoring System for Communication Base Based on Short Message
Xiao Rong Zhao;
Fei Yue Ye;
Xiu Fang Qian;
Han Yu Fu;
Wei Jin
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: January 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
This paper presents design and development of an automatic monitoring system of communication base which is an important means to realize modernization of mobile communication base station management. Firstly, this paper proposes the architecture of the monitoring system. The proposed system consists of mocrocontrollers, sensors, GSM module and MFRC500 etc. The value of parameters is measured in the system including terminal is studied and designed, including hardware design based on embedded system and software design. Finally, communication module is discussed. The monitoring system which is designed based on GSM SMS(short message service) can improve the integrity, reliability, flexibility and intellectuality of monitoring system. DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3200
An Algorithm of Image Quality Assessment Based on Data Fitting of Image Histogram
Qu zhongshui
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: January 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Based on research the connection between the gray image histogram and the gray image quality assessment,an algorithm of the gray image quality assessment based on data fitting of image histogram is proposed.The improved algorithm also applies to the color image.During the course of the color image quality assessment,the histogram is fitted respectively based on the color components and the color quantization.The difference weight data of the fitting coefficients about the image to be evaluted and the reference image is calculated. And the two element evaluation is given according to in the given threshhold range. The experiments show that the image quality assessment is good when the difference weight data of the fitting coefficients about the image to be evaluted and the reference image Less than or equal to 5×10-5.The two element evaluation is also effectively given according to the fitting data about color histogram of the color image based on the color components and the color quantization. DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3021
DSDWA: A DCT-based Spatial Domain Digital Watermarking Algorithm
Jianghua Li;
Qing Cao
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: January 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
DCT-based transformed domain watermarking algorithm has some flaws In the aspects of embedding position, embedding strength and embedding method, which have an important influence on watermarking embedding and watermarking extracting. In this paper we discussed these key techniques on DCT-based transformed domain watermarking algorithm and spatial domain digital watermarking algorithm, and their advantages and disadvantages respectively. We discovered the reason that error is generated during DCT and IDCT, and its influence on watermarking embedding and extracting, as well as the basic change rule of the pixel value matrix of the host image during watermarking embedding. On the basis of our analysis, a DCT-based spatial domain digital watermarking algorithm was proposed,which fully leveragedthe discovered change rule during watermarking embedding using DCT-based transformed domain algorithm. Experimental results showed that the algorithm had the advantages of spatial domain algorithm and transformed domain algorithm and overcamesome of their disadvantages. And itt was superior to DCT-base transformed domain watermarking algorithm. In addition, our work has the certain reference significance to other fields using DCT and IDCT. DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3323
Study of automatically generate test data based on evolutionary algorithm method
Zhag yunlong;
Ni Jian
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: January 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
The study of automatically generate test data based on evolutionary algorithm method focuses on the path coverage direction. The key problem is how to construct a suitable and has a good orientation of the fitness function to evaluate the quality of a test data. This paper introduces several evolution test methods, shows its advantages and problems it can effectively solve, and proposes an improved evolutionary test data generation method, which can generate better test data. DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3342
Optimal Path Planning for Mobile Robot Using Tailored Genetic Algorithm
Fei Liu;
Shan Liang;
Dong Xiao Xian
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: January 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
During routine inspecting, mobile robot may be requested to visit multiple locations to execute special tasks occasionally. This study aims at optimal path planning for multiple goals visiting task based on tailored genetic algorithm. The proposed algorithm will generate an optimal path that has the least idle time, which is proven to be more effective on evaluating a path in our previous work. In proposed algorithm, customized chromosome representing a path and genetic operators including repair and cut are developed and implemented. Afterwards, simulations are carried out to verify the effectiveness and applicability. Finally, analysis of simulation results is conducted and future work is addressed.DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3127