Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

24,092 Article Results

A Neural Network based Intelligent Method for Mine Slope Surface Deformation Prediction Considering the Meteorological Factors

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3332
Sunwen Du , Jin Zhang , Zengbing Deng , Jingtao Li
Accurate mine slope surface deformation forecasting can provide reliable guidance for safe mining production and mine construction planning, which is also important for the personnel safety of the mining staffs. The mine slope surface deformation forecasting is a non-linear problem. Generalized regression neural network (GRNN) has been proven to be effective in dealing with the non-linear problems, but it is still a challenge of how to determine the appropriate spread parameter in using the GRNN for deformation forecasting. In this paper, a mine slope surface deformation forecasting model combining artificial bee colony optimization algorithm (ABC) and generalized regression neural network was proposed to solve this problem. The effectiveness of this proposed forecasting model was proved by experiment comparisons. The test results show that the proposed intelligent forecasting model outperforms the BP neural network forecasting model, BP neural network with genetic algorithm optimization (GA-BPNN) and the ordinary linear regression (LR) forecasting models in the mine slope surface deformation forecasting. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4815
Volume: 12
Issue: 4
Page: 2882-2889
Publish at: 2014-04-01

Using Flash Platform to Realize the Video Question Answering System

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3359
Guie Jiao
Video question answering system is designed and developed  based on Flash platform technology, belongs of B / S (Browser / Server) structure, is used to meet the needs of specific groups’ teaching and studying. This paper describes core codes of database module and the real-time Q&A video module about video creating and video playback, also describes the relevant  realization technology and other functional modules  of the system. At last, it gives some modified suggestions. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4780
Volume: 12
Issue: 4
Page: 3100-3104
Publish at: 2014-04-01

Class Variance Based Instruction function for Microscope Auto-focus

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3364
Lifei Deng , Hongwei Shi , Yaowu Shi , Lanxiang Zhu
This paper proposes an auto-focus Instruction function. The function is derived from Ostu segmentation. It uses class variance of segmentation result to instruct auto-focus process. Compare with the exist functions, class variance function need a small calculation mount. It is immunity to jam coming from camera and other inspection. It responses in a wide object distance range. And the value changes in a large range. All this features make this function is most flexible for microscope real-time auto-focus process. This paper analyzes the function and compares it to some traditional function. All the data are based practical instrument. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4784
Volume: 12
Issue: 4
Page: 3140-3147
Publish at: 2014-04-01

Context-aware Mobile Recommendation System Based on Context History

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3366
Qihua Liu
Recommendation systems for the mobile Web have focused on endorsing specificr content based on user preferences. But, user preferences vary in different contexts, such as at different times of day and in different locations. Therefore, in a mobile networking setting, providing proactive personalized service is more likely to depend on actual user context. This paper proposed a context-aware mobile recommendation system framework based on user models utilizing the context history. The approach was validated in the tourism domain. From our experiment and evaluation, the proposed framework is a promising approach to provider proactive personalized services to mobile users. Moreover, this research offers the personalized services to new users analyzing between the new user’s information and the stored association rules. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4786  
Volume: 12
Issue: 4
Page: 3158-3167
Publish at: 2014-04-01

Fuzzy Synthetic Evaluation Model on Cultural Characteristics behind People’s Selection of Subway

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3339
Ruijie Mu
Taking Zhengzhou urban residents travel means and the city’s traffic conditions as examples, this paper makes in-depth analysis on the Cultural Characteristics behind options of Zhengzhou citizen’s travel means. The paper, after investigating the citizen’s travel intentions, makes both normative and empirical comparisons to different cultural features behind people choosing different urban travel means. Then it drew a conclusion on how different cultural characteristics of urban residents affect their preference to travel means. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4171
Volume: 12
Issue: 4
Page: 2961-2968
Publish at: 2014-04-01

Rough Set Extension Model of Incomplete Information System

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3327
Yue Hou
This paper investigated the incomplete information system in which situation of the more missing or absent unknown values. Based on the original characteristic relation, we proposed a new reflective relation which was controlled by the parameter alpha, beta. By analyzing illustrative examples and comparing to the original characteristic relation, this paper indicated the validity and practicability of the new-defined binary relation. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4732
Volume: 12
Issue: 4
Page: 2843-2849
Publish at: 2014-04-01

Optimal Analysis on Reactive Capacity of Control Winding for Dual Stator-Winding Induction Generator

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3300
Jinyong Yu , Kai Zhang , Lingshun LIU , Shutuan Zhang , Jing Jiang
The minimizing to reactive power of control winding of the dual stator-winding induction generator is key to optimization of the novel generator system. It is determined by parameters of machine, load, rotating speed and speed range and exciting capacitors paralleled with the output terminal of power winding. In this paper, Based on analysis on working principle of conventional three-phase induction generator excited by capacitors with variable load and variable speed,  the determination of excited capacitors to minimize the reactive power of control winding under variable load and speed is proposed, the control law of optimal excited current is presented. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4757
Volume: 12
Issue: 4
Page: 2622-2627
Publish at: 2014-04-01

A Network Intrusion Detection Method Based on Improved ACBM

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3323
Chen Shan , Diao Hong-Bin
In order to solve the problem which includes the difficulties of network intrusion detection, redundancy of network intrusion character, difficulties for feature matching, a network intrusion detection method based on improved ACBM algorithm is proposed in this article. The improved ACBM algorithm is used to achieve matching module, which add the filtering function for module improvement. The distribution characteristics of stability and the use of the bifurcated binary tree model is used to complete the feature classification. In the stable feature, the inter-class distance is used as the classification method of support vector machine, which has strong ability of generalization as well as high identification accuracy, and has the application foreground detection. Finally, the superiority of the proposed method is proved through the data in KDDCup99 database. It shows that the proposed network intrusion detection method by experiment, which combines the ACBM algorithm and the classification mechanism, has a better accuracy than LSSVM and SVM, and it is proved that  this method is very suitable for network intrusion detection under complex features environment. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4246
Volume: 12
Issue: 4
Page: 2808-2815
Publish at: 2014-04-01

The Predictive Method of Power Load Based on SVM

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3355
Feng Lv , Fengning Kang , Hao Sun
For the problems which exist in power load prediction, such as nonlinear and high dimension recognition, support vector machine (SVM) is applied to power load prediction technology, based on the theory analysis of SVM and power load prediction. The predictive model of power load is established by SVM, which overcomes the problems to a great extent such as dimension disaster, over-learning, etc. The new thought of power load prediction is proposed which is more accurate, more intelligent and more humanized. The historical load data from a power grid company are used to establish the predictive model, Simulation is done by Matlab, and the predictive precision is improved greatly. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4834
Volume: 12
Issue: 4
Page: 3068-3077
Publish at: 2014-04-01

Based on Fuzzy Hybrid Inverter Technology Solar Energy Application Research

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3302
Huang Zhiwu , Wang Shuxia
The emergence of solar air conditioning, not only reduces energy consumption of the traditional air conditioning, but also decreases environmental pollution. However, the current market applications of solar air conditioning is not widespread, largely attributed to its internal control strategy has yet to be perfected. In order to achieve energy-efficient scheduling of solar air conditioning in the process of cooling, Firstly, the fuzzy control principle is introduced into the control procedure to solve the control threshold defined problem, the dynamic parameters of the air conditioner are adjusted dynamically to achieve the optimal  balance between multiple operating frequencies and the energy-related parameters at the same time. Then, the finite states machine segmentation techniques is taken in advantage to make that solar energy stay in an optimal status in a finite number of states given at any time. Finally, the Kalman frequency stabilization technology is used to ensure the system operating in the most stable state sustainably. Experimental results show the energy efficiency and performance of the system are improved obviously. Energy consumption per unit of time has decreased by 7%, and the latency of the system meets the applicability requirements. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4248
Volume: 12
Issue: 4
Page: 2636-2644
Publish at: 2014-04-01

Scheduling Two-machine Flowshop with Limited Waiting Times to Minimize Makespan

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3363
Bailin Wang , Tieke Li , Cantao Shi , Haifeng Wang
There are numerous instances of flowshop in the production process of process industry. When such characteristics as continuous production resulted from high-temperature environment or deteriorate intermediate products are took into consideration, it should be ensured that the waiting time of any job between two consecutive machines is not greater than a given value, which results in the flowshop scheduling problem with limited waiting time constraints. The problem with two-machine environment to minimize makespan is studied. Based on the discussion of the lower bound of the minimal makespan and some properties of the optimal schedule, a two-stage search algorithm is proposed, in which the initial schedule is generated by a modified LK heuristic in the first stage and the excellent solution can be obtained by constructing inserting neighborhood in the second stage. The numerical results demonstrate the effectiveness of the algorithm. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4783 
Volume: 12
Issue: 4
Page: 3131-3139
Publish at: 2014-04-01

Joint Optimization of Sensing Time and Fusion Rules for Cognitive Radios

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3325
Yang Liu , Ying Cui , Ou Li
 In Cognitive Radios, sensing-time and fusion rules affect the performance of spectrum sensing when cooperative sensing is applied. Besides, the more unlicensed users are involved in cooperative sensing, the higher spectrum utilization the channel can achieve, while from the unlicensed users’ perspective, the lower average throughput the unlicensed users can obtain. In this paper, we explore the issue on the sensing-time and the fusion rules to optimize the average throughput of the unlicensed users under the constraint that the licensed users are sufficiently protected. At first, we formulate this issue as an optimization problem, and showed the unimodal characteristics of the unlicensed users’ average throughput as a function of the sensing-time and the fusion parameter. Then a numerical optimization algorithm is proposed to obtain the optimal solution. At last, by theoretical analysis and performance comparisons we derived the optimal fusion rule selection scheme under different scenarios. Computer simulations show that significant improvement in the average throughput of unlicensed users is achieved when the sensing-time and the fusion rule are jointly optimized. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4793
Volume: 12
Issue: 4
Page: 2826-2832
Publish at: 2014-04-01

Network Traffic Prediction Algorithm based on Improved Chaos Particle Swarm SVM

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3291
Shuzhen Bai
Abstract—Because network traffic is complexand the existingprediction models have various limitations, a new network traffic prediction model based on wavelettransform and optimized support vector machine(ChOSVM) is proposed.Firstly, the network traffic is decomposed to the scale coefficients andwavelet coefficients by non-decimated wavelet transform based on suitablewavelet base and decomposition level. Then they are sent individually intodifferent SVM with suitable kernel function for prediction. The parameters ofSVM are selected by chaos particle swarm optimization. Finally predictions arecombined into the final result by wavelet reconstruction. Experiments onnetwork traffic of different time granularity show that compared with othernetwork traffic prediction models, ChOSVM has better performance. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4802
Volume: 12
Issue: 4
Page: 2548-2558
Publish at: 2014-04-01

Moving Shadow Removal Algorithm Based on HSV Color Space

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3318
Xinbo Zhang , Kunpeng Liu , Xiaoling Wang , Changhong Yu , Tao Zhang
In order to accurately separate a moving object from its shadow in a monitoring scene, this paper proposes a algorithm, which combines Multi-frame Average method for building background and HSV color space. First, the multi-frame average is used for setting up the background model. Second, the current frame and the background model are converted to HSV color space. In the foreground area, the values of brightness and saturation are smaller than that of the background, while the colors basically remain same. Just using these characters, the shadow is detected and eliminated. Finally, the algorithm is applied in videos with different monitoring scenes from the standard video library, such as highway, laboratory and campus, etc, to verify its effectiveness.  The experiment results show that the algorithm has better accuracy, reliability and robustness than the compared algorithm. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4991
Volume: 12
Issue: 4
Page: 2769-2775
Publish at: 2014-04-01

Recognition Based on Metric-optimized Neighborhood Preserving Embedding

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/3294
Bo Chen , Ye Zhang
Face recognition is a biometric technology with great developable potential. It has a great deal of potential applications in public security and information security. To overcome the problem in the high-dimensional face data processing, the k-nearest neighbors is chose by Linear Discriminate Analysis (LDA). A Metric-optimized is proposed for Neighborhood Preserving Embedding (MONPE).MONPE algorithm, with the dimensions of data reduced by LDA, will be reasonable in NPE algorithm. On the other hand, LDA maximizes the between-class scatter and minimizes the within-class scatter, so the neighbors of a sample will have higher possibility to be picked from the same class .With the ORL face database and the Yale database, the recognition rate and run time is compared among NPE, MONPE and CLMONPE. The simulation results show that CLMONPE has obvious advantage in application DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4825 
Volume: 12
Issue: 4
Page: 2574-2581
Publish at: 2014-04-01
1 2 3
...
1606 1607
Show 1442 of 1607

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration