Articles
50 Documents
Search results for
, issue
"Vol 10, No 6: October 2012"
:
50 Documents
clear
Loan Default Prediction on Large Imbalanced Data Using Random Forests
Lifeng Zhou;
Hong Wang
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 6: October 2012
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
In this paper, we propose an improved random forest algorithm which allocates weights to decision trees in the forest during tree aggregation for prediction and their weights are easily calculated based on out-of-bag errors in training. We compare the performance of our proposed algorithm and the original one on loan default prediction datasets. We also use these two algorithms to create two kinds of balanced random forests to deal with imbalanced data problem. Experiments results show that our proposed algorithm beats the original random forest in terms of both balanced and overall accuracy metrics. Experiments also show that parallel random forests can greatly improve random forests’ efficiency during the learning process.DOI: http://dx.doi.org/10.11591/telkomnika.v10i6.1323
Applications of Metrological Measurement in Wind Power Generation
REN Xiao-ping;
Cai Chang-qing;
Wang Jian;
Xue Zhi-chao
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 6: October 2012
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Development of green energy is the best key for solving environmental problems. The applications of wind force are the most skillful technologies today, which have been as important direction of green energy in highly developed country. Until now the technical development of wind force already achieves the skillful technique of application, and China becomes another leader in this field. Flexibility of modern wind turbine construction becomes more emphasized with the increase in wind turbine size, therefore even bigger vibrational amplitudes. Besides, the supervision blank of the quality of wind power plant by the authority is the reason why manufacture corporation and construction department neglect the quality control. These aspects include: rotor design, improved bearing material and installation, estimation and reduction of frictional effects, improvement in safety and remote monitoring. All of these will require many metrology issues to be addressed. DOI: http://dx.doi.org/10.11591/telkomnika.v10i6.1598
Consensus of Multi-agent Systems with Time Delays and Measurement Noises
Xiaole Xu;
Wei Huang;
Shengyong Chen;
Lixin Gao
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 6: October 2012
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
In this paper, the leader-following consensus problem of high order multi-agent systems with time-varying communication delays and noises is considered. The interconnection topology among the agents is assumed to be switching and undirected. The dynamics of each agent and the leader is a linear system. To track the active leader, a neighbor-based control of each following agent is designed in using local information. The control design technique is based on algebraic graph theory, Riccati inequality and Lyapunov inequality. By using Lyapunov-Razumikhim and stochastic analysis methods, we prove that the closed loop tracking control system is stochastically stable in mean square and the estimation errors converge to zero in mean square as well. Finally, a numerical example is given to illustrate the obtained result. DOI: http://dx.doi.org/10.11591/telkomnika.v10i6.1429
SA- Rough Sets K-means resource dynamic allocation strategy Based on Cloud Computing Environment
Meng Ying;
Luo Ke;
Liu Jian-hua;
Jiang Fei
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 6: October 2012
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Cloud computing has received increasingly attention from network computing model research, which can realize several kinds of resource sharing and dynamic resource allocation. However, how to effectively route storage resource in cloud, reduce dynamic load and cross data center data transmission, take into account global load balancing are important problems to be solved. This paper proposes a kind of SA-RS-K means resource dynamic allocation strategy based on cloud computing, which can reduce the time overhead, get the optimal computing resources and improve efficiency of algorithm. Simulation experiments in the end of paper verify the efficiency of this algorithm. DOI: http://dx.doi.org/10.11591/telkomnika.v10i6.1400
Discussion on Type-I fuzzy boundary and Research on Boundary Definition of High Order Fuzzy Region
Guo Jifa;
Cui Tiejun
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 6: October 2012
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
The definition of fuzzy boundary is crucial in research of modeling and analysis of fuzzy geographical phenomena. The problem “boundary syndrome” has been a longstanding problem in this domain, and this problem has seriously affected the research and application of fuzzy geographical model. The existing fuzzy boundary models were discussed at first, and then some models based on type-I fuzzy sets were analyzed in detail. This paper pointed out the fuzzy boundary models should have three kinds of meaning: “frontier”, “transition” and “division”. Three types of boundary models of high order fuzzy region were proposed based on interval type-2 fuzzy set, and they embody three kinds of meaning of fuzzy boundary respectively. The models proposed by this paper have a positive effect to high order geographical phenomena modeling and analysis. DOI: http://dx.doi.org/10.11591/telkomnika.v10i6.1544
High Performance Resonant Tunneling Electronic Circuit with Suitable Resistance Parameters
Chih Chin Yang;
Yen Chun Lin;
Hsiao Hsuan Cheng
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 6: October 2012
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Well-defined experimental and simulating single peak to valley current density ratio (PVCDR) resonant tunneling electronic circuit (RTEC) element is proposed in this research. The variation of passive element value in RTEC structure is explored using simulation method, which obtains the optimum PVCDR values about 66. The simulating peak current density (PCD) value is such high as 38 mA. Even though the experimental PCD value is less, but the PVCDR value is as high as 22.5, which value is favorably compared with semiconductor resonant tunneling devices (RTDs) in single PVCDR RTEC element. The obvious triple negative differential resistance (NDR) is also completed using composition of three suitable single RTEC elements. Also, experimental triple PVCDR RTEC element significantly exhibits three NDR curves with obvious three PVCDR values about 3.4, 3.8, and 6.0, respectively. Both peak voltage (PV) value and valley voltage (VV) values of experimental triple PVCDR RTEC element is less than 2.8 V, which value is profitable in development of commercial product. Power consumption of triple PVCDR RTEC element is as low as 75.5 μW, which low power consumption will shrink the difficulty of element packaging in heat dissipation. DOI:http://dx.doi.org/10.11591/telkomnika.v10i6.1416
Particle Filter with Gaussian Weighting for Human Tracking
Indah Agustien Siradjuddin;
M. Rahmat Widyanto;
T. Basaruddin
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 6: October 2012
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Particle filter for object tracking could achieve high tracking accuracy. To track the object, this method generates a number of particles which is the representation of the candidate target object. The location of target object is determined by particles and each weight. The disadvantage of conventional particle filter is the computational time especially on the computation of particle’s weight. Particle filter with Gaussian weighting is proposed to accomplish the computational problem. There are two main stages in this method, i.e. prediction and update. The difference between the conventional particle filter and particle filter with Gaussian weighting is in the update Stage. In the conventional particle filter method, the weight is calculated in each particle, meanwhile in the proposed method, only certain particle’s weight is calculated, and the remain particle’s weight is calculated using the Gaussian weighting. Experiment is done using artificial dataset. The average accuracy is 80,862%. The high accuracy that is achieved by this method could use for the real time system tracking. DOI: http://dx.doi.org/10.11591/telkomnika.v10i6.1187
Parameter Design for the Energy-Regeneration System of Series Hydraulic-Hybrid Bus
SONG Yunpu
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 6: October 2012
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
This paper simplifies the energy recovery process in the series hydraulic hybrid bus’ energy regeneration system into a process in which the main axle’s moment of inertia drives the secondary element variable delivery pump/motor and brings hydraulic oil from the oil tank to the accumulator. This process enables braking of the vehicle and also allows recovery of energy to the accumulator. Based on the flow equation for the secondary element variable delivery pump/motor and the torque equilibrium equation for its axle, the force equilibrium equation for vehicle braking and the pressure variation and flow continuity equations for the accumulator, simulation studies are conducted to analyze the effects of various system parameters, such as accumulator capacity, displacement of the secondary element variable delivery pump/motor, initial operating pressure of the system, etc. on system performance during regenerative braking. DOI: http://dx.doi.org/10.11591/telkomnika.v10i6.1420
Electroencephalography Feature Extraction Using High Time-Frequency Resolution Analysis
Zhang Shao-bai;
Huang Dan-dan
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 6: October 2012
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
The way to analyze EEG signals is mainly the method of time-frequency analysis, which cross terms and resolution are two contradictory factors. However, the high time-frequency resolution analysis (HTFRA) can combine both of them. The HTFRA is based on the Wigner-Ville distribution and effectively eliminate the cross of Wigner-Ville distribution without affecting the signal resolution by using the Median Affined Filter MAF method for nonlinear filtering. The simulated signals are analyzed with Short-Time Fourier Transform, Wigner-Ville distribution, and HTFRA, respectively. The results indicate that HTFRA give a better energy distribution in the time-frequency field compared with the traditional methods. DOI: http://dx.doi.org/10.11591/telkomnika.v10i6.1395
Fuzzy Expert System for Tropical Infectious Disease by Certainty Factor
I ketut Gede Darma Putra;
Putu Manik Prihatini
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 6: October 2012
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Communication between doctor and patient play an important role in determining the diagnosis of the illness suffered by the patient. Consultation time constraints led to insufficient information obtained to produce a diagnosis. This limitation is overcome by developing an expert system using fuzzy logic to represent the vagueness of symptoms experienced by patients and the certainty factor represents a relationship between the symptoms and disease. Fuzzy logic method begins with the acquisition of knowledge to produce the facts and rules, implication process, composition and defuzzification. The result of defuzzification used in the calculation of sequential and combined certainty factor which represent the belief percentage of diseases diagnosis that suffered by the patient. The results of the expert diagnosis with expert system for the given cases indicates the system, has the similarity diagnosis with the expert at 93.99%. DOI: http://dx.doi.org/10.11591/telkomnika.v10i6.1223