KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 15

Some of the metrics are blocked by your
consent settings
Discrete wavelet transform and back-propagation neural networks algorithm for fault classification on transmission line
(2009-12-16)
Pothisarn, C.
;
Ngaopitakkul, A.
This paper proposes a technique using Discrete Wavelet Transform (DWT) and Back-Propagation Neural Network (BPNN) to identify the fault types on single circuit transmission lines. The ATP/EMTP is used to simulate fault signals. The mother wavelet daubechies4 (db4) is employed to decompose high frequency component from these signals. The variations of first scale high frequency component that detect fault are used as an input for the training pattern. The result has shown that the proposed technique gives satisfactory results.
Some of the metrics are blocked by your
consent settings
Mitigate the GPS position error by neural network technique
(2008-12-01)
Nontasud, Sarawut
;
Leelaruji, Nipha
This paper presents the error reduction of GPS receiver due to ionospheric irregularities by neural network technique. Normally, when GPS signal passed through the irregularities of ionosphere the scintillation will be appeared. It causes to latitude and longitude error from reference position or pseudo-range error more than 10 meters. GPS position error depends on the strength of scintillation index or S4 which due to total electron content in the ionosphere (TEC).We used the measurement data which include the S4 index to analyze and correct the position error by neural network technique. The result of this research we found the position error can reduce to less than 1 meter. The positions average close to correct position. © 2008 SICE.
Some of the metrics are blocked by your
consent settings
Automatic visual inspection of bump in hard disk drive component using neural network and image processing
(2008-12-01)
Kaitwanidvilai, Somyot
;
Seanton, Anakkapon
This paper presents the progressive development of the automatic visual inspection system for hard disk drive manufacturing. The developed system is applied to inspect the flip-chip solder joints called 'bump' on the flexible PCB. In the designed system, conventional image processing is utilized to find the interesting features from the Flip-Chip image. Such features are adopted as the inputs of the trained artificial neural network (ANN). The designed ANN is used as the expert system for classifying the completeness of bump. To compare performance, the measured value of the bump's length from the proposed inspection system is investigated in comparison with the value from the destructive inspection using micro-electroscope. Experimental results show that our developed system is effectively used to automatically inspect the bump. Inspection time of the proposed system is much faster than that of the human inspection.
Some of the metrics are blocked by your
consent settings
Applied the artificial neural network for reduce the position erroron GPS receiver due to ionospheric irregularities
(2008-12-01)
Nontasud, Sarawut
;
Leelaruji, Nipha
When the GPS signal pass through the ionosphere irregularities effect to rapid fluctuation of signal or scintillation occurred. This effect to the GPS receiver position error. This paper presents the error reduction of GPS receiver due to ionosphere irregularities by artificial neural network. The GPS position error depends on the strength of scintillation which measured in scintillation index or S4 index which due to total electron content (TEC) in the ionosphere. We used the measurement data which include the S4 index to analyze and correct the position error by artificial neural network. The result of this research we found the position error can reduce to less than 1 meter. The positions average close to correct position.© 2008 lEEE.
Some of the metrics are blocked by your
consent settings
Improved model for traffic fluctuation prediction by neural network
(2007-12-01)
Ardhan, S.
;
Satsri, S.
;
Chutchavong, V.
;
Sangaroon, O.
The traffic prediction are mainly used to improve the performance of telecommunication network management. This paper improved model for telephone traffic prediction in Thailand by using artificial neural network (ANN) with back propagation learning algorithms. By applied data which is collected at different node in main routes of TOT, Thailand telephone network for learning process and testing. The neural network structure and input/output musters are descried in detail. We present the comparatively results of simulation with another methods, the results shows traffic fluctuation prediction by the method of ANN is accurately. ©ICROS.
Some of the metrics are blocked by your
consent settings
Fault detection and reconfiguration technique for cascaded H-bridge 11-level inverter drives operating under faulty condition
(2007-12-01)
Khomfoi, Surin
;
Tolbert, Leon M.
A fault detection and reconfiguration technique for a cascaded H-bridge 11-level inverter drives during faulty condition is proposed in this paper. The ability of cascaded H-bridge multilevel inverter drives (MLID) to operate under faulty condition is also discussed. Output phase voltages of a MLID can be used as a diagnostic signal to detect faults and their locations. AI-based techniques are used to perform the fault classification. A neural network (NN) classification is applied to the fault diagnosis of a MLID system. Multilayer perceptron (MLP) networks are used to identify the type and location of occurring faults. The principal component analysis (PCA) is utilized in the feature extraction process to reduce the NN input size. The genetic algorithm (GA) is also applied to select the valuable principal components to train the NN. A reconfiguration technique is also developed. The developed system is validated with simulation and experimental results. The developed fault diagnostic system requires about 6 cycles (∼100 ms at 60 Hz) to clear an open circuit and about 9 cycles (∼150 ms at 60 Hz) to clear a short circuit fault. The experiment and simulation results are in good agreement with each other, and the results show that the developed system performs satisfactorily to detect the fault type, fault location, and reconfiguration. © 2007 IEEE.
Some of the metrics are blocked by your
consent settings
Solving classification problems using supervised self-organizing map
(2007-12-01)
Thammano, Arit
;
Kiatwuthiamorn, Jiraporn
This paper proposes the new approach to deal with the classification problems by modifying the well-known Kohonen self-organizing map in order to make it able to solve classification problems. During training, the fuzzy membership function is used in place of the Euclidean distance to find the best matching cluster for the input pattern. In order to improve the efficiency of proposed model, the fuzzy entropy concept is employed to reduce the number of nodes in the cluster layer. The performance of the proposed model was compared with the fuzzy ARTMAP neural network. The results on five benchmark problems are very encouraging. ©2007 IEEE.
Some of the metrics are blocked by your
consent settings
Credit scoring using least squares support vector machine based on data of Thai financial institutions
(2007-07-03)
Worrachartdatchai, Usanee
;
Sooraksa, Pitikhate
The quantitative method known as credit scoring has been developed for the credit assessment problem. Credit scoring is essentially an application of classification techniques, which classify credit customers into different risk groups. The Financial institutions are being more and more obliged to build credit scoring models assessing the risk of default of their clients. Support Vector Machine is a promising new technique that has recently emanated and become popular for data classification. Least Squares Support Vector Machines (LS-SVM) are re-formulations to the standard SVMs. The cost function is a regularized least squares function with equality constraints. The solution can be found efficiently by iterative method like the conjugate Gradient algorithm. Then in this paper, Least Squares Support Vector Machine is considered by approaching to the credit scoring with the data of Thai financial institutions. The optimum model will be able to divide the group of customers into four groups: very good, rather good, suspiciously bad and very bad with high accuracy.
Some of the metrics are blocked by your
consent settings
Fire detection using neural network
(2006-12-01)
Tipsuwanporn, V.
;
Krongratana, V.
;
Gulpanich, S.
;
Thongnopakun, K.
This study aims to investigate the effectiveness of image processing by using artificially neural network to detect fire in the room by using camera. This uses features of flame images in a simulation fire as input elements, is considered. Flame images are taken from the dynamic image, and features of the images for the ANN application are extracted from a rectified image which considers the difference in distance from the CCD color to the fire source. © 2006 ICASE.
Some of the metrics are blocked by your
consent settings
Human identification system based ECG signal
(2005-01-01)
Saechia, Sukkharak
;
Koseeyaporn, Jeerasuda
;
Wardkein, Paramote
A new human identification system based electrocardiogram (ECG) signal is introduced in this work. The human heart is considered to be a unique system of each person. ECG signal therefore represents as an impulse response of the system. The frequency response of the system (Fourier transform of the ECG signal) is employed to be a tool for feature extraction. In addition, the ECG signals employed in this paper, which may be derived from different heart rates from different subjects at the recording time, are normalized to a standard heart rate. Furthermore, not only the whole sequence of 1 period EC signal, containing P, QRS, and T waves, is processed but also its three subsequences, each respectively representing P, QRS, and T waves, is examined. The results of using neural network have demonstrated that subsequences technique is superior to whole period of ECG signal method.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results