• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.17 no.9
• /
• pp.1006-1012
• /
• 2004

In this paper, neural networks is studied to apply as a PD source classification in XLPE power cable specimen. Two learning schemes are used to classification; BP(Back propagation algorithm), SOM(self organized map - kohonen network). As a PD source, using treeing discharge sources in the specimen, three defected models are made. And these data making use of a computer-aided discharge analyser, statistical and other discharge parameters is calculated to discrimination between different models of discharge sources. And a]so these distribution characteristics are applied to classify PD sources by two scheme of the neural networks. In conclusion, recognition efficiency of BP is superior to SOM.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.1045-1046
• /
• 2015

When using the Support Vector Machine in the online signature verification, SVM kernel function should be chosen to use non-linear SVM and the constant parameters in the kernel functions should be adjusted to appropriate values to reduce the error rate of signature verification. Non-linear SVM which is built on a strong mathematical basis shows better performance of classification with the higher discrimination power. However, choosing the kernel function and adjusting constant parameter values depend on the heuristics of the problem domain. In the signature verification, this paper deals with the problems of selecting the correct kernel function and constant parameters' values, and shows the kernel function and coefficient parameter's values with the minimum error rate. As a result of this research, we expect the average error rate to be less than 1%.

• Journal of Korea Multimedia Society
• /
• v.23 no.9
• /
• pp.1155-1163
• /
• 2020

Deep learning approach is emerging as a new way to improve the accuracy of tree species identification using bark image. However, the approach has not been studied enough because it is confronted with the problem of acquiring a large volume of bark image dataset. This study solved this problem by utilizing a pretrained off-the-shelf DCNN model. It compares the discrimination power of bark features extracted by each DCNN model. Then it extracts the features by using a selected DCNN model and feeds them to a multi-layer perceptron (MLP). We found out that the ResNet50 model is effective in extracting bark features and the MLP could be trained well with the features reduced by the principal component analysis. The proposed approach gives accuracy of 99.1% and 98.4% for BarkTex and Trunk12 datasets respectively.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.49 no.5
• /
• pp.199-204
• /
• 2000

This paper presents new approaches for the calculation for the calculation of each user's wheeling prices based on the economic analysis method with focus on the postage stamp rule. The suggested postage stamp rules can overcome the following problems embedded in the conventional accounting-costs-based methods such as the volatileness of wheeling prices depending deprieciation methods, emerging the wheeling free-riders due to the difference between accounting life-time and technical life-time, price discrimination between firm and non-firm network users, etc. To solve these problems we suggest new postage stamp rules employing capital recovery factor for investment costs treatment and applying technical life-time. Furthermore, we have suggested a new formulation for non-firm wheeling users based on the wheeling energies. In the case study, the results of suggested postage stamp methodologies are compared with those of conventional approaches.

• Proceedings of the KIEE Conference
• /
• 1999.07c
• /
• pp.1465-1467
• /
• 1999

An Algorithm is devised to discriminate power distribution faults from other activites utilizing the arc activity and changes in the loading. This scheme intends to determine the cause of the transients and identify them. the discrimination algorithm was tested using recorded event data.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.31A no.5
• /
• pp.76-84
• /
• 1994

Recently, Optical BJTC as a new approach for real-time multi-target tracking has been intensively studied. But the conventional system has some problems in the practical applications such as the false alarm and target missing and low correlation efficiency, and these poor performances are analyzed to be deeply dependent on the binarization method. So, in this paper, a new BJTC system which has the improved performances in target discrimination and diffraction efficiency is suggested, which is based on the JTPS having the same properties with those of the matched filter and new power spectrum binarization method to use effectively the high frequency components of the JTPS signal. Through the computer simulation and some experiments, the performances of the new BJTC tracking system are analyzed and proved to be superior to those of the conventional system baseds on Median method in multi- target tracking problems.

• Proceedings of the KIEE Conference
• /
• 2001.07b
• /
• pp.666-668
• /
• 2001

In this paper we are to explain the development of circuit breaker characteristic tester for 25.8kV Gas Insulated Switchgear. Because of hermetically sealed cubicle, we have the difficulties of installation and usage of tester. Therefore we developed measuring tester and software. This tester can measure CB close/trip time, coil current, stroke, chattering time. And it has CB positive/ negative discrimination program, trend management program, DB management program.

• Proceedings of the KIEE Conference
• /
• 2002.07a
• /
• pp.438-440
• /
• 2002

In deregulated power market, transmission pricing methodology should maintain non-discrimination amongst all participants while ensure that TRANSCOs recover their revenue requirements. The proposed transmission pricing methodology for Korea needs cost allocation ratios, such as allocation ratio of physical transport to network security and that of generators to loads. In this paper, we studied the nodal transmission price determined by the cost allocation factors and its influence on GENCOs and DISTCOs.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.31A no.6
• /
• pp.78-87
• /
• 1994

In this paper, a binary phase extraction joiont transform correlator (BPEJTC)system is proposed as a new phase-type optical correlator in which the correlation errors and DC component are dramtically reduced and optical efficiency and correlation performance are also improved by reconstructing the joint transform power spectrum (JTPS) of the conventional joint transform correlator (JTC)system form which the autocorrelation and crosscorrelation siganls generated in each self-plane are removed, and the binary phase function is extracted from the phase value of the reconstructed JTPS. Through some computer simulation and optical experimental results, the possibility of the implementation of the real-time multi-target tracking and recognition system is also suggested.

• Proceedings of the KIEE Conference
• /
• 2003.07a
• /
• pp.552-554
• /
• 2003

The second harmonic component is commonly used for blocking differential relay in power transformers. However, it is difficult to distinguish between inrush and internal winding fault with differential current protective relaying. This paper proposed a new method using Nuro-Fuzzy System based on HCM(Hard C-Means). The proposed system is more objective and systematic than existing model. The data used in input are 3-phase primary voltage and fundamental harmonic of differential current. Various states of transformer are simulated using BCTRAN and HYSDAT of EMTP. As a result of the application of algorithm in various cases, the exact discrimination between internal winding fault and inrush is performed.