• Proceedings of the KIEE Conference
• /
• 2006.07a
• /
• pp.212-213
• /
• 2006

Load models are important for improving the accuracy of stability analysis and power flow studies. Load characteristics change for different voltages and frequencies. In this research, ANN is used to construct the load model. Characteristics of some residential loads are tested under various voltage and frequency conditions. Acquired data are used to construct load models by ANN. Experiments and modeling results are presented in conclusions.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.625-627
• /
• 2002

본 논문에서는 의료영상 인식 기술 중 인식률이 뛰어나고 신뢰성 있는 대뇌출혈성 병변인식 시스템을 구현하기 위하여 신호처리 분야에서 주로 사용되는 Wavelet 변환과 신경망 기법을 이용하고자 한다. 그러나 신경망 기법에서 주로 사용되는 비선형 최적화기법인 Gradient descent BP는 최적화 문제점을 해결하기에는 수렴속도가 느리기 때문에 적합하지 않다. 따라서 본 논문에서는 기존 Gradient descent BP를 보완한 Levenberg-Marquardt Back-Propagation을 대뇌출혈성 병변인식에 적용하여 구현함으로써 총 50개의 패턴 중 45개의 영상이 인식에 성공하였고 전체 평균 인식률은 각각 90%와 87%의 인식률을 보였다.

• Journal of Korean Neurosurgical Society
• /
• v.46 no.2
• /
• pp.130-135
• /
• 2009

Objective: The purpose of this study was to determine the normal morphometric landmarks of the uniting and dividing points of the brachial plexus (BP) in the periclavicular region to provide useful guidance in surgery of BP injuries. Methods: A total of 20 brachial plexuses were obtained from 10 adult, formalin-fixed cadavers. Distances were measured on the basis of the Chassaignac tubercle (CT), and the most lateral margin of the BP (LMBP) crossing the superior and inferior edge of the clavicle. Results: LMBP was located within 25 mm medially from the midpoint in all subjects. In the supraclavicular region, the upper trunk uniting at 21$\pm$7 mm from the CT, separating into divisions at 42$\pm$5 mm from the CT, and dividing at 19$\pm$4 mm from the LMBP crossing the superior edge of the clavicle. In the infraclavicular region, the distance from the inferior edge of the clavicle to the musculocutaneous nerve (MCN) origin was 49$\pm$12 mm, to the median nerve origin 57$\pm$7 mm, and the ulnar nerve origin 48$\pm$6 mm. From the lateral margin of the pectoralis minor to the MCN origin the distance averaged 3.3$\pm$10 mm. Mean diameter of the MCN was 4.3$\pm$1.1 mm (range, 2.5-6.0) in males (n = 6), and 3.1$\pm$1.5 mm (range, 1.6-4.0) in females (n = 4). Conclusion: We hope these data will aid in understanding the anatomy of the BP and in planning surgical treatment in BP injuries.

• Journal of the Korean Applied Science and Technology
• /
• v.39 no.5
• /
• pp.632-643
• /
• 2022

Although probiotics have been shown to improve health when consumed, recent studies have reported that they can cause unwanted side effects due to bacterial-human interactions. Therefore, the importance of prebiotics that can form beneficial microbiome in the gut has been emphasized. This study isolated and identified bacteria capable of producing biopoymer as a candidate prebiotic from traditional fermented foods. The isolated and identified strain was named WCYSK01 (Wissella sp. strain YSK01). The composition of the medium for culturing this strain was prepared by dissolving 3 g K₂HPO₄, 0.2 g MgSO₄, 0.05 g CaCl₂, 0.1 g NaCl in 1 L of distilled water. The LMBP(low molecular weight biopoymers) produced when fermentation was performed with sucrose and maltose as substrates were mainly consisted of DP3 (degree of polymer; isomaltotriose), DP4 (isomaltotetraose), DP5 (isomaltopentaose), and DP6 (isomaltoheptaose). The optimization of LMBP (low molecular weight of biopolymer) production was performed using the response surface methodology. The fermentation process temperature range of 18 to 32℃, the fermentation medium pH in the range of 5.1 to 7.9. The yield of LMBP production by the strain was found to be significantly affected by q fermentation temperature and pH. The optimal fermentation conditions were found at the normal point, and the production yield was more than 75% at pH 7.5 and temperature of 23℃.

• Journal of Korea Water Resources Association
• /
• v.36 no.2
• /
• pp.195-209
• /
• 2003

Spatial-Stochastic Neural Networks Model(SSNNM) is used to estimate long-term streamflow in the parallel reservoir groups. SSNNM employs two kinds of backpropagation algorithms, based on LMBP and BFGS-QNBP separately. SSNNM has three layers, input, hidden, and output layer, in the structure and network configuration consists of 8-8-2 nodes one by one. Nodes in input layer are composed of streamflow, precipitation, pan evaporation, and temperature with the monthly average values collected from Andong and Imha reservoir. But some temporal differences apparently exist in their time series. For the SSNNM training procedure, the training sets in input layer are generated by the PARMA(1,1) stochastic model and they covers insufficient time series. Generated data series are used to train SSNNM and the model parameters, optimal connection weights and biases, are estimated during training procedure. They are applied to evaluate model validation using observed data sets. In this study, the new approaches give outstanding results by the comparison of statistical analysis and hydrographs in the model validation. SSNNM will help to manage and control water distribution and give basic data to develop long-term coupled operation system in parallel reservoir groups of the Upper Nakdong River.

• Proceedings of the KIEE Conference
• /
• 2006.11a
• /
• pp.329-331
• /
• 2006

Load models are important for improving the accuracy of stability analysis. Load characteristics are changed for voltage and frequency condition. In this research, ANN with LMBP learning rule is used to construct the load model. Characteristics of some residential loads are tested under various voltage and frequency conditions. Acquired data are used to construct load models by ANN. Constructed ANN load model are applied to transient stability analysis.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.60 no.1
• /
• pp.6-12
• /
• 2011

In this study, we proposed a residential load modeling method based on neuro-fuzzy inference system by considering of various harmonics. The developed method was implemented by using harmonic information, fundamental frequency and voltage which are essential input factors in conventional method. Thus, the proposed method makes it possible to effectively estimate load characteristics in power lines with harmonics. To show the effectiveness, the proposed method has been intensively tested with various dataset acquired under the different frequency and voltage and compared it with a conventional method based on neural networks.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.11
• /
• pp.124-131
• /
• 2001

Fault diagnosis of an assembled small motor relies usually on human experts hearing ability. The quality of diagnosis depends, however, heavily on physical conditions of the human experts. A fault diagnosis system for assembled small motors is developed using artificial neural network (ANN) in this paper. It is consisted of sound sampling device and fault diagnosis software package. Six parameters are defined to characterize the sampled sound waves. The Levenberg-Marquardt Backpropagation (LMBP) Algorithm is used to diagnose the fault of assembled small motors. Experimental results for more than two hundred small motors verify the performance of the developed system.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2004.05b
• /
• pp.1285-1289
• /
• 2004

Elman Discrete Recurrent Neural Networks Model(EDRNNM) was used to be a suitable short-term hydrological forecasting tool yielding a very high degree of flood stage forecasting accuracy at Musung station of Wi-stream one of IHP representative basins in South Korea. A relative new approach method has recurrent feedback nodes and virtual small memory in the structure. EDRNNM was trained by using two algorithms, namely, LMBP and RBP The model parameters, optimal connection weights and biases, were estimated during training procedure. They were applied to evaluate model validation. Sensitivity analysis test was also performed to account for the uncertainty of input nodes information. The sensitivity analysis approach could suggest a reduction of one from five initially chosen input nodes. Because the uncertainty of input nodes information always result in uncertainty in model results, it can help to reduce the uncertainty of EDRNNM application and management in small catchment.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.57 no.2
• /
• pp.96-101
• /
• 2008

The field of load modeling has attracted the attention since it plays an important role for improving the accuracy of stability analysis and power flow estimation. Also, load modeling is an essential factor in the simulation and evaluation of power system performance. However, conventional load modeling techniques have some limitations with respect to accuracy for nonlinear and composite loads. Thus, precision load modeling technique and reasonable application method is needed for more accurate power system analysis. In this paper, we develop an intelligent load modeling method based. on neural network and application techniques for power system. The proposed method makes it possible to effectively estimate the load model for nonlinear models as well as linear models. Reasonable application method is also proposed for stability analysis. To demonstrate the validity of the proposed method, various experiments are performed and their results are presented.