• Proceedings of the KIEE Conference
• /
• 2005.11a
• /
• pp.9-11
• /
• 2005

본 연구는 GIS 진단신뢰성 향상기술 개발을 목적으로, 16개의 인위적 결함을 이용하여 부분방전 신호를 발생시키고 검출하여 그 패턴인식 확률을 높이기 위하여 신경망에 Genetic Algorithm (GA) 을 적용하였다. 이를 위하여 다음과 같은 5가지 서로 다른 신경망 모델을 선택하였다: Back Propagation (BP), Jordan-Elman Network (JEN), Principal Component Analysis (PCA), Self-Organizing Feature Map (SOFM) 및 Support Vector Machine (SVM). 이와 같이 선택된 모델에 동일한 데이터를 학습 시키고 패턴인식 확률을 비교 및 분석하였다. 실험 결과에 의하면, BP의 인식률이 가장 높고 다음으로 JEN의 인식률이 높이 나타났으며, 후자의 경우 모든 결함에 대하여 정확한 패턴분류를 한 반면에 전자의 경우 1.8% 의 분류 오차가 발생하였다. 따라서 인식률이 높은 신경망이 더 정확한 패턴분류를 보장하지 못한다는 실험적 결과를 고려 할 때, 인식률이 높은 두 개의 모델을 선정하여 각각의 출력에 일정한 가중치를 주고 합산하여 새로운 출력을 얻는 방법을 제안한다.

• Child Health Nursing Research
• /
• v.13 no.2
• /
• pp.182-190
• /
• 2007

Purposes: The purposes of this study were to identify the level of knowledge of good posture and postural habits among elementary school children and to identify the relationship between knowledge of good posture and postural habits. Method: A descriptive correlational study was conducted. The participants were 507 elementary school children in Jangheung County. Data were collected using self-administered questionnaires. Descriptive statistics, t-test, ANOVA, and correlation were used for data analysis. Results: The percentage of correct answer for the knowledge test was 65.83%. Postural habits were not good. Although the strength of correlation was low, there is a statistically significant positive correlation between knowledge and postural habits. Not only school health nurses but also class teachers and parents played important roles in spinal health education. Educational needs for spinal health are high. Conclusion: Although more research in this area is warranted, there is a pressing need for interventions aimed at developing healthy habits that promote postural hygiene among elementary school children. Development and evaluation of back education programs in elementary school is necessary.

• Journal of the Korean Society of Safety
• /
• v.12 no.4
• /
• pp.209-213
• /
• 1997

Manual lifting techniques are commonly defined in terms of the postures adopted at the start of the lift. Quantitative definition is problematic, however, because the absolute joint angles adopted to lift an object are influenced by task parameters, such as the initial height of the load. The main objective of this study is to investigate the grip strength of the both hands at the initial lifting points. The survey is conducted by measuring the compression force, anthropometric data and grip strength at the lifting postures for the subjects(n=50) who is assigned to their job as usual. The experiment is peformed at the four lifting postures which involving the combination of two horizontal factors(H1 : 35 cm, H2 : 55 cm) and two vertical factors(V1 : 20~80 cm, V2 : 47~102 cm). The analysis result of lifting posture indicated that each H1-V1, H2-V1 combinations are about 60$^{\circ}$ and each H1-V2, H2-V2 combinations are about $30^{\circ}$. There are significant differences on grip strength between $60^{\circ}$ and $30^{\circ}$ stooped posture. The results of this study can be provided a method defining lifting postures at the minimum grip strength. Also, it is eliminated a hazard of the injuries which are cumulative trauma disorders(CTDs) and back pain, increased a productivity and improved a welfare of workers.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1999.10a
• /
• pp.162-169
• /
• 1999

In this paper, it is presented a new scheme of adaptive-neuro control system to implement real-time control of robot manipulator using digital Signal Processors. Digital signal processors DSPs. are micro-processors that are particularly developed for variables. Digital version of most advanced control algorithms can be defined as sums and products of measured variables, thus it can be programmed and executed through DSPs. In addition, DSPs are as fast in computation as most 32-bit micro-processors and yet at a fraction of their prices. These features make DSPs a biable computatinal tool in digital implementation of sophisticated controllers. Unlike the well-established theory for the adaptive control of linear systems, there exists relatively little general theory for the adaptive control of nonlinear systems. Adaptive control technique is essential for providing a stable and robust performance for application of robot control. The proposed neuro control algorithm is one of learning a model based error back-propagation scheme using Lyapunov stability analysis method. The proposed adaptive-neuro control scheme is illustrated to be a efficient control scheme for implementation of real-time control of robot system by the simulation and experiment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.5
• /
• pp.956-961
• /
• 2006

Keystroke time intervals can be a discriminating feature in the verification and identification of computer users. This paper presents a comparison result obtained using several classification methods including k-NN (k-Nearest Neighbor), back-propagation neural networks, and Bayesian classification for keystroke identification. Performance of k-NN classification was best with small data samples available per user, while Bayesian classification was the most superior to others with large data samples per user. Thus, for web-based on-line identification of users, it seems to be appropriate to selectively use either k-NN or Bayesian method according to the number of keystroke samples accumulated by each user.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.55 no.2
• /
• pp.89-97
• /
• 2006

Interior permanent magnet synchronous motor(IPMSM) has become a popular choice in electric vehicle applications, due to their excellent power to weight ratio. The paper is proposed maximum torque control of IPMSM drive using learning mechanism-fuzzy neural network(LM-FNN) controller and artificial neural network(ANN). The control method is applicable over the entire speed range and considered the limits of the inverter's current and voltage rated value. For each control mode, a condition that determines the optimal d-axis current $i_{d}$ for maximum torque operation is derived. This paper considers the design and implementation of novel technique of high performance speed control for IPMSM using LM-FNN controller and ANN controller. The hybrid combination of neural network and fuzzy control will produce a powerful representation flexibility and numerical processing capability. Also, this paper is proposed speed control of IPMSM using LM-FNN and estimation of speed using ANN controller. The back propagation neural network technique is used to provide a real time adaptive estimation of the motor speed. The proposed control algorithm is applied to IPMSM drive system controlled LM-FNN and ANN controller, the operating characteristics controlled by maximum torque control are examined in detail. Also, this paper is proposed the analysis results to verify the effectiveness of the LM-FNN and ANN controller.

• Journal of Korean Physical Therapy Science
• /
• v.5 no.4
• /
• pp.763-775
• /
• 1998

Some segment or segments of the body must compensate for the heel, and the higher the heel the greater the compensation. Such compensation was once generally thought to take place in the lumbar region and therefore to increase the lumbar lordosis. The purpose of this study is to analyze changes of lumbar sagittal curvature in barefoot and 6cm 12cm high-heel stance. We selected 19 subjects(11 males, 8 females} without history of lower back pain, significant spinal abnormality. And lateral view X-ray of lumbar region from T12 to S1 was taken of each individual. On each X-ray film, lumbar lordotic angle lumbosacral angle and lumbar segmental angles were measured by Cobb method. We drew the following interpretations from the analysis of measured variables of the lumbar region. 1. In comparison of barefoot 6cm heel 12cm heel stance, lumbar lordotic angle had a tendency to decrease according as the heel height was higher. The change in lumbar lordosis measured in high-heel stance was inconsistent with clinical forkelord of hyperlordosis in wearers of high-heeled. 2. Lumbar lordotic angle from T12 to L5 showed sex difference, and was more lordotic in female(p<0.05). 3. There was no sex difference in lumbosacral angle and lumbar segmental angles(p>0.05). 4. There was a significant correlation between lumbar lordotic angle and lumbosacral angle(r>0.60).

• Korean Journal of Applied Biomechanics
• /
• v.22 no.1
• /
• pp.75-82
• /
• 2012

The purpose of this study was to suggest the proper shaft and head fitting methods of the golf club to increase the flight distance of the golf ball. Rotations per minute of the golf ball(RPM), ratio of Ball speed to club head speed(T-Ratio) and launch angle right after impact(LA), which are directly related to ball flight distance, were measured using Spectra with shutter speed of 1/1000sec at the constant head speed of 95mph which was controlled by robot golf swing machine. In order to investigate the effect of club shaft to the 3 selected variables, 10 shafts were used to make ten test clubs with one controlled club head which is the most commonly used by golf players. To measure the effect of the club head to the 3 selected variables, 6 golf club heads which are most commonly used by golfers were selected to make 6 test clubs with a controlled shaft which is one of the best known by players. The shafts and the heads were identified by statistical analysis to increase or decrease the RPM, T-ratio and LA. A proper fitting method of the selected shafts and the club head was suggested to increase the ball flight distance in golf.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.05a
• /
• pp.1086-1092
• /
• 2002

Computer simulation is essential to design the suspension elements of railway vehicle. By computer simulation, engineers can assess the feasibility of a given design factors and change them to get a better design. But if one wishes to perform complex analysis on the simulation, such as railway vehicle dynamic, the computational time can become overwhelming. Therefore, many researchers have used a mega model that has a regression model made by sampling data through simulation. In this paper, the neural network is used a mega model that have twenty-nine design variables and forty-six responses. After this mega model is constructed, multi-objective optimal solutions are achieved by using the differential evolution. This paper shows that this optimization method using the neural network and the differential evolution is a very efficient tool to solve the complex optimization problem.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.42 no.4
• /
• pp.115-123
• /
• 2000

This study compared the degree of consolidation by hyperbolic, curve fitting , Asaoka's and methods using values measured with a theoretical curve in consideration of smear effect and well resistance. The degree of consolidation by the Hyperboilc method was underestimated than the degree of consolidation by Curve fitting. Asaoka's , and Monden's methods. The typical range of the coefficient of horizontal consolidation was Ch=(2-3)Cv in the case considering smear effect and well resistance, and Ch =(0.5-2.1) Cv in the case disregarding smear effect and well resistance. The degree of consolidation obtained by ground settlement monitoring was nearly the same value when the coefficient of smear zone permeability by back analysis was shown to be half that of in-situ and the diameter of the smear zone was shown to be double that of mandrel. By increasing the diameter reduction ratio of the drain, the time of consolidation was delayed. The effect of well resistance showed that the case of a small coefficient of permeability was much more than in the case of a large coefficient of permeability . It was recommended that when designing diameter reduction of a drain, well resistance should be considered.