• 한국산업융합학회 논문집
• /
• 제16권4호
• /
• pp.113-117
• /
• 2013

This paper describes a new technology to develop the character recognition technology based on pattern recognition for non-contacting inspection optical lens slant or precision parts, and including external form state of lens or electronic parts for the performance verification, this development can achieve badness finding. And, establish to existing reflex data because inputting surface badness degree of scratch's standard specification condition directly, and error designed to distinguish from product more than schedule error to badness product by normalcy product within schedule extent after calculate the error comparing actuality measurement reflex data and standard reflex data mutually. Developed system to smallest 1 pixel unit though measuring is possible 1 pixel as $37{\mu}m{\times}37{\mu}m$ ($0.1369{\times}10-4mm^2$) the accuracy to $1.5{\times}10-4mm$ minutely measuring is possible performance verification and trust ability through an experiment prove.

• 전자공학회논문지C
• /
• 제35C권3호
• /
• pp.79-89
• /
• 1998

The Error Back-Propagation(EBP) algorithm is widely applied to train a multi-layer perceptron, which is a neural network model frequently used to solve complex problems such as pattern recognition, adaptive control, and global optimization. However, the EBP is basically a gradient descent method, which may get stuck in a local minimum, leading to failure in finding the globally optimal solution. Moreover, a multi-layer perceptron suffers from locking a systematic determination of the network structure appropriate for a given problem. It is usually the case to determine the number of hidden nodes by trial and error. In this paper, we propose a new algorithm to efficiently train a multi-layer perceptron. OUr algorithm uses stochastic perturbation in the weight space to effectively escape from local minima in multi-layer perceptron learning. Stochastic perturbation probabilistically re-initializes weights associated with hidden nodes to escape a local minimum if the probabilistically re-initializes weights associated with hidden nodes to escape a local minimum if the EGP learning gets stuck to it. Addition of new hidden nodes also can be viewed asa special case of stochastic perturbation. Using stochastic perturbation we can solve the local minima problem and the network structure design in a unified way. The results of our experiments with several benchmark test problems including theparity problem, the two-spirals problem, andthe credit-screening data show that our algorithm is very efficient.

• 조명전기설비학회논문지
• /
• 제26권5호
• /
• pp.21-33
• /
• 2012

This paper presents the new maximum power point tracking(MPPT) control of the photovoltaic(PV) module integrated converter(MIC) system considering the shadow influence. The output characteristics of the solar cell is a nonlinear and affected by a temperature, the solar radiation and influence of a shadow. Particularly, MIC system is very sensitive to the shadow influence because the capacity is very small. In order to increase an output and efficiency of the solar power generation, the maximum power point(MPP) obeying control are necessary. Conventional perturbation and observation(PO) and Incremental conductance(IC) are the method finding MPP by the continued self-excitation vibration. The MPPT control is unable to be performed by rapid output change affected by the shadow. To solve this problem, the new control algorithm of the multi-level in which the step value changes by output change is presented. In case there are the solar radiation, a temperature and shadow influence, the presented algorithm treats and compares the conventional control algorithm and output error. In addition, the validity of the algorithm is proved. through the output error response characteristics.

• Journal of Pharmaceutical Investigation
• /
• 제37권6호
• /
• pp.377-395
• /
• 2007

Near infrared(NIR) spectral data have been used for the noninvasive analysis of various biological samples. Nonetheless, absorption bands of NIR region are overlapped extensively. It is very difficult to select the proper wavelengths of spectral data, which give the best PCR(principal component regression) models for the analysis of constituents of biological samples. The NIR data were used after polynomial smoothing and differentiation of 1st order, using Savitzky-Golay filters. To find the best PCR models, all-possible combinations of available principal components from the given NIR spectral data were derived by in-house programs written in MATLAB codes. All of the extensively generated PCR models were compared in terms of SEC(standard error of calibration), $R^2$, SEP(standard error of prediction) and SECP(standard error of calibration and prediction) to find the best combination of principal components of the initial PCR models. The initial PCR models were found by SEC or Malinowski's indicator function and a priori selection of spectral points were examined in terms of correlation coefficients between NIR data at each wavelength and corresponding concentrations. For the test of the developed program, aqueous solutions of BSA(bovine serum albumin) and glucose were prepared and analyzed. As a result, the best PCR models were found using a priori selection of spectral points and the final model selection by SEP or SECP.

• 한국안전학회지
• /
• 제34권1호
• /
• pp.76-81
• /
• 2019

In this study, the causes of human error were identified through the survey of the drivers of the three organizations: Seoul Metro, Seoul Metropolitan Rapid Transit Corporation, and Korail. It was started with the aim of finding and eliciting causes in various directions including human factors, job factors, and environmental factors. The Cronbach alpha value was 0.95 for the reliability significance of the stress-induced factors in the operational area. The significance probability for organisational factors was shown to be 0.82, and the significance of the sub-accident experience and the driving skill factors in operation was 0.81 In addition, the analysis results showed that stress-induced in the field of driving is higher than the human factors in the reliability analysis. The results of the analysis confirmed that the reliability of the organizational and operational stress-induced factors was higher than other causes. In order to reduce urban railroad accidents, this paper suggests a method for operating safe urban railroad through the minimization human errors.

• Nuclear Engineering and Technology
• /
• 제16권4호
• /
• pp.202-216
• /
• 1984

Nodal method가 소격격자 해석방법의 하나로 정립됨으로써, 계산격자가 비교적 크더라도 각 격자의 평균출력분포를 정확히 계산할 수 있게 하는 균질화변수틀 찾는 방법이 중요하게 되었다. 본 연구에서는 simplified equivalence theory와 approximate node equivalence theory의 두가지 근사방법을 가압경수형 원자로 문제에 적응하여 시험하여 보았다. 균질화계산과 노심분석계산 방법으로서 analytic nodal method에 기초를 둔 ANM 코드를 개발하였다. 여러 균질화 방법외 정확성을 KTDD 코드에 의한 reference solution과 비교하여 본 결과, 균질화 계산은 핵연료영역에서는 영역별 핵연료집합체 계산으로, baffle과 reflector의 공존 격자영역은 이들을 포함하는 color set 계산으로 수행할 수 있음을 알았다. Approximate node equivalence theory에 입각해서 approximate homogenized cross-section들과 approximate discontinuity factor들의 균질화 변수를 사용하면 출력분포와 임계도가 각각 0.8%, 0,1% 오차 범위내에서 예측되었다.

• 한국정보과학회논문지:시스템및이론
• /
• 제36권3호
• /
• pp.135-139
• /
• 2009

여러 문자열들을 비교하여 유사성 또는 거리(오차)를 계산하는 문제는 패턴매칭, 웹검색 바이오인포매틱스, 컴퓨터 보안 등 다양한 응용 분야와의 연관성으로 인해 활발히 연구되어 왔다. 주어진 문자열 집합 내의 여러 문자열들의 거리를 비교하기 위해 주어진 집합 내의 모든 문자열들을 대표하는 한 문자열(대표문자열)을 찾는 방법이 있다. 대표문자열 방법은 주어진 문자열 집합과 가장 유사한 한 문자열을 찾는 방법으로 주로 이용되는 목적함수는 거리반경과 거리합이 있다. 거리반경은 집합 내의 문자열들과 특정 문자열과의 거리들의 최대값으로 정의되며, 모든 문자열들 중에서 최소의 거리반경을 만드는 문자열을 주어진 문자열 집합에 대한 거리반경기반 대표문자열이라 한다. 거리합은 집합 내의 문자열들과 특정 문자열과의 거리들의 합으로 정의되며, 모든 문자열들 중에서 최소의 거리합을 만드는 문자열을 주어진 문자열집합에 대한 거리합기반 대표문자열이라 한다. 본 논문에서는 메트릭 거리함수에 대해 거리반경기반 대표문자열 문제가 NP-완전임을 증명한다.

• 한국정밀공학회지
• /
• 제27권10호
• /
• pp.52-60
• /
• 2010

It is generally important to get a precise position information for autonomous unmanned vehicle(AUV) to run safely. For getting the position of AUV, the GPS has been using to navigation in a vehicle. Though it is useful to finding a position, it is difficult to precisely control a trajectory of the AUV due to large measuring error which may reach over 10 meters. Therefore to apply AUV it needs to compensate for the error. This paper proposes a method to more precisely localize AUV using three low-cost differential global positioning systems (DGPS). The distance errors between each DGPS are minimized as using the least square method (LSM) and the Kalman filter to eliminate a Gaussian white noise. The selected DGPS is cheaper and easier to set up than the RTK-GPS. It is also more precise than the general GPS. The proposed method can compensate the relatively position error according to stationary and moving distance of the AUV. For evaluating the algorithm by simulation, the DGPS signal with the Gaussian white noise to any points is generated by the AR model and compared with the measurement signal. It is confirmed that the proposed method can effectively compensate the position error as comparing with the measurement signal. The compensated position signal can be used to localize and control the AUV in the road.

• 대한인간공학회:학술대회논문집
• /
• 대한인간공학회 1997년도 춘계학술대회논문집
• /
• pp.56-60
• /
• 1997

The study of human erroneous actions has traditionally taken place along two different lines of approach. One has been concerned with finding and explaining the causes of erroneous actions, such as studies in the psychology of "error". The other has been concerned with the qualitative and quantitative prediction of possible erroneous actions, exemplified by the field of human reliability analysis (HRA). Another distinction is also that the former approach has been dominated by an academic point of view, hence emphasising theories, models, and experiments, while the latter has been of a more pragmatic nature, hence putting greater emphasis on data and methods. We have been developing a method to make predictions about error modes. The input to the method is a detailed task description of a set of scenarios for an experiment. This description is then analysed to characterise thd nature of the individual task steps, as well as the conditions under which they must be carried out. The task steps are expressed in terms of a predefined set of cognitive activity types. Following that each task step is examined in terms of a systematic classification of possible error modes and the likely error modes are identified. This effectively constitutes a qualitative analysis of the possibilities for erroneous action in a given task. In order to evaluate the accuracy of the predictions, the data from a large scale experiment were analysed. The experiment used the full-scale nuclear power plant simulator in the Halden Man-Machine Systems Laboratory (HAMMLAB) and used six crews of systematic performance observations by experts using a pre-defined task description, as well as audio and video recordings. The purpose of the analysis was to determine how well the predictions matiched the actually observed performance failures. The results indicated a very acceptable rate of accuracy. The emphasis in this experiment has been to develop a practical method for qualitative performance prediction, i.e., a method that did not require too many resources or specialised human factors knowledge. If such methods are to become practical tools, it is important that they are valid, reliable, and robust.

• 한국학교수학회논문집
• /
• 제16권1호
• /
• pp.113-139
• /
• 2013

본 연구는 초등학생들의 문장제 해결과정에서 나타나는 오류를 분석하고 문제해결전략별 오류 유형 및 그 특징을 파악함으로써 문제해결학습의 실패 원인에 대한 정보를 제공하고 문제해결력을 향상시킬 수 있는 교수학습방안을 제안하기 위한 것이다. 문장제 해결과정에서 학생들이 선호하는 전략을 살펴보면 식 세우기와 예상과 확인, 규칙 찾기 순으로 나타났으며, 단순화하기 전략은 거의 사용하지 않고 있다. 문장제 해결과정에서 나타나는 오류 유형의 특징은 문제해결전략에 따라 차이를 보였는데, 이를테면 식 세우기의 경우, '문항 이해의 오류', '개념 원리의 오류', '풀이 과정의 오류' 순으로 나타난 반면, 그림그리기에서는 문제에서 설명하는 내용을 잘못 이해하여 그림으로 나타내는 오류를 주로 범하였고, 표 만들기의 경우 문제에서 주어진 정보를 표로 나타내는 과정에서 정보들 간의 관계를 잘못 이해하여 오류를 범하는 '문항 이해의 오류'가 많은 것으로 나타났다. 이처럼 문장제를 통한 문제해결 학습에서 학생들이 선호하는 문제해결전략을 확인함과 동시에 문제해결전략별 나타나는 오류의 특징을 확인함으로써 해결전략에 따른 오류를 예상하고 이에 대처하는 교수학습방안을 생각해볼 수 있을 것이다.