• Industry Promotion Research
• /
• v.6 no.1
• /
• pp.1-7
• /
• 2021

We investigated multi-layer perceptrons and supervised learning algorithms, and also examined how to model functional relationships between covariates and response variables using a package called neuralnet. The algorithm applied in this paper is characterized by continuous adjustment of the weights, which are parameters to minimize the error function based on the comparison between the actual and predicted values of the response variable. In the neuralnet package, the activation and error functions can be appropriately selected according to the given situation, and the remaining parameters can be set as default values. As a result of using the neuralnet package for the infertility data, we found that age has little influence on infertility among the four independent variables. In addition, the weight of the neural network takes various values from -751.6 to 7.25, and the intercepts of the first hidden layer are -92.6 and 7.25, and the weights for the covariates age, parity, induced, and spontaneous to the first hidden neuron are identified as 3.17, -5.20, -36.82, and -751.6.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.4
• /
• pp.57-63
• /
• 2010

The damping parameter of Levenberg-Marquardt algorithm switches between error backpropagation and Gauss-Newton learning and affects learning speed. Fixing the damping parameter induces some oscillation of error and decreases learning speed. Therefore, we propose the way of a variable damping parameter with referring to the alternation of error. The proposed method makes the damping parameter increase if error rate is large and makes it decrease if error rate is small. This method so plays the role of momentum that it can improve learning speed. We tested both iris recognition and wine recognition for this paper. We found out that this method improved learning speed in 67% cases on iris recognition and in 78% cases on wine recognition. It was also showed that the oscillation of error by the proposed way was less than those of other algorithms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.11
• /
• pp.2295-2303
• /
• 2009

Underwater acoustic(UWA) communication has multipath error because of reflection by sea-level and sea-bottom. The multipath of UWA channel causes signal distortion and error floor. In this paper, we proposed the compensation method of multipath effect using the impulse response of the UWA channel and then analysis the performance of channel coding such as LDPC code, concatenate code. Also we analysed the time-delay errors and estimated amplitude errors of estimated channel information and its affection on the performance. As shown in simulation results, the performance of proposed compensation method is better than the performance of conventional method.

• Journal of the Korea Convergence Society
• /
• v.10 no.4
• /
• pp.45-50
• /
• 2019

This study proposes a method to measure software reliability according to software reliability measurement model to measure software reliability. The model presented in this study uses the distribution of Non - Homogeneous Poisson Process and presents a measure of the software reliability of the presented model. As a method to select a suitable software reliability growth model according to the presented model, we have studied a method of proposing an appropriate software reliability function by calculating the mean square error according to the estimated value of the reliability function according to the software failure data. In this study, we propose a reliability function to measure the software quality and suggest a method to select the software reliability function from the viewpoint of minimizing the error of the estimation value by applying the failure data.

• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.205-210
• /
• 2021

In this study, I studied how to generate input values to achieve the same value as the target value. The general procedures are explained to regenerate the excitation input, which is made by using the frequency response function between input-output. In this study, a mount model connected by a bushing was used as a numerical model. The response value for the excitation input was compared with the target value. The excitation input was corrected to obtain the same response as the target value. Through the iterative process, the reconstructed input value was obtained to have the same response as the test.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.11a
• /
• pp.269-272
• /
• 2009

본 논문에서는 변이지도의 정확도 향상을 위하여, 비용 함수를 이용한 교차 일치성 검사 기법을 제안하고, 다양한 조건의 실험을 통하여 제안한 알고리듬이 효율적임을 보였다. 좌우 변이정보를 이용하는 교차 일치성 검사로 오정합을 검출하는 방법을 시도해왔다. 하지만 이러한 방법은 물체의 경계에서 발생하는 오정합을 찾기가 어렵다. 본 논문에서는 최종 변이의 신뢰도 향상을 위해 교차 일치성 검사의 정확도를 높이는 방법을 제안하였다. 일반적으로 영역 기반 스테레오정합 방법은 물체의 경계에서 정확도 높지 못하다. 이러한 문제점을 해결하기 위해 정합창의 크기를 늘리거나 특징 점을 이용한 적응적 가변 정합창을 적용하는 방법을 시도하였다. 하지만, 여전히 기존 교차 일치성 검사를 통한 오정합 검출은 부정확하다. 이러한 영역의 비용 함수 값들을 비교한 결과 첫 번째와 두 번째 값의 차이가 적거나 크게 나타난다. 제안한 방법은 기존 방법에 비해 오정합 검출 능력을 향상 시킨다. 제안한 방법의 결과를 확인하기 위해 스테레오 비전에서 많이 사용되는 영상을 적용하고 분석하였다. 또한, 기존 교차 일치성 검사 방법과 제안한 방법의 객관적으로 비교하기 위해 전체 영역에 대한 오차율 (error ratio)과 교차 일치성 검사로 유효하다고 판단된 변이 값 중 실제 변이 값과 일치하지 않은 변이값의 오차율을 비교하였다. 실험 결과 기존 방법에 비해 제안한 방법이 1~5%정도 낮은 오차율을 보였다

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.12 no.9
• /
• pp.702-708
• /
• 2002

The spectrum of impulse response signal from an impulse hammer testing is widely used to obtain frequency response function(FRF). However the FRFs obtained from impact hammer testing have not only leakage errors but also finite record length errors when the record length for the signal processing is not sufficiently long. The errors cannot be removed with the conventional signal analyzer which treats the signals as if they are always steady and periodic. Since the response signals generated by the impact hammer are transient and have damping, they are undoubtedly non-periodic. It is inevitable that the signals be acquired for limited recording time, which causes the errors. This paper makes clear the relation between the errors of FRF and the length of recording time. A new method is suggested to reduce the errors of FRF in this paper. Several numerical examples for 1-dof model are carried out to show the property of the errors and the validity of the proposed method.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.4
• /
• pp.61-68
• /
• 2012

In this paper, a closed-loop sensorless stroke control system for a linear compressor has been designed. In order to estimate the piston position accurately, motor parameters are identified as a function of the piston position and the motor current. These parameters are stored in ROM table and used later for the accurate estimation of piston position. The identified motor parameters are approximated to the several surface functions in order to decrease memory size. They can also be divided into 2 or 4 subsections to decrease identification errors. The effect of the order of surface functions and division of subsections on identification errors and computation time is analyzed.

• Proceedings of the KIPE Conference
• /
• 2013.11a
• /
• pp.39-40
• /
• 2013

본 논문에서는 직접토크 제어에서 자속과 토크의 오차에 따라 결정된 전압벡터와 회전자 위치에 따른 실제 인가될 수 있는 d-q축 전압을 근사 전압함수로 근사화하여, 자속 및 토크오차와 전동기의 속도에 따라 듀티비를 결정하는 방식을 제안한다. 이러한 방식은 선택된 전압벡터가 일정한 상수 크기의 전압을 인가하는 것으로 가정된 기존의 직접토크 제어 방식에 비해 정밀한 전압 기준을 바탕으로 펄스폭의 듀티비를 결정함으로써, 동일한 스위칭 주파수 내에서 토크 및 자속오차의 크기를 감소 시킬 수 있는 장점이 있다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.05b
• /
• pp.314-318
• /
• 2005

잠실 및 신곡 수중보의 영향을 모의할 수 있도록 개선된 FLDWAV 모형을 한강 하류부의 하천구간에 적용하여 모형의 보정을 수행하였다. FLDWAV 모형에 포함된 자동추정 기법을 적용하여 부분 선형함수 가변 조도계수 모형의 매개변수를 추정하였다 팔당대교부터 전류까지의 하천구간을 3개 구간으로 구분하고, 유량 등급별 조도계수의 초기 가정치를 변화시켜 가며 각 경우에 대하여 홍수사상별로 매개변수 추정을 수행하였다. 최소유량(영) 등급 및 최대유량 등급에 대한 조도계수 추정치들은 초기 가정 값에 민감하여 초기치가 최종 추정치로 종료되는 경우가 다수 발생하였다. 대부분의 홍수사상에 대하여 추정 매개변수를 사용한 계산수위와 관측수위의 편차 합은 영에 근접하나, RMS 오차는 다양한 값들을 나타내었다. 양의 오차들과 음의 오차들이 서로 상쇄됨으로써 편차가 영에 근접하게 되는 경우가 빈번히 발생하였으며, 이는 편차 합을 최소화하는 목적함수를 만족시키는 최적해가 유일하지 않음을 의미한다.