• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권7호
• /
• pp.859-868
• /
• 2004

본 논문에서는 능동적 학습이 보다 적은 수의 훈련예제로도 높은 학습성능을 달성할 수 있도록 군집화기법을 이용하여 초기훈련집합을 선정하는 방안을 제안한다. 본 제안 방안은 유사한 예제들보다는 다양한 예제들로 그리고 특수한 예제들보다는 보편적인 예제들로 구성한 집합이 학습에 유리할 것이라는 가정을 바탕으로, 먼저 k-means 군집화 기법으로 예제들을 군집화한 후, 각 군집을 가장 잘 표현하는 대표예제로 개별 군집의 중심점과 가장 가까운 예제를 선정하여 초기훈련집합을 구성한다. 또한 개별 군집의 중심점을 가상의 예제로 가정하여, 이와 연관된 대표예제의 카테고리를 부여함으로써 추가의 훈련예제로 활용하는 방안을 함께 제안한다. 여러 문서 분류 문제를 대상으로 실험한 결과, 본 제안 방안으로 선정한 초기훈련집합에서 출발한 능동적 학습이 임의로 선정한 초기훈련집합에서 출발한 경우에 비해 보다 적은 수의 훈련예제로도 동등한 성능을 달성할 수 있음을 확인하였다.

• 한국항공운항학회지
• /
• 제27권1호
• /
• pp.34-42
• /
• 2019

Ten AOC(Air Operation Certificate) holders certified by MOLIT of Korea are operating their own maintenance training program. Though the maintenance training program is approved by the same authority, the contents of the program are different even in the mandatory training courses among AOC holders. The survey interview showed that the maintenance training in mandatory training should have the same contents and requirements. Throughout the survey and focus group discussion, this paper suggests the list and contents of the initial mandatory training and the list, contents and interval for the recurrent mandatory training. This paper also suggests how to implement the on-line training program for recurrent mandatory training to keep the quality of the airline maintenance training program.

• 한국항행학회논문지
• /
• 제27권3호
• /
• pp.269-273
• /
• 2023

본 연구는 K-UAM 로드맵[1]을 바탕으로, 초기 UAM 조종사 교육훈련 커리큘럼 구성에 필요한 주요 교육훈련 과목을 선정하기 위해 수행하였다. 현재 UAM 기체는 VTOL 기능을 중심으로 수직 이착륙이 가능한 회전익 항공기와 유사한 특성을 갖는다. 따라서 본 연구에서는 회전익 비행교육을 대표하는 육군항공학교의 회전익 조종사 양성 교육 커리큘럼을 비교군으로 선정하여 초기 UAM 조종사 양성을 위한 교육훈련 과목을 선정하였다. 먼저 육군의 회전익 조종사 교육훈련 과목을 바탕으로 AHP 설문을 위한 계층구조를 설계하였으며 각 계층의 전문가들을 선별하여 AHP 설문을 수행하였다. AHP 분석을 통해 우선순위로 부여한 교육훈련 과목을 초기 UAM 조종사 훈련에 적용한다면 교육훈련 효과와 궁극적으로 UAM의 안전운항에 기여할 것으로 본다.

• 전자공학회논문지B
• /
• 제31B권4호
• /
• pp.145-154
• /
• 1994

This paper proposes an efficient method for improving the training performance of the neural network by using a hybrid of a stochastic approximation and a backpropagation algorithm. The proposed method improves the performance of the training by appliying a global optimization method which is a hybrid of a stochastic approximation and a backpropagation algorithm. The approximate initial point for a stochastic approximation and a backpropagation algorihtm. The approximate initial point for fast global optimization is estimated first by applying the stochastic approximation, and then the backpropagation algorithm, which is the fast gradient descent method, is applied for a high speed global optimization. And further speed-up of training is made possible by adjusting the training parameters of each of the output and the hidden layer adaptively to the standard deviation of the neuron output of each layer. The proposed method has been applied to the parity checking and the pattern classification, and the simulation results show that the performance of the proposed method is superior to that of the backpropagation, the Baba's MROM, and the Sun's method with randomized initial point settings. The results of adaptive adjusting of the training parameters show that the proposed method further improves the convergence speed about 20% in training.

• 말소리와 음성과학
• /
• 제5권3호
• /
• pp.31-38
• /
• 2013

This study investigated the influence of English vowel pronunciation training to English word-initial stop pronunciation. For that purpose, VOT values of English stops produced by twenty Korean English learners(five Youngnam dialect male speakers, five Youngnam dialect female speakers, five Kangwon dialect male speakers, and five Kangwon dialect female speakers) were measured using the Speech Analyzer and their post-training production was compared with their pre-training production. The result shows that post-training VOT values of voiced stops became closer to those of native English speakers in all four groups. Hence, it can be inferred that vowel pronunciation training is effective for correcting pronunciation of voiced vowels by analyzing the change of the quality of following vowels(especially low vowels) and the degree of giving stress.

• 지능정보연구
• /
• 제5권1호
• /
• pp.95-101
• /
• 1999

In this paper, a comparison between different methods to combine predictions from neural networks will be given. These methods are bagging, bumping, and balancing. Those are based on the analysis of the ensemble generalization error into an ambiguity term and a term incorporating generalization performances of individual networks. Neural Networks and AI machine learning models are prone to overfitting. A strategy to prevent a neural network from overfitting, is to stop training in early stage of the learning process. The complete data set is spilt up into a training set and a validation set. Training is stopped when the error on the validation set starts increasing. The stability of the networks is highly dependent on the division in training and validation set, and also on the random initial weights and the chosen minimization procedure. This causes early stopped networks to be rather unstable: a small change in the data or different initial conditions can produce large changes in the prediction. Therefore, it is advisable to apply the same procedure several times starting from different initial weights. This technique is often referred to as training ensembles of neural networks. In this paper, we presented a comparison of three statistical methods to prevent overfitting of neural network.

• 대한물리의학회지
• /
• 제10권4호
• /
• pp.49-57
• /
• 2015

PURPOSE: This study aimed to investigate the effect of emphasized initial contact gait training on balance and gait ability in hemiplegia patients. METHODS: Twenty-four hemiplegic patients were randomly allocated to an experimental group or control group. All participants received 30-min neurodevelopmental treatment. Furthermore, the experimental group received initial contact-emphasized auditory feedback gait training, whereas the control group received gait training without auditory feedback. The intervention was performed 3 times per week, 20 min per each time, for a total of 6 weeks. Balance was assessed using the center of pressure path length, center of pressure velocity, and limitation of stability path length, whereas gait ability was assessed using the 10-m walking test and functional gait assessment. RESULTS: In both groups, center of pressure path length and center of pressure velocity significantly decreased after training. Compared to the control group, the experimental group showed a 10% significant improvement (p<.05). In the limitation of stability path length of both sides, the experimental group showed a significant increase compared to that before intervention. Compared to the control group, the experimental group showed a 7% significant improvement in results of the 10-m walking test and functional gait assessment (p<.05). CONCLUSION: Emphasized Initial contact gait training is considered an effective treatment for improving gait ability and balance ability in stroke patients.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -3
• /
• pp.1901-1904
• /
• 2002

A good performance on communication systems is obtained by decreasing the length of training sequence In the initial stage of adaptive equalization. This paper presents a new approach to accomplish this, with the use of a training adaptive equalizer. The approach is based on combining the training and tracking modes, in which the training equalizer is updated by the LMS algorithm with the training sequence and then updated by a blind algorithm. By computer simulations, it is shown that a class of the proposed equalizers provides better performance than the conventional training equalizer.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(3)
• /
• pp.173-176
• /
• 2001

This paper proposes training algorithms of neuro-fuzzy systems. First, we introduce a structure training algorithm, which produces the necessary number of hidden nodes from training data. From this algorithm, initial fuzzy rules are also obtained. Second, the parameter training algorithm using evolution strategy is introduced. In order to show their usefulness, we apply our neuro-fuzzy system to a nonlinear system identification problem. It was found from experiments that proposed training algorithms works well.

• 대한전기학회논문지:전력기술부문A
• /
• 제54권7호
• /
• pp.323-327
• /
• 2005

This paper presents an operator training simulator for power system restoration against massive black-out. The system is designed especially focused on the generality and convenient setting up for initial condition of simulation. The former is accomplished by using power flow calculation methodology, and PSS/E data is used to define the initial situation. The proposed simulator consists of three major components - the power flow(PF) module, data conversion(COW) module and GU subsystem. PF module calculates power flow, and then checks overvoltage of buses and overflow of lines. COW module composes an Y-Bus array and a data base at each restoration action. The initial Y-Bus array is constructed from PSS/E data. The user friendly GUI subsystem is developed including graphic editor and built-in operation manual. As a result, the maximum processing time for one step operation is 15 seconds, which is adequate for training purpose. Comparison with PSS/E simulation proves the accuracy and reliability of the training system.