• The Journal of Korean Physical Therapy
• /
• 제12권1호
• /
• pp.9-13
• /
• 2000

The purpose of this study was to determine the overflow effect and cross training effect of isometric quadriceps training that performed in specific angle of unilateral let. Ten healthy students with an average age of 24 years$(24.1\pm1.3)$, were participated in this study. Then 5 subjects in each group were chosen at random to train using only right quadriceps muscle two time per day(group 2), five times a week and the other 5 subjects(group 1) were chosen to train one times per day, five times a week for 2 weeks at only 50 degrees (contract 6 seconds, rest 10 seconds, 3 sets). Before and after the training, isometric quadriceps muscle testing of the both leg was Performed at three different angles, 60, 50 and 40 degrees respectively by BHN-COM (isokinetic dynamometer) in sitting position. The data was analyzed with paired t-test to determine significant difference between before and after training. In this study, we have found that the isometric quadriceps muscle training on specific angle of right side produced overflow effect In healthy subjects. However, increasing the peak torque of specific angle(training angle) of trained limb did not have an effect on increasing the peak torque of contralateral limb. These results demonstrate that the cross training effect did nut found in this study but a alight increase of peak torque of the untrained limb would recognized the possibility of cross training effect.

• 한국항행학회논문지
• /
• 제27권1호
• /
• pp.23-35
• /
• 2023

증거기반훈련(EBT)은 고속화되고 대형화되는 항공운송시장의 안전 운항을 위해, 실제 항공기 사고, 준사고, 운항, 훈련 데이터(Evidence)를 기반으로 조종사의 역량(Competency) 및 자신감(Confidence)을 향상하고 문제해결을 위한 회복력(Resilience)을 강화하는 훈련·평가 프로그램이다. 이러한 증거기반훈련(EBT)을 전문교육기관의 교육 체계에 적용하고 문제점을 개선하기 위해, 현재의 평가 기준에서 EBT의 핵심역량을 적용한 평가 기준으로의 개선과 실기시험관 및 교관 표준화를 위한 제도 개선, 모의비행훈련장치의 활용이라는 3가지 개선방안을 제시하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.154.2-154
• /
• 2001

This paper presented a adaptation approach based on maximum model distance (MMD) method. This method shares the same framework as they are used for training speech recognizers with abundant training data. The MMD method could adapt to all the models with or without adaptation data. If large amount of adaptation data is available, these methods could gradually approximate the speaker-dependent ones. The approach is evaluated through the phoneme recognition task on the TIMIT corpus. On the speaker adaptation experiments, up to 65.55% phoneme error reduction is achieved. The MMD could reduce phoneme error by 16.91% even when ...

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.99.1-99
• /
• 2001

This paper presented an adaptation approach based on maximum model distance (MMD) method. This method shares the same framework as they are used for training speech recognizers with abundant training data. The MMD method could adapt to all the models with or without adaptation data. If large amount of adaptation data is available, these methods could gradually approximate the speaker-dependent ones. The approach is evaluated through the phoneme recognition task on the TIMIT corpus. On the speaker adaptation experiments, up to 65.55% phoneme error reduction is achieved. The MMD could reduce phoneme error by 16.91% even when only one adaptation utterance is used.

• 대한인간공학회지
• /
• 제35권4호
• /
• pp.237-245
• /
• 2016

Objective: This study aims to introduce the bridge resource management (BRM) training courses implemented in Korea and to analyze their effectiveness in several views. Background: BRM training will be a mandatory course for crew members of ships from 2017. At this stage, it is needed to check if the BRM training courses implemented until now was effective to the Korean maritime safety and to investigate if there are more effective training methods. Method: The effectiveness of BRM training intervention in Korea was compared with that of the other countries, using Kirkpatrick's (1976) training evaluation framework. Kim (2012)'s data on the BRM training effectiveness were re-analyzed in order to check if the effects of BRM training are dependent on the bridge work experience. Results: Many BRM training courses has been opened in Korea. However, the methods to assess BRM training effects used in Korea focused on the survey of subjective satisfaction level, not investigating trainees' attitude and behavior change. On the other hand, the effectiveness of BRM training was higher to the bridge officers with long work experience than with shorter work experience. Conclusion: The contents of BRM training should be changed to effectively apply to the context of the real-world exercise and be differentiated depending on the work experience. Research on the methods to measure the BRM training effectiveness is also more required. Application: The results of this study will aid to develop the BRM training courses for bridge officers of ships in the BRM training institutions.

• 동의신경정신과학회지
• /
• 제7권1호
• /
• pp.39-48
• /
• 1996

This study was performed to investigate the effects of Qigong training after physical training stress in untrained college students For this study, 6 voluntary subjects(male 4, female 2) were chosen in untrained students of K University. they were trained by teachers during 6 weeks and tested just before Qingong training and after 6 weeks. Each subject was performed a treadmill exercise(model Q65, Quinton Co, U.S.A.) to the all-out state. During exercise stress test, electrocardiogram, heart rate were checked by stress test monitor(model Q4500, Quinton Co, U.S.A) and also oxygen uptake, maximal oxygen uptake analyzed continuously by automatic gas analysis(model QMC, Quinton Co, U.S.A). During physical training the serum were collected 3 times, pre-experimental rest time, and serum catecholamine were measured by HPLC.T-test of statistical analysis system was used in every experiment for statistical assessment. The results of T-test on these data were summarized as follow:1.Heart rate change during exercise stress test after Qigong training was shown more decreasing tendency than before training. Especially, heart rate change after Qigong training during resting periods was decreased significantly than before training.2. Oxygen uptake change during exercise stress test after Qigong training was shown more increasing tendency than before training, And also maximal oxygen uptake after Qigong training was shown more increasing tendency than before 6 weeks.3. Epinephrine level of after Qigong training was more decreased significantly than before training in all-out state. And norepinephrine level of after Qigong training was shown more decreasing tendency than before training in all-out state and after 30 minutes rest time. Above results indicate that Qigong training for 6 weeks could be effective to elevate the cardiopulmonary functions and diminish the stress responses of the physical stress.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2009년도 학술발표회 초록집
• /
• pp.1211-1214
• /
• 2009

The goal of this research is to apply the neural networks models for the disaggregation of the pan evaporation (PE) data, Republic of Korea. The neural networks models consist of generalized regression neural networks model (GRNNM) and multilayer perceptron neural networks model (MLP-NNM), respectively. The disaggregation means that the yearly PE data divides into the monthly PE data. And, for the performances of the neural networks models, they are composed of training and test performances, respectively. The training data consist of the generated data using PARMA (1,1). And, the testing data consist of the historic data, respectively. From this research, we evaluate the impact of GRNNM and MLP-NNM for the disaggregation of the nonlinear time series data. We should, furthermore, construct the credible data of the monthly PE data from the disaggregation of the yearly PE data, and can suggest the methodology for the irrigation and drainage networks system.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제9권1호
• /
• pp.33-38
• /
• 2020

본 논문에서는 드론에 의하여 획득된 영상을 분석하여 건축자재의 수량을 측정하는 기술을 제안한다. 제안하는 기술은 드론 및 카메라 정보가 담겨있는 드론 로그와 영상 내 건축자재더미 종류와 영역을 예측하는 RCNN, 실제적인 수량 계산을 위한 사진측량법을 사용한다. 기존 연구에선 학습 데이터의 부족으로, 자재 종류 및 건축자재더미 영역 예측 정확도의 오류 범위가 컸다. 논문에서는 이러한 오류 범위를 줄이고 예측 안정성을 높이기 위해 자료 증가 방법으로 학습 데이터를 증가시킨다. 자료 증가는 학습 모델의 과적합을 막기 위해 회전에 의한 증가 방법만 사용한다. 수량 계산 방법으로는 Yaw, FOV 등의 드론 및 카메라 정보가 담겨있는 드론 로그와 영상 내 건축자재더미 영역을 찾고, 종류를 예측해 줄 RCNN 모델을 사용하고, 이 모든 정보를 종합해 논문에서 제안하는 수식에 적용하여 자재더미의 실제적인 수량을 계산한다. 제안하는 방법의 우수성은 실험을 통하여 확인한다.

• 전기학회논문지P
• /
• 제67권4호
• /
• pp.183-190
• /
• 2018

Predicting accurate electricity prices is an important task in the electricity trading market. To address the electricity price forecasting problem, various approaches have been proposed so far and it is known that linear regression-based approaches are the best. However, the use of such linear regression-based methods is limited due to low accuracy and performance. In traditional linear regression methods, it is not practical to find a nonlinear regression model that explains the training data well. If the training data is complex (i.e., small-sized individual data and large-sized features), it is difficult to find the polynomial function with n terms as the model that fits to the training data. On the other hand, as a linear regression model approximating a nonlinear regression model is used, the accuracy of the model drops considerably because it does not accurately reflect the characteristics of the training data. To cope with this problem, we propose a new electricity price forecasting method that divides the entire dataset to multiple split datasets and find the best linear regression models, each of which is the optimal model in each dataset. Meanwhile, to improve the performance of the proposed method, we modify the proposed localized linear regression method in the map and reduce way that is a framework for parallel processing data stored in a Hadoop distributed file system. Our experimental results show that the proposed model outperforms the existing linear regression model. Specifically, the accuracy of the proposed method is improved by 45% and the performance is faster 5 times than the existing linear regression-based model.

• International Journal of Computer Science & Network Security
• /
• 제22권2호
• /
• pp.214-222
• /
• 2022

Convolutional Neural networks (CNNs) are a category of deep learning networks that have proven very effective in computer vision tasks such as image classification. Notwithstanding, not much has been seen in its use for remote sensing image classification in developing countries. This is majorly due to the scarcity of training data. Recently, transfer learning technique has successfully been used to develop state-of-the art models for remote sensing (RS) image classification tasks using training and testing data from well-known RS data repositories. However, the ability of such model to classify RS test data from a different dataset has not been sufficiently investigated. In this paper, we propose a deep CNN model that can classify RS test data from a dataset different from the training dataset. To achieve our objective, we first, re-trained a ResNet-50 model using EuroSAT, a large-scale RS dataset to develop a base model then we integrated Augmentation and Ensemble learning to improve its generalization ability. We further experimented on the ability of this model to classify a novel dataset (Nig_Images). The final classification results shows that our model achieves a 96% and 80% accuracy on EuroSAT and Nig_Images test data respectively. Adequate knowledge and usage of this framework is expected to encourage research and the usage of deep CNNs for land cover mapping in cases of lack of training data as obtainable in developing countries.