• 한국컴퓨터정보학회논문지
• /
• 제20권1호
• /
• pp.21-28
• /
• 2015

특징 정규화는 인식기를 적용하기 이전의 전처리 단계로 특징 차원에 따라 서로 다른 스케일에 의해 발생하는 오류를 줄이기 위해 널리 사용된다. 하지만 기존 정규화 방법은 클래스 라벨을 고려하지 않으므로 정규화 결과가 인식률에서 최적임을 보장하지 못하는 문제점이 있다. 이를 개선하기 위해 클래스 라벨을 사용하여 정규화를 시행하는 교사 정규화 방법이 제안되었고 기존 정규화 방법에 비해 나은 성능을 보임이 입증되었다. 이 논문에서는 교사 랭크 정규화 방법에 학습 샘플 선택 방법을 적용함으로써 교사 랭크 정규화 방법을 더욱 개선할 수 있는 방법을 제안한다. 학습 샘플 선택은 잡음이 많은 샘플을 학습에서 제외함으로써 잡음에 보다 강한 분류기를 학습시키는 전처리 단계로 많이 사용되며 랭크 정규화에서도 역시 사용될 수 있다. 학습 샘플 선택은 이웃한 샘플이 속하는 클래스와 이웃한 샘플까지의 거리를 바탕으로 하는 두 가지 척도를 제안하였고, 두 가지 척도 모두에서 기존 정규화 방법에 비해 인식률이 향상되었음을 실험 결과를 통해 확인할 수 있었다.

• 대한원격탐사학회지
• /
• 제20권5호
• /
• pp.353-359
• /
• 2004

This study proposes an approach to unsupervisedly estimate the number of classes and the parameters of defining the classes in order to train the classifier. In the proposed method, the image is segmented using a spatial region growing based on hierarchical clustering, and fuzzy training is then employed to find the sample classes that well represent the ground truth. For cluster validation, this approach iteratively estimates the class-parameters in the fuzzy training for the sample classes and continuously computes the log-likelihood ratio of two consecutive class-numbers. The maximum ratio rule is applied to determine the optimal number of classes. The experimental results show that the new scheme proposed in this study could be used to select the regions with different characteristics existed on the scene of observed image as an alternative of field survey that is so expensive.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권11호
• /
• pp.4028-4042
• /
• 2021

Aiming at the problem of software defect prediction difficulty caused by insufficient software defect marker samples and unbalanced classification, a semi-supervised software defect prediction model based on a tri-training algorithm was proposed by combining feature normalization, over-sampling technology, and a Tri-training algorithm. First, the feature normalization method is used to smooth the feature data to eliminate the influence of too large or too small feature values on the model's classification performance. Secondly, the oversampling method is used to expand and sample the data, which solves the unbalanced classification of labelled samples. Finally, the Tri-training algorithm performs machine learning on the training samples and establishes a defect prediction model. The novelty of this model is that it can effectively combine feature normalization, oversampling techniques, and the Tri-training algorithm to solve both the under-labelled sample and class imbalance problems. Simulation experiments using the NASA software defect prediction dataset show that the proposed method outperforms four existing supervised and semi-supervised learning in terms of Precision, Recall, and F-Measure values.

• The Journal of Asian Finance, Economics and Business
• /
• 제9권2호
• /
• pp.255-260
• /
• 2022

SME sector's success also depends on its employees' job satisfaction as satisfied employees are likely to be more productive at the workplace and positively enhance SME business performance. Small and medium firms are the heart of the economy, and employees are the main and valuable asset for the SME firms. If SME business managers can increase employee satisfaction, then SMEs' performance will also increase in the future. Hence, the current study aims to determine the job satisfaction of SME employees by analyzing the impact of job training (JT) and promotion (PRO) opportunities on employee job satisfaction. Purposive sampling is applied in the study, and 202 SME employees have participated as sample respondents. The final sample size is n = 202. SPSS 26.0 version is used to analyze the hypotheses. The study findings show that both job training (JT) and promotion (PRO) have a positive effect on SME employee job satisfaction. It does indicate that SME managers need to provide necessary training programs and timely promotion to their current working employees to keep them satisfied with their job. Promotion and effective job training will certainly enhance employees' job satisfaction. The study has also offered a few strategic implications for SME business managers.

• Journal of the Korean Statistical Society
• /
• 제28권1호
• /
• pp.107-124
• /
• 1999

An approximate Bayes criterion for multivariate Behrens-Fisher problem is proposed and examined. Development of the criterion involves derivation of approximate Bayes factor using the imaginary training sample approach introduced by Speigelhalter and Smith (1982). The criterion is designed to develop a Bayesian test, so that it provides an alternative test to other tests based upon asymptotic sampling theory (such as the tests suggested by Bennett(1951), James(1954) and Yao(1965). For the derived criterion, numerical studies demonstrate routine application and give comparisons with the classical tests.

• 수산해양기술연구
• /
• 제58권1호
• /
• pp.85-93
• /
• 2022

In this study, we investigated how satisfaction with on-board training had an effect on career motivation of the trainees. For this purpose, satisfaction for on-board training and career motivation were used as variables. Satisfaction for on-board training were classified into education, environment and operation, and then measurement items were composed. Career motivation consisted of career identity, career insight and career resilience. To establish and test nine hypotheses, a questionnaire survey was conducted by 57 trainees who participated in the Gyeongsang National University on-board sailing training in 2021. To analyze the questionnaire responses, frequency analysis, factor analysis, multiple regression analysis and paired sample t-test were used. As a result of factor analysis, six factors for satisfaction for on-board training were derived. Among the factors, it was analyzed that satisfaction with assignments, the satisfaction with accommodation, and the satisfaction with the adequate condition of facilities and equipment had a significant effect on career motivation. In addition, it was found that career motivation significantly increased through on-board training as a result of comparing the difference between the averages of career motivation before and after on-board training.

• 대한교통학회지
• /
• 제18권4호
• /
• pp.75-85
• /
• 2000

본 연구에서는 도시부도로 신호교차로의 대기행렬을 단기(one cycle ahead)예측함에 있어 단일검지체계에 기반을 둔 한 지점의 시계열적 패턴을 갖는 검지자료(detection data)를 학습자료로 구성할 경우와 통합차량검지체계하에 기반을 둔 시공간적 상관관계를 갖는 검지자료를 학습자료로 이용할 경우를 가정하여 이에 대한 인공신경망의 학습능력과 예측능력을 비교하였다. 연구결과는 도시부도로 신호교차로상에서 차량군(platoon)의 이동에 따라 발생되는 시공간적인 상관관계를 갖는 교통류변수 $\ulcorner$상류유입교통량(k-1)->통행시간(k-1)->대기행렬(k)->유출교통량(k)->대기행렬(k+1)$\lrcorner$를 인공신경망의 학습자료로 구성할 경우, 교통류 패턴의 학습능력이 뛰어난 것으로 밝혀졌다.

• Asian Journal of Business Environment
• /
• 제5권3호
• /
• pp.23-28
• /
• 2015

Purpose - The aim of this study is to evaluate the effectiveness of a corporate training program. The case study of HCL Technologies was used to investigate how training programs improve the performance of employees on the job, as well as to identify unnecessary aspects of the training for the purpose of eliminating these from future training programs. Research design, data, and methodology - An exploratory research design was used to conduct the study. The research sample size included 50 HCL employees. The sampling technique for the data collection was convenience sampling. Results - Training is a crucial process in an organization and thus needs to be well designed. Specifically, the training programs should provide adequate knowledge to all employees, ensure correct methods are used for the selection of trainees, and avoid any perception of biasness. Conclusions - Employees were not fully satisfied by the separation of the training program into two parts, on the job and off the job training, but if sufficient data is provided to employees in advance, this could help them during the training process.

• 운동영양학회지
• /
• 제23권1호
• /
• pp.36-47
• /
• 2019

[Purpose] We conducted a meta-analysis to evaluate the effects of Taekwondo training on the physical fitness factors in Korean elementary students comprehensively and quantitatively. [Methods] We classified research studies published until November 2018 according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines and selected a total of 17 research items; a meta-analysis of these items was then conducted. We used the Comprehensive Meta-Analysis 3.0 and Review Manager 5.3 to analyze the mean effect size, study quality, and publication bias. [Results] Taekwondo training improved the cardiopulmonary endurance, muscle endurance, and power of the elementary students, but was not practical or less useful on other physical fitness factors. The meta-regression analysis of the cardiopulmonary endurance and power items showed that the effect size was large when the sample size was small. Therefore, it is necessary to consider the sample size in interpreting the effect size for these two items. Further, during correction of the publication bias for the power items, the improvement effect by Taekwondo training was eliminated. [Conclusion] Taekwondo training is helpful for improving the cardiopulmonary endurance and muscle endurance of Korean elementary students but is not useful for other physical fitness factors.

• 대한정형도수물리치료학회지
• /
• 제28권1호
• /
• pp.71-80
• /
• 2022

Background: This study investigated the effect of robot-assisted arm training on muscle activity of arm and weight bearing in stroke patients. Methods: The study subjects were selected 20 stroke patients who met the selection criteria. 10 people in the robot-assisted arm training group and 10 people in the task-oriented arm training group were randomly assigned. The experimental group performed robot-assisted arm training, and the control group performed task-oriented arm training for 6 weeks, 5 days a week, 30 minutes a day. The measurement tools included surface electromyography and smart insole system. Data were analyzed using independent sample t-test and the paired sample t-test. Results: Comparing the muscle activity of arm within the group, the experimental group and the control group showed significant differences in muscle activity in the biceps brachii, triceps brachii, anterior deltoid, upper trapezius, middle trapezius, and lower trapezius. Comparing the muscle activity of arms between the groups, the experimental group showed significant difference in all muscle activity of arm compared to the control group. Comparing the weight bearing within the groups, the experimental group showed significant difference in the affected side and non-affected side weight bearings and there were significant differences in anterior and posterior weight bearing. The control group showed significant difference only in the non-affected side weight bearing. Comparing the weight bearings between groups, the experimental group showed significant difference in the affected side and non-affected side weight bearings compared to the control group. Conclusion: This study confirmed that robot-assisted arm training applied to stroke patients for 6 weeks significantly improved muscle activity of arm and weight bearing. Based on these results, it is considered that robot-assisted arm training can be a useful treatment in clinical practice to improve the kinematic variables in chronic stroke patients.