• 대한원격탐사학회지
• /
• 제24권5호
• /
• pp.507-515
• /
• 2008

Many studies have generally used a large number of pure pixels as an approach to training set design. The training set are used, however, varies between classifiers. In the recent research, it was reported that small mixed pixels between classes are actually more useful than larger pure pixels of each class in Support Vector Machine (SVM) classification. We evaluated a usability of small mixed pixels as a training set for the classification of high-resolution satellite imagery. We presented an advanced approach to obtain a mixed pixel readily, and evaluated the appropriateness with the land cover classification from IKONOS satellite imagery. The results showed that the accuracy of the classification based on small mixed pixels is nearly identical to the accuracy of the classification based on large pure pixels. However, it also showed a limitation that small mixed pixels used may provide insufficient information to separate the classes. Small mixed pixels of the class border region provide cost-effective training sets, but its use with other pixels must be considered in use of high-resolution satellite imagery or relatively complex land cover situations.

• Computers and Concrete
• /
• 제19권6호
• /
• pp.717-724
• /
• 2017

In this paper, four formulas are proposed via gene expression programming (GEP)-based models and regression analysis (RA) to predict the flexural strength ($f_s$) values of mortars containing different mineral admixtures that are ground granulated blast-furnace slag (GGBFS), silica fume (SF) and fly ash (FA) at different ages. Three formulas obtained from the GEP-I, GEP-II and GEP-III models are constituted to predict the $f_s$ values from the age of specimen, water-binder ratio and compressive strength. Besides, one formula obtained from the RA is constituted to predict the $f_s$ values from the compressive strength. To achieve these formulas in the GEP and RA models, 972 data of the experimental studies presented with mortar mixtures were gathered from the literatures. 734 data of the experimental studies are divided without pre-planned for these formulas achieved from the training and testing sets of GEP and RA models. Beside, these formulas are validated with 238 data of experimental studies un-employed in training and testing sets. The $f_s$ results obtained from the training, testing and validation sets of these formulas are compared with the results obtained from the experimental studies and the formulas given in the literature for concrete. These comparisons show that the results of the formulas obtained from the GEP and RA models appear to well compatible with the experimental results and find to be very credible according to the results of other formulas.

• International Journal of Advanced Culture Technology
• /
• 제7권1호
• /
• pp.209-215
• /
• 2019

In order to provide a safe free-weight-training environment to people without workout trainers, we suggest a smart bench press machine with an automatic weight control system sensitive to user tiredness. Physical weight plates on the machine are replaced with a hydraulic cylinder as a press load and the cylinder knob is coupled with a step motor to change its tensile force automatically in-between lifting exercises. Three subjects participated to verify the usability of the smart bench press machine. They were asked to lift a 6-RM press load 10 times with 3 different lifting conditions: 1) no assistance, 2) a human assistance, and 3) the automatic weight control. All subjects were not able to complete the 10 sets without assistance due to tiredness, but they finished the full sets under the two assistive conditions. Average lifting speeds under the automatic weight control condition showed the most consistent level. Normalized quasi-tension data based on surface electromyogram signals of both Pectoralis Majors revealed that the subjects maintained the target muscle activation level above 50% but not more than 80% throughout the 10 sets. Therefore, the smart bench press machine is expected to both keep pace with the lifting exercise and reduce risk of injuries due to excessive muscle tensions.

• Water Engineering Research
• /
• 제1권2호
• /
• pp.129-136
• /
• 2000

Predicting water levels is a difficult task because a lot of uncertainties are included. Therefore the neural network which is appropriate to such a problem, is introduced. One day ahead forecasting of river stage in the Bocheong River is carried out by using the neural network model. Historical water levels at Snagye gauging point which is located at the downstream of the Bocheong River and average rainfall of the Bocheong River basin are selected as training data sets. With these data sets, the training process has been done by using back propagation algorithm. Then waters levels in 1997 and 1998 are predicted with the trained algorithm. To improve the accuracy, a filtering method is introduced as predicting scheme. It is shown that predicted results are in a good agreement with observed water levels and that a filtering method can overcome the lack of training patterns.

• ETRI Journal
• /
• 제31권2호
• /
• pp.121-128
• /
• 2009

In this paper, we describe a fixed-threshold sequential minimal optimization (FSMO) for structured SVM problems. FSMO is conceptually simple, easy to implement, and faster than the standard support vector machine (SVM) training algorithms for structured SVM problems. Because FSMO uses the fact that the formulation of structured SVM has no bias (that is, the threshold b is fixed at zero), FSMO breaks down the quadratic programming (QP) problems of structured SVM into a series of smallest QP problems, each involving only one variable. By involving only one variable, FSMO is advantageous in that each QP sub-problem does not need subset selection. For the various test sets, FSMO is as accurate as an existing structured SVM implementation (SVM-Struct) but is much faster on large data sets. The training time of FSMO empirically scales between O(n) and O($n^{1.2}$), while SVM-Struct scales between O($n^{1.5}$) and O($n^{1.8}$).

• The Journal of Korean Physical Therapy
• /
• 제29권5호
• /
• pp.255-258
• /
• 2017

Purpose: This study aimed to investigate the effects of compelled weight shift in paretic lower limb training on balance ability in patients with stroke. Methods: Thirty-six individuals with hemiparesis, who were randomly assigned to a 10CWST (10 mm constrained -weight shift training) group, a 5CWST (5 mm constrained-weight shift training) group, and a control group participated in this study. Compelled weight shift training was performed in 3 sets of 5 min with a rest period of 1 min between sets. Both the 5CWST and 10CWST groups performed 5 times per week for 4 weeks. Static (mediolateral and anteroposterior sway velocities) and dynamic balance (mediolateral and anteroposterior distances) was assessed using the Good Balance system. Results: Significant differences were found in the M-L and A-P sway velocities, and the M-L sway distance. The M-L and A-P sway velocities, and M-L sway distance showed significantly large group effects (p<0.05), time effects (p<0.05), and group-by-time interaction (p<0.05). The post hoc analyses indicated that, following intervention, the 10CWST group showed more significant changes in the M-L and A-P sway velocities, and the M-L sway distance than the control group. Conclusion: These results suggest that the use of compelled weight shift in paretic lower limb training may be an effective method to improve balance ability in patients with stroke.

• 대한원격탐사학회지
• /
• 제28권5호
• /
• pp.489-499
• /
• 2012

이 논문에서는 원격탐사 자료의 분류를 목적으로 서로 다른 훈련 집단들과 분류자들로부터 생성된 분류 결과들을 결합하는 분류 틀을 제안하였다. 제안 분류 틀의 핵심 부분은 서로 다른 훈련 집단과 분류자들을 이용함으로써 분류 결과 사이의 다양성을 증가시켜서 결과적으로 분류 정확도를 향상시키는데 있다. 제안 분류 틀에서는 우선 서로 다른 샘플링 밀도를 가지는 서로 다른 훈련 집단들을 생성한 후에, 이들을 서로 다른 구분 능력을 나타내는 분류자들의 입력 훈련 자료로 사용한다. 그리고 초기 분류 결과들에 다수결 규칙을 적용하여 최종 분류 결과를 얻게 된다. 다중 시기 ENVISAT ASAR 자료를 이용한 토지 피복 분류사례 연구를 통해 제안 방법론의 적용 가능성을 검토하였다. 사례 연구에서 3개의 훈련 집단과 최대우도 분류자, 다층 퍼셉트론 분류자, support vector machine 등과 같은 3개의 분류자를 이용한 9개의 분류 결과를 결합하였다. 사례 연구 결과, 제안 분류 틀 안에서 토지 피복 구분에 관한 상호 보완적인 정보의 이용이 가능해져서 가장 높은 분류 정확도를 나타내었다. 서로 다른 결합들을 비교하였을 때, 다양성이 크지 않은 분류 결과들을 결합한 경우에는 분류 정확도의 향상이 나타나지 않았다. 따라서 다중 분류 시스템의 설계시 분류자들의 다양성을 확보하는 것이 중요함을 확인할 수 있었다.

• 문화기술의 융합
• /
• 제8권5호
• /
• pp.489-495
• /
• 2022

언어모델(Language Model)을 구축하기 위한 딥러닝 기법인 LSTM의 경우 학습에 사용되는 말뭉치의 전처리 방식에 따라 그 결과가 달라진다. 본 연구에서는 유명한 문학작품(기형도의 시집)을 말뭉치로 사용하여 LSTM 모델을 학습시켰다. 원문을 그대로 사용하는 경우와 조사/어미 등을 삭제한 경우에 따라 상이한 단어벡터 세트를 각각 얻을 수 있다. 이러한 전처리 방식에 따른 유사도/유추 연산 결과, 단어벡터의 평면상의 위치 및 언어모델의 텍스트생성 결과를 비교분석했다. 문학작품을 말뭉치로 사용하는 경우, 전처리 방식에 따라 연산된 단어는 달라지지만, 단어들의 유사도가 높고 유추관계의 상관도가 높다는 것을 알 수 있었다. 평면상의 단어 위치 역시 달라지지만 원래의 맥락과 어긋나지 않았고, 생성된 텍스트는 원래의 분위기와 비슷하면서도 이색적인 작품으로 감상할 수 있었다. 이러한 분석을 통해 문학작품을 객관적이고 다채롭게 향유할 수 있는 수단으로 딥러닝 기법의 언어모델을 활용할 수 있다고 판단된다.

• ETRI Journal
• /
• 제39권5호
• /
• pp.621-631
• /
• 2017

Abnormal samples are usually difficult to obtain in production systems, resulting in imbalanced training sample sets. Namely, the number of positive samples is far less than the number of negative samples. Traditional Support Vector Machine (SVM)-based anomaly detection algorithms perform poorly for highly imbalanced datasets: the learned classification hyperplane skews toward the positive samples, resulting in a high false-negative rate. This article proposes a new imbalanced SVM (termed ImSVM)-based anomaly detection algorithm, which assigns a different weight for each positive support vector in the decision function. ImSVM adjusts the learned classification hyperplane to make the decision function achieve a maximum GMean measure value on the dataset. The above problem is converted into an unconstrained optimization problem to search the optimal weight vector. Experiments are carried out on both Cloud datasets and Knowledge Discovery and Data Mining datasets to evaluate ImSVM. Highly imbalanced training sample sets are constructed. The experimental results show that ImSVM outperforms over-sampling techniques and several existing imbalanced SVM-based techniques.

• 대한인간공학회지
• /
• 제32권1호
• /
• pp.77-85
• /
• 2013

Objective: The aim of this study sets factors from previous research known to impact transfer effects as the independent variables, and examines their relationship with the dependent variables, near transfer effects and far transfer effects. Background: Transfer of Training refers to the application of what learners acquire knowledge and skills in training programs to their job. The ultimate goal of training is to apply what employees learn in training sessions to their workplace. In this sense, transfer of training has been a vital concern for training effectiveness. For training to be effective, trainees(learners) should be able to use what they learn in training program back on the job. Method: For this research purpose, this study conducted a survey on 170 nuclear operators in nuclear education and training center. Of these, survey result from the 167 recruits were sampled. Theoretical model of this study is based on Holton & Baldwin's(2003) distance model of transfer effects. This study sets transfer effects(near transfer, far transfer) as the main dependent variables. Meanwhile, the independent variables are trainee characteristics, training characteristics, organizational transfer climate. Each independent variable has subordinate variables. Subordinate variables of trainee characteristics are self-efficacy, motivation to learn, motivation to transfer and ability to transfer. Subordinate variables of training characteristics are training contents, ability of trainers, training design, training climate. The last Subordinate variables of organizational transfer climate are support of supervisors, support of peer, support of organization. Conclusion: As a analysis result, trainee characteristics appeared to be in effect only significant influence near far transfer of training, the effect of the far transfer of training, there is no significant. In addition, the training characteristics appeared to be having a significant influence on near and far transfer effects. Organizational transfer climate appeared to be having a significant influence on near and far transfer effects. Finally, near transfer effect appeared to be having a significant influence on far transfer effects. Application: Results of this analysis in the study to training organization and training characteristics of the transition environment effects on nuclear power institutions and operators training organization having a significant impact that says. The transfer of knowledge and technology, as well as that can be applied to a new situation in terms of education and training are important characteristics.