• Journal of the Korean Data and Information Science Society
• /
• 제14권4호
• /
• pp.965-974
• /
• 2003

In this paper we propose an incremental classification of multi-class data set by LS-SVM. By encoding the output variable in the training data set appropriately, we obtain a new specific output vectors for the training data sets. Then, online LS-SVM is applied on each newly encoded output vectors. Proposed method will enable the computation cost to be reduced and the training to be performed incrementally. With the incremental formulation of an inverse matrix, the current information and new input data are used for building another new inverse matrix for the estimation of the optimal bias and lagrange multipliers. Computational difficulties of large scale matrix inversion can be avoided. Performance of proposed method are shown via numerical studies and compared with artificial neural network.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.386-389
• /
• 2008

It is important that the training stage of a supervised classification is designed to provide the spectral information. On the design of the training stage of a classification typically calls for the use of a large sample of randomly selected pure pixels in order to characterize the classes. Such guidance is generally made without regard to the specific nature of the application in-hand, including the classifier to be used. An approach to the training of a support vector machine (SVM) classifier that is the opposite of that generally promoted for training set design is suggested. This approach uses a small sample of mixed spectral responses drawn from purposefully selected locations (geographical boundaries) in training. A sample of such data should, however, be easier and cheaper to acquire than that suggested by traditional approaches. In this research, we evaluated them against traditional approaches with high-resolution satellite data. The results proved that it can be used small mixed pixels to derive a classification with similar accuracy using a large number of pure pixels. The approach can also reduce substantial costs in training data acquisition because the sampling locations used are commonly easy to observe.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권10호
• /
• pp.1259-1265
• /
• 2004

분류학습에서 높은 정확도를 유지하기 위해서는 충분한 분류 데이타가 필요하게 되는데 분류 데이타는 미 분류 데이타보다 생성하기가 어려운 경우가 많다. 따라서 미 분류 데이타를 활용하여 분류의 정확도를 향상시키는 것은 큰 효용성을 가지며 이러한 미 분류 데이타를 활용하는 대표적인 학습방법 중의 하나는 협력학습(co-training) 알고리즘이다. 이는 데이타를 두 개의 독립적인 속성그룹으로 나누어 두개의 분류자로 학습한 후 미 분류 데이타를 분류하고 그중 가장 신뢰성이 높은 데이타를 분류 데이터에 포함하고 이를 반복하는 학습모델이다. 하지만 이 방법은 전체 데이타의 속성을 독립적인 두개의 집합으로 분할하여야하는 제약이 있다. 따라서 본 연구에서는 이와 같은 문제점을 개선하여 보통의 데이터베이스에 적용시킬 수 있는 새로운 협력학습방법을 제시 하고자한다. 즉. 두 개의 독립적인 속성 그룹으로 나누는 가정을 따르지 않고 전체 속성을 사용할 수 있으며 두 개 이상의 분류자를 사용하는 새로운 협력학습방법을 제안하였다.

• 한국응급구조학회지
• /
• 제19권2호
• /
• pp.99-115
• /
• 2015

Purpose: This study aimed to provide basic data for clinical training program development by analyzing the operating conditions and satisfaction in a clinical training program for 119 emergency medical technicians (EMTs) in South Korea. Methods: Data from 84 EMTs were collected on June 19, 2014. We administered a 64-item questionnaire about operating conditions and satisfaction in the clinical training program, and analyzed data (SPSS v 21.0). Results: The degree of performance in the field, importance of the item in the field, and level of difficulty were 3.36, 4.23, and 3.21, respectively. In the number of times that an item was directly performed according to the subjects' general characteristics a statistically difference in sex (p = .000), duty (p =.021), and total working time of trainees (p = .002). The subjects' total satisfaction score was 3.77. The difference in satisfaction according to the subjects' characteristics was a statistically significant in terms of sex (p = .016) and clinical training area (p = .005). Conclusion: A more efficient training system for hospital clinical training courses should be developed. The operation condition analyzed in this research may contribute to the improvement of the performance of EMTs.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.1075-1087
• /
• 2020

Aviation ICT technology is a convergence technology between aviation and electronics, and has a wide variety of applications, including navigation and education. Among them, in the field of aerial pilot training, there are many problems such as the possibility of accidents during training and the lack of coping skills for various situations. This raises the need for a simulated pilot training system similar to actual training. In this paper, pilot training data were collected in pilot training system using VR/AR to increase immersion in flight training, and Customized Pilot Training Platform with Collaborative Deep Learning in VR/AR Environment that can recommend effective training courses to pilots is proposed. To verify the accuracy of the recommendation, the performance of the proposed collaborative deep learning algorithm with the existing recommendation algorithm was evaluated, and the flight test score was measured based on the pilot's training data base, and the deviations of each result were compared. The proposed service platform can expect more reliable recommendation results than previous studies, and the user survey for verification showed high satisfaction.

• 성인간호학회지
• /
• 제22권2호
• /
• pp.200-210
• /
• 2010

Purpose: The purpose of this study was to examine the training effectiveness and behavior towards the elderly of 180 caregiver trainees. Methods: Data were collected from five caregiver training institutions located in G city. All subjects were surveyed about the training effectiveness and behavior towards the elderly by using the Training Effectiveness Scale and the Behavior towards the Elderly Scale. Data were analyzed by SPSS/WIN 12.0 program. Results: The study subjects gained a training effectiveness score of 3.84 out of 5 points and a behavior towards the elderly score 3.40 out of 4 points. The training effectiveness differed significantly depending on subject's characteristics, intention to work as a caregiver, and hours of training. There were significant differences in behavior towards the elderly depending on their age and hours of training. The training effectiveness was significantly correlated with the level of behavior towards the elderly. Conclusion: These findings demonstrated the necessity of developing a level of educational training that will help improve caregiver trainees' care by positively changing their behavior towards the elderly.

• 한국경영과학회지
• /
• 제27권1호
• /
• pp.75-94
• /
• 2002

The development of Information technologies huts contributed on-line training as one of important education methods. On-line training In firms, which is similar to e-learning or virtual education, provides trainees with more education opportunities in diverse ways. It has developed a range of innovative services with an one-stop solution of education within the electronic sector. Also under the on-line training environment, trainees can undertake customized training packages at anytime and any places. Moreover, information technology allows both the trainers and other trainees to be decoupled in any of the elements of time, place, and space. Two research questions are investigated : what are the determinants affecting the on-line training effectiveness and how those variables effect the two aspects of training effectiveness: learning performance and transfer performance. Based on the previous literature conducted on the traditional training environment, the determinants of training effectiveness are derived. light hypotheses are developed based on literature reviews and tested by questionnaires survey data. The collected data have been analyzed by LISREL. It is found that the relationship between individual, organizational and on-line sloe design variables and training effectiveness (learning and transfer) are significant. The contribution and limitations of this research are also discussed tilth future studies.

• 대한원격탐사학회지
• /
• 제18권6호
• /
• pp.369-376
• /
• 2002

본 연구에서는 공간 영상 자료의 감독 분류에 있어, 분석자에 의하여 선정된 분류 항목별 교사 자료를 분광 특징별로 다수의 군집으로 분리하고, 각각의 군집을 새로운 분류 항목의 교사 자료로서 설정함으로써 분류 성능을 향상시킬 수 있는 기법을 제안하고자 한다 특징 분리를 통하여 생성된 교사 자료는 비교적 작은 값의 밴드별 분산값을 가질 뿐 아니라 정규분포 형태의 자료 분포를 보이게 되어 통계적 감독 분류 기법의 적용에 적합한 교사 자료로서의 성격을 가지게 된다. 제안된 기법은 부산 지역에 대한 Landsat TM 영상 자료를 이용하여 그 적용성이 시험되었으며, 기존의 통계적 분류 기법들에 의한 결과와 그 성능이 정성적으로 비교되었다. 시험 적용 결과, 본 기법은 분석자가 선정한 교사 자료의 분광적인 분포 형태에 관계없이 우수한 분류 성능을 나타내는 것으로 판단되며, 따라서 분류 항목의 설정 및 항목별 교사 자료의 선정에 있어 교사 자료의 분광적 특징에 대한 동일성을 유지하기 위한 노력을 줄여줄 것으로 기대된다.

• 대한원격탐사학회지
• /
• 제39권5_1호
• /
• pp.507-519
• /
• 2023

Multi-temporal optical images have been utilized for time-series monitoring of croplands. However, the presence of clouds imposes limitations on image availability, often requiring a cloud removal procedure. This study assesses the applicability of various machine learning algorithms for effective cloud removal in optical imagery. We conducted comparative experiments by focusing on two key variables that significantly influence the predictive performance of machine learning algorithms: (1) land-cover types of training data and (2) temporal variability of land-cover types. Three machine learning algorithms, including Gaussian process regression (GPR), support vector machine (SVM), and random forest (RF), were employed for the experiments using simulated cloudy images in paddy fields of Gunsan. GPR and SVM exhibited superior prediction accuracy when the training data had the same land-cover types as the cloud region, and GPR showed the best stability with respect to sampling fluctuations. In addition, RF was the least affected by the land-cover types and temporal variations of training data. These results indicate that GPR is recommended when the land-cover type and spectral characteristics of the training data are the same as those of the cloud region. On the other hand, RF should be applied when it is difficult to obtain training data with the same land-cover types as the cloud region. Therefore, the land-cover types in cloud areas should be taken into account for extracting informative training data along with selecting the optimal machine learning algorithm.

• 한국융합학회논문지
• /
• 제9권5호
• /
• pp.21-26
• /
• 2018

본 연구는 고용노동부가 운영하는 직업훈련 통합전산망인 'HRD-NET(http://hrd.go.kr)'을 통해 구직자가 필요로 하는 직업훈련 정보 등이 원활하게 제공되고 있는지를 확인하기 위해 질문게시판을 빅데이터 기법에 가장 최적화된 'R'프로그램을 이용해서 추출하였다. 따라서, 이를 통해 직업훈련제도의 유효성, 적절성, 시각화, 빈도 분석, 연관분석 등을 실시하였으며, 연구결과는 다음과 같다. 첫째, 직업훈련 카드발급 및 동영상 시청, 공인인증서 문제, 등록오류 이 발견되었으며, 둘째, 내일배움카드에 대한 노동관서에서의 관리 및 처리절차가 복잡하고 까다로워 제도개선이 필요한 것으로 나타났다. 또한, 교육훈련의 수강에 있어 훈련직종 및 과정, 훈련기관에 따라서 차등화 된 훈련비 시스템과 환급구조가 애로요인으로 작용하는 것으로 분석되었다. 본 논문 기초로 하여 향후 고용노동부의 훈련시스템 뿐만 아니라 정부부처의 다양한 훈련 전산망시스템에 대한 전반적인 빅데이터 분석을 통한 개선점 등을 연구하고자 한다.