• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.7C
• /
• pp.428-434
• /
• 2011

Recently, subspace analysis has raised its performance to a higher level through the adoption of kernel-based nonlinearity. Especially, the radial basis function, based on its nonparametric nature, has shown promising results in face recognition. However, due to the endemic small sample size problem of face data, the conventional kernel-based feature extraction methods have difficulty in data representation. In this paper, we introduce a novel variant of the RBF kernel to alleviate this problem. By adopting the concept of the nearest feature line classifier, we show both effectiveness and generalizability of the proposed method, particularly regarding the small sample size issue.

• Journal of Technology Innovation
• /
• v.2 no.1
• /
• pp.58-88
• /
• 1994

There have been fierce debates on the issue of generalizability of management functions, techniques, and practices between public and private sectors. Recognizing the growing concerns for the similarities and differences in R&D settings between the two sectors, we compared three public and three private R&D institutes in terms of environment and resources, project management, and R&D productivity. Our results show that there coexist similarities and differences at the same time between the two types of R&D institutes. So, we cannot conclude definitely whether R&D management is really generic or not. But, the authors weakly reject the assertion of generic property of management as far as R&D management is concerned.

• Korean journal of food and cookery science
• /
• v.19 no.2
• /
• pp.155-164
• /
• 2003

The purpose of this study was to examine, in a service context, construct validity and generalizability of widely used and accepted measures of perceived organizational support, job satisfaction, organizational commitment, and service duality, and to test each measures' predictive utility in this context with path analysis. Of 350 subjects, 309 subjects participated in the analysis. Descriptive statistics (frequencies), exploratory factor analysis, reliability analysis, zero-order partial correlation analysis, and confirmatory factor analysis were used for this study. The findings from this study are as follows. First, perceived organizational support significantly influenced job satisfaction, organizational commitment. and service quality. Second, Job satisfaction had a directional impact upon organizational commitment and service quality. Third, organizational commitment showed to have a predictive impart on service quality. Finally, the results of the study provide some insight into the types of internal marketing strategies that can be applied successfully by operators of hotel F & B departments.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.165-165
• /
• 2023

Streamflow prediction is a critical task in water resources management and essential for planning and decision-making purposes. However, the streamflow prediction is challenging due to the complexity and non-linear nature of hydrological processes. The transfer learning is a powerful technique that enables a model to transfer knowledge from a source domain to a target domain, improving model performance with limited data in the target domain. In this study, we apply the transfer learning using the Informer model, which is a state-of-the-art deep learning model for streamflow prediction. The model was trained on a large-scale hydrological dataset in the source basin and then fine-tuned using a smaller dataset available in the target basin to predict the streamflow in the target basin. The results demonstrate that transfer learning using the Informer model significantly outperforms the traditional machine learning models and even other deep learning models for streamflow prediction, especially when the target domain has limited data. Moreover, the results indicate the effectiveness of streamflow prediction when knowledge transfer is used to improve the generalizability of hydrologic models in data-sparse regions.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.862-873
• /
• 2023

Determining whether an autonomous self-driving agent is in the middle of an intersection can be extremely difficult when relying on visual input taken from a single camera. In such a problem setting, a wider range of views is essential, which drives us to use three cameras positioned in the front, left, and right of an agent for better intersection recognition. However, collecting adequate training data with three cameras poses several practical difficulties; hence, we propose using data collected from one camera to train a three-camera model, which would enable us to more easily compile a variety of training data to endow our model with improved generalizability. In this work, we provide three separate fusion methods (feature, early, and late) of combining the information from three cameras. Extensive pedestrian-view intersection classification experiments show that our feature fusion model provides an area under the curve and F1-score of 82.00 and 46.48, respectively, which considerably outperforms contemporary three- and one-camera models.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.22 no.1
• /
• pp.1-12
• /
• 2020

As one of the essential resources in the agricultural process, soil moisture has been carefully managed by predicting future changes and deficits. In recent years, statistics and machine learning based approach to predict soil moisture has been preferred in academia for its generalizability and ease of use in the field. However, little is known that machine learning based soil moisture prediction is applicable in the situation of South Korea. In this sense, this paper aims to examine 1) whether publicly available weather data generated in South Korea has sufficient quality to predict soil moisture, 2) which machine learning algorithm would perform best in the situation of South Korea, and 3) whether a single machine learning model could be generally applicable in various regions. We used various machine learning methods such as Support Vector Machines (SVM), Random Forest (RF), Extremely Randomized Trees (ET), Gradient Boosting Machines (GBM), and Deep Feedforward Network (DFN) to predict future soil moisture in Andong, Boseong, Cheolwon, Suncheon region with open source weather data. As a result, GBM model showed the lowest prediction error in every data set we used (R squared: 0.96, RMSE: 1.8). Furthermore, GBM showed the lowest variance of prediction error between regions which indicates it has the highest generalizability.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.5
• /
• pp.323-330
• /
• 2018

This study examined the fairness of the teaching aptitude and personality test assigned to pre-service engineering teachers in a graduate school of education based on measurement traits. For this study, we analyzed the teaching aptitude and personality test scores of 99 students enrolled in engineering education in a graduate school of education located in the Seoul metropolitan area from 2013 to 2017. The main results were as follows. First, the estimated variance due to residual was generally the highest, followed by nesting of items within domains, pre-service engineering teachers, interactions of pre-service engineering teachers with domains, domains, and occasions. Second, dependability coefficients were better indicators than Cronbach's because the latter may have been overestimated by applying the traditional reliability coefficient in inappropriate manners. Third, the teaching aptitude and personality test can be applied to pre-service engineering teachers in a graduate school of education based on empirical evidence considering dependability coefficients. Fourth, a total of 96 items from the original 210 items, with 2 occasions and 12 domains containing 8 items in each domain, were optimal measurement conditions to reach adequate degrees of reliability based on the total number of items. Finally, the results were discussed, the study limitations described and future research directions proposed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.1
• /
• pp.318-326
• /
• 2011

The purpose of this study is to investigate whether standardized patient(SP) can be used as a reliable examiner in Objective Structured Clinical Examination(OSCE). 4 SPs and 4 faculties who have more than 2 years experience of OSCE scoring were selected. For 1 assignment 2 members of faculty and 2 SPs were designated as raters. SPs were educated for assessing 2 technical skills, male Foley catheter insertion and wound dressing, for 8 hours (4 hours / day, each topic). The definition, method, cautions and complications for each of procedural skills were covered in the education. Theoretical lectures, video learning, faculty demonstration and practical training on mannequins were employed. The 8 raters were standardized for an hour with simulated OSCE scoring using previous videos on the day before the OSCE. Each assessment was composed of 14 checklists and 1 global rate. The allotted time for each assignment was 5minutes and for evaluation time 2 minutes per student. The evaluation from the faculty and SPs were compared and analyzed with the GENOVA program. The overall generalizability coefficient (G coefficient) was 0.839 from two cases of OASTS. The reliability of the raters was high, 0.946. The inter-rater agreement between faculty group and SP group was 0.949 for checklist and 0.908 for global rating. Therefore SPs can play a role of raters in OSCE for procedural skills, if they are given the appropriate training.

• Korean Journal of Radiology
• /
• v.24 no.4
• /
• pp.294-304
• /
• 2023

Objective: We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods. Materials and Methods: We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired t-test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume. Results: The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all P < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998). Conclusion: Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.

• Research in Community and Public Health Nursing
• /
• v.13 no.1
• /
• pp.98-114
• /
• 2002

Purpose: This review examined literature relevant to adolescent's health behavior in order to identify key behaviors and factors related to health behaviors for targeting health promotion interventions. Method: A critical review of 29 research articles was carried out using the guidelines suggested by Cooper. Result: The majority of the studies were descriptive and cross-sectional. Generally. the study includes sub-dimensions such as general hygiene and daily life habit, safety and accident prevention, nutrition and eating (tobacco, drinking), exercise, mental health and stress management, health duty (drug, health examination, disease prevention). Factors highly related to health behaviors were age, living areas, economic status, parent health behaviors, parent health concern, social support, friends influence, self-efficacy, self-esteem, locus of control, and the perceived health status. Sex, parent education and health knowledge were not related to health behaviors of adolescents. Conclusion: Several conceptual and methodological problems were identified in the studies review, such as restricted conceptualization of health behaviors and sampling issues which limit the generalizability of the study outcomes. Further research is needed to enhance the concept clarification and generalizablity of the study results.