http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
의사결정나무 Random Forest를 이용한 스마트워치 이용자의 만족도와 추천의도에 대한 영향요인 분석
박경원 ( Park¸ Kyoungwon ),조성빈 ( Cho¸ Sungbin ) 한국경영공학회 2021 한국경영공학회지 Vol.26 No.3
Purpose This study analyzes influencing factors on smart phone user's perceived satisfaction, continuous use intention, and recommendation intention. Methods The influencing factors include usefulness, convenience, appearance, enjoyment, innovation, security, and privacy, whereas response is measured through satisfaction, continuous use intention, and recommendation intention. Two methods are employed - decision tree using GINI index and random forest approach. Results The analysis results revealed that most significant factors for user’s satisfaction and continuous use intention are usefulness in daily life and that usefulness in daily life and fashion are influential to recommendation intention. According to the Random Forest Model, the importance of usefulness in daily life and efficient handling of tasks were crucial for satisfaction level, the importance of rapid access to information for continuous use intention, and a combination of fashion for recommendation intention. Conclusion The findings of this study are consistent with existing literature in the sense that the usefulness is important. We additionally suggest that fast information accessibility and fashion should be recognized as important factors in smart watch industry.
Kyoungwon Jung,John Cook-Jong Lee,Rae Woong Park,Dukyong Yoon,Sungjae Jung,Younghwan Kim,Jonghwan Moon,Yo Huh,Junsik Kwon 대한중환자의학회 2016 Acute and Critical Care Vol.31 No.3
Background: Injury severity scoring systems that quantify and predict trauma outcomes have not been established in Korea. This study was designed to determine the best system for use in the Korean trauma population. Methods: We collected and analyzed the data from trauma patients admitted to our institution from January 2010 to December 2014. Injury Severity Score (ISS), Revised Trauma Score (RTS), and Trauma and Injury Severity Score (TRISS) were calculated based on the data from the enrolled patients. Area under the receiver operating characteristic (ROC) curve (AUC) for the prediction ability of each scoring system was obtained, and a pairwise comparison of ROC curves was performed. Additionally, the cut-off values were estimated to predict mortality, and the corresponding accuracy, positive predictive value, and negative predictive value were obtained. Results: A total of 7,120 trauma patients (6,668 blunt and 452 penetrating injuries) were enrolled in this study. The AUCs of ISS, RTS, and TRISS were 0.866, 0.894, and 0.942, respectively, and the prediction ability of the TRISS was significantly better than the others (p < 0.001, respectively). The cut-off value of the TRISS was 0.9082, with a sensitivity of 81.9% and specificity of 92.0%; mortality was predicted with an accuracy of 91.2%; its positive predictive value was the highest at 46.8%. Conclusions: The results of our study were based on the data from one institution and suggest that the TRISS is the best prediction model of trauma outcomes in the current Korean population. Further study is needed with more data from multiple centers in Korea.
Cortical Thickness and Brain Glucose Metabolism in Healthy Aging
Kyoungwon Baik,Seun Jeon,Soh-Jeong Yang,Yeona Na,Seok Jong Chung,Han Soo Yoo,Mijin Yun,Phil Hyu Lee,Young H. Sohn,Byoung Seok Ye 대한신경과학회 2023 Journal of Clinical Neurology Vol.19 No.2
Background and Purpose We aimed to determine the effect of demographic factors on cortical thickness and brain glucose metabolism in healthy aging subjects. Methods The following tests were performed on 71 subjects with normal cognition: neurological examination, 3-tesla magnetic resonance imaging, 18F-fluorodeoxyglucose positronemission tomography, and neuropsychological tests. Cortical thickness and brain metabolism were measured using vertex- and voxelwise analyses, respectively. General linear models (GLMs) were used to determine the effects of age, sex, and education on cortical thickness and brain glucose metabolism. The effects of mean lobar cortical thickness and mean lobar metabolism on neuropsychological test scores were evaluated using GLMs after controlling for age, sex, and education. The intracranial volume (ICV) was further included as a predictor or covariate for the cortical thickness analyses. Results Age was negatively correlated with the mean cortical thickness in all lobes (frontal and parietal lobes, p=0.001; temporal and occipital lobes, p<0.001) and with the mean temporal metabolism (p=0.005). Education was not associated with cortical thickness or brain metabolism in any lobe. Male subjects had a lower mean parietal metabolism than did female subjects (p<0.001), while their mean cortical thicknesses were comparable. ICV was positively correlated with mean cortical thickness in the frontal (p=0.016), temporal (p=0.009), and occipital (p=0.007) lobes. The mean lobar cortical thickness was not associated with cognition scores, while the mean temporal metabolism was positively correlated with verbal memory test scores. Conclusions Age and sex affect cortical thickness and brain glucose metabolism in different ways. Demographic factors must therefore be considered in analyses of cortical thickness and brain metabolism.