• Neurospine
• /
• 제15권4호
• /
• pp.329-337
• /
• 2018

Objective: Machine learning algorithms excel at leveraging big data to identify complex patterns that can be used to aid in clinical decision-making. The objective of this study is to demonstrate the performance of machine learning models in predicting postoperative complications following anterior cervical discectomy and fusion (ACDF). Methods: Artificial neural network (ANN), logistic regression (LR), support vector machine (SVM), and random forest decision tree (RF) models were trained on a multicenter data set of patients undergoing ACDF to predict surgical complications based on readily available patient data. Following training, these models were compared to the predictive capability of American Society of Anesthesiologists (ASA) physical status classification. Results: A total of 20,879 patients were identified as having undergone ACDF. Following exclusion criteria, patients were divided into 14,615 patients for training and 6,264 for testing data sets. ANN and LR consistently outperformed ASA physical status classification in predicting every complication (p < 0.05). The ANN outperformed LR in predicting venous thromboembolism, wound complication, and mortality (p < 0.05). The SVM and RF models were no better than random chance at predicting any of the postoperative complications (p < 0.05). Conclusion: ANN and LR algorithms outperform ASA physical status classification for predicting individual postoperative complications. Additionally, neural networks have greater sensitivity than LR when predicting mortality and wound complications. With the growing size of medical data, the training of machine learning on these large datasets promises to improve risk prognostication, with the ability of continuously learning making them excellent tools in complex clinical scenarios.

• 한국콘텐츠학회논문지
• /
• 제21권6호
• /
• pp.350-358
• /
• 2021

본 연구는 코로나19 상황에서 발달 장애 학생의 온라인 학습권 실태 분석과 증진 방안 제시를 목적으로 한다. 이를 위해 발달 장애 학생 자녀를 둔 학부모 충북지역 200인을 대상으로 한 설문조사 자료와 학부모 6인이 참여한 FGI 자료를 함께 사용하는 혼합방법론을 적용하였다. 주요 결과로, 가장 시급한 학습보조 제도는 보조인력 지원으로 확인되었고, 재택근무 등으로 자녀를 지원할 수 없는 응답자가 50.5%로 나타났다. FGI 자료 분석결과, '코로나19 온라인 학습 실태', '양육환경을 고려한 비대면 학습환경 개선'의 2가지 범주와 '화상수업 등 교수 방법 다양화', '필요 학습 자원 지원', '상황에 맞는 평가제도 도입', '돌봄 지원 강화', '건강 지원 확대'의 5가지 주제가 도출되었다. 이러한 연구 결과를 토대로 발달 장애 학생 온라인 수업 관련 법적 근거마련 검토, 학습지원 인력 파견 확대, 온라인 학습 환경 증진 대안 마련 등을 제안하였다.

• 대한공업교육학회지
• /
• 제34권2호
• /
• pp.286-303
• /
• 2009

본 연구는 한국에서의 산.학 e-Learning 운영 실태를 조사 분석하여 중국에서의 e-Learning 운영을 위한 발전 전략을 탐색하는 것이 목적이다. 연구방법은 주로 문화 기술적 연구 방법인 문헌 조사법, 전문가 상담법과 자료 분석법을 이용하였으며 연구 결과는 다음과 같다. 첫째, 한국의 정책적 경험을 거울삼아, 중국 정부가 기업 e-Learning에 관련된 정책 (기업 e-Learning 제도, LMS, 표준화, 품질 보장 등)을 지속적으로 수정.보완하여야 하며 국제 교류와 합작 등은 중국의 기업e -Learning 운영에 도움이 될 수 있을 것으로 조사되었다. 둘째, 한국의 e-Learning은 LMS의 표준화 및 콘텐츠 개발 등과 같이 실제적인 발전을 중시하여 좋은 효과를 얻고 있다. 그러나 중국에서의 e-Learning은 외형적인 관리제도만을 중시하였다. 따라서 e-Learning의 확대일로 시점에 있는 중국은 한국 사례를 통해 LMS의 표준화 및 콘텐츠의 질 관리 등과 같이 실제적인 발전 전략을 도모하여야 할 것이다. 셋째, 한국의 WBI, LMS, 팀워크 등의 학습 방법을 중국 e-Learning에 도입하면 개별화 학습과 협동학습이 적절히 혼합하여 발전할 수 있을 것이고 Blended Learning 등의 학습 방법을 중점적으로 다루어야 할 것이다.

• 한국게임학회 논문지
• /
• 제7권4호
• /
• pp.105-116
• /
• 2007

게임 환경에서의 학습은 다양한 분야에서 유용하게 활용될 수 있다. 그러나, 학습이 게임에서 만족스러운 결과를 산출하기까지는 많은 학습 시간이 요구된다. 이러한 점을 개선하기 위하여 학습시간을 단축시킬 수 있는 방법론들이 필요하다. 본 논문에서는 예측 정보를 이용한 Q-학습의 성능개선 방안을 제안한다. Q-학습 알고리즘에서는 Q-테이블의 각 상태별 선택된 액션을 참조한다. 참조한 값은 예측 모듈의 P-테이블에 저장되고, 이 테이블에서 출연 빈도가 가장 높은 값을 찾아 2차 보상 값을 갱신할 때 활용한다. 본 연구에서 제시한 방법은 상태내의 전이가 가능한 액션의 수가 많을수록 성능이 높아짐을 확인하였다. 또한 실험결과로 실험 중반 이후부터 제안한 방식이 기존 방식보다 평균 9%의 성능 향상을 보였다.

• Educational Technology International
• /
• 제17권2호
• /
• pp.229-251
• /
• 2016

This study was designed to investigate the relationship between middle school students' smart media competency and online learning outcomes. The context of this study was on online inquiry-based mathematics and science learning environment, and four-hundred and fifty-five (455) 7^th to 9^th grade students in Korea participated in this research. To assess students' smart device competency, Smart Media Literacy Quotient (SMLQ) which consisted of 18 items regarding the operation ability of smart media and its application (14 items) and positive beliefs of smart media (4 items) was administered to each student. The findings of this study first showed that students' smart media literacy varied according to their characteristics such as gender, grade, class (subject), and socio-economic status. Female students' scores were higher in overall smart media literacy operation and learning ability of smart media than male students. 7^th grade middle school students represented lower smart media literacy scores, compared to 8^th and 9^th graders. Also, minority students were significantly lower in smart media literacy, operation and learning ability of smart media, and positive belief of smart media than the non-minority students. Second, overall smart media literacy and operation and learning ability of smart media varied among high, medium, and low score achievers in inquiry tasks. Low scored students in inquiry tasks were significantly lower in overall smart media literacy and operation and learning ability of smart media than medium scored students. Lastly, smart media literacy also varied by students' dropout/completion. Students who dropped out reported significantly lower scores in overall smart media literacy, operation and learning ability of smart media, and positive belief of smart media.

• Educational Technology International
• /
• 제7권2호
• /
• pp.1-21
• /
• 2006

Blended learning has become one of the major trends in Korean corporate training. However, there has been scant research on blended learning in corporate trainings settings in Korea. The purpose of the present study was to explore current and future trends of blended learning in corporate and other training settings in Korea. 136 people from training related fields such as human resource development (HRD), training, and e-learning participated in this research. The findings revealed many interesting current trends and future expectations related to blended learning in training settings. In regards to the overall status of blended learning in Korean corporations, participants displayed strong interest in blended learning and were expecting that the importance of blended learning would grow in their organizations either modestly or significantly during the next few years. In addition, the perceptions of the respondents regarding the benefits of blended learning and the barriers to implementation in their respective organizations were analyzed.

• 산업경영시스템학회지
• /
• 제43권2호
• /
• pp.33-38
• /
• 2020

Anomaly detection of Machine Learning such as PCA anomaly detection and CNN image classification has been focused on cross-sectional data. In this paper, two approaches has been suggested to apply ML techniques for identifying the failure time of big time series data. PCA anomaly detection to identify time rows as normal or abnormal was suggested by converting subjects identification problem to time domain. CNN image classification was suggested to identify the failure time by re-structuring of time series data, which computed the correlation matrix of one minute data and converted to tiff image format. Also, LASSO, one of feature selection methods, was applied to select the most affecting variables which could identify the failure status. For the empirical study, time series data was collected in seconds from a power generator of 214 components for 25 minutes including 20 minutes before the failure time. The failure time was predicted and detected 9 minutes 17 seconds before the failure time by PCA anomaly detection, but was not detected by the combination of LASSO and PCA because the target variable was binary variable which was assigned on the base of the failure time. CNN image classification with the train data of 10 normal status image and 5 failure status images detected just one minute before.

• 한국과학교육학회지
• /
• 제27권9호
• /
• pp.765-777
• /
• 2007

과학 선행학습의 실태 조사와 과학 선행학습이 학생 들의 과학 학습 태도에 미치는 효과에 대해 연구 분석 하였다. 선행학습의 실태 조사에서는 학생들의 선행학습 경험 유 무,선행학습의 형태 (자기 및 타의 주도적 선행학습),선행학습 시작 동기로서 본인 의사 여부, 선행학습에서 문제해결 방법 및 선행학습에서 중요한 요인 등을 조사하였다. 선행학습이 과학 학습 태도에 미치는 영향을 흥미도, 자신감,학습의욕 및 가치 등 4가지 측면에서 연구하였다. 이들 4가지 측면에서 나타나는 효과를 학업 성취 수준,선행학습 형태,선행학습 시작 동기 및 선행학습에서 이해 정도 등의 관점에서 조사 분석하였다. 분석 결과를 살펴보면,자신감,학습의욕 및 가치 측면에서는, '자기주도적 선행학습'에서 보다 높은 긍정적 값이 나왔으며,이것은 '자기주도적 선행학습'을 수행함으로서 스스로 할 수 있다는 가능성,성취감에 따른 내재적 동기 유발,학습에 필요한 내용들을 스스로 찾아가는 자발적 학습 등 긍정적 인식의 결과로 볼 수 있다. 반면,흥미도 측면에서는 수업을 이끌어주는 교사와 또래 친구들 사이에서 형성되는 교감 등으로 인해 '타의주도적 선행학습'이 더 긍정적으로 나타났다. 이상의 연구 결과를 바탕으로,학습자들에게 자신감. 학습의욕 및 가치 등이 필요할 시에는 자기주도적으로 선행학습을 권장하는 것이 바람 직하며,흥미도를 고취시키기 위해서는 타의주도적으로 선행 학습하는 것이 바람직하다.

• International Journal of Computer Science & Network Security
• /
• 제23권6호
• /
• pp.13-16
• /
• 2023

This study aims to explore the status of e-learning in the public sector institutes of the Sukkur region in Pakistan. A survey was conducted to collect data from students and teachers regarding their awareness, access, and use of e-learning resources. The results showed that although there is a widespread use of the internet and mobile devices for accessing information, there is a lack of awareness and access to e-learning resources. Barriers to accessing e-learning content and a lack of familiarity with e-learning content development technologies were also identified. The study concludes that there is a need for improved e-learning facilities and curriculum in the public sector institutes of the Sukkur region in Pakistan. Recommendations are provided for developing a correctness-centered e-learning based curriculum that is tailored to the specific needs of the students in the region. It is hoped that the findings of this study will inform efforts to improve the teaching and learning process in the region and provide students with greater flexibility and access to study materials.

• 한국환경교육학회지:환경교육
• /
• 제14권1호
• /
• pp.107-126
• /
• 2001

The interest in environmental issues and the awareness of the importance of environmental education have been increasing. This research was carried out in part to respond to such a change, and it aims to search for and suggest ways to strengthen subject-based environmental education in Korea, the most significant part of the formal environmental education. One of the most important of this research was understanding the present status of environmental education of elementary, middle, and high schools in Korea, which was conducted by the questionnaire survey targeted to teachers on the subject-based environmental education. The survey was carried out comprehensively to include respondents from technical and home economics course as well as from vocational high schools. Through this survey, we gained information on the awareness of teachers and students on the objective, learning-teaching strategies and evaluation of environmental education as well as an understanding of the present status of environmental education in schools of Korea.