• Korea Trade Review
• /
• v.47 no.2
• /
• pp.69-88
• /
• 2022

This paper aims to predict Busan's regional product and employment using the logistic regression models and machine learning models. The following are the main findings of the empirical analysis. First, the OLS regression model shows that the main industries such as electricity and electronics, machine and transport, and finance and insurance affect the Busan's income positively. Second, the binomial logistic regression models show that the Busan's strategic industries such as the future transport machinery, life-care, and smart marine industries contribute on the Busan's income in large order. Third, the multinomial logistic regression models show that the Korea's main industries such as the precise machinery, transport equipment, and machinery influence the Busan's economy positively. And Korea's exports and the depreciation can affect Busan's economy more positively at the higher employment level. Fourth, the voting ensemble model show the higher predictive power than artificial neural network model and support vector machine models. Furthermore, the gradient boosting model and the random forest show the higher predictive power than the voting model in large order.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.2
• /
• pp.13-21
• /
• 1996

The necessity and usefulness of higher-order neural networks have been well-known since early days of neurocomputing. However the explosive number of terms has hampered the design and training of such networks. In this paper we present an evolutionary learning method for efficiently constructing problem-specific higher-order neural models. The crux of the method is the neural tree representation employing both sigma and pi units, in combination with the use of an MDL-based fitness function for learning minimal models. We provide experimental results in classification and prediction problems which demonstrate the effectiveness of the method. I. Introduction topology employs one hidden layer with full connectivity between neighboring layers. This structure has One of the most popular neural network models been very successful for many applications. However, used for supervised learning applications has been the they have some weaknesses. For instance, the fully mutilayer feedforward network. A commonly adopted connected structure is not necessarily a good topology unless the task contains a good predictor for the full *d*dWs %BH%W* input space.

• Wind and Structures
• /
• v.36 no.6
• /
• pp.393-404
• /
• 2023

Skewness and kurtosis are important higher-order statistics for simulating non-Gaussian wind pressure series on low-rise buildings, but their predictions are less studied in comparison with those of the low order statistics as mean and rms. The distribution gradients of skewness and kurtosis on roofs are evidently higher than those of mean and rms, which increases their prediction difficulty. The conventional artificial neural networks (ANNs) used for predicting mean and rms show unsatisfactory accuracy in predicting skewness and kurtosis owing to the limited capacity of shallow learning of ANNs. In this work, the deep neural networks (DNNs) model with the ability of deep learning is introduced to predict the skewness and kurtosis on a low-rise building. For obtaining the optimal generalization of the DNNs model, the hyper parameters are automatically determined by Bayesian Optimization (BO). Moreover, for providing a benchmark for future studies on predicting higher order statistics, the data sets for training and testing the DNNs model are extracted from the internationally open NIST-UWO database, and the prediction errors of all taps are comprehensively quantified by various error metrices. The results show that the prediction accuracy in this study is apparently better than that in the literature, since the correlation coefficient between the predicted and experimental results is 0.99 and 0.75 in this paper and the literature respectively. In the untrained cornering wind direction, the distributions of skewness and kurtosis are well captured by DNNs on the whole building including the roof corner with strong non-normality, and the correlation coefficients between the predicted and experimental results are 0.99 and 0.95 for skewness and kurtosis respectively.

• Journal of Digital Convergence
• /
• v.17 no.11
• /
• pp.509-515
• /
• 2019

The purpose of this study is to analyze the learning needs for lifelong education of the baby boom generation, the role of higher education and to reorganization plan the lifelong learning system at higher education levels to realize the lifelong learning system. In order to do this, this study analyzes the present condition of lifelong learning for each age group in South Korea, especially the participation and learning needs of the baby boom generation. Based on this, present lifelong learning reorganization plans in universities examine for the realization of a lifelong learning system.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.352-354
• /
• 2006

패턴완성(Pattern Completion)은 사용되는 패턴 성분들 사이의 higher-order correlation 정보가 중요한 의미를 가질 수 있는 기계학습 문제 중 하나이다. higher-order correlation은 확률라이브러리모델(Probabilistic Library Model)로 구현되는 hypernetwork 개념을 도입해서 나타낼 수 있다. 하지만 확률라이브러리모델을 사용하여 higher-order 정보를 나타내려할 때 초기라이브러리가 모든 가능한 조합의 원소들을 가지도록 구성하기는 쉽지 않다. 그 대안으로 초기라이브러리 구성 시 학습패턴들을 subsampling하여 적은 숫자의 원소들만으로 higher-order correlation의 근사치를 나타내게 할 수 있다. 본 논문에서는 이와 같이 subsampling이 사용되어 구성된 확률라이브러리모델을 이용한 패턴완성시의 correlation의 order에 따른 효과를 분석하여 본다.

• Journal of Computing Science and Engineering
• /
• v.4 no.1
• /
• pp.80-95
• /
• 2010

In order to truly integrate e-Learning system into regular curriculum at a university, mobile access to Learning Management Systems has to be enabled. Mobile devices have the potential to be integrated into the classroom, because they contain unique characteristics such as portability, social interactivity, context sensitivity, connectivity and individuality. Adoption of Learning Management Systems by students is still on the low rate, mostly because of poor usability of existing e-Learning systems. Our initial research has confirmed this hypothesis. Usability issue is rising to the higher level on the mobile platform, because of the mobile devices' limited screen size, input interfaces and bandwidth, and also because of the context of use. Our second hypothesis was that it is wrong to consider a mobile device as a surrogate for desktop or laptop personal computer (PC). By just adopting the existing Learning Management System on mobile devices with adaptive technologies such as Google proxy, we do not acquire the satisfactory results. Usability can prove to be even lower compared to desktop application. One possible solution to the problem could be development of rich client applications for today's mobile devices that would raise the usability to a higher level. We developed a PocketPC prototype application by using user-centered design principles, which we presented as a third alternative in usability research conducted among university students. Results gathered in such a way have confirmed that development of e-Learning system, in order to be widely accepted by students, needs to have the user(student) in the center of development process.

• Journal of Korean Academy of Nursing
• /
• v.29 no.4
• /
• pp.963-976
• /
• 1999

This study was undertaken to investigate the general characteristics of students, which include the degree of satisfaction, motives of admission, the recognition of advantages and disadvantages, opinion of students on self-directed learning, and planning and anticipatory effects after graduation. Data was collected through a questionnaire survey over a period of four months, from May 1997 to August 1997. The subjects used for this study consisted of 322 RN students sampled from six RN-to-BSN programs in Korea using the census sampling method. Statistical methods employed for this study included discriptive statistics, M ANOVA, and F-test. The results of the study are as follows 1. The RN students' motives of admission to RN-to-BSN programs were ‘for personal advancement’, ‘to earn a BSN degree’, and ‘for professional development’ in this order. 2. The RN students' responses to the advantages of RN-to-BSN programs were ‘acquisition of new knowledge and a BSN degree’ and ‘to gain professional thinking and a broader view’, while as the disadvantages of RN-to-BSN programs were ‘geographical isolation of institutions’, ‘limitation of information’, and ‘underdeveloped school environments’ in this order. 3. The survey based on opinions toward self-directed learning showed that there was a need of detailed guidelines for self-directed learning. Most agreed that it was a very effective learning method for a RN student, and the self-directed learning method Increases motives for learning. 4. The students' anticipatory effect after graduation were ‘self-achievement’, ‘development of professional skills’, and ‘admission to post-graduate school or programs to study abroad’. 5. The students were very satisfied with the quality of faculty members, and satisfied with the quality of lectures and teaching. However, students were unsatisfied with rented lecture rooms, and very unsatisfied with self-directed learning methods. 6. School nurses showed higher statistical significances in the need for teaching material and anticipatory effect after graduation than other RN students working in hospitals and public health agencies. Also, school nurses, public health nurses, and industry nurses showed higher statistical significances in motives of admission than RN students working in hospitals. Further more, staff nurses, school nurses, and industry nurses showed higher levels of satisfaction toward a RN-to-BSN programs than nurses in higher positions, such as administrators or directors of nursing. 7 City residents were more satisfied with RN-to-BSN programs than rural residents. Otherwise, the rural residents had higher motives for admission, a bigger need for teaching materials, and recognition of the disadvantages of RN-to-BSN programs than city residents. Finally, RN students who earned below a monthly income of ￦1,000,000 showed higher motivation for admission than those who earned more than ￦1,000,000.

• Journal of Korean Physical Therapy Science
• /
• v.30 no.3
• /
• pp.84-90
• /
• 2023

Background: This study aimed to investigate the effects of flipped learning education on academic motivation and class satisfaction in physical therapy students. Design: Cross-sectional study. Methods: Participants included 72 physical therapy students (experimental group=36, control group=36). In order to compare the effects of flipped learning education, flipped learning and lecture-style learning were provided in a class titled Acticities of Daily Living and Practice. An independent t-test was used to compare academic motivation and class satisfaction between two groups. Results: The flipped learning group showed a significantly higher level of academic motivation and class satisfaction compared to the traditional learning group (p<0.05). Conclusion: These results showed that flipped learning education is an effective learning strategy for improving the academic motivation and class satisfaction of physical therapy students.

• Journal of Information Technology Services
• /
• v.10 no.3
• /
• pp.61-76
• /
• 2011

The purpose of this paper was to design and implement effective learning model for internet ethics education, following the learning principle and procedure of PBL(Problem-Based Learning) which is one of the constructivism teaching-learning theories(, and to apply it). In this learning model, online learning and face-to-face classes were systematically combined for achieving the teaching-learning goals and the main module for online learning run on Moodle, an open source LMS(Learning Management System). It is possible for learner to participate actively in creation of micro-contents and reorganize contents using various SNS(Social Network Service). The learner can achieve the learner-oriented learning and select micro-contents in order to reorganize the personalized learning contents to take advantage of SNS among learners. To examine educational effectiveness of the proposed learning model, an experimental study was conducted through the education content and method to the subjects of two classes in the second-grade of university located in OO city. 60 students(treatment group=30, control group=30) participated in the experiment. The result statistically verified that the proposed learning method is more effective in cultivating consciousness of internet ethics than the face-to-face PBL learning method. The results of this paper also showed that a lecture using blended learning is efficient in achieving learning performance and that learners responded positively(, which are indicating that the higher effectiveness of learning would be expected) by forming connectedness among learners using SNS. The results of this paper showed that a lecture using blended learning is effectiveness in achieving learning performance and that learners responded positively, which are indicating that the higher effectiveness of learning would be expected by forming connectedness among learners using SNS.

• 한국디지털정책학회:학술대회논문집
• /
• 2004.11a
• /
• pp.283-294
• /
• 2004

Within the rapidly changing environment of global economics, the environment of higher education in the universities & companies, also, has been, encountering various changes. Popularization on higher education related to lifetime education system, putting emphasis on the productivity of education services and the acquisition of competitiveness through the market of open education, the breakdown of the ivory tower and the Multiversitization of universities & companies, importance of obtaining information in the universities & companies, and cooperation between domestic and oversea universities, industry and educational system must be acquired. Therefore, in order to adequately cope with these kinds of rapid changes in the education environment, operating E-Learning Education & company by utilizing various information technologies and its fixations such as Internet, E-mail. CD-ROMs. Interactive Video Networks (Video Conferencing, Video on Demand), CableTV etc., which has no time or location limitation, is needed.