• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.741-747
• /
• 2022

Fatigue lowers an individual's ability and makes it difficult to perform work. As fatigue accumulates, concentration decreases and thus the possibility of causing a safety accident increases. Awareness of fatigue is subjective, but it is necessary to quantitatively measure the level of fatigue in the actual field. In previous studies, it was proposed to measure the level of fatigue by expert judgment by adding objective indicators such as bio-signal analysis to subjective evaluations such as multidisciplinary fatigue scales. However this method is difficult to evaluate fatigue in real time in daily life. This paper is a study on the fatigue classification model that determines the fatigue level of workers in real time using speech data recorded in the field. Machine learning models such as logistic classification, support vector machine, and random forest are trained using speech data collected in the field. The performance evaluation showed good performance with accuracy of 0.677 to 0.758, of which logistic classification showed the best performance. From the experimental results, it can be seen that it is possible to classify the fatigue level using speech signals.

• Journal of The Korean Association of Information Education
• /
• v.13 no.3
• /
• pp.313-323
• /
• 2009

The objective of this paper is an implementation of analysing and predicting functions to promote self-directed learning for student's performance assessment system in programming subjects. By adapting Rubric model, the proposed functions inform a student of the assessment criteria and level to be carried out with respects to two-way specifications such as rational ability, problem solving ability and creativity. The proposed system also provides a graphical results of each ability instead of assessment result, for better understanding and analyzing himself/herself based on to the performance assessment and the result. Moreover, the proposed system contains a method to predict future achievement result with moving average technique. Therefore, an academic achievement can be precisely determined by himself/herself to estimate self-directed learning. The teacher can provide different level of educational resources such as supplement learning, problem explains and private instructor etc., in order to maximize efficiency of education.

• Hwankyungkyoyuk
• /
• v.14 no.2
• /
• pp.28-39
• /
• 2001

The purpose of this study is to understand the characteristics and the differences regarding the teaching & learning objectives of Environment textbooks for middle school students with the consideration of the 7th Korean National Curriculum. For this the teaching & teaming objectives of three Environment textbooks currently used categorized according to the domain frame of environmental education in the Report of UNESCO(1980). three Environment textbooks and their teacher's guide books are those printed by three companies(A, B, and C) and Joongahng co.. The five objective categories recommended by UNESCO are awareness, knowledge, attitude, skills and participation and six types of skills by National Curriculum Council of England are communication skills, numeracy skills, study skills, problem-solving skills, personal and social skills and information technology skills. It is showed that'Human and Environment'domain is emphasized roughly in the awareness and the knowledge section without any statement of the participation section, 'Environmental Problems and its Counter-plan'domain in the knowledge and the skills section, 'Environmental Conservation'domain in the skills and the participation section of objectives. It is revealed that the skills section of the teaching 8t learning objectives is mainly involved in 'Environmental Problems and its Counter-plan'domain and'Environmental Conservation' domain. According to the result of the analysis of the connectivity between the Environment Curriculum of the 7th Korean National Curriculum and the Environment textbooks regarding objectives stated in the sub-domain level, it says those are generally appropriate ones. But some objectives are emphasized weakly or not at all in several sub-domains such as'The living environment to keep','The environmental problems of the earth','Making environment pleasant'. It is proposed that the efforts to state objectives in the Environment textbooks evenly are needed to be paid (or the well-balanced teaching & teaming of the Environment subject.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.2
• /
• pp.665-673
• /
• 2013

The main objective of this study was to investigate the effect of learning organization on social worker's organizational commitment and turnover intention in the social welfare organization. For the research, learning organization was consisted of shared vision, personal mastery, team learning and system thinking on the P. Senge's learning organization model. The results of this study were summarized as follows: Mean analyses showed that social workers perceived the level of learning organization had a higher than medium. By using a hierarchical multiple regression, shared vision, personal mastery and team learning had a positive effect on the social workers' organizational commitment. Shared vision and team learning had a negative effect on the social workers' turnover intention. This study finally discusses theoretical implications for future study and practical implications for learning organization strategies on the results.

• Journal of People, Plants, and Environment
• /
• v.24 no.6
• /
• pp.651-662
• /
• 2021

Background and objective: This study identifies whether children's planning-organizing executive function can be significantly classified and predicted by home environment quality and wealth factors. Methods: For empirical analysis, we used the data collected from the 10th Panel Study on Korean Children in 2017. Using machine learning tools such as support vector machine (SVM) and random forest (RF), we evaluated the accuracy of the model in which home environment factors classify and predict children's planning-organizing executive functions, and extract the relative importance of variables that determine these executive functions by income group. Results: First, SVM analysis shows that home environment quality and wealth factors show high accuracy in classification and prediction in all three groups. Second, RF analysis shows that estate had the highest predictive power in the high-income group, followed by income, asset, learning, reinforcement, and emotional environment. In the middle-income group, emotional environment showed the highest score, followed by estate, asset, reinforcement, and income. In the low-income group, estate showed the highest score, followed by income, asset, learning, reinforcement, and emotional environment. Conclusion: This study confirmed that home environment quality and wealth factors are significant factors in predicting children's planning-organizing executive functions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3790-3803
• /
• 2018

Content-based image retrieval is an approach used to query images based on their semantics. Semantic based retrieval has its application in all fields including medicine, space, computing etc. Semantically generated binary hash codes can improve content-based image retrieval. These semantic labels / binary hash codes can be generated from unlabeled data using convolutional autoencoders. Proposed approach uses semi-supervised deep hashing with semantic learning and binary code generation by minimizing the objective function. Convolutional autoencoders are basis to extract semantic features due to its property of image generation from low level semantic representations. These representations of images are more effective than simple feature extraction and can preserve better semantic information. Proposed activation and loss functions helped to minimize classification error and produce better hash codes. Most widely used datasets have been used for verification of this approach that outperforms the existing methods.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.11a
• /
• pp.267-270
• /
• 1997

In this paper, we proposed an optimazation method using Genetic Algorithm for nonlinear system modeling. Fuzzy Neural Network(FNNs) was used as basic model of nonlinear system. FNNs was fused of Fuzzy Inference which has linguistic property and Neural Network which has learning ability and high tolerence level. This paper, We used FNNs which was proposed by Yamakawa. The FNNs was composed Simple Inference and Error Back Propagation Algorithm. To obtain optimal model, parameter of membership function, learning rate and momentum coefficient of FNNs are tuned using genetic algorithm. And we used simplex algorithm additionaly to overcome limit of genetic algorithm. For the purpose of evaluation of proposed method, we applied proposed method to traffic choice process and waste water treatment process, and then obtained more precise model than other previous optimization methods and objective model.

• Korean Journal of Adult Nursing
• /
• v.17 no.5
• /
• pp.697-708
• /
• 2005

Purpose: This study was to develop, implement, and evaluate an e-learning education program for improving practical knowledge and preventing nursing errors and adverse events of nurses working in the operating room (OR). Method: The e-learning program was developed and evaluated according to the following processes: 1) preparation phase 2) implementation phase 3) evaluation phase. In evaluation phase, the effectiveness was analyzed based on the Kirkpatrick's model. Results: The e-learning program consisted of OR basic nursing skills and techniques and nursing activities' manual based on the categories of nursing errors: surgical operation preparation, nursing skills and techniques, environment management, patient safety and comfort, and patient monitoring. The program was provided through on-line, http://cafe.daum.net/pnuhorn, for 4 weeks. The mean score(percent) of participants' satisfaction was $21.24{\pm}1.71$(68.2%). Their total knowledge level was significantly improved(Z=-3.00, p=.003) and specifically in the category of environment management(Z=-3.77, p<.001) and patient monitoring(Z=-2.46, p=.014). The occurrence of nursing errors or adverse events was a little decreased, but not statistically significant(Z=-3.10, p=.756). Conclusion: E-learning for nurses is one way of effective and efficient teaching-learning strategies. For better e-learning, it is important to develop the vital content of the education and objective measures for detecting nursing errors and adverse events.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.13 no.2
• /
• pp.265-282
• /
• 2002

The purpose of this study is to investigate the principles of school library media center program and to finds out present level and future outlook of the program implementation in primary and middle school. The fundamental objective of school is learning and school library functions as a link to support this objective. Therefore quality of education must always be linked to the library media programs. A questionaire which consists of 13 questions covering school library media center operation was designed to final out how learning-teaching media program is being practiced in Korea. Based on this study, it is concluded that there is significant difference between present practice level and desired future-oriented practice. It is hoped that this study will help planners in formulating school library policy to achieve educational goal of the school.

• Journal of Korea Multimedia Society
• /
• v.25 no.7
• /
• pp.895-902
• /
• 2022

Building segmentation using satellite imagery such as EO (Electro-Optical) and SAR (Synthetic-Aperture Radar) images are widely used due to their various uses. EO images have the advantage of having color information, and they are noise-free. In contrast, SAR images can identify the physical characteristics and geometrical information that the EO image cannot capture. This paper proposes a learning framework for efficient building segmentation that consists of a teacher-student-based privileged knowledge distillation and deformable convolution block. The teacher network utilizes EO and SAR images simultaneously to produce richer features and provide them to the student network, while the student network only uses EO images. To do this, we present objective functions that consist of Kullback-Leibler divergence loss and knowledge distillation loss. Furthermore, we introduce deformable convolution to avoid pixel-level noise and efficiently capture hard samples such as small and thin buildings at the global level. Experimental result shows that our method outperforms other methods and efficiently captures complex samples such as a small or narrow building. Moreover, Since our method can be applied to various methods.