• Title/Summary/Keyword: Subjective learning

Search Result 321, Processing Time 0.027 seconds

Improvement of Support Vector Clustering using Evolutionary Programming and Bootstrap

  • Jun, Sung-Hae
    • International Journal of Fuzzy Logic and Intelligent Systems
    • /
    • v.8 no.3
    • /
    • pp.196-201
    • /
    • 2008
  • Statistical learning theory has three analytical tools which are support vector machine, support vector regression, and support vector clustering for classification, regression, and clustering respectively. In general, their performances are good because they are constructed by convex optimization. But, there are some problems in the methods. One of the problems is the subjective determination of the parameters for kernel function and regularization by the arts of researchers. Also, the results of the learning machines are depended on the selected parameters. In this paper, we propose an efficient method for objective determination of the parameters of support vector clustering which is the clustering method of statistical learning theory. Using evolutionary algorithm and bootstrap method, we select the parameters of kernel function and regularization constant objectively. To verify improved performances of proposed research, we compare our method with established learning algorithms using the data sets form ucr machine learning repository and synthetic data.

Comparison of Convolutional Neural Network Models for Image Super Resolution

  • Jian, Chen;Yu, Songhyun;Jeong, Jechang
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2018.06a
    • /
    • pp.63-66
    • /
    • 2018
  • Recently, a convolutional neural network (CNN) models at single image super-resolution have been very successful. Residual learning improves training stability and network performance in CNN. In this paper, we compare four convolutional neural network models for super-resolution (SR) to learn nonlinear mapping from low-resolution (LR) input image to high-resolution (HR) target image. Four models include general CNN model, global residual learning CNN model, local residual learning CNN model, and the CNN model with global and local residual learning. Experiment results show that the results are greatly affected by how skip connections are connected at the basic CNN network, and network trained with only global residual learning generates highest performance among four models at objective and subjective evaluations.

  • PDF

A Study on The Mediating Effect of Cognitive Flexibility on Academic Stress and Subjective Happiness of Nursing Students (간호대학생의 학업 스트레스와 주관적 행복감: 인지적 유연성의 매개효과)

  • JI YEONG NO;EUN JAE KIM
    • The Journal of the Convergence on Culture Technology
    • /
    • v.10 no.1
    • /
    • pp.1-9
    • /
    • 2024
  • The purpose of this study was to identify the degree of academic stress, subjective happiness, and cognitive flexibility of nursing students, and to identify the mediating effect of cognitive flexibility between learning stress and subjective happiness. The subject of the study was 186 nursing students from a university in J City. The data collection period was from October 4 to October 23, 2023, and the data were analyzed using SPSS 23.0. The results of the study showed a significant correlation between academic stress, cognitive flexibility, and subjective happiness among nursing students, and it was found that cognitive flexibility partially mediated the relationship between academic stress and subjective happiness. Therefore, in order to improve the subjective well-being of nursing students, it is necessary to develop and apply programs that can reduce academic stress and increase cognitive flexibility.

The impact to Learning-accomplishing rate on mutual cooperation studies of small group by different level class (수준별 체동수업에 의한 소집단 상호 협력 학습이 학업성취도에 미치는 영향)

  • 이종연;박세천
    • Journal of Educational Research in Mathematics
    • /
    • v.8 no.2
    • /
    • pp.587-603
    • /
    • 1998
  • Being in Learning-accomplishing rate on mutual cooperation studies of small group by different class, we can find that the sujective class of high group is much more efficient than the compared class of high group and that the subjective class of low group is more efficient than the compared class of low group as times goes. Moreover, in analysis of all directions on mathematical attitude, high group appears to be a great efficient in all areas such as confidence, flexibility, reaction, value, etc. and low group seems to have a little effect, by comparing the subjective class with the compared class. A. The result of a scholastic ability test High group had a great effect in the result of the first (Number and an expression) and second(An equation of a figure) scholastic ability test. As the time of research goes, the difference of average between the subjective class and the compared class has increased. Low group had no effect in the result of the first (Number and an expression) and the second (An equation of figure) scholastic ability test. But the difference of average grade between the subjective class and the compared class proved to be some efficient as time goes. (the first test is 0.94 and the second test is 3.33)We can find that the result of the third test (An exponent and log function) turned out be efficient. B. The change of mathematical attitudeHigh group had a great effect in confidence(+1.21), fiexibility(+1.92), will(-0.06), curiosity(+2.64), reaction(+1.50), value(+1.44). Low group appeared to be a little efficient in comparison between the subjective class and compared class. the average of both the subjective class and the compared class in low group decreased if not the result of pre-test but in that of pose-test. Therefore, we can find that the difference between mathematics of maddle school and that of high school gets bigger in Low group.C. The result of a question examinationAfter this research, the reaction that It is helpful to studying accomplishm- ent is 33.7%, the reaction that It is not helpful is 14.7%. After all, this research appears to be a positive reaction. After this study, the change of studying will seems to be much more not in Low group but in High group.

  • PDF

Learning Process Monitoring of e-Learning for Corporate Education (기업교육을 위한 인터넷 원격훈련 학습과정 모니터링 연구)

  • Kim, Do-Hun;Jung, Hyojung
    • The Journal of Industrial Distribution & Business
    • /
    • v.9 no.8
    • /
    • pp.35-40
    • /
    • 2018
  • Purpose - The purpose of this study is to conduct a monitoring study on the learning process of e-learning contents. This study has two research objectives. First, by conducting monitoring research on the learning process, we aim to explore the implications for content development that reflects future student needs. Second, we want to collect empirical basic data on the estimation of appropriate amount of learning. Research design, data, and methodology - This study is a case study of learner's learning process in e-learning. After completion of the study, an in-depth interview was made after conducting a test to measure the total amount of cognitive load and the level of engagement that occurred during the learning process. The tool used to measure cognitive load is NASA-TLX, a subjective cognitive load measurement method. In the monitoring process, we observe external phenomena such as page movement and mouse movement path, and identify cognitive activities such as Think-Aloud technique. Results - In the total of three research subjects, the two courses showed excess learning time compared to the learning time, and one course showed less learning time than the learning time. This gives the following implications for content development. First, it is necessary to consider the importance of selecting the target and contents level according to the level of the subject. Second, it is necessary to design the learner participation activity that meets the learning goal level and to calculate the appropriate time accordingly. Third, it is necessary to design appropriate learning support strategy according to the learning task. This should be considered in designing lessons. Fourth, it is necessary to revitalize contents design centered on learning activities such as simulation. Conclusions - The implications of the examination system are as follows. First, it can be confirmed that there is difficulty in calculating the amount of learning centered on learning time and securing objective objectivity. Second, it can be seen that there are various variables affecting the actual learning time in addition to the content amount. Third, there is a need for reviewing the system of examination of learning amount centered on 'learning time'.

Development of a Deep Learning-Based Automated Analysis System for Facial Vitiligo Treatment Evaluation (안면 백반증 치료 평가를 위한 딥러닝 기반 자동화 분석 시스템 개발)

  • Sena Lee;Yeon-Woo Heo;Solam Lee;Sung Bin Park
    • Journal of Biomedical Engineering Research
    • /
    • v.45 no.2
    • /
    • pp.95-100
    • /
    • 2024
  • Vitiligo is a condition characterized by the destruction or dysfunction of melanin-producing cells in the skin, resulting in a loss of skin pigmentation. Facial vitiligo, specifically affecting the face, significantly impacts patients' appearance, thereby diminishing their quality of life. Evaluating the efficacy of facial vitiligo treatment typically relies on subjective assessments, such as the Facial Vitiligo Area Scoring Index (F-VASI), which can be time-consuming and subjective due to its reliance on clinical observations like lesion shape and distribution. Various machine learning and deep learning methods have been proposed for segmenting vitiligo areas in facial images, showing promising results. However, these methods often struggle to accurately segment vitiligo lesions irregularly distributed across the face. Therefore, our study introduces a framework aimed at improving the segmentation of vitiligo lesions on the face and providing an evaluation of vitiligo lesions. Our framework for facial vitiligo segmentation and lesion evaluation consists of three main steps. Firstly, we perform face detection to minimize background areas and identify the face area of interest using high-quality ultraviolet photographs. Secondly, we extract facial area masks and vitiligo lesion masks using a semantic segmentation network-based approach with the generated dataset. Thirdly, we automatically calculate the vitiligo area relative to the facial area. We evaluated the performance of facial and vitiligo lesion segmentation using an independent test dataset that was not included in the training and validation, showing excellent results. The framework proposed in this study can serve as a useful tool for evaluating the diagnosis and treatment efficacy of vitiligo.

Using Machine Learning Techniques to Predict Health-Related Quality of Life Factors in Patients with Hypertension (머신러닝 기법을 활용한 고혈압 환자의 건강 관련 삶의 질 요인 예측)

  • Jae-Hyeok Jeong;Sung-Hyoun Cho
    • Journal of The Korean Society of Integrative Medicine
    • /
    • v.12 no.3
    • /
    • pp.11-24
    • /
    • 2024
  • Purpose : This study aims to identify the factors influencing health-related quality of life through machine learning of the general characteristics of patients with hypertension and to provide a basis for related research on patients, such as intervention strategies and management guidelines in the field of physical therapy for health promotion. Methods : Annual data from the second Korean Health Panel (Version 2.0) from 2019 to 2020, conducted jointly by the Korea Health and Social Research Institute and the National Health Insurance Service, were analyzed (Korea Health Panel, 2024). The data used in this study was collected from January to July 2020, and the data was collected using computer-assisted face-to-face interviews. Of the 13,530 household members surveyed, 1,368 were selected as the final study participants after removing missing values from 3,448 individuals diagnosed with hypertension by a doctor. Results : The results showed that walking (P2) was the most significant factor affecting health-related quality of life in random forest, followed by perceived stress (HS1), body mass index (BMIc), total household income (TOTc), subjective health status (SRHc), marital status (Marr), and education level (Edu). Conclusion :To prevent and manage chronic diseases such as hypertension, as well as to provide customized interventions for patients in advanced stages of the disease, research should be conducted in the field of physical therapy to identify influencing factors using machine learning. Based on the findings of this study, we believe that there is a need for additional content that can be utilized in the field of physical therapy to improve the health-related quality of life of patients with hypertension, such as diagnostic assessment and intervention management guidelines for hypertension, and education on perceived stress and subjective health status.

The associated factors with subjective oral symptoms experience in obesity adolescent (비만 청소년의 주관적 구강증상경험 관련 요인)

  • Park, Sin-Young
    • Journal of Korean society of Dental Hygiene
    • /
    • v.17 no.5
    • /
    • pp.757-767
    • /
    • 2017
  • Objectives: The purpose of this study is to identify the associated factors with subjective oral symptoms experience of obesity adolescents. Methods: The study subjects were targeting 8,139 obesity adolescents and 55,601 non-Obesity adolescents who completed 2016 Korean Youth Risk Behavior Web-based survey. Dependent variables were subjective oral symptoms experiences of fracture teeth, pain, throbbing pain, periodontal pain & bleeding, mucosal disease and bad breath. Independent variables were demographic characteristics of the subjects, oral health behaviors, health behaviors and eating habits. Results: Obesity adolescents were 12.8% with 61.9% subjective oral symptoms experience. Regarding the related factors of subjective oral symptoms experience of obesity adolescents, the factors were identified to be significantly higher in high school (OR=1.72) compared to middle school, learning achievement was higher in middle (OR=1.09) and lower (OR=1.31) compared to high, economic status was higher in lower (OR=1.09) compared to high, sealant experience (OR=1.10) and scaling experiences (OR=1.12) responded no were higher compared to responded yes, smoking experiences responded yes(OR=1.08) were higher compared to responded no, sweet drink (OR=1.14) and fastfood (OR=1.13) consumption were higher in consumption compared to non-consumption and females (OR=0.46) were higher than males. Oral symptoms experience were lower that father and mother's level of education were under high school graduation (OR=0.86) compared to unknown, economic status was in case of middle (OR=0.93) compared to high, tooth brushing was lower in under 1 time (OR=0.76), 2 times (OR=0.61) compared to more than 3 times, vigorous physical activities responded no (OR=0.75) were lower, compared to yes, vegetable consumption was lower in non-consumption (OR=0.68) compared to consumption. Conclusions: Subjective oral symptoms experiences were identified higher in obesity adolescents than non-obesity adolescents. It would be useful to use the results of this study to reduce oral symptoms and necessary to develop a program system considering characteristics of obesity adolescents.

A Study on the Effect of Career Shock Experienced in the COVID-19 Pandemic on the Level of Subjective Career Success Perception. (코로나19 팬데믹 상황에서 경험한 커리어쇼크가 주관적 경력 성공 인식 수준에 미치는 영향에 관한 연구)

  • Jin Kim;Jong Seok Cha;Na Jung Kim
    • Asia-Pacific Journal of Business
    • /
    • v.14 no.2
    • /
    • pp.85-100
    • /
    • 2023
  • Purpose - The purpose of this study is to identify the factors of shocking events in the career aspect experienced by Korean workers in the context of the Covid-19 pandemic, and to find out whether these career shocks affect individual perceptions of the importance of subjective career success. Design/methodology/approach - In the survey of 146 respondents, the career shock events experienced in the context of the Covid-19 pandemic were largely divided into three categories; 'work change', 'employment anxiety', and 'life anxiety'. For the subjective career success, seven dimensions - 'financial security', 'financial achievement', 'entrepreneurship', 'positive relationship', 'positive impact', 'learning and development', 'work-life balance' - were used. Findings - As a result, there was no difference in the perception of subjective career success due to the experience of 'work change' during the Covid-19 period. However, the respondents who experienced 'employment anxiety' came to recognize that 'financial security' and 'financial achievement' were more increasing in terms of the degree of difference of importance. And respondents who experienced 'lifetime anxiety' perceived that the degree of difference of importance was increasing in the six dimensions except for 'social influence'. Particularly, the increase in the importance of 'work-life balance' and 'positive relationship' was found to be the greatest among the career success dimensions. Research implications or Originality - Finally, it was concluded that changes in the external environment such as Covid-19 pandemic influence as a career shock and affect the level of importance in subjective career success perception. Based on the results, the theoretical implication on current career study and some practical implications for organizational career management were suggested.

The Effects of Sign Language Video Location in e-Learning System for the Hearing-impaired

  • Muhn, Seung Ho;Jung, Kwang Tae
    • Journal of the Ergonomics Society of Korea
    • /
    • v.34 no.6
    • /
    • pp.597-607
    • /
    • 2015
  • Objective: The purpose of this study is to identify the effects of sign language video location in e-learning system for the hearing-impaired. Background: E-learning education is a good way to resolve the inequality of education for the disabled. Providing a sign language video in e-learning education for the hearing-impaired is very important for their learning. Although the location of sign language video is an important factor in the design of the video, the effect of its location in learning using the e-learning system was not studied. Method: In order to identify the effect of sign language video location on the learning of the hearing-impaired using the e-learning system, the prototypes of the system with different locations were developed. Eighteen people with hearing impairment participated in this experiment. Learning presence, learning immersion, and learning satisfaction were used to measure learning effects with sign language video location. Results: Bottom right position was more preferred through preference evaluation for sign language video location. The learning effect with sign language video location (bottom-left and bottom-right) was not significant. That is, the effects of learning presence, immersion, and satisfaction were not statistically significant with video location. Conclusion: From this study, the following have to be considered in e-learning system design for the hearing-impaired. Although the location of a sign language video is not a significant factor from the experiment, the bottom right position in the design is proposed because learning presence and satisfaction is slightly higher at the bottom right position, and the position is preferred from subjective evaluation. From the analysis of interview data, it was also proposed that the design of a sign language video should be improved for the hearing-impaired. Application: The result of this study can be applied to the e-learning system design for the hearing-impaired.