• Journal of Korean Public Health Nursing
• /
• v.27 no.3
• /
• pp.513-526
• /
• 2013

Purpose: The purpose of this study was to determine the effects of the Traditional Play-centered Obesity Control Cooperative Learning Program based on the cooperative learning theory on obesity rate, physical fitness, self-esteem, and body image specifically in obese elementary school children. Methods: The research design for this study was based on a non- equivalent control group pretest-posttest design. The study was conducted from September, 5 to November 30, 2012. The subjects included 74 obese children ($Exp.=25^{(a)}$, $Com.=24^{(b)}$, $Cont.=25^{(c)}$) with an obesity rate above 20% at an elementary school in G City. Data analysis was performed using SPSS/WIN 18.0, using Chi-square test, one-way ANOVA, and Scheffe test. Results: The obesity rate (F=4.033, p<.022) in the experimental group was significantly lower than that in the group (Com, Cont), in which the Traditional Play-Centered Obesity Control Cooperative Learning Program was not implemented. Self-esteem (F=4.310, p<.017) also caused significant differences. However, physical fitness (Muscular endurance F=1.545, p=.220; Flexibility F=.671, p=.514; Agility F=1.594, p=.210; Speed F=5.386, p<.007, scheffe (a,b

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.2
• /
• pp.51-58
• /
• 2023

This paper proposes a deep learning method for estimating the heart rate from facial videos. Our proposed method estimates remote photoplethysmography (rPPG) signals to predict the heart rate. Although there have been proposed several methods for estimating rPPG signals, most previous methods can not be utilized in low-power single board computers due to their computational complexity. To address this problem, we construct a lightweight student model and employ a knowledge distillation technique to reduce the performance degradation of a deeper network model. The teacher model consists of 795k parameters, whereas the student model only contains 24k parameters, and therefore, the inference time was reduced with the factor of 10. By distilling the knowledge of the intermediate feature maps of the teacher model, we improved the accuracy of the student model for estimating the heart rate. Experiments were conducted on the UBFC-rPPG dataset to demonstrate the effectiveness of the proposed method. Moreover, we collected our own dataset to verify the accuracy and processing time of the proposed method on a real-world dataset. Experimental results on a NVIDIA Jetson Nano board demonstrate that our proposed method can infer the heart rate in real time with the mean absolute error of 2.5183 bpm.

• Proceedings of the Korea Contents Association Conference
• /
• 2017.05a
• /
• pp.257-258
• /
• 2017

Modern society tends to bring excessive labor to people and, therefore, further health management is required. In this paper, by using the clustering technique, one of machine learning methods, we try to bring out the measure of fatigue from heart rate (HR) variation during daytime work, helping people to get high-quality of healthy and calm life.

• Korean Journal of Artificial Intelligence
• /
• v.10 no.1
• /
• pp.21-25
• /
• 2022

Korea has relatively less crime than other countries. However, the crime rate is steadily increasing. Many people think the crime rate is decreasing, but the crime arrest rate has increased. The goal is to check the relationship between CCTV and the crime rate as a way to lower the crime rate, and to identify the correlation between areas without CCTV and areas without CCTV. If you see a crime that can happen at any time, I think you should use a random forest algorithm. We also plan to use machine learning random forest algorithms to reduce the risk of overfitting, reduce the required training time, and verify high-level accuracy. The goal is to identify the relationship between CCTV and crime occurrence by creating a crime prevention algorithm using machine learning random forest techniques. Assuming that no crime occurs without CCTV, it compares the crime rate between the areas where the most crimes occur and the areas where there are no crimes, and predicts areas where there are many crimes. The impact of CCTV on crime prevention and arrest can be interpreted as a comprehensive effect in part, and the purpose isto identify areas and frequency of frequent crimes by comparing the time and time without CCTV.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.4
• /
• pp.993-1000
• /
• 2016

Semi-supervised learning makes it easy to use an unlabeled data in the supervised learning such as classification. Applying the semi-supervised learning on the regression analysis, we propose two methods for a better regression function estimation. The proposed methods have been assumed different marginal densities of independent variables and different smoothing parameters in unlabeled and labeled data. We shows that the overfitted pilot estimator should be used to achieve the fastest convergence rate and unlabeled data may help to improve the convergence rate with well estimated smoothing parameters. We also find the conditions of smoothing parameters to achieve optimal convergence rate.

• Journal of Digital Convergence
• /
• v.18 no.8
• /
• pp.231-242
• /
• 2020

The thesis presents a system that continuously collects the human body's physiological vital information at rest with sensors and ICT information technology and predicts diabetes using the collected information. it shows the artificial neural network machine learning method and essential basic variable values. The study method analyzed the correlation between heart rate measurements of BCG and ECG sensors in 20 DM- and 15 DM+ subjects. Artificial Neural Network (ANN) machine learning program was used to predictability of diabetes. The input variables are time domain information of HRV, heart rate, heart rate variability, respiration rate, stroke volume, minimum blood pressure, highest blood pressure, age, and sex. ANN machine learning prediction accuracy is 99.53%. Thesis needs continuous research such as diabetic prediction model by BMI information, predicting cardiac dysfunction, and sleep disorder analysis model using ANN machine learning.

• Korean Journal of Construction Engineering and Management
• /
• v.20 no.5
• /
• pp.31-41
• /
• 2019

The purpose of this study is to investigate the participation of vocational training program of construction engineers and the impact of workplace learning (formal learning and informal learning) on human resource performances of construction engineers. The data of 306 construction engineers were extracted from 10,069 workers in various industries those were collected by 6th human resource company panel survey done by Korea Research Institute of Vocational Education & Training. This study found that, compared with workers in other industries, participation rate of construction engineers in workplace learning (formal learning, informal learning) was relatively low, and especially the participation rate of informal learning was significantly low. Regression analysis showed that participation in formal learning did not affect positive job performance and job satisfaction. On the other hand, informal learning has a positive effect on job capability, job satisfaction, and organizational commitment.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.3
• /
• pp.149-165
• /
• 2017

This study is to discover and substantiate the casual relation between Learning Organization and Organizational Citizenship Behavior, with Supervisor Trust used as moderating variable. Learning Organization and Organization Citizenship Behavior are used, respectively, as independent and dependent variable, Supervisor Trust as moderating variable. The data for this study was collected from 340 public officials who participated in the training program. Data collection tools were used to collect structured questionnaire questionnaires, and dissemination and retrieval of questionnaires were carried out over 6 weeks from February 6 to March 10, 2017. Of the questionnaire distributed, the questionnaire was finally recovered from the questionnaire, with a recall rate of 91.8 %, showing a very high rate of recall. The result showed that Learning Organization is a significant factor for Organization Citizenship Behavior and also that Supervisor Trust plays a role in the control of the relationship between Learning Organization and Organization Citizenship Behavior; thus, in order for Public Organizations to achieve advanced competitiveness, vitalizations of Learning Organization is important.

• Journal of Digital Convergence
• /
• v.11 no.6
• /
• pp.199-204
• /
• 2013

Speech recognition system is shall be composed model of learning from the inaccurate input speech. Similar phoneme models to recognize, because it leads to the recognition rate decreases. Therefore, in this paper, we propose a method of speech recognition optimal learning model configuration using the Bhattacharyya algorithm. Based on feature of the phonemes, HMM feature extraction method was used for the phonemes in the training data. Similar learning model was recognized as a model of exact learning using the Bhattacharyya algorithm. Optimal learning model configuration using the Bhattacharyya algorithm. Recognition performance was evaluated. In this paper, the result of applying the proposed system showed a recognition rate of 98.7% in the speech recognition.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.1
• /
• pp.267-274
• /
• 2021

The purpose of this study is to investigate differences in learning flow and teaching presence according to the lecturer's appearance and the lecturer's speech rate. For this experiment, 183 freshman students from Xingtai University in China were selected as subjects of the experiment, and a total of four types of lecture videos were developed to test the lecturer's appearance and their speech rates. Data was analyzed through multivariate analysis of variance. According to the results of the analysis, first, learning flow and teaching presence of groups who experienced the presence of the lecturer appeared were significantly higher than the groups who learned without the appearance of the lecturer. Second, the groups who learned from videos with a fast speech rate showed higher learning flow and teaching presence than the group who learned at a slow speech rate. Third, there were no significant differences in both learning flow and teaching presence according to the lecturer's appearance and speech rate. This result provides a theoretical and practical basis for developing customized videos according to learners' characteristics.