• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.6
• /
• pp.87-96
• /
• 2022

The traffic vulnerable, including elderly pedestrians, have a relatively low walking speed and slow cognitive response time due to reduced physical ability. Although a smart crossing system has been developed and operated to improve problem, it is difficult to operate a signal that reflects the appropriate walking speed for each pedestrian. In this study, a neural network model and a multiple regression model-based traversing speed estimation model were developed using image information collected in an area with a high percentage of traffic vulnerability. to support the provision of optimal walking signals according to real-time traffic weakness. actual traffic data collected from the urban traffic network of Paju-si, Gyeonggi-do were used. The performance of the model was evaluated through seven selected indicators, including correlation coefficient and mean absolute error. The multiple linear regression model had a correlation coefficient of 0.652 and 0.182; the neural network model had a correlation coefficient of 0.823 and 0.105. The neural network model showed higher predictive power.

• Journal of Korean Biological Nursing Science
• /
• v.12 no.2
• /
• pp.89-96
• /
• 2010

Purpose: This study was aimed to develop and evaluate an obesity-management program for middle-aged obese women. Methods: Two 12 week session of the obesity-management programs constituted of weekly education and exercise such as aquarobic, pilates & yoga, and power-walking during 60 min for 3 days a week from June to December, 2006. The subjects included 47 middle-aged obese women between 30 and 60 yr. The effectiveness of the program was evaluated according to the change of body weight, body component, abdominal circumference, and serum lipid concentration. Data were measured by Inbody, tape measure, and blood test. Data were analyzed by descriptive statistics, and a paired t-test with an SPSS/PC. Results: There were statistically significant decreases in body weight, body mass index, body fat mass, Hemoglobin, abdominal circumference, total cholesterol level, and low density lipoprotein after the program was completed. But there were not statistically significant difference in fat free mass, muscle mass and triglyceride. Conclusion: The results of this study showed that an obesity-management program have positive effects in body composition, abdominal circumference, and lipid metabolism for middle-aged obese women.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.35-40
• /
• 2021

People counting data is crucial for most business owners, since they can derive meaningful information about customers movement within their businesses. For example, owners of the supermarkets can increase or decrease the number of checkouts counters depending on number of occupants. Also, it has many applications in smart buildings, too. Where it can be used as a smart controller to control heating and cooling systems depending on a number of occupants in each room. There are advanced technologies like camera-based people counting system, which can give more accurate counting result. But they are expensive, hard to deploy and privacy invasive. In this paper, we propose a method and a hardware sensor for counting people passing through a passage or an entrance using IR Infrared sensors. Proposed sensor operates at low voltage, so low power consumption ensure long duration on batteries. Moreover, we propose a new method that distinguishes human body and other objects. Proposed method is inexpensive, easy to install and most importantly, it is real-time. The evaluation of our proposed method showed that when counting people passing one by one without overlapping, recall was 96% and when people carrying handbag like objects, the precision was 88%. Our proposed method outperforms IR Infrared based people counting systems in term of counting accuracy.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.1
• /
• pp.497-505
• /
• 2018

This study was conducted to investigate the characteristics of private health insurance subscribers and non-subscribers as they relate to severely ill patients, and to identify the factors of participation. The study was conducted using the National Health and Nutrition Examination Survey for 2015, and data were analyzed using SPSS ver. 23.0. The subjects were 417 patients with severe disease (cancer, heart disease, cerebrovascular disease) over 19 years of age. Crossover analysis was employed to identify differences between the state of private health insurance participation, while binary logistic regression analysis was used to confirm the factors affecting private health insurance subscription. Analysis of the effects of the subjects on the private health insurance participation rate revealed that the social and demographic characteristics were higher in younger individuals regardless of sex, residence, or marital status. Moreover, higher household income, regardless of the education level, was associated with a higher participation rate of health insurance target individuals compared to medical benefit target individuals. The private health insurance participation rate was low and the explaining power was 51.7%, regardless of subjective health awareness and walking practice. Therefore, efforts should be made to improve the living environment and support local governmental programs for the elderly, low income households, socially vulnerable groups with limited activities and groups with limited health behavior. It is also necessary to consider various health policies, such as providing government health education or programs to prevent severe illness.

• Korean Journal of Applied Biomechanics
• /
• v.18 no.2
• /
• pp.115-124
• /
• 2008

The purpose of this study was to examine the effects of customized foot orthotics on lower extremity muscle activity and fatigue during march in combat boots. Four volunteers with normal foot and five volunteers with excessive pronation foot among soldiers on service were fitted with foot orthotics. The electromyography signal from activity of low extremity muscles were collected with surface electromyography device during walking on the treadmill. The walk on the treadmill was performed with a speed of 4.5 km/h. The experiment design for reseach wes composed two experimentation. The first experiment was to examine the muscle activity of lower extremity between normal foot and excessive pronator foot during march. The second experiment was to examine the muscle activity of lower extremity between wearing orthotics and no wearing orthotics. These data were analyzed by the averaged integral EMG and the mean power frequency. The analyzed results were compared by independent T-test method and paired T-test method of SPSS(windows version 12.0). The result of the study were the muscle activity on pronator foot tend to increase during march but a statistically significant increase in muscle fatigue of vastus lateralis and fibularis longus. A statistically significant decrease in muscle activity of anterior tibialis and fibularis longus and fatigue occurred using the customized foot orthotics in volunteers with excessive pronation foot compared to volunteers with normal foot. Clinically, the application of orthotics for the soldiers with excessive pronation foot appears to delay muscle fatigue and prevent from variable foot injuries. This may contribute to enhancing fighting efficiency.