• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.119-126
• /
• 2023

Sarcopenia is not well known enough to be classified as a disease in 2021 in Korea, but it is recognized as a social problem in developed countries that have entered an aging society. The diagnosis of sarcopenia follows the international standard guidelines presented by the European Working Group for Sarcopenia in Older People (EWGSOP) and the d Asian Working Group for Sarcopenia (AWGS). Recently, it is recommended to evaluate muscle function by using physical performance evaluation, walking speed measurement, and standing test in addition to absolute muscle mass as a diagnostic method. As a representative method for measuring muscle mass, the body composition analysis method using DEXA has been formally implemented in clinical practice. In addition, various studies for measuring muscle mass using abdominal images of MRI or CT are being actively conducted. In this paper, we develop an AI image segmentation model based on abdominal images of CT with a relatively short imaging time for the diagnosis of sarcopenia and describe the multicenter validation. We developed an artificial intelligence model using U-Net that can automatically segment muscle, subcutaneous fat, and visceral fat by selecting the L3 region from the CT image. Also, to evaluate the performance of the model, internal verification was performed by calculating the intersection over union (IOU) of the partitioned area, and the results of external verification using data from other hospitals are shown. Based on the verification results, we tried to review and supplement the problems and solutions.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.41-51
• /
• 2023

In this paper, we propose a technique of multi-time window feature extraction for anger detection in gait data. In the previous gait-based emotion recognition methods, the pedestrian's stride, time taken for one stride, walking speed, and forward tilt angles of the neck and thorax are calculated. Then, minimum, mean, and maximum values are calculated for the entire interval to use them as features. However, each feature does not always change uniformly over the entire interval but sometimes changes locally. Therefore, we propose a multi-time window feature extraction technique that can extract both global and local features, from long-term to short-term. In addition, we also propose an ensemble model that consists of multiple classifiers. Each classifier is trained with features extracted from different multi-time windows. To verify the effectiveness of the proposed feature extraction technique and ensemble model, a public three-dimensional gait dataset was used. The simulation results demonstrate that the proposed ensemble model achieves the best performance compared to machine learning models trained with existing feature extraction techniques for four performance evaluation metrics.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.5 no.1
• /
• pp.125-141
• /
• 1998

The purpose of this research is to analyze the effects of aerobic exercise on body composition, cardiopulmonary function, serum lipid level and antioxidants of obese and normal college female students. The subject group was made up of 13 normal students (below 30% body fat ratio) and 12 obese students (above 30% body fat ratio). After a pretest, the subjects were given an 8-week aerobic program. Then the subjects were given a posttest and analyzed of body composition, serum lipid level, antioxidants and cardiopulmonary function after the 6th and the 8th week of the program. The program schedule was made up of 4 days per week, 60 minutes per day. Test includes B.W., subscapular and triceps subcutaneous fat thickness, change of respiratory gas, and two blood sampling before treadmill exercise and post all out state, which analyzed serum lipid and antioxidants. The subjects performed treadmill exercise starting with 4km/hr of walking and then gradually increase the speed of 1km/hr per minute until all out state. The obtained data were analyzed using SAS program. The statistical methods employed here were one-way ANOVA with repeated measure, Duncan Multiple range test, paired-t test and t-test. The test results and conclusion of this research were as follows. 1. The effects of aerobic exercise on body composition were as follows ; Percent body fat was significantly reduced 6 weeks after the program and lean body mass was significantly increased 8 weeks after the program in both groups(obese group: F=3.44 P=.044, normal group: F=3.30 P=.048). subscapular skinfold of the obese group showed a remarkable decrease after the 6th week(F=4.33 P=.021) triceps skinfold of the normal group showed a remarkable decrease after the 6th and the 8th week(F=4.55 P=.017) compared with readings before the aerobic program, the aerobic program made a bigger difference concerning body fat, lean body mass, subscapular skinfold in the obese group than in the normal group(t=2.41 P=.024, t=2.40 p=.025, t=2.43 p=.028). 2. The effects of aerobic exercise on cardiopulmonary function were as follows ; Maximal $O_2$ uptake/kg was significantly increased 6 weeks after the program in the obese group(F=3.20 P=.054), but not much difference was observed in the normal group. Maximal pulse rate was significantly reduced in both groups after 6 weeks of the program(obese group: F=2.77 P=.087, normal group: F=7.17 P=.001). 3. The effects of aerobic exercise on serum lipid level were as follows ; In a resting period, total cholesterol, Triglyceride, and LDL-cholesterol were slightly higher in the obese group than in the normal group, but HDL-cholesterol was higher in the normal group. But, with the aerobic program, total-cholesterol, Triglyceride, LDL-cholesterol were reduced gradually and HDL-choleterol got increased in both groups, but not much change was noticed in the normal group. However, in the obese group, serum HDL-cholesterol level got increased significantly(F=5.12 P=.012). 4. The effects of aerobic exercise in serum antioxidants were as follows ; In a resting period, the obese group's serum Free Radical and GSSG content were higher than the normal group's and the normal group's serum GSH content was higher than the obese group's. After 6 weeks of the aerobic program, Free Radical was reduced significantly in both groups(obese group: F=13.87 P=.000, normal group: F=18.60 P=.000) In the obese group, 8 weeks after the program, GSH was increased significantly(F=13.78, P=.000). In the normal group, 6 weeks after the program, GSH was reduced but increased again after 8 weeks(F=6.07 P=.005). Plasma GSSG was significantly increased after 8 weeks of exercise in both groups(obese group: F=19.75 P=.000, normal group: F=22.42 P=.000,) Compared with readings before the aerobic program, the aerobic program made a bigger difference serum GSH in the normal group than in the obese group(t=3.37 p=.003). As this result shows, it is known that the regular aerobic exercise improves cardiopulmonary function, body composition, serum lipid effectively and through the serum Free Radical reduction and antioxidant system activation, oxidant stress was suppressed. This effect was higher in the obese group than in the normal one. At least 6weeks exercise period need for improvement of body composition, cardiopulmonary function and activation of antioxidant system. This result suggest that improvement of serum lipid profile was needed longer than 8weeks exercise period.

• Journal of Korean Society of Forest Science
• /
• v.108 no.3
• /
• pp.382-391
• /
• 2019

This study was conducted to verify whether smartphone hiking apps, which generate social network data including location information, are useful tools for analyzing the use characteristics of a forest recreation area. For this purpose, the study identified the functions and service characteristics of smartphone hiking apps. Also, the use characteristics of the area of Daegwallyoung were analyzed, compared with the results of the field survey, and the applicability of hiking apps was reviewed. As a result, the service types of hiking apps were analyzed in terms of three categories: "information offering," "hiking record," and "information sharing." This study focused on an app that is one of the "hiking record" types with the greatest number of users. Analysis of the data from hiking apps and a field survey in the Daegwallyoung area showed that both hiking apps and the field survey can be used to identify the movement patterns, but hiking apps based on a global positioning system (GPS) are more efficient and objective tools for understanding the use patterns in a forest recreation area, as well as for extracting user-generated photos. Second, although it is advantageous to analyze the patterns objectively through the walking-speed data generated, field surveys and observation are needed as complements for understanding the types of activities in each space. The hiking apps are based on cellphone use and are specific to "hiking" use, so user bias can limit the usefulness of the data. It is significant that this research shows the applicability of hiking apps for analyzing the use patterns of forest recreation areas through the location-based social network data of app users who record their hiking information voluntarily.