• Journal of the Korean Society of School Health
• /
• v.36 no.3
• /
• pp.113-125
• /
• 2023

Purpose: The purpose of this study is to develop a model for predicting mental health risk among adolescents based on health behavior information by employing a hybrid machine learning method. Methods: The study analyzed data of 51,850 domestic middle and high school students from 2022 Youth Health Behavior Survey conducted by the Korea Disease Control and Prevention Agency. Firstly, mental health risk levels (stress perception, suicidal thoughts, suicide attempts, suicide plans, experiences of sadness and despair, loneliness, and generalized anxiety disorder) were classified using the k-mean unsupervised learning technique. Secondly, demographic factors (family economic status, gender, age), academic performance, physical health (body mass index, moderate-intensity exercise, subjective health perception, oral health perception), daily life habits (sleep time, wake-up time, smartphone use time, difficulty recovering from fatigue), eating habits (consumption of high-caffeine drinks, sweet drinks, late-night snacks), violence victimization, and deviance (drinking, smoking experience) data were input to develop a random forest model predicting mental health risk, using logistic and XGBoosting. The model and its prediction performance were compared. Results: First, the subjects were classified into two mental health groups using k-mean unsupervised learning, with the high mental health risk group constituting 26.45% of the total sample (13,712 adolescents). This mental health risk group included most of the adolescents who had made suicide plans (95.1%) or attempted suicide (96.7%). Second, the predictive performance of the random forest model for classifying mental health risk groups significantly outperformed that of the reference model (AUC=.94). Predictors of high importance were 'difficulty recovering from daytime fatigue' and 'subjective health perception'. Conclusion: Based on an understanding of adolescent health behavior information, it is possible to predict the mental health risk levels of adolescents and make interventions in advance.

• PNF and Movement
• /
• v.5 no.2
• /
• pp.73-88
• /
• 2007

Purpose : The purpose of this study was to find out The effect of Low back pain on the total pattens of Proprioceptive neuromuscular facilitation(PNF). Methods : The subjects of the study were 62 low back pain patients. They were divided into two groups: 31 in the experimental group and 31 in the control group. the experimental group performed modalities and PNF total patterns three times for a week. the control group performed only modalities and ROM exercise three times for a week. Back muscle strength was measured by a back muscle strength measuring machine, the intensity of pain was measured by the Visual Analogue Scale (VAS), and the level of disability was measured by Oswestry low back pain disability index. Study measurements were compared before and after 6 weeks exercise program. The two groups of subjects were assessed by utilizing two different balance measurement: Static standing balance was measured by balance performance monitor (BPM) and Dynamic standing balance was measured by one leg standing(OLS). The scale for static standing balance was measured by using, sway area, sway path, max velocity. Results : The results of this study were as follow: 1) The score on visual analogue scale shows statistically significant increase on PNF group of post test(p<.05). 2) The score on Oswestry low back pain disability index. shows statistically significant decrease on PNF group of post test(p<.05). 3) The change sway area was statistically significant on pre-test and post-test(p<.05). 4) The change sway path was statistically significant on pre-test and post-test(p<.05). 5) The change max velocity was statistically significant on pre-test and post-test(p<.05). 6) The score on one leg standing shows statistically significant increase on PNF group of post test(p<.05). Conclusion : These results of this study indicated that Proprioceptive Neuromuscular Facilitation Total patterns which performed for six weeks had a statistically significant influence on low back pain. If the exercise for muscle strength is performed along with therapeutic stabilizing exercise, a better effect can be expected on low back pain. We hope that this study will provide a basic data for further research with a bigger group and on a long-term effect.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.491-493
• /
• 2021

최근 코로나 19 상황으로 인해 많은 사람들이 모이는 병원 방문을 꺼리거나, 치료비에 부담을 느끼는 근골격계 재활 환자들이 많다. 이러한 환자들을 위해 이 프로젝트에서는 재활 치료 빈도가 높은 어깨와 손목 등 여섯 가지 근골격 부위의 자가 재활 치료를 돕는 기계 학습 기반 웹 페이지을 구현한다. 이 웹 페이지는 각 부위에 대한 재활 치료 자세를 구글 티처블 머신으로 학습 시킨 데이터를 기반으로 환자가 올바른 자세로 운동하는지를 판별해 준다. 이 때, 사용자의 재활 치료 자세는 웹 카메라로부터 캡쳐한다.

• Clinical and Experimental Pediatrics
• /
• v.52 no.5
• /
• pp.576-580
• /
• 2009

Purpose : Growth-promoting attempts are widespread in Korea, but little is known about their prevalence or associated factors. This study was designed to assess the prevalence of growth-promoting attempts among children visiting a university growth clinic. Methods : A questionnaire-based survey was carried out with 823 children (416 boys, 407 girls) who visited the growth clinic at Paik Hospital. Results : The mean age of the subjects was $10.4{\pm}2.6$ yr, and the height z-score was $-1.58{\pm}0.91$. Approximately 33.4% of the children had tried growth promotion. Among the height-gain methods, herbal medicine was the most frequently used (37.8%), followed by health-promoting supplements (37.1%), exercise or machine (3.0%), and growth hormone treatment (2.9 %). The mean age at which the parents began to worry about their children's height was 7.7 yr. The mean age at which they started height-gain methods was 8.9 yr for herbal medicine, 9.1 yr for health-promoting supplements, 9.4 yr for exercise or machine, and 9.9 yr for growth hormone treatment. Motivating factors included advice from relatives or friends (36.0%), advertisements in the Internet or newspaper (28.4%), advice from pharmacist (16.8%), and advice from their medical doctor (5.5%). The degree of satisfaction from the height-gain methods was 29.1% with growth hormone treatment, 6.6% with exercise or machine, 6.4% with herbal medicine, and 2.8% with growth-promoting supplements. Conclusion : Approximately one third of the children reported use of growth-promoting methods, but the satisfaction rate was not high. The benefits of growth-promoting methods should be carefully weighed against their costs and side effects.

• Korean Journal of Applied Biomechanics
• /
• v.15 no.1
• /
• pp.207-219
• /
• 2005

The purpose of this study was to determine the effect of the foot rotation on the lower limb muscles. Fourteen subjects performed step-up/step-down at a cadence of 80 beats/min, exercises with the foot neutral, $35^{\circ}$ internally rotated, and $35^{\circ}$ externally rotated, respectively. For each variable, a one-way analysis of variance (ANOVA) was used to determine whether there were significant differences between genders and among the eight types of jump. When a significant difference was found in jump type, post hoc analyses were performed using the Tukey procedure. A confidence level of p < .05 was used to determine statistical significance. The results showed that significant changes in averaged IEMG values occurred with the internal rotation of the foot in the lateral gastrocnemius during the knee extension, and in the semitendinosus during the knee flexion. During the knee extension, however, the internal rotation of the foot produced a significantly lower Averaged IEMG values than the neutral foot position in the medial gastrocnemius. The results also found that the peak IEMG activity of the rectus femoris during the knee extension for the external rotation of the foot was Significantly higher than the corresponding values in the neutral position of the foot, while the intenal rotaion of the foot exhibited a significant difference with the neutral position of the foot in the semitendinosus during the knee flexion. In general, the foot rotation position did not influence the average IEMG and Peak IEMG values of most muscles. The practice of adopting foot rotation to selectively strengthen individual muscles of the lower limb was not supported by this study. The external rotation of the foot produced high muscle activities in the quadriceps during the knee extension. For the knee extension, therefore, maintaining a laterally rotated position should be need for stable and comfortable position.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.3
• /
• pp.134-139
• /
• 2023

Rehabilitators perform outpatient treatment and daily rehabilitation exercises to recover physical function with the aim of quickly returning to society after surgical treatment. Unlike performing exercises in a hospital with the help of a professional therapist, there are many difficulties in performing rehabilitation exercises by the patient on a daily basis. In this paper, we propose a CNN-LSTM-based upper limb rehabilitation real-time monitoring system so that patients can perform rehabilitation efficiently and with correct posture on a daily basis. The proposed system measures biological signals through shoulder-mounted hardware equipped with EMG and IMU, performs preprocessing and normalization for learning, and uses them as a learning dataset. The implemented model consists of three polling layers of three synthetic stacks for feature detection and two LSTM layers for classification, and we were able to confirm a learning result of 97.44% on the validation data. After that, we conducted a comparative evaluation with the Teachable machine, and as a result of the comparative evaluation, we confirmed that the model was implemented at 93.6% and the Teachable machine at 94.4%, and both models showed similar classification performance.

• Journal of the Korean Society of Safety
• /
• v.20 no.3 s.71
• /
• pp.188-196
• /
• 2005

Accident reports from 1991 to 2000 of a steel company were used to analyze which factors induce industrial accidents. The subjects were 8,311 blue-collar workers, who sustained 114 occupational injuries and work on a continuous full-day 3-team 3-shift system of backward rotation(mornings to afternoons to nights). With respect to marital status, the occupational injury rate(OIR) on the married workers was significantly higher compared to unmarried workers. With respect to no, the OIR of those in their early 20s was significantly higher when compared to other age groups. The OIR of highly educated workers showed a reduction when compared with lower educated workers. The OIR of shift workers were significantly higher compared with the daytime workers. The OIR of type of work decreased across the steel manufacturing process, rolling process, machine maintenance section forwarding products section to the field management section. With respect to the block of shift work(morning, afternoon, and night shifts) by the type of work, the OIR of the night shift was higher than those of the morning shift in the steel manufacturing process or forwarding products section. The OIR of the machine maintenance section was slightly higher in the morning shift than those of the night shift. The OIR of the time of day of the shift workers reached a peak between 09:00 and 11:00. The OIR of a slight injury to shift workers decreased across the night, afternoon, to morning shifts whereas the OIR of a serious injury tended to decrease across the night, morning, to afternoon shift. The body parts most commonly injured were the arm and the crus.

• Journal of Creative Information Culture
• /
• v.7 no.4
• /
• pp.235-242
• /
• 2021

Recently, many human activity recognition(HAR) researches using smartphone sensor data have been studied. HAR can be utilized in various fields, such as life pattern analysis, exercise measurement, and dangerous situation detection. However researches have been focused on recognition of basic human behaviors or efficient battery use. In this paper, exercising activities performed indoors and outdoors were defined and recognized. Data collection and pre-processing is performed to recognize the defined activities by SVM, random forest and gradient boosting model. In addition, the recognition result is determined based on voting class approach for accuracy and stable performance. As a result, the proposed activities were recognized with high accuracy and in particular, similar types of indoor and outdoor exercising activities were correctly classified.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.40 no.12
• /
• pp.1700-1707
• /
• 2011

This study evaluated the effect of multigrain supplementation on exercise-related changes in running time and glycogen storage capacity of male SD rats engaged in treadmill exercise. Thirty-six 6-week-old rats were divided into six groups: normal (Nor) fed normal feed, control (Con) fed with 20% normal feed and 80% milled rice, test group one (GI) fed with multigrain feed I, test group two (GII) fed with multigrain feed II, test group three (GIII) fed with multigrain feed III, and test group four (GIV) fed with multigrain feed IV. Endurance tests by treadmill machine were administered after 24 days of multigrain feed supplementation and adaptive training. Running time was extended and glycogen storage capacity increased in the multigrain-treated group compared to the non-treated group. Also, the fatigue indicators of inorganic phosphorous, CPK, and lactate concentration were all reduced in the multigrain feed group compared to the control group after 25 min and/or exhausted exercise. But there was no difference in GOP, GTP, lactate, or LDH concentrations between the groups. Our results demonstrated that endurance improved with multigrain feed in rats. Specifically, running time, glycogen storage capacity, inorganic phosphorous, CPK, and lactate serum concentration increased. Importantly, the improvements in endurance brought about in the GII group fed with waxy barley was the greatest among the experimental groups.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.2
• /
• pp.91-102
• /
• 2017

Many of the wearable smart fitness devices provide services related to users' heartbeat rates. These services use fixed standards which have been pre-determined based on statistical data. However, because body conditions significantly differ between individuals, the services applying fixed standards to all individuals are not reliable. This paper proposes the Feedback-RFC model which adapts heartbeat standards to individual users' exercise abilities and also proposes a method to implement the model. This paper also shows the effectiveness of the Feedback-RFC model by collecting heartbeat data from 12 participants and evaluating the model with the data.