• Korean Journal of Artificial Intelligence
• /
• v.11 no.3
• /
• pp.29-34
• /
• 2023

Recently, the rapid development of artificial intelligence technology, many studies are being conducted to predict the risk of heart disease in order to lower the mortality rate of cardiovascular diseases worldwide. This study presents exercise or dietary improvement contents in the form of a software app or web to patients with cardiovascular disease, and cardiovascular disease through digital devices such as mobile phones and PCs. LR, LDA, SVM, XGBoost for the purpose of developing "Life style Improvement Contents (Digital Therapy)" for cardiovascular disease care to help with management or treatment We compared and analyzed cardiovascular disease prediction models using machine learning algorithms. Research Results XGBoost. The algorithm model showed the best predictive model performance with overall accuracy of 80% before and after. Overall, accuracy was 80.0%, F1 Score was 0.77~0.79, and ROC-AUC was 80%~84%, resulting in predictive model performance. Therefore, it was found that the algorithm used in this study can be used as a reference model necessary to verify the validity and accuracy of cardiovascular disease prediction. A cardiovascular disease prediction analysis algorithm that can enter accurate biometric data collected in future clinical trials, add lifestyle management (exercise, eating habits, etc.) elements, and verify the effect and efficacy on cardiovascular-related bio-signals and disease risk. development, ultimately suggesting that it is possible to develop lifestyle improvement contents (Digital Therapy).

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.6 no.1
• /
• pp.51-58
• /
• 2012

In this study, the active exercise load control system was developed that monitors patient's muscular condition based on EMG signals and controls the load by biofeedback in real-time. In order to select appropriate muscular parameter for the system, the pre-exercise test was performed to obtain EMG signals from healthy 12 males. Subsequently, the main exercise test was performed to evaluate the active exercise load control system based on IEMG: a selected muscular parameter, on healthy 10 males without musculoskeletal disorder. The accuracy and availability of developed system were confirmed through observing changes between exercise load and IEMG. A correlation was analyzed between the fatigue of muscles and RPE indicating the individual subjective fatigue. As a result, the active exercise load control system that was suggested in this study could be useful to control the initial load-balancing and the amount of exercise appropriate for individual in rehabilitation exercise therapy.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.3
• /
• pp.79-86
• /
• 2020

It is important to exercise in the correct posture in order to increase the exercise effect of the core exercise. This paper introduces a system that can train an exercise posture by providing feedback so that a user who performs core exercise in a virtual reality environment can take an accurate posture. It targeted three core movement postures, such as squat, lunge, and bridge, and provides visual feedback and haptic feedback to the user to take an accurate posture. The reference posture is generated by adjusting the expert's posture to the user's body length, and the accuracy of the exercise posture is calculated by comparing the user's posture with the reference posture. The effectiveness of the feedback was verified through user experiments, and the training effects according to the design of the feedback were compared.

• Journal of muscle and joint health
• /
• v.26 no.2
• /
• pp.141-154
• /
• 2019

Purpose: This study aimed to analyze the effects of exercise on pulmonary function in patients with ankylosing spondylitis (AS). Methods: Randomized controlled trials (RCTs) were identified by searching MEDLINE, EMBASE, CENTRAL, and CINAHL (through Jan 2019). Three reviewers independently retrieved articles, extracted data, and assessed methodological quality using the Cochrane's Risk of Bias for randomized studies. Results: Fourteen studies met the inclusion criteria with a total of 729 participants. CE (SMD 0.58, 95% CI 0.41~0.75, p<.001) and $VO_2peak$ (SMD 0.56, 95% CI 0.24~0.88, p=.001) had a significant effect on the most exercise interventions. As a secondary variable, BASFI (SMD -0.53, 95% CI -0.70~-0.37, p<.001), BASMI (SMD -0.75, 95% CI -0.92~-0.58, p<.001) showed an effect size of more than medium. However, PFT and QoL did not produce a significant results. Conclusion: Pulmonary involvement is common in patients with AS and might have disturbed functionality and exercise modality. Exercise can be an effective intervention to improve pulmonary function in patients with AS. More attention is needed to improve the chest and spinal mobility to maintain the appropriate pulmonary function. It is also necessary to consider how to construct a patient-tailored exercise program to increase performance, accuracy and safety of exercise.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.9
• /
• pp.1688-1693
• /
• 2007

The aim of this paper is to develop and verify the system which can detect heart rate during exercise by using conductive fabric electrode and transportable measurement module. The experiment was performed under 4 conditions(resting, walking, jogging, running) and 18 subjects data are used. By using the ECG measurement system used in cardiac stress testing as reference value in order to verify the accuracy of the developed system, the relative error and correlation coefficient was calculated for each subject at every 3 seconds. The results have shown that the high correlation between the developed system and the reference system for detecting heart rate during exercise. Relative error and correlation coefficient are 2.27% and 0.9877, respectively. 7 subjects data are omitted in these calculations because of severe noises. Therefore, it is expected that this system could be used as a health monitoring system in ubiquitous environment in the future.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.1
• /
• pp.334-343
• /
• 2014

In this paper, we suggest a method to improve the fusion of an accelerometer and gyro sensor by using a Kalman filter to produce a more high-quality respiration signal to supplement the weakness of using a single accelerometer. To evaluate our proposed algorithm's performance, we developed a chest belt-type module. We performed experiments consisting of aerobic exercise and muscular exercises with 10 subjects. We compared the derived respiration signal from the accelerometer with that from our algorithm using the standard respiration signal from the piezoelectric sensor in the time and frequency domains during the aerobic and muscular exercises. We also analyzed the time delay to verify the synchronization between the output and standard signals. We confirmed that our algorithm improved the respiratory rate's detection accuracy by 4.6% and 9.54% for the treadmill and leg press, respectively, which are dynamic. We also confirmed a small time delay of about 0.638 s on average. We determined that real-time monitoring of the respiration signal is possible. In conclusion, our suggested algorithm can acquire a more high-quality respiration signal in a dynamic exercise environment away from a limited static environment to provide safer and more effective exercises and improve exercise sustainability.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.178-180
• /
• 2022

An application implementation that allows users to train yoga posture based on the landmark of yoga posture of yoga instructors obtained from the Google Firebase ML Kit was introduced. Using the ML Kit, the user's posture is classified and landmarks corresponding to each joint are obtained. The accuracy measurement reference value for the yoga posture is set through the angle formed by the joints of the obtained landmark. The accuracy between the reference landmark for the yoga posture of professional yoga instructors and the landmark for the user's pose through the ML Kit was compared. According to the accuracy reference value, information on malfunction and correct motion is provided to the user through Text-to-Speech (TTS). Users are managed effectively with Firebase, and a system that displays the amount of exercise through a counter and timer when the user performs an exercise that meets the accuracy reference value was explained.

• The Journal of Korean Physical Therapy
• /
• v.24 no.6
• /
• pp.414-418
• /
• 2012

Purpose: Muscle fatigue affects proprioception, and it causes problems in spinal stability. The purpose of this study was to examine the effect on the accuracy of reproducing the lumbar angles before lumbar exercise and after fatiguing isokinetic lumbar exercise. Methods: Thirty healthy adults participated in this study. Before induction of fatigue by exercise, the proprioception was measured by Biodex. Lumbar positions were passively maintained on stimulation position ($25^{\circ}$ flexion and $25^{\circ}$ extension), and back to the starting position. Subjects actively repositioned the remembered stimulation position, and error degrees between the stimulation position and reposition were measured. Using an isokinetic device at $120^{\circ}$/sec of velocity of angle lumbar flexion/extension exercise resulted in muscle fatigue. The post-fatigue proprioceptive position sense was used in the same way as in pre-fatigue measurement. Results: Means of position sense of pre-fatigue were $2.19{\pm}1.97$ on flexion angle, and $5.04{\pm}2.84$ on extension angle. After exercise induced fatigue, means of position sense were $2.37{\pm}1.83$ on flexion angle, and $4.93{\pm}2.57$ on extension angle. Results of this study showed significant differences of lumbar proprioceptive position sense between pre- and post-fatigue. Conclusion: Lumbar proprioception sense in active repositioning in flexion and extension was affected in the presence of muscle fatigue. Therefore, it should be noted that therapeutic exercise for patients with abnormal proprioceptive sense or elderly people must be performed with care because muscle fatigue can cause secondary damage.

• Journal of The Korean Society of Integrative Medicine
• /
• v.8 no.2
• /
• pp.169-185
• /
• 2020

Purpose : This study aimed to conduct a comprehensive meta-analysis to evaluate the effect size for pulmonary function and gait capacity of treadmill exercise in stroke patients. In addition, we aimed to examine the current status of treadmill interventions and compare the effect sizes of treadmill training to provide evidence-based practice for future development and application. Methods : The meta-analysis study was conducted using research articles that applied treadmill exercise to stroke patients and were published between January 2005 and February 2020. For a systematic meta-analysis, we conducted a search using the PICOS framework and selected 25 domestic stroke- and treadmill-related studies. The Comprehensive Meta-Analysis program was used to calculate the effect sizes for lung function and gait capacity (6-minute walk test and 10 m walk test). As Cohen's d has a tendency to overestimate the effect size, we used Hedge's g to increase the accuracy in computing the effect size. Results : Based on the results of the meta-analysis, the total effect size of treadmill exercise was 0.535, which was statistically significant, with a medium effect size (p<0.05). The effects of treadmill exercise in stroke patients were divided into dependent variables, namely pulmonary function (0.372) and gait capacity (0.584). In addition, for gait capacity, the effect sizes were evaluated for both the 6-minute walk test (0.756) and the 10 m walk test (0.514). Conclusion : This study provides objective evidence of the effectiveness of treadmill-based gait training programs. We hope that the results of this study will help support the development and implementation of treadmill-based gait training in stroke patients. Treadmill training is expected to improve not only pulmonary function, but also the gait capacity of stroke patients. Long-term investigations on the effects of treadmill training in stroke patients are necessary.

• Journal of the Korean Society of Physical Medicine
• /
• v.5 no.2
• /
• pp.233-243
• /
• 2010

Purpose : This study aimed to examine the effects of sling exercise therapy on the relief of low back pain and the cross-sectional area change of lumbar muscles by CT analysis for chronic low back pain patients. Methods : Forty-one patients with diagnosis of chronic low back pain was divided sling exercise therapy group(SEG) 19 subjects and conservative physical therapy group(CPG) 22 subjects. we randomized and treated them(subjects) for 12 weeks. As using visual analogue scale(VAS), we evaluated recovery accuracy of pain, and for investigating cross-section area change of lumbar muscles for before and after treatment we used computed tomography(CT). Results : This study were summarized as follows : 1) As treatment period, in each compared testing on VAS of SEG and CPG, the both group was significantly different(p<.05). 2) Compared testing on VAS of between-subject groups(SEG and CPG) were not significantly different(p>.05). 3) At SEG of before and after treatment, in compared testing on cross-section area size of lumbar muscles, All muscles of psoas major, quadratus lumborum, erector spinae and multifidus were significantly different(p<.05). At CPG, psoas major was significantly different(p<.05). But other muscles were not significantly different(p>.05). Conclusion : From this result, both sling exercise therapy and the conservative physical therapy are effect on decrease of pain for chronic low back pain patients. but Increasing of the cross-section area being proportioned with muscular strengthening of low back muscle is noticeable difference in SEG. Therefore, sling exercise therapy have affect both decreasing of pain for chronic low back pain patients and lumbar muscles strengthening.