Byunggul Lim

@agrilife.tamu.edu

Postdoctoral Research Associate / Institute for Advancing Health Through Agriculture, Texas A&M University
Texas A&M University

Byunggul Lim


            Download Compact PDF  
https://researchid.co/happenly

RESEARCH, TEACHING, or OTHER INTERESTS

Public Health, Environmental and Occupational Health
11

Scopus Publications

Scopus Publications

  • Explainable artificial intelligence models for accurate physical activity prediction using wearable device data
    Byunggul Lim, Sang-jun Park, Jun-Hyun Bae, Gabrielli T. de Mello, Chad D. Rethorst
    Journal of Science and Medicine in Sport, 2026
    OBJECTIVES: Wearable devices such as smartwatches are increasingly used for physical activity monitoring, but their proprietary algorithms often lack transparency and limit generalizability. Existing machine learning models prioritize accuracy, overlooking interpretability and real-world applicability. This study addresses these gaps by applying explainable deep learning techniques to raw sensor data from commercial devices. DESIGN: A cross-sectional secondary data analysis was conducted using publicly available datasets collected from Apple Watch and Fitbit devices. METHODS: Machine learning models (Decision Tree, Random Forest) and deep learning models (Gated Recurrent Unit, Long Short-Term Memory, Convolutional Neural Network-Long Short-Term Memory) were trained to classify physical activity intensity into sedentary, light, and vigorous levels. Model interpretability was assessed using Shapley Additive Explanations. Model performance was evaluated using accuracy, precision, recall, and F1-score. RESULTS: The Convolutional Neural Network-Long Short-Term Memory model demonstrated the best overall performance, achieving F1 scores of 82.5 (Apple Watch) and 82.3 (Fitbit). Shapley Additive Explanations analysis revealed device-specific patterns: Apple Watch models placed greater emphasis on heart rate-related features, particularly in vigorous physical activity, while Fitbit models prioritized step-based metrics across physical activity intensity levels. CONCLUSIONS: The integration of deep learning models with Shapley Additive Explanations enhances both predictive accuracy and interpretability in physical activity intensity level prediction. This approach may aid future health monitoring systems and support just-in-time adaptive interventions with real-time feedback.
  • A sequential deep learning model for predicting people with obesity in adults aged 18–64 using physical fitness variables
    Xinxing Li, Yunho Sung, Yanjie Zhang, Byunggul Lim, Dae Young Kim, Jun-Hyun Bae
    International Journal of Obesity, 2026
  • Development and validation of machine learning models for classifying cancer-related sarcopenia using Kinect-based mixed-reality exercises in breast cancer survivors
    Byunggul Lim, Wook Song
    Translational Cancer Research, 2025
    Background: Sarcopenia in cancer survivors is often underdiagnosed due to limited access to imaging-based diagnostic tools such as computed tomography (CT) or dual-energy X-ray absorptiometry (DXA). Indirect classification using movement data may offer a practical, scalable alternative. This study aimed to develop and validate machine learning (ML)-based classification models for cancer-related sarcopenia using joint angle data obtained from Kinect-based mixed-reality (KMR) devices, aiming to improve classification accuracy and identify key movement-related predictors. Methods: ) and handgrip strength (HGS) (<18 kg). KMR device data were collected during 8 weeks of exercise. After preprocessing, the dataset was randomly split (8:2) for training and testing. Four ML models-support vector machine (SVM), K-nearest neighbor (KNN), random forest (RF), and XGBoost (XGB)-were trained. Five-fold cross-validation was used for tuning, and feature importance was analyzed. Results: Of the 38 participants in the exercise group included in the final analysis, 12 (31.5%) were initially diagnosed with sarcopenia. After the 8-week KMR device exercise intervention, 3 participants showed recovery from sarcopenia, resulting in 9 (23.6%) remaining classified with the condition. In the test set, the XGB model demonstrated the highest performance, achieving 94.7% accuracy, 91.2% recall, 95.8% precision, 93.4% F1 score, and 96.2% area under the curve (AUC). Feature importance analysis using RF and XGB consistently identified right "knee flexion (right)" as the most influential predictor. Conclusions: Among ML classification models trained on KMR device joint data, XGB demonstrated the best performance. Right knee flexion emerged as the most influential feature in sarcopenia classification. These findings suggest that KMR device movement analysis may serve as a practical, non-invasive screening tool for sarcopenia, enabling early detection and personalized intervention strategies for breast cancer survivors in both clinical and remote settings.
  • Kinect-Based Mixed Reality Exercise Program Improves Physical Function and Quality of Life in Breast Cancer Survivors: A Randomized Clinical Trial
    Byunggul Lim, Xinxing Li, Yunho Sung, Parivash Jamrasi, SoYoung Ahn, Hyejung Shin, Wook Song
    Cancer Research and Treatment, 2025
    Purpose Exercise is an effective non-pharmacological approach for alleviating treatment-related adverse effects and enhancing physical fitness in breast cancer survivors. A Kinect-based mixed reality device (KMR), with real-time feedback and user data collection, is an innovative exercise intervention for breast cancer survivors. This study aimed to investigate the effect of KMR exercise program on quality of life (QOL) and physical function in breast cancer survivors.Materials and Methods Seventy-seven participants were randomly assigned to either the KMR exercise group or home stretching group with an 8-week intervention. Physical function (shoulder range of motion, body composition, aerobic capacity, and hand grip strength) was evaluated before and after the intervention period. Participants completed questionnaires such as the Disabilities of the Arm, Shoulder, and Hand (DASH), Functional Assessment of Cancer Therapy-Breast, and International Physical Activity Questionnaire (IPAQ) to assess upper extremity disabilities, QOL, and physical activity levels.Results Significant group-by-time interaction was found for flexion of the operated arm (154.3±12.5 to 165.8±11.2), and the non-operated arm (158.2±13.8 to 166.5±12.2), abduction of the non-operated arm (154.8±31.6 to 161.1±28.1), and adduction of the operated arm (46.5±9.1 to 52.6±7.2). Significant improvements were also observed in DASH (46.8±9.1 to 40.8±9.3) and IPAQ (1,136.3±612.8 to 1,287±664.1).Conclusion The KMR exercise program effectively improved the physical function, alleviated edema, reduced upper extremity disability, and enhanced the QOL in breast cancer survivors. Coupled with significant group-by-time interactions for various outcomes, the results emphasize the potential benefits of incorporating the KMR exercise program to improve the QOL in breast cancer survivors.
  • Machine Learning for Movement Pattern Changes during Kinect-Based Mixed Reality Exercise Programs in Women with Possible Sarcopenia: Pilot Study
    Yunho Sung, Ji-won Seo, Byunggul Lim, Shu Jiang, Xinxing Li, Parivash Jamrasi, So Young Ahn, Seohyun Ahn, Yuseon Kang, Hyejung Shin, Donghyun Kim, Dong Hyun Yoon, Wook Song
    Annals of Geriatric Medicine and Research, 2024
    Background: Sarcopenia is a muscle-wasting condition that affects older individuals. It can lead to changes in movement patterns, which can increase the risk of falls and other injuries.Methods: Older women participants aged ≥65 years who could walk independently were recruited and classified into two groups based on knee extension strength (KES). Participants with low KES scores were assigned to the possible sarcopenia group (PSG; n=7) and an 8-week exercise intervention was implemented. Healthy seniors with high KES scores were classified as the reference group (RG; n=4), and a 3-week exercise intervention was conducted. Kinematic movement data were recorded during the intervention period. All participants' exercise repetitions were used in the data analysis (number of data points=1,128).Results: The PSG showed significantly larger movement patterns in knee rotation during wide squats compared to the RG, attributed to weakened lower limb strength. The voting classifier, trained on the movement patterns from wide squats, determined that significant differences in overall movement patterns between the two groups persisted until the end of the exercise intervention. However, after the exercise intervention, significant improvements in lower limb strength in the PSG resulted in reduced knee rotation range of motion and max, thereby stabilizing movements and eliminating significant differences with the RG.Conclusion: This study suggests that exercise interventions can modify the movement patterns in older individuals with possible sarcopenia. These findings provide fundamental data for developing an exercise management system that remotely tracks and monitors the movement patterns of older adults during exercise activities.
  • Herbal extract (Cervus elaphus Linnaeus, Angelica gigas Nakai, and Astragalus membranaceus Bunge) ameliorates chronic fatigue: A randomized, placebo-controlled, double-blind trial
    SoYoung Ahn, Parivash Jamrasi, Byunggul Lim, Ji-won Seo, Xinxing Li, Shu Jiang, Yunho Sung, Seo Hyun Ahn, Chaeyoung Shin, Dongjin Noh, Bora Jin, Seonjoo Lee, Ki Won Lee, Jin Soo Kim, Young Tae Koo, Wook Song
    Integrative Medicine Research, 2024
    Chronic fatigue syndrome (CFS) reduces the health-related quality of life in the working-age population; however, studies have rarely investigated this group. A mixture of Cervus elaphus Linnaeus, Angelica gigas Nakai, and Astragalus membranaceus Bunge (CAA) may be an effective anti-fatigue supplement. However, few clinical trials have explored the anti-fatigue effects of herbal medicines in human participants. Therefore, this study aimed to investigate the effects of the CAA herbal complex on muscle fatigue and endurance capacity in a randomized, placebo-controlled, double-blind trial. In an 8-week trial, 80 patients with chronic fatigue symptoms were randomly assigned to the CAA (43.5 ± 1.2 years) or placebo group (41.8 ± 1.3 years). Fatigue and cardiorespiratory endurance were measured at baseline, interim, and post-intervention. Fatigue-related blood biomarkers were assessed before and at the end of the intervention. A significant improvement in overall fatigue scores was observed on the fatigue severity scale ( p = 0.038), multidimensional fatigue inventory ( p = 0.037), and 24-hour visual analog scale ( p = 0.002) in the CAA group compared to those in the placebo group. Fatigue improvement was observed in the CAA group, as well as physiological variables, such as increased maximal exercise time to exhaustion ( p = 0.003), distance until exhaustion ( p = 0.003), and maximum oxygen consumption ( p = 0.039). CAA positively and significantly affected fatigue and cardiorespiratory endurance in patients with chronic fatigue, suggesting the potential use of herbal supplements for treating chronic fatigue. Clinical Research Information Service (CRIS, https://cris.nih.go.kr/ ): KCT0005613.
  • Impact of Taekwondo training on cognitive and physical function in elderly individuals: A comprehensive review of randomized controlled trials
    Xinxing Li, Jun-Hyun Bae, Byunggul Lim, Ji-won Seo, Yunho Sung, Shu Jiang, Parivash Jamrasi, SoYoung Ahn, Chaeyoung Shin, Mingzhu Pan, Wook Song
    Complementary Therapies in Clinical Practice, 2024
  • Exploring CrossFit performance prediction and analysis via extensive data and machine learning
    Byunggul LIM, Wook SONG
    Journal of Sports Medicine and Physical Fitness, 2024
    BACKGROUND: The analysis of athletic performance has always aroused great interest from sport scientist. This study utilized machine learning methods to build predictive models using a comprehensive CrossFit (CF) dataset, aiming to reveal valuable insights into the factors influencing performance and emerging trends. METHODS: ) values and mean squared error (MSE). Feature importance analysis was conducted using RF, XGBoost, and AdaBoost models. RESULTS: =0.93). Across exercises, clean and jerk consistently emerged as a crucial predictor. The feature importance analysis revealed intricate relationships among exercises, with gender significantly impacting deadlift performance. CONCLUSIONS: This research advances our understanding of performance prediction in CF through machine learning techniques. It provides actionable insights for practitioners, optimize performance, and demonstrates the potential for future advancements in data-driven sports analytics.
  • Effect of unsupervised Kinect-based mixed reality fitness programs on health-related fitness in men during COVID-19 pandemic: randomized controlled study
    So Ahn, Yun Ho, Jun Hyun Bae, Byung Gul Lim, LI Xinxing, et al.
    Journal of Men S Health, 2023
    This study aimed to investigate the effect of Kinect-based mixed reality (KMR) exercise and unsupervised individual exercise on health-related fitness. A total of 27 participants underwent cardiorespiratory fitness tests for the inclusion criteria and were randomly assigned to three groups: a KMR group (KMRG), an unsupervised individual group (UIG), or a control group (CG). Pre and post-tests were conducted to measure Maximum oxygen uptake (VO₂max), body composition, upper and lower-body (LB) muscle strength, and endurance. KMRG and UIG attended exercise sessions 3 days per week for 8 weeks. KMRG used the KMR device and UIG used an instructive banner for exercise. All groups maintained their daily routines and submitted diet records every 4 weeks. Results showed that VO₂max, upper-body muscle endurance, and LB muscle endurance of knee extension was increased in KMRG and UIG. LB muscle strength in knee flexion was increased in UIG and LB muscle endurance in knee flexion was increased in KMRG. VO₂max, LB muscle strength, and LB muscle endurance were greater in KMRG than in CG. LB muscle strength in knee flexion was greater in KMRG than in UIG. Body fat was increased and skeletal muscle mass was decreased in CG. KMR exercise showed better performance than unsupervised individual (UI) exercise, and the exercise program was effective in both KMR and UI environments. These findings contribute to the growing evidence supporting the use of technology-based exercise interventions as a potential strategy to enhance health-related fitness.
  • Prediction equations of physical fitness age for korean adults
    Byoung-goo Ko, Ji-won Seo, Bong-ju Sung, Wook Song, Jun Hyun Bae, Byunggul Lim, Parivash Jamrasi
    Exercise Science, 2021
    PURPOSE: This study aimed to develop prediction equations for estimating the physical fitness age (PFA) of Korean adults in young (19-40 years), middle (41-64 years), and old (65-80 years) age groups.METHODS: Data from 122,842 individuals who participated in Korea National Physical Fitness Survey and National Fitness 100 from 2009 to 2014 were collected. Body composition, muscular strength, muscular endurance, flexibility, cardiorespiratory endurance, agility, power, balance, and coordination were measured. Pearson’s correlation and stepwise regression analyses were used to analyze the data.RESULTS: The equations were as follows: PFA for young males=22.321 −.088 (20-m PACER)+.317 (body mass index [BMI]); PFA for young females=24.486 −.143 (20-m PACER)+.304 (BMI); PFA for middle-aged males=66.644 −.044 (standing long jump) −.069 (20-m PACER) – .201 (weight) −.075 (modified sit-ups)+.269 (10-m shuttle run)+.320 (BMI); PFA for middle-aged females=66.814 −.098 (standing long jump) −.113 (modified sit-ups); PFA for older males=84.795+.093 (figure-of-8 walk) −.100 (chair standing) −.122 (weight) −.102 (relative grip strength) −.060 (sit-and-reach)+.147 (3-m up-and-go); and PFA for older females=80.577+.097 (figureof-8 walk)+.306 (3-m up-and-go) −.280 (weight) −.088 (relative grip strength) −.069 (sit-and-reach)+.393 (BMI) −.088 (chair standing) −.011 (2-min step-in-place).CONCLUSIONS: Our prediction equations for PFA can be used as a tool to prescribe sex- and age-appropriate exercise program and to verify the effect of the application of the exercise program by comparing pre -and post-PFA.
  • Effect of masticatory movement using gum on walking and cycling: A randomized crossover design
    Byung-Gul Lim, Hyunji Kim, Jun-Hyun Bae, Ji-Won Seo, Seong-Eun Kwak, Chae-Young Shin, Jooeun Ahn, Wook Song
    Exercise Science, 2021