CGChandra Sekara Guru

Chandra Sekara Guru

*This is an algorithmically generated author record based on publicly available information.

Chandra Sekara Guru has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Can we predict archery performance using shooting heart rate and other biophysical parameters? A machine learning approach

    by Chandra Sekara Guru, Uma Mahajan, Anup Krishnan, Karuna Datta, Deep Sharma

    Background: Heart rate (HR) during different shooting phases, along with other biophysical parameters, is used for performance analysis. Given the stochastic and complex nature of these parameters, machine learning (ML) models have recently be...


  • Open Access

    Can we Predict Training Performance with Shooting Heart Rate in Archers? – A Machine Learning Approach

    by Chandra Sekara Guru, Uma Mahajan, Anup Krishnan, Karuna Datta, Deep Sharma

    Purpose Heart rate (HR) values during different phases of shooting can be used for performance analysis. Machine learning (ML) methods are used in predicting performance. We aimed to develop ML model to predict performance scores using shooting HR values and also to predict the importance of these parameters in an archer. Methods 32 archers (15 elite & 17 non-elite) shot two sessions of 30 arrows each indoor wearing heartrate chest monitor and were videographed. When each arrow was shot, 11 HR values were identified at different shooting phases. Other parameters with 35 linear variables and second-degree polynomial HR values were used to build ML models in Python V3.11.4. Session 1 and 2 total scores were used to train and test respectively. Root Mean Squared Error (RMSE) was used to evaluate the model performance after fine-tuning. Results RMSE of all 12 ML models ranged from 6.262 – 9.612. The Cat Boost model with the lowest RMSE of 6.262 was used to predict the Session 2 score. SHapley Additive exPlanations (SHAP) values showed each variable’s importance in prediction. Conclusions Sports age, resting systolic blood pressure, previous competition score, right hand grip-strength, age, HR before 2sec of arrow release, waist-to-hip ratio, concentration disruption trait anxiety and HR after 5sec of release are top parameters to predict score. Practical Applications ML model with shooting HR provides a better prediction of archery score of an individual archer.


  • How aware are we about doping in sports? : A cross-sectional pilot survey of doctors

    by K. Prabhakaran, Chandra Sekara Guru, Prafull Mohan, Karuna Datta


  • Heart rate monitoring in sports performance

    by Chandra Sekara Guru, Uma Mahajan, Karuna Datta, Deep Sharma

    Predicting performance outcomes has been challenging because of multiple and highly dynamic determinants of sports performance. HR measures have invariably been part of these prediction models owing to the easy, noninvasive, objective nature of this parameter. In-depth knowledge of HR measures provides a good basis for practical on-field decisions and training load management. However, because of the random and stochastic nature of HR measures determined by multiple confounding factors, correlation with other parameters is essential for interpretation (Noakes et al., 1998). This is very much pertinent when HR measures are used to prescribe intensity. The influence of environment, duration of exercise, and hydration status independently affect HR measures. Future studies focusing on artificial intelligence and computational algorithms to cater to these influences may prove useful in improving the accuracy and reliability. Presently, commercial sports events are at an all-time high in India and government agencies promoting the participation of school-going and college-going young athletes with flagship Khelo India Games and incorporation of these accurate and reliable technologies would benefit grass-root level coaches and athletes. Most of the studies have incorporated HR measures during training conditions for performance assessment and prediction. This is again a focus area as the training parameters may not be comparable to competitive outcomes, especially with competitive stress again independently influencing HR measures. Future 46studies, either including actual competitive HR measures or using simulated competitive conditions, need to be undertaken to make performance assessments and predictions using HR measures. This could be possible with emerging easy-to-use wearable technology with computational algorithms. One more essential theme for future research should be to compare the lab-based HR measures with field-based performance HR measures. The inherent difference in the lab-based assessment protocols/tests and the actual performance of motor qualities certainly affects the HR measures. For example, MHR measured during a lab-based maximal exercise testing may not be the MHR during the sports-specific exercise activity. The comparison gives an idea about the demands of the sports and input to the coach on the sports-specific training requirement. The rising trend in the usage of wearable technology and easy acquisition of HR data during sporting activities have paved the way for research avenues of HR monitoring in multiple sports fields, namely noninvasive surrogate markers for LT training, prediction algorithms for wellness and readiness incorporating RHR and resting HRV measures, and machine-learning programs incorporating training HR measures for performance prediction. However, all of these approaches require appropriate guidelines for optimum utility on the field to monitor sports performance.

  • Open Access

    Physical activity levels and sleep quality among military aircrew during COVID-19: A questionnaire-based pilot study

    by Chandra Sekara Guru, Murtaza Murtaza, Uma Mahajan

    Objective: Adequate physical activities (PAs) and sleep quality are also crucial factors for maintaining optimal performance in military aircrew given the physiological demands of alien flying conditions and the occupational stress of the military lifestyle. During the COVID-19 pandemic, PA levels and sleep quality are compromised globally. Due to a lack of adequate research studies, this pilot study was aimed at assessing the PA levels and sleep quality among military aircrew during the COVID-19 pandemic.Material and Methods: Fifty-nine aircrew (Weight: 68.7 ± 6.45 kg and body mass index: 22.6 ± 1.76 kg/m2) of a training establishment voluntarily participated in this anonymous pen-paper pilot survey. The participants included instructors/trainee aircrew and one female aircrew. Responses for the validated International Physical Activity Questionnaire, Pittsburgh Sleep Quality Index (PSQI) questionnaire, and self-rating before the pandemic along with demographic details were collected. Data were expressed as a median and interquartile range with statistical significance set at 0.05.Results: About 80% of participants reported participating in games and PA regularly. Before the pandemic, 68% of aircrew did moderate-vigorous PA and >93% had average-good sleep quality. Total PA during the pandemic was 1059 (594, 1074) MET-min/week with an energy expenditure of 1226.48 (623.7, 2036.7) Kcal/week. Time spent sitting was 6 (5, 10) h/day and more than 86% of aircrew reported good global PSQI score. The effect of the pandemic was observed as significantly reduced energy expenditure, that is, 1001.25 (673.2, 1794) Kcal/week among aircrew who self-rated high levels of PA before the pandemic (P= 0.042). Aircrew who regularly played games significantly engaged in more total PA of 1547 (827, 1911) MET-min/weeks (P< 0.0001) with a significantly higher energy expenditure of 1752.7 Kcal/week (P< 0.0001).Conclusion: Despite pandemic restrictions, aircrew who were regularly involved in PA/games were able to maintain a better PA level. Moreover, aircrew with better sleep quality significantly engaged in higher PA levels and lesser sitting time. Sedentary behavior was assessed as sitting time increased in trainee aircrew, aircrew who were not involved in active flying, and aircrew with bad sleep quality.

  • Physician empathy during crisis: A survey of doctors in COVID-19 pandemic (COPE study)

    by Antonieo Jude Raja B, Sriambika K, Ketki Khandhadiya, Chandra Sekara Guru, Uma Mahajan


  • Open Access

    EFFECT OF COVID-19 LOCKDOWN ON SPORTS PERFORMANCE PARAMETERS OF COMPETITIVE ATHLETES

    by Rupak Singh, Jayant Rastogi, Chandra Guru, Varad Apte, Karuna Datta, Atul Sharma

    Background: Nationwide lockdown was enforced due to the spread of the new Coronavirus-19. This resulted in cessation of all sports training across the country, including elite athletes. This COVID-19 lockdown was hypothesized to result in detraining effects on elite athletes. Aim: We aimed to study the impact of COVID-19 lockdown on athletes’ physiological and anthropometric sports performance parameters. Methodology: Seventy-five athletes (age: 23.25 ± 3.9 years, training experience 7.49 ± 3.5 years) from different sports participated voluntarily. International Physical Activity Questionnaire was used to grade home-based non-supervised physical activity undertaken during COVID-19 lockdown (137.81 ± 39.20 days). We compared the measured anthropometric, aerobic, and anaerobic performance parameters post-lockdown with pre-lockdown competitive phase recordings using Kruskal Wallis non-parametric test. Parameters were expressed as mean ± SD with level of significance fixed at p < .05. Results: Statistically significant reduction of 33.28% was observed in aerobic capacity post- COVID-19 lockdown (p = .01). We did not find any statistically significant variation in the other anthropometric and physiological performance parameters, namely weight (↑17.50 %), body mass index (↑20.69 %), body fat mass (↑20.76 %), waist (↑21.07 %), hip (↑19.13 %), waist: hip ratio (↑10.71 %), peak power (↑11.32 %) and mean power (↑5.17 %). Conclusions: We found that the athletes exhibited generalized detraining features despite maintaining home-based physical activity. Compared to other performance parameters, there was a significant decrease in the aerobic capacity post-lockdown. This shows the importance of incorporating an indoor-based supervised program including aerobic exercises to guide and monitor athletes. Practical Implications: Off -season/home confinement requires a remotely supervised tailored exercise program with optimal stimuli to maintain training adaptations. Awareness and incorporation of these findings would aid coaches and trainers in designing training programs to promote athletes’ injury-free gradual return to sports.