Ponnusamy Yoga Lakshmi

Ponnusamy Yoga Lakshmi

Auto-generated profile, based on publicly available information

Ponnusamy Yoga Lakshmi

Department of Computer Science, Faculty of Science and Humanities, SRM Institute of Science and Technology

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 August 2024 in Journal of Human Sport and Exercise
Verified
Journal Article
Open access
PDF file
SSSwamynathan Sanjaykumar
Swamynathan Sanjaykumar
SNSubhashree Natarajan
Subhashree Natarajan
PLPonnusamy Yoga Lakshmi
Ponnusamy Yoga Lakshmi
YKYuliya Kalmykova
Yuliya Kalmykova
JLJoseph Lobo
Joseph Lobo
ESEdi Setiawan
Edi Setiawan
Talent identification and player development are crucial aspects of sports management, particularly in volleyball, where understanding players' performance predictors is essential. The primary objective is to investigate the relationships between players' demographic and physical attributes and their on-court performance, providing valuable insights for talent identification and player development strategies. The dataset comprises demographic and physical attributes alongside performance metrics of college-level female volleyball players in India. Data were meticulously collected from various institutions participating in volleyball tournaments across India. Three machine learning algorithms—linear regression, random forest regression, and XGBoost regression—were trained using the pre-processed dataset. Standard regression evaluation metrics such as mean squared error (MSE), root mean squared error (RMSE), and R-squared (R2) score were used to assess model performance. Random forest regression emerged as the top-performing ML technique, achieving a prediction accuracy of 94.18%, followed by XGBoost regression with 92.76%. Height, muscle mass, and bone mass exhibited strong positive correlations with performance prediction, emphasizing their significance. This study highlights ML techniques' potential, particularly random forest regression, in improving talent identification and performance prediction in college-level female volleyball players in India.

22 April 2024 in Physical Education Theory and Methodology
Verified
Journal Article
Open access
PDF file
SSSwamynathan Sanjaykumar
Swamynathan Sanjaykumar
SNSubhashree Natarajan
Subhashree Natarajan
PLPonnusamy Yoga Lakshmi
Ponnusamy Yoga Lakshmi
Farjana Akter BobyFarjana Akter Boby
Farjana Akter Boby
Background. Random Forest is a popular machine learning algorithm used for classification and regression tasks. The study purpose is to investigate the use of Random Forest machine learning to predict the winning chances of teams in the 2024 Indian Premier League (IPL) season. Objectives. By analyzing comprehensive player statistics, including matches played, batting and bowling averages, as well as fielding contributions, the study aims to understand the factors that influence team success in T20 cricket and provide actionable insights for team management, betting markets, and cricket enthusiasts. Material and methods. The study involved 10 cricket teams competing in the IPL 2024 season. Player statistics and match outcomes data from previous IPL seasons were collected and cleaned, with missing values addressed through imputation. The features were based on player statistics, including both aggregate measures and calculated metrics. A Random Forest is chosen as the machine learning model, trained using preprocessed data, with features derived from player statistics as input and match outcomes as the target variable. The dataset was split into training and validation sets, using methodologies such as cross-validation to ensure a robust model performance. Results. The Random Forest model demonstrates strong predictive performance, with a low Mean Squared Error (MSE) of 8.2174, Root Mean Squared Error (RMSE) of 2.8666, and a high R-Squared value of 0.9173, indicating approximately 91.73% variance explained in the data. Chennai Super Kings emerge as frontrunners with a predicted performance percentage of 83.4%, while teams like Punjab Kings and Lucknow Super Giants show lower predicted performance percentages, suggesting potential areas for its improvement. Conclusions. This study reveals the effectiveness of Random Forest machine learning in forecasting IPL match outcomes based on player statistics. It provides valuable insights into team dynamics and offers actionable recommendations for team management and cricket enthusiasts. The findings enrich our understanding of IPL match dynamics, contribute to the evolution of cricket analytics, and promote greater engagement with sport, ultimately enhancing the fan experience in the IPL.

29 February 2024 in Physical Education Theory and Methodology
Verified
Journal Article
Open access
PDF file
PLPonnusamy Yoga Lakshmi
Ponnusamy Yoga Lakshmi
SSSwamynathan Sanjaykumar
Swamynathan Sanjaykumar
MDManiazhagu Dharuman
Maniazhagu Dharuman
AEAarthi E
Aarthi E
Background. The interest in women’s premier league cricket has caused the need for advanced analytics to understand the multifaceted dynamics of the sport. Study Purpose. This study aimed to contribute to sports analytics by assessing the efficacy of Support Vector Regression (SVR) kernel models in predicting the most valuable player. Such research methods as ANOVA, Bessel function, and Inverse MultiQuadratic kernel application have been deliberately chosen for their diverse mathematical approaches, aligning with the nuanced intricacies of women's premier league cricket. Materials and methods. Player performance was analyzed by using the following study methods: ANOVA, Bessel function and Inverse MultiQuadratic kernel application. The data, sourced from espncricinfo.com and the International Cricket Council, includes essential metrics for five teams. Rigorous preprocessing techniques, such as imputation and outlier removal, enhance data reliability, ensuring robust predictive models. Results. The application of the Inverse MultiQuadratic kernel exhibits exceptional predictive performance, surpassing ANOVA and Bessel function models. The kernels radial basis function proves effective in capturing the intricate dynamics of women’s premier league cricket. The findings underscore the suitability of kernel method for predicting standout performers in the Womenʼs Premier League 2024 season. Conclusions. The study revealed the dynamic interplay between sports analytics and machine learning in women's premier league cricket. The application of the Inverse MultiQuadratic kernel stands out as the most effective model, providing key insights into player predictions. This emphasizes the continual integration of advanced analytical techniques to enhance our understanding of the evolving landscape of women’s premier league cricket. As the sport gains prominence on the global stage, such analytical endeavors become imperative for strategic decision-making and sustained growth.

13 May 2024 in Sleep Science
Verified
Journal Article
Open access
PDF file
DBDeenadayalan Boopalan
Deenadayalan Boopalan
VVVenugopal Vijayakumar
Venugopal Vijayakumar
Karuppasamy GovindasamyKaruppasamy Govindasamy
Karuppasamy Govindasamy
KDKaur Dilpreet
Kaur Dilpreet
PRPoornima Ravi
Poornima Ravi
MKMaheshkumar kuppusamy
Maheshkumar kuppusamy
Objectives Insufficient sleep leads to several short- and long-term physical and mental consequences. Yoga is a popularly known complementary health approach that maintains physical and mental health through asanas, meditation, and breathing techniques. Cyclic meditation (CM), derived from one of the Upanishads, is practiced by combining physical postures (asanas) with relaxation techniques. Recent findings emphasize the significance of CM as a means to enhance sleep quality. The current review aims to find the effects of CM on sleep quality through the available scientific data. Methods The current review includes research articles evaluating CM's effect on sleep quality from various databases such as PubMed, Cochrane, Embase, and Google Scholar up to January 22, 2023. We conducted a literature search using keywords related to CM and sleep quality, and search results were restricted to studies published in the English language. Results There were 5 articles with 277 participants meeting inclusion criteria, all conducted in India. Of those, 2 were randomized controlled trials and 3 were single-group or two-group pre-post and crossover studies. Participants ranged from healthy volunteers, type-2 diabetic patients, alcohol dependents, and caregivers for special needs children. Based on the available scientific evidence, CM has been found to be effective (d = 0.56–4.90) in enhancing the quality of sleep. Conclusion The CM technique could be tentatively considered as a beneficial practice to improve sleep. However, further, adequately powered, and randomized controlled studies with various other parameters of sleep are required to strongly recommend CM as a stand-alone yogic intervention for sleep disturbance.

30 December 2023 in Physical rehabilitation and recreational health technologies
Verified
Journal Article
Open access
PDF file
SSSwamynathan Sanjaykumar
Swamynathan Sanjaykumar
STSRM Institute of Science and Technology
SRM Institute of Science and Technology
NRNavaraj Chelliah Jesus Rajkumar
Navaraj Chelliah Jesus Rajkumar
PLPonnusamy Yoga Lakshmi
Ponnusamy Yoga Lakshmi
Purpose: secondary oligomenorrhea, characterized by infrequent menstrual cycles, is a significant concern in women's reproductive health. Understanding the multifaceted determinants of this menstrual disorder is essential for developing effective interventions and improving women's well-being. This study aims to comprehensively investigate the interplay between diverse temperature living conditions, stress levels, and sleeping duration in relation to secondary oligomenorrhea. Material & Methods: to achieve our objectives, we conducted a cross-sectional survey involving a diverse cohort of women aged 18 to 23 years, all of whom had experienced secondary oligomenorrhea. We employed a carefully crafted questionnaire to collect extensive data on various aspects, including demographic information, menstrual history, exposure to different temperature conditions, and sleeping patterns. Subsequently, the collected data underwent statistical analyses, including correlation and regression analyses, to unravel the intricate associations between temperature, stress, sleeping duration, and secondary oligomenorrhea. Results: the study unveiled intriguing correlations across a spectrum of temperature conditions and identified a consistent negative correlation between sleeping duration and menstrual cycle length, regardless of temperature fluctuations. This finding suggests that longer sleeping durations are associated with slightly shorter menstrual cycles. However, the impact of stress on secondary oligomenorrhea displayed variability depending on temperature conditions, indicating a more complex relationship. Conclusion: this investigation significantly enhances our understanding of how diverse temperature living conditions, stress levels, and sleeping patterns collectively influence secondary oligomenorrhea. While the observed correlations are of moderate strength, they underscore the intricate and multifaceted nature of menstrual cycle regulation. These findings emphasize the need for a holistic approach when addressing secondary oligomenorrhea, considering factors beyond temperature, stress, and sleeping duration.

19 December 2024 in Health, Sport, Rehabilitation
Verified
Journal Article
Open access
PDF file
SSSwamynathan Sanjaykumar
Swamynathan Sanjaykumar
NRNavaraj Chelliah Jesus Rajkumar
Navaraj Chelliah Jesus Rajkumar
PLPonnusamy Yoga Lakshmi
Ponnusamy Yoga Lakshmi
BSBaby Salini
Baby Salini
Farjana Akter BobyFarjana Akter Boby
Farjana Akter Boby
Mert KURNAZMert KURNAZ
Mert KURNAZ
Background and purpose Oligomenorrhea (infrequent menstrual periods), can significantly impact women's reproductive health and quality of life. This study explores the potential connection between exercise timing and menstrual regularity, aiming to provide insights for tailored exercise interventions in women with such irregularity. Material and methods A 12-week pretest-posttest design with multiple experimental groups was conducted with fifteen participants aged 18-23, each with a history of consistent menstruation for at least six months and without hormonal contraceptive usage. Participants were allocated to morning, afternoon, and evening exercise sessions, engaging in a personalized exercise regimen that combined cardiovascular and strength training activities thrice weekly. Pre- and post-intervention assessments were employed to comprehensively assess menstrual regularity, focusing on cycle length and characteristics. Analysis of Covariance (ANOVA) tests were utilized to scrutinize the potential impacts of exercise timing on menstrual regularity. Results The results showed noteworthy changes in cycle lengths after the training sessions, indicating the potential effectiveness of such interventions for individuals experiencing menstrual irregularity. Regarding Oligomenorrhea, morning sessions demonstrated the most considerable reduction in cycle length, while afternoon and evening sessions had less pronounced effects. Conclusion This study confirms the significant impact of exercise timing on menstrual cycle length and characteristics for women with Oligomenorrhea. Varied responses emphasize the importance of tailored interventions considering distinct times of the day.