RAMAKRISHNAN R

Dr. RAMAKRISHNAN R

Department of Physical Education and Sports Sciences, Hindustan Institute of Technology and Science, Chennai, India
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
1 December 2022
Verified
Conference Paper
Closed access
GRG. Radhakrishnan
G. Radhakrishnan
TPT. Parasuraman
T. Parasuraman
DHD. Harigaran
D. Harigaran
RAMAKRISHNAN RRAMAKRISHNAN R
RAMAKRISHNAN R
RKR. Krishnakumar
R. Krishnakumar
KRK. A. Ramesh
K. A. Ramesh
In recent years, there has been a proliferation of machine learning and deep learning in the sports business, which has resulted in substantial breakthroughs in the assessment of athletic performances. These developments have been made possible as a consequence of the rise of deep learning. It is feasible that the teams will not have coaches available in the not-too-distant future to offer comments on how they are doing. The goal of this study is to present a hybrid optimization algorithm-based machine learning approach for the analysis of players' performances in sports, as well as for the improvement of performances by individuals and the team in a variety of sports. The Grey Wolf Optimization (GWO) based Machine Learning (CNN) Technique that has been suggested is used for the purpose of performance plan prediction in order to bring about an improvement in the degree of quality achieved. In addition to this, the paper will examine how machine technology may aid players in identifying their present levels of performance as well as how they might develop in the future. When compared to other current approaches, the GWO-CNN model performs quite well.

15 November 2023
Verified
Conference Paper
Closed access
KRK.Vishnuvardhan Reddy
K.Vishnuvardhan Reddy
BKB. Kumar
B. Kumar
NKN. Prem Kumar
N. Prem Kumar
TPT. Parasuraman
T. Parasuraman
CBC.M. Balasubramanian
C.M. Balasubramanian
RAMAKRISHNAN RRAMAKRISHNAN R
RAMAKRISHNAN R
Chess, a timeless game of strategy, has captivated minds for centuries and continues to challenge enthusiasts and grandmasters alike. “Chess Match Outcome Prediction via Sequential Data Analysis with Deep Learning” presents an innovative approach to forecasting the results of chess games by harnessing the sequential data inherent in each move. This research capitalizes on extensive datasets of chess games, encompassing diverse player ratings, time controls, and openings. The pre-process this data into a structured format, allowing for the encoding of chess positions and move sequences. Through the application of cutting-edge deep learning techniques such as Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks, proposed model the intricate temporal relationships within the games. Suggested study addresses multiple prediction tasks, from binary classification (win/loss) to multi-class classification (win/draw/loss), enabling a comprehensive evaluation of the model's predictive capabilities. The research also delves into hyperparameter tuning and model interpretability, shedding light on the crucial factors influencing prediction accuracy. The results of proposed experiments unveil the potential of deep learning in chess outcome prediction, offering promising accuracy and performance. As chess remains an evolving game, proposed model serves as a dynamic tool adaptable to the ever-changing landscape of strategies and player behaviors. In an age where chess is both a game of tradition and innovation, this research bridges the two worlds, enriching the analytical toolkit of chess enthusiasts and offering practical applications in chess analysis tools and services.

22 November 2023
Verified
Conference Paper
Closed access
TPT. Parasuraman
T. Parasuraman
LML. Marina
L. Marina
LML. Mohandass
L. Mohandass
BSB. Selvamuthukrishnan
B. Selvamuthukrishnan
NNN. Balaji Naik
N. Balaji Naik
RAMAKRISHNAN RRAMAKRISHNAN R
RAMAKRISHNAN R
Cricket, a sport cherished by millions worldwide, has witnessed a surge in its digital presence, transforming the way fans engage with the game. In this era of digital spin, where data-driven insights play a pivotal role in understanding player performance and predicting match outcomes, this research endeavors to harness the power of deep learning techniques for cricket data analysis and score prediction. In the era of data-driven decision-making, our research aims to contribute to the understanding and forecasting of cricket match outcomes. The research begins by collecting and preprocessing a comprehensive dataset containing historical cricket match statistics, including player performance, venue conditions, and match outcomes. Through the Convolutional Long Short-Term Memory (CLSTM) hybrid deep learning model combines the power of Convolutional Neural Networks (CNNs) and Long Short-Term Memory Networks (LSTMs) to process both spatial and temporal dependencies in sequential data, it analyzes this dataset to uncover valuable insights and patterns within the game. Our methodology focuses on various aspects of cricket, including batting and bowling performance, team dynamics, pitch conditions, and historical match data. By leveraging these deep learning models, this research work aims to predict match scores and outcomes with a high degree of accuracy, thereby assisting cricket enthusiasts, analysts, and bookmakers in making informed decisions. Furthermore, this research contributes to the growing field of sports analytics, showcasing the potential of deep learning in predicting the unpredictable nature of cricket matches. The results of our experiments demonstrate the effectiveness of our models in providing valuable insights into the dynamics of the game and in predicting match scores and outcomes. This study highlights the significance of deep learning techniques in cricket data analysis and score prediction. By leveraging the wealth of cricket data available, this research work aims to enhance the understanding of this beloved sport and provide stakeholders with valuable tools for making data-driven decisions in the world of cricket.

30 March 2024 in International Research Journal of Multidisciplinary Technovation
Verified
Journal Article
Open access
PDF file
SSShri Bharathi S.V
Shri Bharathi S.V
PTParasuram T
Parasuram T
ASAkila S
Akila S
RAMAKRISHNAN RRAMAKRISHNAN R
RAMAKRISHNAN R
SKShivaraju K
Shivaraju K
VCVijayalakshmi C
Vijayalakshmi C
Yoga is an ancient Indian discipline that promotes mental and physical well-being. It's become popular due to the stress of modern life. There are many ways to learn yoga, including studios, private instructors, and online resources. Many students of yoga struggle to identify their own mistakes when learning on their own. This article proposes a new approach for the effective identification and classification of different yoga poses using deep learning algorithms. The Media-pipe library is used to extract user-relevant features from 85 videos featuring 15 yoga practitioners doing 6 different poses. In the study, results from many deep learning models are compared, both with and without extracting features. Several different learning models achieved their best performance when fed skeletonized pictures to a neural network for training. Results from several models are compared in order to demonstrate the beneficial effect of skeletonization. With a validation accuracy of 99.9% on non-skeletonized images, Mobile-Net with CNN outperforms CNN, LSTM and SVM by a wide margin. Skeletonized images are used by the proposed model MobileNet, which achieves an accuracy result of 99.9%.

22 January 2025 in Metallurgical and Materials Engineering
Verified
Journal Article
Open access
PDF file
PSPriyadarshini S
Priyadarshini S
RAMAKRISHNAN RRAMAKRISHNAN R
RAMAKRISHNAN R
Polycystic Ovarian Disease (PCOD) is an endocrine pathology prevalent among women of reproductive age, distinguished by menstrual irregularities, hyperandrogenic manifestations, and the presence of polycystic ovarian morphology. Non-pharmacological interventions, such as yoga, are increasingly explored for managing PCOD symptoms. This study evaluates the research trajectory on yoga interventions for PCOD using bibliometric data analysis. A bibliometric analysis was conducted using the SCOPUS database. Stringent inclusion criteria were applied, focusing on studies centered on yoga interventions for PCOD, published in English, and accessible through Open Access journals. Out of the initial pool of 26 journals, 17 articles were closely examined, resulting in the final selection of 6 articles for in-depth analysis. The analysis revealed a significant rise in publications on yoga for PCOD, highlighting its growing recognition as a non-pharmacological treatment. These findings emphasize the need for interdisciplinary collaboration and further evidence-based studies to confirm yoga's effectiveness in managing PCOD, suggesting its potential role in comprehensive care for women with PCOD.