P. Sundaravadivel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
P. Sundaravadivel has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
R. Augustian Isaac
Saveetha Engineering College
3 shared publicationsD. Elangovan
Saveetha Engineering College, Chennai, India
2 shared publicationsD. KrishnaRaj
Saveetha Engineering College, Chennai, India
2 shared publicationsR. Raja
Saveetha Engineering College, Chennai, India
2 shared publications- Rajesh Kumar Dhandapani
Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology, Chennai, India
2 shared publications S. Navaneetha Krishnan
2 shared publications
Latest Publications
- Open Access
- 4 September 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1) , 1044
Adaptive multimodal large language model with hierarchical cross modal grounding for real time industrial visual anomaly detection on edge devices
- 4 September 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1) , 1044
Open AccessAdaptive multimodal large language model with hierarchical cross modal grounding for real time industrial visual anomaly detection on edge devices
- Open Access
- 9 August 2026
- Published by Springer Nature in Discover Materials
Machine learning for mechanical property assessment and optimisation in hybrid natural fibre/epoxy composites
- 9 August 2026
- Published by Springer Nature in Discover Materials
Open AccessMachine learning for mechanical property assessment and optimisation in hybrid natural fibre/epoxy composites
- 2 July 2026
- Published by Springer Nature
- p. 167-190
AI-Driven IoT Framework for Predictive Healthcare Monitoring Using Wearable Sensors
- 2 July 2026
- Published by Springer Nature
- p. 167-190
AI-Driven IoT Framework for Predictive Healthcare Monitoring Using Wearable Sensors
- RetractionOpen Access
- 22 December 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 44239
Retraction Note: Optimizing credit card fraud detection with random forests and SMOTE
- 22 December 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 44239
RetractionOpen AccessRetraction Note: Optimizing credit card fraud detection with random forests and SMOTE
- 1 November 2025
- Published by Springer Nature
- p. 163-180
Harnessing Artificial Intelligence and Machine Learning in English Language Teaching: Trends and Applications
- 1 November 2025
- Published by Springer Nature
- p. 163-180
Harnessing Artificial Intelligence and Machine Learning in English Language Teaching: Trends and Applications
- 1 October 2025
- Published by Springer Nature
- p. 125-142
Comparative Analysis of Machine Learning Techniques in the Oil and Gas Pipeline and Automobile Industries
- 1 October 2025
- Published by Springer Nature
- p. 125-142
Comparative Analysis of Machine Learning Techniques in the Oil and Gas Pipeline and Automobile Industries
- RetractedOpen Access
- 22 May 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-12
RETRACTED ARTICLE: Optimizing credit card fraud detection with random forests and SMOTE
In the financial world, Credit card fraud is a budding apprehension in the banking sector, necessitating the development of efficient detection methods to minimize financial losses. The usage of credit cards is experiencing a steady increase, thereby leading to a rise in the default rate that banks encounter. Although there has been much research investigating the efficacy of conventional Machine Learning (ML) models, there has been relatively less emphasis on Deep Learning (DL) techniques. In this article, a machine learning-based system to detect fraudulent transactions using a publicly available dataset of credit card transactions. The dataset, highly imbalanced with fraudulent transactions representing less than 0.2% of the total, was processed using techniques like Synthetic Minority Over-sampling Technique (SMOTE) to handle class imbalance. To predict credit card default, this study evaluates the efficacy of a DL (Deep Learning) model and compares it to other ML models, such as Decision Tree (DT) and Adaboost. The objective of this research is to identify the specific DL parameters that contribute to the observed enhancements in the accuracy of credit card default prediction. This research makes use of the UCI ML repository to access the credit card defaulted customer dataset. Subsequently, various techniques are employed to pre-process the unprocessed data and visually present the outcomes through the use of exploratory data analysis (EDA). Furthermore, the algorithms are hyper tuned to evaluate the enhancement in prediction. We used standard evaluation metrics to evaluate all the models. The evaluation indicates that the Adaboost and DT exhibit the highest accuracy rate of 82 % in predicting credit card default, surpassing the accuracy of the ANN model, which is 78 %. Several classification algorithms, comprising Logistic Regression, Random Forest, and Neural Networks, were evaluated to determine their effectiveness in identifying fraudulent activities. The Random Forest model emerged as the best performing algorithm with an accuracy of 99.5% and a high recall score, indicating its robustness in detecting fraudulent transactions. This system can be deployed in real-time financial systems to enhance fraud prevention mechanisms and ensure secure financial transactions.
- 22 May 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-12
RetractedOpen AccessRETRACTED ARTICLE: Optimizing credit card fraud detection with random forests and SMOTE
In the financial world, Credit card fraud is a budding apprehension in the banking sector, necessitating the development of efficient detection methods to minimize financial losses. The usage of credit cards is experiencing a steady increase, thereby leading to a rise in the default rate that banks encounter. Although there has been much research investigating the efficacy of conventional Machine Learning (ML) models, there has been relatively less emphasis on Deep Learning (DL) techniques. In this article, a machine learning-based system to detect fraudulent transactions using a publicly available dataset of credit card transactions. The dataset, highly imbalanced with fraudulent transactions representing less than 0.2% of the total, was processed using techniques like Synthetic Minority Over-sampling Technique (SMOTE) to handle class imbalance. To predict credit card default, this study evaluates the efficacy of a DL (Deep Learning) model and compares it to other ML models, such as Decision Tree (DT) and Adaboost. The objective of this research is to identify the specific DL parameters that contribute to the observed enhancements in the accuracy of credit card default prediction. This research makes use of the UCI ML repository to access the credit card defaulted customer dataset. Subsequently, various techniques are employed to pre-process the unprocessed data and visually present the outcomes through the use of exploratory data analysis (EDA). Furthermore, the algorithms are hyper tuned to evaluate the enhancement in prediction. We used standard evaluation metrics to evaluate all the models. The evaluation indicates that the Adaboost and DT exhibit the highest accuracy rate of 82 % in predicting credit card default, surpassing the accuracy of the ANN model, which is 78 %. Several classification algorithms, comprising Logistic Regression, Random Forest, and Neural Networks, were evaluated to determine their effectiveness in identifying fraudulent activities. The Random Forest model emerged as the best performing algorithm with an accuracy of 99.5% and a high recall score, indicating its robustness in detecting fraudulent transactions. This system can be deployed in real-time financial systems to enhance fraud prevention mechanisms and ensure secure financial transactions.
- 20 September 2024
- Published by Springer Nature in Optical and Quantum Electronics
- Vol. 56 (10) , 1-15
A novel moon-shaped flexible four-element co-planar antenna for 5G applications
- 20 September 2024
- Published by Springer Nature in Optical and Quantum Electronics
- Vol. 56 (10) , 1-15
A novel moon-shaped flexible four-element co-planar antenna for 5G applications
- 16 September 2024
- Published by Springer Nature
- p. 295-303
Harnessing AI Mining Methodologies to Anticipate the Probability of Gestational Diabetes Mellitus Occurrence
- 16 September 2024
- Published by Springer Nature
- p. 295-303
Harnessing AI Mining Methodologies to Anticipate the Probability of Gestational Diabetes Mellitus Occurrence
- Open Access
- 8 August 2024
- Published by IOP Publishing in Physica Scripta
- Vol. 99 (9) , 095530
A four-element metasurface loaded high gain MIMO antenna for X-band applications
This research presents a novel four-port metamaterial-backed Multiple Input Multiple Output (MIMO) antenna system designed for X-band applications. Each modified circular-shaped antenna element is meticulously printed on a 1.6 mm thick FR4 substrate, resonating within the 9.2 to 9.9 GHz frequency range, encompassing a significant portion of the X-band spectrum. To enhance overall gain, a tilted square-shaped 4 × 4-unit cell is strategically printed on the ground plane of the substrate. The proposed MIMO antenna achieves a maximum gain of up to 8 dBi across the operating spectrum, coupled with an impressive radiation efficiency of up to 80%. Fabrication of the designed antenna is performed, and comprehensive parameter measurements validate its performance, exhibiting a close correlation with simulated results. Essential MIMO parameters such as ECC (10 dB), CCL (<0.3), and diversity gain are calculated to affirm the antenna’s proficiency further. The results show that the proposed antenna could be a suitable contender for X-band applications.
- 8 August 2024
- Published by IOP Publishing in Physica Scripta
- Vol. 99 (9) , 095530
Open AccessA four-element metasurface loaded high gain MIMO antenna for X-band applications
This research presents a novel four-port metamaterial-backed Multiple Input Multiple Output (MIMO) antenna system designed for X-band applications. Each modified circular-shaped antenna element is meticulously printed on a 1.6 mm thick FR4 substrate, resonating within the 9.2 to 9.9 GHz frequency range, encompassing a significant portion of the X-band spectrum. To enhance overall gain, a tilted square-shaped 4 × 4-unit cell is strategically printed on the ground plane of the substrate. The proposed MIMO antenna achieves a maximum gain of up to 8 dBi across the operating spectrum, coupled with an impressive radiation efficiency of up to 80%. Fabrication of the designed antenna is performed, and comprehensive parameter measurements validate its performance, exhibiting a close correlation with simulated results. Essential MIMO parameters such as ECC (10 dB), CCL (<0.3), and diversity gain are calculated to affirm the antenna’s proficiency further. The results show that the proposed antenna could be a suitable contender for X-band applications.