Sanmugasundaram Ravichandran
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Sanmugasundaram Ravichandran has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Hui-Kai Su
Department of Electrical Engineering, National Formosa University, Yunlin 632, Taiwan
4 shared publications - Manikandan Mahalingam
Department of Electronics and Communication Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai 600062, India
3 shared publications - Bruhathi Sathyanarayanan
Department of Computer and Communication Engineering, Rajalakshmi Institute of Technology, Chennai 600124, India
2 shared publications - Dileepan Dhanasekaran
Department of Electronics & Communication Engineering, Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology, Chennai 600062, India
2 shared publications - Kabilan Saravanan
Department of Electronics and Communication Engineering, Rajalakshmi Institute of Technology, Chennai 600124, India
2 shared publications - Kanimozhi Janarthanan
Department of Computer and Communication Engineering, Rajalakshmi Institute of Technology, Chennai 600124, India
2 shared publications
Latest Publications
- Open Access
Parallel Processing of Sobel Edge Detection on FPGA: Enhancing Real-Time Image Analysis
Detection of object boundaries and significant features within an image is one of the most important processes in image processing and computer vision, as it allows the identification of object boundaries and significant features within an image. In applications such as autonomous vehicles, surveillance systems, and medical imaging, real-time processing has become increasingly important, which requires hardware accelerators. In this paper, the improved Sobel edge detection algorithm was implemented using Verilog as an FPGA-based algorithm designed to perform real-time image processing under the Sobel edge detection algorithm for specially RGB images. The proposed design proposes an application of horizontal and vertical Sobel kernels in parallel in order to compute the gradient magnitudes for 1028 × 720 RGB images by taking the gradient magnitudes of 3 × 3 pixel windows. This work focuses on algorithmic complex reduction by using eight directional approaches, and parallel processing leads to reducing the architectural utilization.
Open AccessParallel Processing of Sobel Edge Detection on FPGA: Enhancing Real-Time Image Analysis
Detection of object boundaries and significant features within an image is one of the most important processes in image processing and computer vision, as it allows the identification of object boundaries and significant features within an image. In applications such as autonomous vehicles, surveillance systems, and medical imaging, real-time processing has become increasingly important, which requires hardware accelerators. In this paper, the improved Sobel edge detection algorithm was implemented using Verilog as an FPGA-based algorithm designed to perform real-time image processing under the Sobel edge detection algorithm for specially RGB images. The proposed design proposes an application of horizontal and vertical Sobel kernels in parallel in order to compute the gradient magnitudes for 1028 × 720 RGB images by taking the gradient magnitudes of 3 × 3 pixel windows. This work focuses on algorithmic complex reduction by using eight directional approaches, and parallel processing leads to reducing the architectural utilization.
- Open Access
Federated Learning and EEL-Levy Optimization in CPS ShieldNet Fusion: A New Paradigm for Cyber–Physical Security
As cyber–physical systems are applied not only to crucial infrastructure but also to day-to-day technologies, from industrial control systems through to smart grids and medical devices, they have become very significant. Cyber–physical systems are a target for various security attacks, too; their growing complexity and digital networking necessitate robust cybersecurity solutions. Recent research indicates that deep learning can improve CPS security through intelligent threat detection and response. We still foresee limitations to scalability, data privacy, and handling the dynamic nature of CPS environments in existing approaches. We developed the CPS ShieldNet Fusion model as a comprehensive security framework for protecting CPS from ever-evolving cyber threats. We will present a model that integrates state-of-the-art methodologies in both federated learning and optimization paradigms through the combination of the Federated Residual Convolutional Network (FedRCNet) and the EEL-Levy Fusion Optimization (ELFO) methods. This involves the incorporation of the Federated Residual Convolutional Network into an optimization method called EEL-Levy Fusion Optimization. This preserves data privacy through decentralized model training and improves complex security threat detection. We report the results of a rigorous evaluation of CICIoT-2023, Edge-IIoTset-2023, and UNSW-NB datasets containing the CPS ShieldNet Fusion model at the forefront in terms of accuracy and effectiveness against several threats in different CPS environments. Therefore, these results underline the potential of the proposed framework to improve CPS security by providing a robust and scalable solution to current problems and future threats.
Open AccessFederated Learning and EEL-Levy Optimization in CPS ShieldNet Fusion: A New Paradigm for Cyber–Physical Security
As cyber–physical systems are applied not only to crucial infrastructure but also to day-to-day technologies, from industrial control systems through to smart grids and medical devices, they have become very significant. Cyber–physical systems are a target for various security attacks, too; their growing complexity and digital networking necessitate robust cybersecurity solutions. Recent research indicates that deep learning can improve CPS security through intelligent threat detection and response. We still foresee limitations to scalability, data privacy, and handling the dynamic nature of CPS environments in existing approaches. We developed the CPS ShieldNet Fusion model as a comprehensive security framework for protecting CPS from ever-evolving cyber threats. We will present a model that integrates state-of-the-art methodologies in both federated learning and optimization paradigms through the combination of the Federated Residual Convolutional Network (FedRCNet) and the EEL-Levy Fusion Optimization (ELFO) methods. This involves the incorporation of the Federated Residual Convolutional Network into an optimization method called EEL-Levy Fusion Optimization. This preserves data privacy through decentralized model training and improves complex security threat detection. We report the results of a rigorous evaluation of CICIoT-2023, Edge-IIoTset-2023, and UNSW-NB datasets containing the CPS ShieldNet Fusion model at the forefront in terms of accuracy and effectiveness against several threats in different CPS environments. Therefore, these results underline the potential of the proposed framework to improve CPS security by providing a robust and scalable solution to current problems and future threats.
- Open Access
- 11 April 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 92 (1) , 7
Guarded Diagnosis: Preserving Privacy in Cervical Cancer Detection with Convolutional Neural Networks on Pap Smear Images
Advancements in image processing have advanced medical diagnostics, especially in image classification, impacting healthcare by offering faster and more accurate analyses of magnetic resonance imaging (MRI) and X-rays. The manual examination of these images is slow, error-prone, and costly. Therefore, we propose a new method focusing on the Pap smear exam for early cervical cancer detection. Using a convolutional neural network (CNN) and the SIPaKMeD dataset, cervical cells are classified into normal, precancerous, and benign cells after segmentation. The CNN’s architecture is simple yet efficient, achieving a 91.29% accuracy.
- 11 April 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 92 (1) , 7
Open AccessGuarded Diagnosis: Preserving Privacy in Cervical Cancer Detection with Convolutional Neural Networks on Pap Smear Images
Advancements in image processing have advanced medical diagnostics, especially in image classification, impacting healthcare by offering faster and more accurate analyses of magnetic resonance imaging (MRI) and X-rays. The manual examination of these images is slow, error-prone, and costly. Therefore, we propose a new method focusing on the Pap smear exam for early cervical cancer detection. Using a convolutional neural network (CNN) and the SIPaKMeD dataset, cervical cells are classified into normal, precancerous, and benign cells after segmentation. The CNN’s architecture is simple yet efficient, achieving a 91.29% accuracy.
- Open Access
- 11 April 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 92 (1) , 8
Revolutionizing Prenatal Care: Harnessing Machine Learning for Gestational Diabetes Anticipation
We implemented a robust framework for diabetes prediction, leveraging a diverse array of machine learning algorithms. Through an analysis of diabetes-related characteristics, we identified the most accurate classifier. Diverse algorithms were tested to compare their accuracies with the complexities of data: K-nearest neighbors (KNN), random forest (RF), support vector machine (SVM), logistic regression (LR), Naïve Bayes (NB), and decision tree (DT). The decision tree algorithm demonstrated the best accuracy in predicting diabetes.
- 11 April 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 92 (1) , 8
Open AccessRevolutionizing Prenatal Care: Harnessing Machine Learning for Gestational Diabetes Anticipation
We implemented a robust framework for diabetes prediction, leveraging a diverse array of machine learning algorithms. Through an analysis of diabetes-related characteristics, we identified the most accurate classifier. Diverse algorithms were tested to compare their accuracies with the complexities of data: K-nearest neighbors (KNN), random forest (RF), support vector machine (SVM), logistic regression (LR), Naïve Bayes (NB), and decision tree (DT). The decision tree algorithm demonstrated the best accuracy in predicting diabetes.
- Open Access
- 1 October 2019
- Published by IOP Publishing in IOP Conference Series: Materials Science and Engineering
- Vol. 590 (1) , 012061
Coplanar Waveguide fed MIMO RDR Antenna for ISM Band Frequencies
A Multiple-Input-Multiple-Output (MIMO) Rectangular Dielectric Resonator Antenna (RDRA) is presented in this paper for industrial scientific and medical applications with 2.45 GHz. The geomentry of proposed antenna is fabricated on low cost FR-4 substrate with dielectric constant of 4.4 with coplanar waveguide (CPW) inductive slot and its physical dimension is 69.3 X 73 X 1.6 mm3 (Length x Width x Height). In this work, RDRA uses two orthogonal modes with two different mechanisms and they are coplanar waveguide (CPW) and coaxial probe. The proposed MIMO RDR Antenna is expected to give various features such as isolation beyond 20 dBi range over the frequency of operation, positive gain, VSWR, Z-parameters display, 2-D current distribution using azimuthal and elevation patterns.
- 1 October 2019
- Published by IOP Publishing in IOP Conference Series: Materials Science and Engineering
- Vol. 590 (1) , 012061
Open AccessCoplanar Waveguide fed MIMO RDR Antenna for ISM Band Frequencies
A Multiple-Input-Multiple-Output (MIMO) Rectangular Dielectric Resonator Antenna (RDRA) is presented in this paper for industrial scientific and medical applications with 2.45 GHz. The geomentry of proposed antenna is fabricated on low cost FR-4 substrate with dielectric constant of 4.4 with coplanar waveguide (CPW) inductive slot and its physical dimension is 69.3 X 73 X 1.6 mm3 (Length x Width x Height). In this work, RDRA uses two orthogonal modes with two different mechanisms and they are coplanar waveguide (CPW) and coaxial probe. The proposed MIMO RDR Antenna is expected to give various features such as isolation beyond 20 dBi range over the frequency of operation, positive gain, VSWR, Z-parameters display, 2-D current distribution using azimuthal and elevation patterns.