Utilizing Optimized Mixed-Order Relation-Aware Recurrent Neural Network for Metacarpophalangeal Rheumatoid Arthritis Grading via Ultrasound Images G. Sudha, M. Mohammadha Hussaini, T. Dharma Raj, Veeresh R. K. Ultrasonic Imaging, 2026 The diagnostic problem of grading evaluation of ultrasonic images of Metacarpophalangeal rheumatoid arthritis (RA) is mostly dependent on the skills of sonographers with training. A grading system is used to identify and evaluate the geometric and textural features of bone deterioration and synovium thickening. In this manuscript, utilizing optimized mixed-order relation-aware recurrent neural network for metacarpophalangeal rheumatoid arthritis grading via ultrasound images (MRAG-UI-MORARNN-BWKA) is proposed. First, Tianjin University of Traditional Chinese Medicine’s First Teaching Hospital provides the input ultrasound images. The pre-processing step uses confidence partitioning sampling filtering (CPSF) to resize the input images and eliminate background noise. Afterward, the pre-processed images were given to unpaired multi-view graph clustering (UMGC) for segmenting the region of interest (ROI). The holistic dynamic frequency transformer (HDFT) was used for extracting the geometric features like area, thickness, and shape. The Black winged kite algorithm (BWKA) was then employed to optimize the mixed-order relation-aware recurrent neural network (MORARNN) for precise grading of rheumatoid arthritis detection, with grades 0 (no synovium thickening), 1, 2, and 3 (mild, moderate, and severe, respectively). Python is used in the implementation of the proposed MRAG-UI-MORARNN-BWKA method. The proposed strategy achieves significant improvements over existing methods in grading rheumatoid arthritis via ultrasound images. The proposed model attains an accuracy of 97.02%, precision of 97.5% and sensitivity of 97.25%, respectively. These results clearly indicate the better performance and robustness of the proposed method analyzed to existing methods.
EEG SIGNAL ANALYSIS FOR CLASSIFYING ALZHEIMER’S AND FRONTOTEMPORAL DEMENTIA DISORDERS USING ENSEMBLE METHODS G Sudha, N Mohankumar, Gousia Thahniyath, Raja Thimmarayan International Journal of Advances in Signal and Image Sciences, 2025 Accurate identification of neurodegenerative disorders, including Alzheimer’s Disease (AD) and Frontotemporal Dementia (FTD), is crucial for prompt medical intervention. This research introduces an EEG-based ensemble classification framework aimed at differentiating between AD, FTD, and Cognitively Normal (CN) people. The system uses ElectroEncephaloGram (EEG) signals derived from the publicly accessible dataset from Kaggle. Independent Component Analysis (ICA) is used for preprocessing to remove artefacts and noise. The important key characteristics are identified and chosen by Recursive Feature Elimination (RFE) to provide optimum input for classification from the features of Discrete Wavelet Transform (DWT) sub-bands. Several classifiers, including Support Vector Machine (SVM), Random Forest (RF), and Artificial Neural Network (ANN), are trained, and their predictions are aggregated using Logistic Regression (LR) as the meta-classifier. The resulting model has exceptional diagnostic performance, with the LR ensemble achieving an accuracy of 98.98% in differentiating the three subject groups. Results proved the capability of combining EEG signal analysis with ensemble learning techniques to enhance clinical decision making for the early identification of dementia-related disorders.
Base-Station Slot Antenna for Milli-Meter Wave Application Using SIW Technology S Elango, K Sakthimurugan, G Sudha, J Kirubakaran, K Hazee Shabbeer Basha, S. Selvarasu Proceedings IEEE 10th International Conference on Smart Structures and Systems Icsss 2025, 2025 This work analyzes a slot-based antenna structure designed to operate at millimetre-wave frequencies. The investigation focuses on a rectangular slot etched on the top conductor of the SIW and includes design, modelling, and performance evaluation. Copper is the conducting material, while Roggers is the material utilised to construct SIW structures. Parameters like S11, voltage standing wave ratio, and Radiation Pattern (RP) are used to assess the suggested model. High isolation and efficient impedance matching at the ports are revealed by S parameter simulations. With values ranging from roughly 1.2 to 3.5, the VSWR analysis shows moderate to good impedance matching. The simulated field patterns match the performance parameters of the device, and high field intensity is seen close to the SIW’s edges and perforations. At certain frequencies, the device shows very little reflection, indicating improved transmission efficiency. This showed that the millimetre wave frequency is a good fit for the suggested design.
GreenSterz: Solar Driven Autoclave for Medical Sharps Sterilization in Rural Healthcare Anjali Ashank Chandane, S.B. Abitha, R. Santhoshi, G. Sudha, K. Shivashanker, A. Swetha Anand 2025 2nd International Conference on Circuits Power and Intelligent Systems Ccpis 2025, 2025 The healthcare sector in rural areas faces significant challenges due to unreliable electricity, inadequate medical sharps waste management, and limited access to essential resources. This paper presents GreenSterz Solution, an integrated approach that utilizes a data handling system for medical sharps waste management and a solar-powered autoclave system for sterilization. The proposed system aims to address two critical issues: improving the transparency and efficiency of waste disposal processes through a web application and reducing reliance on unstable energy sources by utilizing solar energy for autoclave operation. The integration of Internet of Things sensors enables real-time monitoring of waste metrics and autoclave operations, ensuring consistent performance and accountability. By employing a monocrystalline Photovoltaic array, the system generates sustainable energy for autoclave operation, while a battery stores energy for continuous use. The application platform provides a secure, decentralized ledger to track medical waste disposal, ensuring compliance with regulatory standards. The solar-powered autoclave, optimized for rural settings, reduces the dependency on local electricity grids and ensures effective sterilization of medical instruments. This research demonstrates the feasibility and impact of this integrated solution, offering an eco-friendly and cost-effective approach to healthcare in resource-limited regions. Future work will focus on scaling this solution for broader applications and conducting field trials to assess its long-term performance.
Multi Class Retinal Disorder Detection Using VGG 19 with PCA Enabled Feature Reduction and SVM G Sudha, M Birunda, R Usha, S Elango, M Hariharan, C Selvi Proceedings IEEE 10th International Conference on Smart Structures and Systems Icsss 2025, 2025 Collection of fluids in the macula, the core part of retina that provides clear, complete vision, is a defining feature of macular edema, a dangerous retinal disorder. Retinal vein occlusion and diabetic retinopathy are two underlying diseases that often cause it. If treatment is not received, it can cause blurry vision and possibly blindness. In this study investigates the classification of macular edema using OCT images through DL and hybrid ML techniques At first, the preprocessed OCT images were classified using the VGG19 model, which produced a accuracy of 93%, a recollection of 92%, F1-score 92%, and overall accuracy of 94%. To enhance performance, VGG19 features were further optimized using PCA and classified with an SVM, resulting in improved metrics of accuracy of 95%, accuracy of 95%, recollection of $95 \%$, F1 score of 95 %, and a higher AUC. Comparative analysis shows that the VGG19 PCA SVM model offers superior classification capability and greater reliability.
Infrared thermal images using PCSAN-Net-DBOA: An approach of breast cancer classification S. M. Vijayarajan, D. Manoj Kumar, G. Sudha, A. Basi Reddy Microscopy Research and Technique, 2024 This manuscript proposes thermal images using PCSAN‐Net‐DBOA Initially, the input images are engaged from the database for mastology research with infrared image (DMR‐IR) dataset for breast cancer classification. The adaptive distorted Gaussian matched‐filter (ADGMF) was used in removing noise and increasing the quality of infrared thermal images. Next, these preprocessed images are given into one‐dimensional quantum integer wavelet S‐transform (OQIWST) for extracting Grayscale statistic features like standard deviation, mean, variance, entropy, kurtosis, and skewness. The extracted features are given into the pyramidal convolution shuffle attention neural network (PCSANN) for categorization. In general, PCSANN does not show any adaption optimization techniques to determine the optimal parameter to offer precise breast cancer categorization. This research proposes the dung beetle optimization algorithm (DBOA) to optimize the PCSANN classifier that accurately diagnoses breast cancer. The BCD‐PCSANN‐DBO method is implemented using Python. To classify breast cancer, performance metrics including accuracy, precision, recall, F1 score, error rate, RoC, and computational time are considered. Performance of the BCD‐PCSANN‐DBO approach attains 29.87%, 28.95%, and 27.92% lower computation time and 13.29%, 14.35%, and 20.54% greater RoC compared with existing methods like breast cancer diagnosis utilizing thermal infrared imaging and machine learning approaches(BCD‐CNN), breast cancer classification from thermal images utilizing Grunwald‐Letnikov assisted dragonfly algorithm‐based deep feature selection (BCD‐VGG16) and Breast cancer detection in thermograms using deep selection based on genetic algorithm and Gray Wolf Optimizer (BCD‐SqueezeNet), respectively.Research Highlights The input images are engaged from the breast cancer dataset for breast cancer classification. The ADQMF was used in removing noise and increasing the quality of infrared thermal images. The extracted features are given into the PCSANN for categorization. DBOA is proposed to optimize PCSANN classifier that classifies breast cancer precisely. The proposed BCD‐PCSANN‐DBO method is implemented using Python.
Combined localization and clustering approach for reduced energy presumption in heterogeneous IoT Jasmine Xavier A, Suthanthira Vanitha N, Sudha G, Birunda M Physica Scripta, 2024 The field of H-IoT is emerging with enormous potential to empower various technologies. Smart cities and advanced manufacturing are a few of the fields where H-IoT is currently used. The issue with H-IoT is its heavy energy consumption while transmitting data, which makes scaling difficult. To overcome such issues, a hybrid approach of Crayfish Optimization (CFO) with FCM and Restricted Boltzmann Machine (RBM) with Soft Sign Activation (SSA) has been proposed. Initially, Node initialization lays the foundation by configuring individual sensor nodes for network participation. After initialization, Fuzzy C Means clustering optimizes data aggregation by categorizing nodes into clusters based on similarity. Gathering Neighbor Node Traffic Data (NNTD) provides insights into communication patterns. Based on the threshold of NNTD, node localization is performed that enhances network accuracy by pinpointing sensor node locations. Integration of CFO into clustering, along with localization further improves cluster head selection for optimal data routing. Classification through the RBM with SSA function enhances anomaly detection, combining data analysis for optimizing energy utilization in heterogeneous IoT environments. The ‘combined CFO-FCM and SSA-RBM’ has been implemented in MATLAB and achieved an accuracy of 94.50%. As a result, the overall performance of the system is improved.
A study on blockchain's transformation of healthcare systems M. Rajkumar, G. Sudha, Ruchi Agarwal, V. Elizabeth Jesi, N. Bagyalakshmi, M. Sudhakar Lightweight Digital Trust Architectures in the Internet of Medical Things Iomt, 2024 Blockchain technology has emerged as a transformative force in the healthcare sector, and this chapter explores the emerging applications of blockchain technology in the global healthcare system through a series of case studies. The case studies cover a wide range of use cases, such as electronic health records, clinical trials, patient privacy and consent management, pharmaceutical supply chain management, and medical research. The findings underscore the potential of blockchain to revolutionize healthcare by improving data security, enhancing transparency and accountability, enabling patient-centric care, and fostering collaboration among stakeholders. However, challenges such as scalability, privacy concerns, regulatory frameworks, and interoperability need to be addressed for widespread adoption. The chapter concludes with a call for further exploration and adoption of blockchain technology in healthcare to improve patient outcomes.
Digital Diagnosis of Mouth Disease Using Deep Learning Algorithms G. Sudha, M. Mohammadha Hussani, N. Bagyalakshmi, R. Avanthika, M. Saraswathi, S. Renuka Proceedings of the 2024 10th International Conference on Biosignals Images and Instrumentation Icbsii 2024, 2024
Design of Compact Folded SIW Hybrid Coupler for Ka Band Application K. Harini, T.R. Ganesh Babu, R. Praveena, G. Sudha, K. Gokul Kannan, J. Gnanasoundharam Proceedings of the 2022 3rd International Conference on Intelligent Computing Instrumentation and Control Technologies Computational Intelligence for Smart Systems Icicict 2022, 2022
Analysis of Neural Networks for Object Detection using Image Processing Techniques R. Praveena, T.R. Ganesh Babu, K. Sakthimurugan, G. Sudha, M. Birunda, J. Surendiran Proceedings of the 2022 3rd International Conference on Intelligent Computing Instrumentation and Control Technologies Computational Intelligence for Smart Systems Icicict 2022, 2022
RECENT SCHOLAR PUBLICATIONS
Energy Efficient Internet of Things and Wireless Sensor Networks in Smart Agriculture NS Vanitha, G Sudha, J Gowrishankar, K Radhika, A Kalaiyarasan, ... Energy Efficient Internet of Things‐Based Wireless Sensor Network, 429-452 , 2026 2026
Cryptography of Radiology Images for PACS system using DWT and Advanced Encryption standard with Swarm Intelligence based Optimization PS Venugopal, D Sasikala, G Sudha, R Selvaraj 2026 International Conference on Smart Electronic Devices and Intelligent … , 2026 2026
A Review on Artificial Intelligence for Smart Agriculture NS Vanitha, J Gowrishankar, G Sudha, K Radhika, CS Satheesh, ... New Technologies in Agronomy for Sustainability, 77-102 , 2026 2026
A review on integration of Virtual Internet of Things (VIoT) for smart healthcare NS Vanitha, B Nirajenadevi, K Radhika, SK Devi, G Sudha, A Mubarakali Virtual Internet of Things: Smart Environments, Smart Healthcare, Industry 4 … , 2025 2025
Multi Class Retinal Disorder Detection Using VGG 19 with PCA Enabled Feature Reduction and SVM G Sudha, M Birunda, R Usha, S Elango, M Hariharan, C Selvi 2025 10th International Conference on Smart Structures and Systems (ICSSS), 1-7 , 2025 2025
Base-Station Slot Antenna for Milli-Meter Wave Application Using SIW Technology S Elango, K Sakthimurugan, G Sudha, J Kirubakaran, KHS Basha, ... 2025 10th International Conference on Smart Structures and Systems (ICSSS), 1-7 , 2025 2025
Utilizing Optimized Mixed-Order Relation-Aware Recurrent Neural Network for Metacarpophalangeal Rheumatoid Arthritis Grading via Ultrasound Images G Sudha, MM Hussaini, T Dharma Raj, V RK Ultrasonic Imaging, 01617346251389620 , 2025 2025
Variational Onsager Neural Network optimized with Golden search optimization algorithm fostered for lung disease detection system in IoT G Sudha, V Angayarkanni, KR Kanagavalli, T Pattewar Biomedical Signal Processing and Control 108, 107951 , 2025 2025 Citations: 2
GreenSterz: Solar Driven Autoclave for Medical Sharps Sterilization in Rural Healthcare AA Chandane, SB Abitha, R Santhoshi, G Sudha, K Shivashanker, ... 2025 2nd International Conference on Circuits, Power and Intelligent Systems … , 2025 2025
EEG SIGNAL ANALYSIS FOR CLASSIFYING ALZHEIMER’S AND FRONTOTEMPORAL DEMENTIA DISORDERS USING ENSEMBLE METHODS G. Sudha, N. Mohankumar, G. Thahniyath, and R. Thimmarayan INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES Current … , 2025 2025 Citations: 15
Emerging Technologies for 6G Communication System I Kalphana, R Praveena, S Elango, S Thulasi, TRG Babu, G Sudha International Conference on Signal Processing and Computer Vision (SIPCOV … , 2024 2024
Remote Monitoring and Analytics For Cloud-Based Drip Saline Fluid Management System J Gnanasoundharam, G Sudha, JAJ Singh, M Birunda, EN Ganesh 2024 5th International Conference on Smart Electronics and Communication … , 2024 2024 Citations: 1
Implementation of embedded system based poultry feeding trolley automation N Mahesh, K Prabhu, G Sudha, S Dharun 2024 5th International Conference on Smart Electronics and Communication … , 2024 2024 Citations: 2
Infrared thermal images using PCSAN‐Net‐DBOA: An approach of breast cancer classification SM Vijayarajan, D Manoj Kumar, G Sudha, AB Reddy Microscopy Research and Technique 87 (8), 1742-1752 , 2024 2024 Citations: 5
Combined localization and clustering approach for reduced energy presumption in heterogeneous IoT G Sudha, M Birunda Physica Scripta 99 (7), 075222 , 2024 2024
Digital Diagnosis of Mouth Disease Using Deep Learning Algorithms G Sudha, MM Hussani, N Bagyalakshmi, R Avanthika, M Saraswathi, ... 2024 Tenth International Conference on Bio Signals, Images, and … , 2024 2024 Citations: 2
Dynamically stabilized recurrent neural network optimized with Artificial Gorilla Troops espoused Alzheimer’s disorder detection using EEG signals MMMB G. Sudha, N. Saravanan Health Information Science and Systems 12 (25) , 2024 2024 Citations: 5
Wearable Sepsis Early Warning Using Cloud Computing and Logistic Regression Predictive Analytics JAJ Singh, J Gnanasoundharam, M Birunda, G Sudha, SP Maniraj, ... 2024 11th International Conference on Reliability, Infocom Technologies and … , 2024 2024 Citations: 63
NON INVASIVE CHOLESTEROL AND GLUCOSE DETECTION USING FINGER PRINT RSR G.Sudha , M.Mohammadha Hussani , N.Bagyalakshmi , S.Gokul Raj , A.Harish African Journal of Biological Sciences 6 (10), 881-886 , 2024 2024
Wearable Sepsis Early Warning Using Cloud Computing and Logistic Regression Predictive Analytics JAJ Singh, J Gnanasoundharam, M Birunda, G Sudha, SP Maniraj, ... 2024 11th International Conference on Reliability, Infocom Technologies and … , 2024 2024 Citations: 63
Prediction of rainfall analysis using logistic regression and support vector machine R Praveena, TRG Babu, M Birunda, G Sudha, P Sukumar, ... Journal of Physics: Conference Series 2466 (1), 012032 , 2023 2023 Citations: 26
EEG SIGNAL ANALYSIS FOR CLASSIFYING ALZHEIMER’S AND FRONTOTEMPORAL DEMENTIA DISORDERS USING ENSEMBLE METHODS G. Sudha, N. Mohankumar, G. Thahniyath, and R. Thimmarayan INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES Current … , 2025 2025 Citations: 15
Classification of WBC cell classification using fully connected convolution neural network K Gokul Kannan, TR Ganesh Babu, R Praveena, P Sukumar, G Sudha, ... Journal of Physics: Conference Series 2466 (1), 012033 , 2023 2023 Citations: 11
A Novel Data Mining Based Approach for Healthcare Applications G Sudha, M Birunda, J Gnanasoundharam, JAJ Singh International Journal of Industrial Engineering 6 (2), 34-40 , 2022 2022 Citations: 10
Design of compact folded siw hybrid coupler for ka band application K Harini, TRG Babu, R Praveena, G Sudha, KG Kannan, ... 2022 Third International Conference on Intelligent Computing Instrumentation … , 2022 2022 Citations: 10
Analysis of Neural Networks for Object Detection using Image Processing Techniques R Praveena, TRG Babu, K Sakthimurugan, G Sudha, M Birunda, ... 2022 Third International Conference on Intelligent Computing Instrumentation … , 2022 2022 Citations: 8
Performance based comparison between various ZN tuninng PID and fuzzy logic PID controller in position control system of DC motor G Sudha, R Anita International Journal on Soft Computing 3 (3), 55 , 2012 2012 Citations: 8
Infrared thermal images using PCSAN‐Net‐DBOA: An approach of breast cancer classification SM Vijayarajan, D Manoj Kumar, G Sudha, AB Reddy Microscopy Research and Technique 87 (8), 1742-1752 , 2024 2024 Citations: 5
Dynamically stabilized recurrent neural network optimized with Artificial Gorilla Troops espoused Alzheimer’s disorder detection using EEG signals MMMB G. Sudha, N. Saravanan Health Information Science and Systems 12 (25) , 2024 2024 Citations: 5
Distracted driver detection using deep learning classifier of image net models R Praveena, TRG Babu, G Sudha, M Birunda, J Gnanasoundharam, ... 2022 international conference on augmented intelligence and sustainable … , 2022 2022 Citations: 4
Design of Tilted E-Shaped Monopole Antenna for Vehicular Communication R Praveena, TRG Babu, G Sudha, N Mahesh, J Ganasoundharam, ... 2022 8th International Conference on Smart Structures and Systems (ICSSS), 1-6 , 2022 2022 Citations: 4
ALCOHOL SENSOR BASED VEHICLE IGNITION CONTROL SYSTEM USING ARDUINO UNO G Sudha, P Pavithra, P Priya, M Manikandan International Research Journal of Modernization in Engineering Technology … , 2020 2020 Citations: 3
Variational Onsager Neural Network optimized with Golden search optimization algorithm fostered for lung disease detection system in IoT G Sudha, V Angayarkanni, KR Kanagavalli, T Pattewar Biomedical Signal Processing and Control 108, 107951 , 2025 2025 Citations: 2
Implementation of embedded system based poultry feeding trolley automation N Mahesh, K Prabhu, G Sudha, S Dharun 2024 5th International Conference on Smart Electronics and Communication … , 2024 2024 Citations: 2
Digital Diagnosis of Mouth Disease Using Deep Learning Algorithms G Sudha, MM Hussani, N Bagyalakshmi, R Avanthika, M Saraswathi, ... 2024 Tenth International Conference on Bio Signals, Images, and … , 2024 2024 Citations: 2
A Study on Blockchain's Transformation of Healthcare Systems MS M. Rajkumar, G. Sudha, Ruchi Agarwal, V. Elizabeth Jesi, N. Bagyalakshmi Lightweight Digital Trust Architectures in the Internet of Medical Things … , 2024 2024 Citations: 2
Deep Learning System in Curvelet Domain for Skin Cancer Diagnosis G Sudha, M Birunda, J Gnanasoundharam, JAJ Singh 2023 4th International Conference on Electronics and Sustainable … , 2023 2023 Citations: 2
Implementation of Bluetooth based boat system to clean oil spill in Coastline N Mahesh, KN Baluprithviraj, G Sudha, S Elamathi, S Hari Prasath, ... 2023 International Conference on Innovative Data Communication Technologies … , 2023 2023 Citations: 2
Lung Cancer Image Segmentation and Detection Using Deep Learning Algorithms NS G. Sudha*, M. Birunda , R. Khowshalya , S. Preneshvar , S. Jayanthiswari ... Cardiometry, 556-562 , 2023 2023 Citations: 2
