Hexapod robot for enhancing emergency response in disaster scenarios Vani R, Lalitha K, Prasanna Venkatesh, Walter Priesnitz Filho, Maria Emilia Camargo, Mithileysh Sathiyanarayanan Discover Applied Sciences, 2026 Target search operations are confronted with substantial obstacles and hazards in unstructured environments, particularly in enclosed spaces such as underground systems and collapsed structures. Traditional human-led efforts have been limited in terms of safety, accessibility, and speed. This paper proposes a hexapod walking robot that can be characterized by its fault tolerance for walking on unstructured terrains. These species mimic the motions and agilities of insects and other arthropods. The robot was equipped with an array of advanced sensors, including 360-degree LiDAR for spatial mapping and obstacle detection, infrared cameras for identifying human heat signatures in low-visibility conditions, and gas sensors for detecting hazardous substances that could pose risks to rescue teams. The hexapod robot combines manual and autonomous operational modes, providing flexible control options and enabling real-time decision making to enhance rescue efficiency while minimizing human risk. The robot has dual communication system namely LoRa and Wi-Fi. The proposed telemetry can receive the control signals above 500 m. The composite leg structure consisting of 3D printed modulator components that could be easily switched based on the environment. The novelty of this work lies in combining a robot’s dynamic stability and locomotion efficiency across various gait cycles with adaptive leg compliance.
FLOWSAFE- A Hybrid Feature-Localization Transformer Model for Flood Probability Prediction G. Vasumathi, R. Vani Proceedings of the 4th International Conference on Intelligent Data Communication Technologies and Internet of Things Idciot 2026, 2026 In disaster risk management, flood prediction task is considered as a critical component. For resilience planning and early warning at the time of flood occurrence, predicting it based on environmental, infrastructural, and socio-economic data can be of great help. In this paper, one such concept called FLOWSAFE - a novel feature-localization and weighted self-attention model for flood probability prediction from multivariate environmental and socio-economic data is proposed. It consists of three functional modules namely: Feature Action Encoder (FAE) for capturing hierarchical and multiplicative interactions among numeric predictions. Next, a Cross-Variable Self-Attention Transformer (XVSAT) is used for modelling long-range dependencies across attributes treated as tokens. Finally, the Interpretable Fusion Head (IFH) block produces the flood probability estimate while providing attention-based feature contributions for downstream decision-making. The framework is tested on a large flood prediction dataset with 21 flood-related variables (monsoon intensity, urbanization level, coastal vulnerability, siltation levels, and so on). Experimental results on FLOWSAFE show that it outperforms baseline models like ANN, LSTM, RNN, BPNN, CNN, and XGBoostthrough attainment of 0.96 in <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{R}^{2}$</tex> metric, 0.11 in RMSE, 0.95 in accuracy, and 0.08 in MAE. Overall, the developed FLOWSAFE model demonstrated improved predictive accuracy, interpretability, and generalization making it best for early flood warning tasks.
EARLY DIAGNOSIS OF GLAUCOMA BY OPTIC DISC AND OPTIC CUP SEGMENTATION OVER RETINAL FUNDUS IMAGES USING DEEP LEARNING ALGORITHM Journal of Theoretical and Applied Information Technology, 2024
Deep Learning-based Automated Knee Joint Localization in Radiographic Images Using Faster R-CNN T. Sivakumari, R. Vani Current Medical Imaging, 2024 Background:: Osteoarthritis is a condition that poses a risk to the knee joint, resulting in pain and impaired function. However, traditional knee X-ray evaluations using the Kellgren-Lawrence grading system have proven to be inefficient. These evaluations are subjective, time-consuming, and labor-intensive, particularly in busy hospital settings. Objective:: The objective of this research was to present a deep learning-based approach that can detect knee joint regions in medical images. By addressing the limitations of traditional methods, the aim was to develop a more efficient and automated approach for knee joint analysis. Methods:: The proposed method utilizes the Faster R-CNN model, which consists of a region proposal network (RPN) and Fast R-CNN. The RPN generates region proposals that potentially contain knee joint regions, while the Fast R-CNN network categorizes and extracts features from these proposals. To train the model, a dataset of knee joint images was employed. The performance of the model was evaluated using metrics, such as accuracy, precision, recall, F1-score, and mean IoU (Intersection Over Union). Results:: The results demonstrated the high accuracy of the proposed method in detecting knee joint regions. The model achieved a mean IoU of 94.5, indicating a strong overlap between the predicted and ground truth regions. These findings highlight the potential of deep learning-based approaches in automating medical image analysis, specifically in the diagnosis and management of knee joint disorders. Conclusion:: This study emphasizes the significance of leveraging advanced technologies, such as deep learning, in medical imaging. By developing more efficient and accurate methods for identifying knee joint regions in medical images, it becomes feasible to enhance patient outcomes and healthcare delivery. The proposed deep learning-based approach showcases promising results, paving the way for further advancements in the field of medical image analysis and contributing to improved diagnostic capabilities for knee joint disorders.
Smart vision-based sensing and monitoring of power plants for a clean environment K. Sujatha, R. Krishnakumar, N.P.G. Bhavani, U. Jayalatsumi, V. Srividhya, C. Kamatchi, R. Vani Intelligent Manufacturing Management Systems Operational Applications of Evolutionary Digital Technologies in Mechanical and Industrial Engineering, 2023
Computational intelligence for automation of industrial processes K. Sujatha, G. Nalinashini, N. Kanimozhi, A. Kalaivani, N.P.G. Bhavani, V. Srividhya, R. Vani Industrial Transformation Implementation and Essential Components and Processes of Digital Systems, 2022
Survey on H.264 standard R. Vani, M. Sangeetha Lecture Notes of the Institute for Computer Sciences Social Informatics and Telecommunications Engineering, 2012
RECENT SCHOLAR PUBLICATIONS
Deep Learning-Based Degradation Detection and Inpainting of Tamil Nadu Temple Murals Using Transformer Networks and Diffusion Models A Ramachandran, V Rajamanickam International Arab Journal of Information Technology (IAJIT) 23 (2), 342 , 2026 2026
Design and development of a synchronous dual-band patch antenna with enhanced bandwidth using defective ground structure (DGS) technique VL Yarram, VV Rao, A Rajesh, V Rajamanickam AIP Conference Proceedings 3342 (1), 060021 , 2025 2025
OPTIMIZING BROKERAGE COMPANY MARKETING: A WEB-BASED PERFORMANCE MONITORING SYSTEM WITH CODEIGNITER AA PERMANA, F LATIFAH, H GHARBI, MRL ELAACHAK, MRA FENNAN, ... Journal of Theoretical and Applied Information Technology 102 (15) , 2024 2024
Resource Constrained Scheduling using Behavioral Network Graph M Sangeetha, R Vani, T Vijayan I3CAC 2021: Proceedings of the First International Conference on Computing … , 2021 2021
Novel approach for melanoma detection through iterative deep vector network R Vani, JC Kavitha, D Subitha Journal of Ambient Intelligence and Humanized Computing, 1-10 , 2021 2021 Citations: 16
Performance analysis of matrix inversion algorithms for massive MIMO precoding under rural and urban scenarios D Subitha, S Velmurugan, R Vani, E Nirmala 2021 7th International Conference on Advanced Computing and Communication … , 2021 2021 Citations: 1
RETRACTED: ResNet: A convolutional Neural Network for detecting and diagnosing of coronavirus pneumonia R Angeline, R Vani IOP Conference Series: Materials Science and Engineering 1084 (1), 012011 , 2021 2021 Citations: 10
Analysis of linear precoding techniques for massive MIMO-OFDM systems under various scenarios D Subitha, R Vani IOP conference series: materials science and engineering 1084 (1), 012053 , 2021 2021 Citations: 17
Overview of Automatic Segmentation of Retinal Fundus Image for Medical Diagnosis. R Geethalakshmi, R Vani Ilkogretim Online 20 (1) , 2021 2021 Citations: 1
Recent Trends in Person Re-Identification: An Overview RV Perni Dedeepya Turkish Journal of Computer and Mathematics Education 12 (9), 1841 - 1846 , 2021 2021 Citations: 1
Development of High Yield Farming using IoT based UAV AM C Bhuvaneshwari, G Saranyadevi, R Vani IOP Conference Series: Materials Science and Engineering 1055, 1-6 , 2021 2021 Citations: 29
Sensorless Speed Control of Induction Motor Using Modern Predictive Control NPG Bhavani, M Aruna, K Sujatha, R Vani, N Priya Congress on Intelligent Systems, 675-683 , 2020 2020 Citations: 1
A Novel Unified Scheme for Missing Image Data Suggestion Based on Collaborative Generative Adversarial Network R Angeline, R Vani Congress on Intelligent Systems, 463-471 , 2020 2020
Automation of Transportation Process using IoT for Enhanced Production RA D.Subitha, R.Vani Journal of Green Engineering 10 (11), 11031-11039 , 2020 2020
Health Monitoring Wearable Device Using Internet Of Things DS R.Vani European Journal of Molecular & Clinical Medicine 7 (3), 395-400 , 2020 2020 Citations: 3
Lifetime Improvement of Wireless Sensor Networks Using Tree Based Routing Protocol RS Rajagopal, Sushaptha, R. Vani, J. C. Kavitha EAI Big Data Innovation for Sustainable Cognitive Computing, 51 - 61 , 2020 2020 Citations: 9
Waste Disposal Management System for Smart City Using LoRa G. Saranyadevi, R.Vani, V.N. Bhargavee Jour of Adv Research in Dynamical & Control Systems, 12 (3), 1360-1364 , 2020 2020 Citations: 3
Dual Axis Writing Controlled Robot for Physically Handicapped People GSD R.Vani, Vinod Kumar Udutha, Sai Krishna Prasad Kammili, Pavan Sai ... International Journal of Advance Science and Technology 29 (10s), 7515-7519 , 2020 2020
Modified Conjugate Gradient algorithms for Gram matrix Inversion of Massive MIMI downlink Linear Precoding RV D.Subitha, J.M.Mathana, J.S.Leena Jasmine International Journal of Recent Technology and Engineering 8 (2S11), 2834 – 2840 , 2019 2019 Citations: 4
Intelligent traffic control system with priority to emergency vehicles R Vani, N Thendral, JC Kavitha, NPG Bhavani IOP Conference Series: Materials Science and Engineering 455 (1), 012023 , 2018 2018 Citations: 35
MOST CITED SCHOLAR PUBLICATIONS
Intelligent traffic control system with priority to emergency vehicles R Vani, N Thendral, JC Kavitha, NPG Bhavani IOP Conference Series: Materials Science and Engineering 455 (1), 012023 , 2018 2018 Citations: 35
Development of High Yield Farming using IoT based UAV AM C Bhuvaneshwari, G Saranyadevi, R Vani IOP Conference Series: Materials Science and Engineering 1055, 1-6 , 2021 2021 Citations: 29
Analysis of linear precoding techniques for massive MIMO-OFDM systems under various scenarios D Subitha, R Vani IOP conference series: materials science and engineering 1084 (1), 012053 , 2021 2021 Citations: 17
Novel approach for melanoma detection through iterative deep vector network R Vani, JC Kavitha, D Subitha Journal of Ambient Intelligence and Humanized Computing, 1-10 , 2021 2021 Citations: 16
Survey on H. 264 standard R Vani, M Sangeetha International Conference on Computer Science and Information Technology, 397-410 , 2012 2012 Citations: 11
RETRACTED: ResNet: A convolutional Neural Network for detecting and diagnosing of coronavirus pneumonia R Angeline, R Vani IOP Conference Series: Materials Science and Engineering 1084 (1), 012011 , 2021 2021 Citations: 10
Lifetime Improvement of Wireless Sensor Networks Using Tree Based Routing Protocol RS Rajagopal, Sushaptha, R. Vani, J. C. Kavitha EAI Big Data Innovation for Sustainable Cognitive Computing, 51 - 61 , 2020 2020 Citations: 9
Modified Conjugate Gradient algorithms for Gram matrix Inversion of Massive MIMI downlink Linear Precoding RV D.Subitha, J.M.Mathana, J.S.Leena Jasmine International Journal of Recent Technology and Engineering 8 (2S11), 2834 – 2840 , 2019 2019 Citations: 4
Modified Cross Hexagon Diamond Search Algorithm for Fast Block Matching Motion Estimation R Vani, P Davis, M Sangeetha International Journal of Engineering and Technology (IJET) 20 , 2014 2014 Citations: 4
Health Monitoring Wearable Device Using Internet Of Things DS R.Vani European Journal of Molecular & Clinical Medicine 7 (3), 395-400 , 2020 2020 Citations: 3
Waste Disposal Management System for Smart City Using LoRa G. Saranyadevi, R.Vani, V.N. Bhargavee Jour of Adv Research in Dynamical & Control Systems, 12 (3), 1360-1364 , 2020 2020 Citations: 3
Fast motion estimation algorithm using hybrid search patterns for video streaming application U Nageswaran, S Marikkannan INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL 12 (5), 715-727 , 2017 2017 Citations: 3
A new hybrid search algorithm with novel cross-diagonal-hexagon search video coding algorithm for block motion estimation R Vani, M Sangeetha Wireless Personal Communications 88 (2), 211-222 , 2016 2016 Citations: 3
Performance analysis of matrix inversion algorithms for massive MIMO precoding under rural and urban scenarios D Subitha, S Velmurugan, R Vani, E Nirmala 2021 7th International Conference on Advanced Computing and Communication … , 2021 2021 Citations: 1
Overview of Automatic Segmentation of Retinal Fundus Image for Medical Diagnosis. R Geethalakshmi, R Vani Ilkogretim Online 20 (1) , 2021 2021 Citations: 1
Recent Trends in Person Re-Identification: An Overview RV Perni Dedeepya Turkish Journal of Computer and Mathematics Education 12 (9), 1841 - 1846 , 2021 2021 Citations: 1
Sensorless Speed Control of Induction Motor Using Modern Predictive Control NPG Bhavani, M Aruna, K Sujatha, R Vani, N Priya Congress on Intelligent Systems, 675-683 , 2020 2020 Citations: 1
Efficient block-based motion estimation architecture using particle swarm optimization. V Rajamanickam, S Marikkannan Int. Arab J. Inf. Technol. 13 (6A), 732-739 , 2016 2016 Citations: 1
Performance evaluation of motion estimation in H. 264/AVC encoder V Rajamanickam, S Marikkannan Proceedings of the International Conference on Advances in Computing … , 2012 2012 Citations: 1
Deep Learning-Based Degradation Detection and Inpainting of Tamil Nadu Temple Murals Using Transformer Networks and Diffusion Models A Ramachandran, V Rajamanickam International Arab Journal of Information Technology (IAJIT) 23 (2), 342 , 2026 2026
