Digital Image processing, Deep Learning, Machine learning
10
Scopus Publications
85
Scholar Citations
4
Scholar h-index
3
Scholar i10-index
Scopus Publications
Smart Quality Monitoring System for Edible Oils S. Deivanayagi, Palanivel P, Vignesh S R, Nithish P 2026 2nd International Conference on Intelligent Systems for Communication Iot and Security Iciscois 2026, 2026 This project is centered on adulteration detection and quality monitoring of edible oils with Machine Learning (ML) methods combined with a hardware sensing system. The model to be proposed is designed to assess the quality and purity of different edible oils like groundnut, mustard, sunflower, palm, coconut, soybean, and olive oils in terms of prominent physicochemical parameters like Free Fatty Acid (FFA), Peroxide Value (PV), Iodine Value (IV), Saponification Value (SV), Refractive Index (RI), and Density. The software module is designed to predict these parameters employing ML algorithms-specifically, the XGBoost classifier-to label oil samples adulterated or nonadulterated. In the hardware setup, the density parameter has been accurately measured employing an ultrasonic sensor with an Arduino Mega interface. The measured density values are incorporated into the software model for prediction. Experimental findings show that the system offers sound classification and forms a basis for an automated oil quality monitoring equipment in the future.
Portable ECG Device Detecting Abnormalities Using Deep Learning S. Deivanayagi, Giridharan D, Alvin Kennedy S, Dharshan RE 2025 International Conference on Computing and Communication Technologies Iccct 2025, 2025 This paper presents a portable ECG device combined with a deep learning model to provide ECG analysis in real-time to predict cardiac abnormalities. ECG signals are captured using a compact hardware setup and processed using an advanced, sophisticated neural network model which provides meaningful and timely detection of the possibility of any heart conditions. Deep learning models were trained and optimized to differentiate various forms of heart abnormalities using real-time data from the portable ECG device. Being portable and real-time, the device is meant for dual use by health professionals and common men. The portable nature of the device means that it allows continuous heart monitoring outside the clinical setup, thus providing an opportunity for earlier detection and timely intervention. This paper talks about the hardware setup, data acquisition, model architecture, and performance evaluation of the system. Initial tests show the potential of the device for the high-sensitivity detection of heart illnesses, including arrhythmias, meaning a real shift in a personal health scale tailored to remote patient monitoring. Future work will delve into other improvements that will augment diagnostic accuracy and widen the range of cardiovascular health monitoring coverage.
Roving Crabber in Aquatics S. Deivanayagi, K. Thirupura Sundari, M. Ranjithvel, K. Gokulan, S. Karshin 2025 International Conference on Intelligent Control Computing and Communications Ic3 2025, 2025 Underwater pollution, primarily caused by plastics and other waste materials, poses significant threats to marine ecosystems and human health. To address this issue, “CRABBER” is an innovative waste-gathering underwater robot designed to combat pollutants in freshwater environments. Equipped with sensors, IoT technology, machine learning, and image processing capabilities, it autonomously collects submerged waste, captures underwater images and videos, and monitors pollution levels. Utilizing wireless communication for data sharing, “CRABBER” provides an intelligent solution for reducing harmful materials, supporting sustainable waste management practices, and promoting marine conservation efforts.
Smart Menu Ordering System S. Deivanayagi, K. Thirupura Sundari, Kerutheka A, Kokilavani GM, Sowmiya S 4th International Conference on Power Energy Control and Transmission Systems Harnessing Power and Energy for an Affordable Electrification of India Icpects 2024, 2024 In a restaurant, handling a large number of patrons is necessary, and ensuring that they are satisfied is essential to success. Nonetheless, the majority of restaurants in use today provide traditional services. Because order tracking and bill creation are manual processes, things are tough to manage when there are more orders than there are staff members if resources are few. Dealing with a pile of papers becomes a laborious process under such circumstances. There is a discrepancy between restaurant services and patron pleasure because of these issues. We employ a computerized menu ordering mechanism to get over these issues with the manual system that will free the chefs from manual serving. This application supports services like display of menu items, taking orders, order update and confirmation of the order. It is accurate menu ordering software that features reliability, ease of maintenance, faster services, and handle multiple orders at a time.
Pipe Inspection and Cleaning Robot K. Thirupura Sundari, S. Deivanayagi, Nandhini S, Vijayalakshmi R, Gayathri A, Swathi K 4th International Conference on Power Energy Control and Transmission Systems Harnessing Power and Energy for an Affordable Electrification of India Icpects 2024, 2024 Automating the movement of waste from collection locations to central processing facilities is possible through the use of sophisticated pneumatic waste conveying systems (PWCS). By doing away with the requirement for conventional waste collection trucks, this technology reduces its negative effects on the environment and boosts productivity. Smart Sensors and Monitoring: Adding smart sensors to PWC's network and at waste collection locations. By giving real-time fill level data, these sensors enable preventative maintenance and optimised waste transportation routes. Automated Sorting and Recycling: Modern technology is installed in central waste processing facilities to enable automated sorting and recycling. By doing this, trash sent to landfills is reduced and recycling rates are maximised by effectively separating recyclables and non-recyclables.
Computer Aided Coronary Atherosclerosis Plaque Detection and Classification S. Deivanayagi, P. S. Periasamy Intelligent Automation and Soft Computing, 2022 Coronary artery disease (CAD) remains a major reason for increased mortality over the globe, comprising myocardial infarction and ischemic cardiomyopathy. The CAD is highly linked to coronary stenosis owing to the encumbrance of atherosclerotic plaques. Particularly, diversified atherosclerotic plaques are highly responsible for major cardiac adverse events over the calcified and non-calcified plaques. There, the recognition and classification of atherosclerotic plaques play a vital role to prevent and intervene in CAD. The process of detecting various class labels of the atherosclerotic plaques is significant to identify the disease at the earlier stages. Since several automated coronary plaque recognition models are mainly based on handcrafted features, it is needed to design deep learning (DL) models for improved performance. With this motivation, this study introduces an automated invasive weed optimization with densely connected networks (AIWO-DN) for coronary atherosclerosis plaque recognition and classification. Primarily, the Two Dimensional (2D) transverse cross-sectional image with the provided centreline from the input 3-D Computed Tomography Angiography (CTA) image is extracted in three orthographic aspects. In addition, the coronary lumen is segmented on every cross section and extracts the region of interest (RoI). Moreover, the Densely Connected Networks (DenseNet169) model is applied to derive the useful set of features vectors. Furthermore, invasive weed optimization (IWO) with weighted extreme learning machine (WELM) based classification model is employed to detect and classify different classes of atherosclerotic plaques. In order to validate the performance of the superior outcomes of the Automated Invasive Weed Optimization – Deep Learning (AIWO-DN) technique, a set of simulations were performed and the outcomes are inspected interms of varying metrics. The experimental results showed the betterment of the AIWO-DN technique over the existing techniques interms of several evaluation metrics.
Detection and Classification of Muscular Fatigueness on Upper Extremities using Surface EMG Electrode Interfaced with Labview K.Thirupura Sundari, R. Giri, S. Durgadevi, S. Deivanayagi, Srivarsha U 2022 1st International Conference on Computational Science and Technology Iccst 2022 Proceedings, 2022 Long-term use of mobile phones fosters the continual usage of the trapezius muscles, which contributes to degradation to the muscle fibres, compounding impairment like acute trauma, and myogenic tonus, which mostly affects the collar and shoulders. Before it becomes evident, physical weariness must be noticed to improve the performance and prevent more catastrophes.. The objective of this paper is to measure the weariness of the muscles in cervical erector spinae and trapezius muscles and also to categorise the effect of fatigueness created due to prolonged use of cell phones. The surface electromyography signals are used for analysing and also for extracting the features from muscle activities. These signals are non-linear, non-stationary and exhibit self-similar multifractal behaviour. Experimental session where 30 individuals are involved to record surface electromyography signals before and after usage of smart phone by connecting electrodes to the cervical erector spinae and trapezius muscles to note down the variations in the parameters obtained by sending the data via DAQ card to the LABVIEW software. A similar system was also constructed and measured the performance using MATLAB software through data acquisition system. Fatigue mostly influences the frequency spectrum and strength of the signal. Thus, as crucial components of the EMG signal, the most credible metrics, such as Variance, Median value, Root Mean Square (RMS),Mean Frequency of the power spectrum (MNF), are adopted and a classification algorithm was developed using Fuzzy logic techniques that estimates the extent of muscle fatigueness.
Pupil detection algorithm based on feature extraction for eye gaze Jaimeet Parthpancholi, Saumil Patel, Ajmera, Taka Yasu, Ito, et al. International Journal of Recent Technology and Engineering, 2019 Exact real-time pupil tracking is an essential step in a live eye gaze. Since pupil centre is a base point’s reference, eye centre localization is essential for many applications. In this research, we extract pupil eye features exactly within different intensity levels of eye images, mostly with localization of determined interest objects and where the human is looking for. Since it’s a digital world and digital transformation, everything is becoming virtual. Hence this concept has a huge scope in e-learning, class room training and analyzing human behaviour. This research covers eye tracking technology to track and analyze the learners' behavior and emotion on e-learning platform like level of attention and tiredness. Harr’s cascade classifier was used to first locate the eye’s area, and once found and support vector machine (SVM) for classification with the trained datasets. We also include the state of emotions, facial landmarks of the salient patches on face image using automated learning-free facial landmark detection technique.Experimental results help in developing learner eye gaze detection in system using Pycharm and hardware output using Raspberry Pi. In Raspberry Pi is given with the input image captured using external webcam and based on the engagement level of the learner content 1 or 2 would be displayed in the Raspbian OS environment
RECENT SCHOLAR PUBLICATIONS
Experimental investigation of synthetic fiber reinforced composites PS P. Ranjith , S. Deivanayagi , J. Kamalakannan Materials Today proceedings , 2023 2023.0
Detection And Classification Of Tumour Using Image Processing And Machine Learning DP RANI, S DEIVANAYAGI, P SHALINI Elementary Education Online 19 (3), 4535-4535 , 2022 2022.0
A review of classification algorithms in machine learning for medical IOT. R Prabha, S Deivanayagi, VKG Kalaiselvi, DP Rani International Journal of Pharmaceutical Research (09752366) 13 (1) , 2021 2021.0 Citations: 17
Computational analysis of INVELOX wind turbine to analyze the venturi velocity by change the parameter of diffuser S Suthagar, T Kumaran, G Gowtham, T Maridurai, T Sathish, ... Materials Today: Proceedings 46, 4245-4249 , 2021 2021.0 Citations: 17
Vehicular Pollution Monitoring and Risk Management System NG S.Deivanayagi, D.Pushgara Rani, Vishall.V, Nithish Senan.R IN Patent App. 202041018449 A , 2020 2020.0
Pollution Risk Management For Petrol Engines Based On Iot S DEIVANAYAGI, DP RANI, V VISHALL, P ANUSRUTHI Ilkogretim Online 19 (4), 6533-6539 , 2020 2020.0
Pupil Detection Algorithm Based on Feature Extraction for Eye Gaze GA S.Deivanayagi, V.G.Nandhini Sri, P.Kalai Priya International Journal of Recent Technology and Engineering 8 (2S5), 73-76 , 2019 2019.0 Citations: 3
SIDDHA MEDICINES AND METHODOLOGIES ON DYNAMIC GAIT INDEX OF CEREBRAL PALSY CHILDREN P Arul Mozhi, R Pattarayan, S Deivanayagi, V Banumathi 2016.0
The Effect of Brahmi Nei with Massage and Varmam on Spasticity of Cerebral Palsy Children DS Arul Mozhi P., Pattarayan R. Global Journal For Research Analysis 5 (11) , 2016 2016.0
Spectral Analysis of EEG signals uring Hypnotic Analgesia DPR S.Deivanayagi, Dr.M.Manivannan International Journal of Applied Engineering Research 10 (75) , 2015 2015.0
Spectral Analysis of EEG signals uring Hypnotic Analgesia DPR S.Deivanayagi, Dr.M.Manivannan International Journal of Applied Engineering Research 10 (75) , 2015 2015.0
Spectral analysis of EEG signals during hypnosis S Deivanayagi, M Manivannan, P Fernandez International Journal of Systemics, Cybernetics and Informatics 4, 75-80 , 2007 2007.0 Citations: 42
Emerging Technologies in Engineering Research S Deivanayagi, N Gopinath, V Nagaraju, K Venusamy
Analytical Standardization of Brahmi Nei and Effect of Siddha Methodologies on Spasticity in Cerebral Palsy BV Dr. Arul Mozhi P, Pattarayan R, Deivanayagi.S International Journal of Current Research in Medical Sciences 2 (10), 82-89 , 0 Citations: 2
MOST CITED SCHOLAR PUBLICATIONS
Spectral analysis of EEG signals during hypnosis S Deivanayagi, M Manivannan, P Fernandez International Journal of Systemics, Cybernetics and Informatics 4, 75-80 , 2007 2007.0 Citations: 42
A review of classification algorithms in machine learning for medical IOT. R Prabha, S Deivanayagi, VKG Kalaiselvi, DP Rani International Journal of Pharmaceutical Research (09752366) 13 (1) , 2021 2021.0 Citations: 17
Computational analysis of INVELOX wind turbine to analyze the venturi velocity by change the parameter of diffuser S Suthagar, T Kumaran, G Gowtham, T Maridurai, T Sathish, ... Materials Today: Proceedings 46, 4245-4249 , 2021 2021.0 Citations: 17
Pupil Detection Algorithm Based on Feature Extraction for Eye Gaze GA S.Deivanayagi, V.G.Nandhini Sri, P.Kalai Priya International Journal of Recent Technology and Engineering 8 (2S5), 73-76 , 2019 2019.0 Citations: 3
Analytical Standardization of Brahmi Nei and Effect of Siddha Methodologies on Spasticity in Cerebral Palsy BV Dr. Arul Mozhi P, Pattarayan R, Deivanayagi.S International Journal of Current Research in Medical Sciences 2 (10), 82-89 , 0 Citations: 2
Experimental investigation of synthetic fiber reinforced composites PS P. Ranjith , S. Deivanayagi , J. Kamalakannan Materials Today proceedings , 2023 2023.0
Detection And Classification Of Tumour Using Image Processing And Machine Learning DP RANI, S DEIVANAYAGI, P SHALINI Elementary Education Online 19 (3), 4535-4535 , 2022 2022.0
Vehicular Pollution Monitoring and Risk Management System NG S.Deivanayagi, D.Pushgara Rani, Vishall.V, Nithish Senan.R IN Patent App. 202041018449 A , 2020 2020.0
Pollution Risk Management For Petrol Engines Based On Iot S DEIVANAYAGI, DP RANI, V VISHALL, P ANUSRUTHI Ilkogretim Online 19 (4), 6533-6539 , 2020 2020.0
SIDDHA MEDICINES AND METHODOLOGIES ON DYNAMIC GAIT INDEX OF CEREBRAL PALSY CHILDREN P Arul Mozhi, R Pattarayan, S Deivanayagi, V Banumathi 2016.0
The Effect of Brahmi Nei with Massage and Varmam on Spasticity of Cerebral Palsy Children DS Arul Mozhi P., Pattarayan R. Global Journal For Research Analysis 5 (11) , 2016 2016.0
Spectral Analysis of EEG signals uring Hypnotic Analgesia DPR S.Deivanayagi, Dr.M.Manivannan International Journal of Applied Engineering Research 10 (75) , 2015 2015.0
Spectral Analysis of EEG signals uring Hypnotic Analgesia DPR S.Deivanayagi, Dr.M.Manivannan International Journal of Applied Engineering Research 10 (75) , 2015 2015.0
Emerging Technologies in Engineering Research S Deivanayagi, N Gopinath, V Nagaraju, K Venusamy
