Dr. M. Sumathi

Scopus Publications

AI-powered detection and classification of harmful algal blooms (HABs) using a Volterra Convolutional Neural Network (VCNN) and advanced image processing techniques
R. Mahalakshmi Priya, J. I. Christy Eunaicy, T. S. Urmila, C. Jayapratha, J. Naveen Ananda Kumar, G. B. Govindaprabhu, M. Sumathi
Iran Journal of Computer Science, 2026
OPTIMISED DEEP LEARNING FOR ORAL CANCER CLASSIFICATION
Chellasamy Sulochana, Mahadevan Sumathi
Acta Polytechnica, 2026
Oral cancer detection is essential, especially in areas with high occurrence rates, is essential for better early diagnosis and individualised treatment plans. SV-OnionNet is a deep learning framework presented in this article that aims to improve the classification accuracy of oral cancer diagnosis. While maintaining important structural details, the method lowers noise in medical pictures by integrating an adaptive Non-Linear Means (NLM) filter. Spatial features are improved by the Label-Guided Attention (LGA) module, which guarantees constant labelling and improves feature extraction. By enabling accurate pixel-level segmentation of lesions, Seg-UNet provides increased classification reliability. The Support Vector Machines (SVM) deep learning classification model used in the SV-OnionNet architecture preserves spatial relationships for improved feature learning, replacing traditional fully linked layers (LKN). The Competitive Search Optimization (CSO) algorithm fine-tunes model parameters, therefore optimising feature selection and classification. The evaluation on the Mouth and Oral Diseases dataset demonstrated exceptional accuracy, precision, recall, and specificity, with the proposed classification achieving a 99.94% accuracy. These findings emphasise the effectiveness of SV-OnionNet in improving the diagnostic accuracy and reliability. The study highlights the potential of integrating deep learning techniques with optimisation strategies to advance oral cancer detection. Future research will focus on expanding datasets and exploring additional optimisation methods to further improve the classification performance.
Machine Learning and Deep Learning Algorithms and Cognitive Approach for VR, AR Model Building
R. Mahalakshmi Priya, J. Naveen Ananda Kumar, C. Jayapratha, T.S. Urmila, M. Sumathi
Virtual Reality and Augmented Reality with 6g Communication, 2025
VR/AR experiences are evolving as a result of machine learning, deep learning, and cognitive approaches. A symbiotic relationship is created between AI and immersive technologies. This chapter examines how advanced algorithms create realistic virtual environments. The application of ML and DL techniques to real-time object tracking, voice commands, and dynamics is discussed. AI is used to develop VR and AR experiences. Creating user-centric designs with cognitive models makes them more intuitive. This exploration involves a cognitive approach. A VR/AR experience is optimized by AI-driven systems that predict user preferences. Research challenges are discussed along with cutting-edge solutions. AI-generated virtual environments and multimodal learning systems are discussed as future trends for VR and AR. In addition, the comprehensive overview considers the broader implications of these technologies for privacy.
PollenMorph AI: quantum contours based segmentation and deep learning for pollen recognition using microscopic images
Mahalakshmi Priya Rajendran, Sumathi Mahadevan
Iran Journal of Computer Science, 2025
Impact of Microorganisms on Food Spoilage and Human Health: A Comprehensive Review of Advances in Identification using Image Processing and Artificial Intelligence Techniques
Mahalakshmi Priya R, Sumathi M
International Research Journal of Multidisciplinary Scope, 2025
Food spoilage and human health are greatly affected by microorganisms, such as bacteria, algae, fungi, and protozoa. While traditional identification methods are reliable, they are often laborious and time-consuming. In recent years, artificial intelligence (AI) and image processing have made significant progress in identifying and classifying microorganisms quickly and accurately. In this review, we will examine image processing and artificial intelligencebased techniques for identifying and classifying microorganisms relevant to human health and food spoilage, comparing their effectiveness to traditional methods and assessing their impact on food safety. Bacteria, algae, fungi, and protozoa are the four major groups of microorganisms examined in this review. A review of applications in food safety, clinical microbiology, and environmental monitoring is presented in this paper. It examines how bacteria, yeast, and molds cause food spoilage and examines their mechanisms of action. Furthermore, the article highlights common foodborne illnesses and the health consequences of eating contaminated food. The paper also discusses advances in identifying spoilage-causing microorganisms, with a particular emphasis on artificial intelligence (AI) and image processing. With modern techniques, microbial contamination can be detected more accurately and efficiently, thus improving food safety. Finally, the review concludes by analyzing current challenges and future directions in the field, emphasizing the need for continued innovation in microbial detection methods. In the review, rapid detection of foodborne pathogens is highlighted, as well as automated spoilage monitoring. This technology has the potential to revolutionize food safety practices and clinical microbiology, so it must continue to be developed and validated.
Fungal Species Classification Using MixNet-Lite: A Lightweight Deep Learning Approach
R. Mahalakshmi Priya, M. Sumathi
Proceedings of 2025 IEEE International Conference on Contemporary Computing and Communications Inc4 2025, 2025
Health care, agriculture, and environmental monitoring rely heavily on fungal classification. The challenge of accurate classification is hampered by variables such as limited datasets, inconsistent image quality, and computational constraints. Using MixNet-Lite for fungal species classification, this study presents a lightweight deep learning model. The quality of images is enhanced through grayscale conversion, resizing, and histogram equalization during preprocessing. With the help of the De-Fungi dataset, the model predicts fungal images into five classes while addressing imbalances within the classes. With significantly fewer parameters, MixNet-Lite outperforms VGG16 ($66 \%$) and DenseNet ($56 \%$) in experiments. With its efficiency, it is an ideal choice for portable medical devices and low-power agricultural tools. Compared to MixNet-Lite, MixNet-Lite has superior feature extraction, reduced computational cost, and is adaptable to a wide range of imaging environments. A further enhancement of performance will be achieved through Explainable AI (XAI) and data augmentation techniques.
Bridging AI and Ecology: CILNN and XAI for Acoustic Based Prediction of Dangerous Wild Animals
Govindaprabhu GB, Sumathi M, Sharan Neyvasagam, Naveen Ananda Kumar J
International Research Journal of Multidisciplinary Scope, 2025
In habitats that are encroaching on humans, human-wildlife conflict is an increasing global challenge. There is a significant risk of human injury and retaliatory action being taken if humans encounter dangerous animals. This work presents a novel approach to automated detection and classification of dangerous animals using audio signals, with a focus on model interpretability. This work introduces the Convolutional Interconnected Layer Neural Network (CILNN), a deep learning architecture designed to effectively process and classify animal vocalizations. Our method leverages a comprehensive set of audio features, including Mel-frequency cepstral coefficients (MFCCs) and spectral characteristics, optimized through SHAP-based feature selection. The CILNN incorporates interconnected layers and attention mechanisms to enhance feature extraction and model performance. It evaluates proposed approach on a diverse dataset of vocalizations from five dangerous animal species: bears, bison, cheetahs, elephants, and wild boars. Experimental results demonstrate that the CILNN outperforms traditional machine learning models such as Random Forests and Decision Trees in classification accuracy and robustness. Crucially, it employs Explainable AI (XAI) techniques, including SHAP values and decision tree visualizations, to interpret the decision-making processes of both our CILNN (90.6% accuracy) and other models. This interpretability analysis provides insights into feature importance and model behavior, enhancing trust and understanding in the classification process. Our work contributes to wildlife monitoring and human-wildlife conflict mitigation by offering an efficient, accurate, and interpretable method for acoustic-based animal detection
RETRACTED ARTICLE: Fuzzy assisted fog and cloud computing with MIoT system for performance analysis of health surveillance system (Journal of Ambient Intelligence and Humanized Computing, (2021), 12, 3, (3423-3436), 10.1007/s12652-020-02156-y)
S. Selvakanmani, M. Sumathi
Journal of Ambient Intelligence and Humanized Computing, 2024
Safeguarding Humans from Attacks Using AI-Enabled (DQN) Wild Animal Identification System
Govindaprabhu GB, Sumathi M
International Research Journal of Multidisciplinary Scope, 2024
Without advanced artificial intelligence (AI) technologies, monitoring and identifying wildlife has become increasingly difficult. To examine AI-driven methodologies for wild animal identification, this work uses a diverse dataset of annotated images with human, domestic and wild animal annotations. Convolutional Neural Networks (CNNs), AlexNet, and Deep Q-Learning (DQN) models are developed and compared by combining sophisticated preprocessing techniques such as dynamic color space conversion and day-night image translation. The models are evaluated on accuracy, precision, recall, F1-score, and mean percent error (MPE) loss metrics for classifying diverse species. The DQN model achieves the best performance with 79.5% accuracy, 0.78 precision, 0.84 F1-score, and 0.24 MPE loss. These findings demonstrate AI's potential to support conservation efforts by enabling accurate and automated wildlife monitoring. The comparative assessment of different models and factors influencing performance provides methodological insights to guide future research toward robust and generalizable AI solutions for biodiversity and habitat management.
Enhancing Oral Cancer Diagnosis: IAWMF based Preprocessing in RGB and CT Images
C. Sulochana, M. Sumathi
2024 International Conference on Recent Advances in Electrical Electronics Ubiquitous Communication and Computational Intelligence Raeeucci 2024, 2024
Globally, there are over 350,000 cases of oral cancer, mainly oral squamous cell carcinomas that arise in the mouth and tongue tissues. For metastatic cases, the survival rate drops dramatically from 83% to only 65% if detected early. It is challenging, however, to identify oral lesions and precancerous conditions in their earliest stages when treatment can be most effective. CT scans and intraoral RGB photography are critical imaging methods for screening and diagnosing oral cancers. It is difficult to detect oral cancer accurately with these imaging techniques due to artifacts, noise, and poor lesion visibility. In current CAD methods, preprocessing pipelines for oral cavity images across RGB and CT are not robust or tailored. An automated, adaptive, and multimodal preprocessing pipeline is presented in this study to reduce this gap by facilitating early detection of oral cancer from RGB photographs and CT scans. A region-of-interest cropping technique is used to focus on diagnostically significant areas, specialized noise filters are used to reduce noise while maintaining tissue features, and adaptive histogram equalization is used to normalize contrast dynamically across images and highlight lesions. Oral cavity images in RGB and CT formats were used to evaluate the proposed techniques. As compared to original images, the results demonstrated significant improvements in image quality, noise reduction, lesion conspicuity, and feature visibility. Among the noise filters assessed, the Iterative Adaptive Weighted Median Filter (IAWMF) performed best with PSNR 33, SNR 28.2817, and RMSE 5.7088, which indicated the filter's effectiveness for high fidelity denoising. The median filter was also capable of reducing noise effectively with PSNR of 26.7701, SNR of 22.0518, and RMSE of 11.696. Image quality was the poorest when using Total Generalized Variation. A tailored preprocessing pipeline shows promise in aiding early diagnosis and treatment of oral cancer.
Watershed Segmentation with Gradient Vista and SOBEL-Crafted Contours for Analyzing EMDS-6 Microbial Environmental Dataset
R Mahalakshmi Priya, M. Sumathi
Proceedings of Inc4 2024 2024 IEEE International Conference on Contemporary Computing and Communications, 2024
An Integrated Approach to Bacteria Structure Detection using Frangi-Thresholding Segmentation and its Impact on Analysis
R. Mahalakshmi Priya, M. Sumathi
2024 International Conference on Recent Advances in Electrical Electronics Ubiquitous Communication and Computational Intelligence Raeeucci 2024, 2024
Ethno medicine of Indigenous Communities: Tamil Traditional Medicinal Plants Leaf detection using Deep Learning Models
G.B. Govindaprabhu, M. Sumathi
Procedia Computer Science, 2024
An Elephant Identification Emissary: A Technological Odyssey in Elephant Recognition with IP & AI Solutions
G B Govindaprabhu, M. Sumathi
Proceedings of Inc4 2024 2024 IEEE International Conference on Contemporary Computing and Communications, 2024
Machine Learning for Plankton Species Identification and Classification: A New Era in Marine Ecology
R.Mahalakshmi Priya, R. Barani, M. Sumathi
Proceedings of the 5th International Conference on Inventive Research in Computing Applications Icirca 2023, 2023
Segmentation and Sentiment Word Categorization Using Feature Extraction—A Novel ASFW Framework
S. Ashika Parvin, M. Sumathi
Lecture Notes in Electrical Engineering, 2022
Challenges of Sentiment Analysis - A Survey
S.Ashika Parvin, M. Sumathi, C. Mohan
Proceedings of the 5th International Conference on Trends in Electronics and Informatics Icoei 2021, 2021
Nuances of data pre-processing and its impact on business
M. Sumathi, S.Ashika Parvin
Proceedings 5th International Conference on Intelligent Computing and Control Systems Iciccs 2021, 2021
Fuzzy assisted fog and cloud computing with MIoT system for performance analysis of health surveillance system
S. Selvakanmani, M. Sumathi
Journal of Ambient Intelligence and Humanized Computing, 2021
Survey on data security in cloud environment
International Journal of Advanced Research in Engineering and Technology, 2020
Id based adaptive-key signcryption for data security in cloud environment
International Journal of Advanced Research in Engineering and Technology, 2020
Energy efficient algorithm for high speed packet data transfer on smartphone environment
S. Pandikumar, M. Sumathi
International Journal of Engineering and Advanced Technology, 2019
Building a Data Mining Based Software Reliability Estimation Model
A. R. Visagan, M. Sumathi, G. Sujatha
1st IEEE International Conference on Advances in Information Technology Icait 2019 Proceedings, 2019
Adaptive PET/CT fusion using empirical wavelet transform
R. Barani, M. Sumathi
Advances in Intelligent Systems and Computing, 2018
Salinity sensor using photonic crystal fiber
D. Vigneswaran, N. Ayyanar, Mohit Sharma, M. Sumathi, Mani Rajan M.S., K. Porsezian
Sensors and Actuators A Physical, 2018
Tunable differential modal gain in FM-EDFA system using dual pumping scheme at 100 Gbps system capacity
D. Vigneswaran, N. Ayyanar, M. Sumathi, M. S. Mani Rajan
Photonic Network Communications, 2017
Design of temperature sensor using liquid filled photonic crystal fiber
S. K. Methaprian, N. Ayyanar, P. Mahalakshmi, M. Sumathi, D. Vigneswaran, M. S. Mani Rajan
2016 IEEE Conference on Recent Advances in Lightwave Technology Cralt 2016, 2017
A novel channel selection algorithm in cognitive radio networks
S. Selvakanmani, M. Sumathi
Applied Mathematics and Information Sciences, 2017
Manipulating high birefringence in elliptical core meta fiber by varying metal/dielectric concentration of the framed AMM
P. Mahalakshmi, S. Venkatesh, M. Sumathi, R. Yamunadevi, N. Ayyanar, M. S. Mani Rajan
Optical and Quantum Electronics, 2017
Hydrostatic Pressure Sensor Using High Birefringence Photonic Crystal Fibers
N. Ayyanar, D. Vigneswaran, Mohit Sharma, M. Sumathi, M. S. Mani Rajan, S. Konar
IEEE Sensors Journal, 2017
Highly efficient compact temperature sensor using liquid infiltrated asymmetric dual elliptical core photonic crystal fiber
N. Ayyanar, R. Vasantha Jayakantha Raja, D. Vigneswaran, B. Lakshmi, M. Sumathi, K. Porsezian
Optical Materials, 2017
Design of elliptical ring core fiber with support of four lp modes in SDM applications
N. Ayyanar, M. Sumathi, D. Vigneswaran, M.S. Mani Rajan
Optics Infobase Conference Papers, 2017
Prediction of stock market price using hybrid of wavelet transform and artificial neural network
S. Kumar Chandar, M. Sumathi, S. N. Sivanandam
Indian Journal of Science and Technology, 2016
Foreign exchange rate forecasting using Levenberg-Marquardt learning algorithm
S. Kumar Chandar, M. Sumathi, S. N. Sivanandam
Indian Journal of Science and Technology, 2016
Forecasting response time in elastic cloud for secure resource access in transactional database using two phase authentication system
N. G. S. Parameswaran, M. Sumathi
Indian Journal of Science and Technology, 2016
Forecasting gold prices based on extreme learning machine
Kumar Chandar Sivalingam, Sumathi Mahendran, Sivanandam Natarajan
International Journal of Computers Communications and Control, 2016
Design of circular-helical and elliptical-helical PCF with inducing of circular polarization
vigneswaran dhasarathan
Optics Infobase Conference Papers, 2016
Efficient implementation of dynamic hierarchical structure for ART2 network
M. Sumathi, P. Vijayalakshmi
Proceedings of 2015 IEEE International Conference on Electrical Computer and Communication Technologies Icecct 2015, 2015
Crude oil prediction using a hybrid radial basis function network
Journal of Theoretical and Applied Information Technology, 2015
Forecasting of foreign currency exchange rate using neural network
International Journal of Engineering and Technology, 2015
CRCN CORMEN-An on demand opportunistic routing protocol for mobile cognitive radio ad hoc networks
S. Selvakanmani, M. Sumathi
Proceedings of Icccs 2014 IEEE International Conference on Computer Communication and Systems, 2014
An opportunistic routing protocol for mobile cognitive radio ad hoc networks
International Journal of Engineering and Technology, 2014
Performance comparison of artificial neural network techniques for foreign exchange rate forecasting
International Journal of Applied Engineering Research, 2014
Design of algorithm for vehicle identification by number plate recognition
P. Vijayalakshmi, M. Sumathi
4th International Conference on Advanced Computing Icoac 2012, 2012
A survey on semantic similarity between words in semantic web
P. Ilakiya, M. Sumathi, S. Karthik
2012 International Conference on Radar Communication and Computing Icrcc 2012, 2012
Qualitative evaluation of pixel level image fusion algorithms
M. Sumathi, R. Barani
International Conference on Pattern Recognition Informatics and Medical Engineering Prime 2012, 2012
Abstract Information Model for presenting database query results
M. Sumathi, T. Kalaikumaran
2012 International Conference on Computer Communication and Informatics Iccci 2012, 2012
Design of efficient objective function for stochastic search algorithm
Paulraj Vijayalakshmi, Mahadevan Sumathi
Communications in Computer and Information Science, 2012
GA-based optimization of tapering windows for artifact reduction in fourier electron magnetic resonance images
M. SUMATHI, MURALI C. KRISHNA, R. MURUGESAN
International Journal of Computational Intelligence and Applications, 2009
Lightpath reconfiguration with traffic priority consideration
M. Sumathi, P.T. Vanathi
International Journal of Communication Networks and Distributed Systems, 2009
Evolutionary computational approach for artifact-free image reconstruction from reduced samples: Application to Fourier EMRI
V.V. Gohokar, V.N. Gohokar
Proceedings International Conference on Computational Intelligence and Multimedia Applications Iccima 2007, 2008
Load balancing in WDM network with single and multiple lightpath additions
M. Sumathi, P.T. Vanathi
Malaysian Journal of Computer Science, 2008
Priority based dynamic reconfiguration of lightpath in WDM networks
M. Sumathi, P.T. Vanathi
Proceedings of Icscn 2007 International Conference on Signal Processing Communications and Networking, 2007
Dynamic reconfiguration of lightpath with priority based deletion
M. Sumathi, P.T. Vanathi
2006 IEEE Singapore International Conference on Communication Systems Iccs 2006, 2006
Minimizing congestion in optical WDM networks for dynamic traffic
M. Sumathi, P.T. Vanathi
Proceedings of Indicon 2005 an International Conference of IEEE India Council, 2005

RECENT SCHOLAR PUBLICATIONS

AI-powered detection and classification of harmful algal blooms (HABs) using a Volterra Convolutional Neural Network (VCNN) and advanced image processing techniques
R Mahalakshmi Priya, JI Christy Eunaicy, TS Urmila, C Jayapratha, ...
Iran Journal of Computer Science 9 (1), 20 , 2026
2026
Citations: 1
Machine Learning and Deep Learning Algorithms and Cognitive Approach for VR, AR Model Building
RM Priya, JNA Kumar, C Jayapratha, TS Urmila, M Sumathi
Virtual Reality and Augmented Reality with 6G Communication, 169-195 , 2025
2025
Bridging AI and Ecology: CILNN and XAI for Acoustic Based Prediction of Dangerous Wild Animals
G GB, DM Sumathi, J Kumar
International Research Journal of Multidisciplinary Scope 6 (01), 10.47857 , 2025
2025
Citations: 1
Fungal Species Classification Using MixNet-Lite: A Lightweight Deep Learning Approach
RM Priya, M Sumathi
2025 IEEE International Conference on Contemporary Computing and … , 2025
2025
Bridging ai and ecology: Cilnn and xai for acoustic based prediction of dangerous wild animals
GB Govindaprabhu, M Sumathi, S Neyvasagam, NAJ Kumar
International Research Journal of Multidisciplinary Studies 6 (1), 1280-1298 , 2025
2025
Citations: 5
Impact of Microorganisms on food spoilage and human health: a comprehensive review of advances in identification using image processing and artificial intelligence techniques
RM Priya, M Sumathi
Int. Res. J. Multidiscipl. Scope 6 (1), 1299-1316 , 2025
2025
Citations: 3
An integrated approach to bacteria structure detection using Frangi-thresholding segmentation and its impact on analysis
RM Priya, M Sumathi
2024 International Conference on Recent Advances in Electrical, Electronics … , 2024
2024
Citations: 5
Safeguarding Humans from Attacks Using AI-Enabled (DQN) Wild Animal Identification System
G GB, DM Sumathi
Available at SSRN 5244356 , 2024
2024
Citations: 1
An Elephant Identification Emissary: A Technological Odyssey in Elephant Recognition with IP & AI Solutions
GB Govindaprabhu, M Sumathi
2024 IEEE International Conference on Contemporary Computing and … , 2024
2024
Citations: 1
Watershed segmentation with gradient vista and SOBEL-crafted contours for analyzing EMDS-6 microbial environmental dataset
RM Priya, M Sumathi
2024 IEEE International Conference on Contemporary Computing and … , 2024
2024
Citations: 3
Safeguarding humans from attacks using AI-enabled (DQN) wild animal identification system
GB Govindaprabhu, M Sumathi
Int. Res. J. Multidiscip. Scope 5 (3), 285-302 , 2024
2024
Citations: 14
Ethno medicine of indigenous communities: Tamil traditional medicinal plants leaf detection using deep learning models
GB Govindaprabhu, M Sumathi
Procedia Computer Science 235, 1135-1144 , 2024
2024
Citations: 18
A Novel Approach to Classify Sentiments on Different Datasets Using Hybrid Approaches of Sentiment Analysis
SA Parvin, M Sumathi, R Barani
Indian Journal of Science and Technology 16 (44), 3962-3970 , 2023
2023
Citations: 2
Machine Learning for Plankton Species Identification and Classification: A New Era in Marine Ecology
RM Priya, R Barani, M Sumathi
2023 5th International Conference on Inventive Research in Computing … , 2023
2023
Citations: 2
Segmentation and Sentiment Word Categorization Using Feature Extraction—A Novel ASFW Framework
S Ashika Parvin, M Sumathi
Proceedings of Third International Conference on Communication, Computing … , 2022
2022
Hybrid Genetic Algorithm with K-Means for Detection of Brain Tumor
M Sumathi, C Mohan, S Pandikumar, SB Sethupandian
Design Engineering, 17248-17256 , 2021
2021
SPI Transactional Database Using Secure Elastic Cloud Access with OOB.
M Sumathi, NGS Parameswaran
Turkish Online Journal of Qualitative Inquiry 12 (9) , 2021
2021
Challenges of sentiment analysis-a survey
SA Parvin, M Sumathi, C Mohan
2021 5th International Conference on Trends in Electronics and Informatics … , 2021
2021
Citations: 11
Nuances of data pre-processing and its impact on business
M Sumathi, SA Parvin
2021 5th International Conference on Intelligent Computing and Control … , 2021
2021
Citations: 4
Anomaly Detection Using PSO In Cloud Integrated IoT Devices Using MDGAN
NGSP M.Sumathi
International Journal of Aquatic Science 12 (03) , 2021
2021

Dr. M. Sumathi

EDUCATION

RESEARCH INTERESTS

Scopus Publications

RECENT SCHOLAR PUBLICATIONS

MOST CITED SCHOLAR PUBLICATIONS