• Completed Ph.D under the guidance of , Principal on the thesis titled “Certain Investigations on Automatic Segmentation of Colon using Clustering and Neural Network Approaches”- Highly Commended .
• Received Ph.D. Guide ship Recognition - Anna University Chennai, Ref. No. 2940076 in Information and Communication Engineering in Jan 2016. Appointed as Doctoral Committee member for guiding scholars.
• Published 2 Patent and 15 papers in reputed Journals,3 Book Chapters, 1 Book and 18 Conference publications.
• Published a book “Artificial Intelligence Trends for Data Analytics Using Machine Learning and Deep Learning Approaches” CRC Press, Taylor and Francis Group, ISBN No- 978036741727,2020
• Completed 15 online certification courses from NPTEL, Coursera, Mathworks and Great Learning. Topper in the “Digital Image Processing of Remote Sensing Images” and “Outcome based pedagogic principles for effective teaching “ conducted by NPTEL.
• Recipient of Proficiency award
EDUCATION
Ph.D - Anna University, Chennai,2016
ME- College of Engineering and Technology, Pollachi. Anna University-Chennai,2007
BE- Coimbatore Institute of Technology, Coimbatore,Bharathiar University,1998
RESEARCH INTERESTS
Image Processing, AI, Machine learning, Deep Learning
33
Scopus Publications
Scopus Publications
A Comprehensive Review of Diabetes Prediction using Tongue Image Analysis with Machine and Deep Learning Methods Devi K. Gayathri, M. Tamilarasan, V.R. Vinothini, K. Sakthisudhan Research Journal of Biotechnology, 2026 Diabetic is a chronic disorder that must be managed to control blood sugar levels. If undetected or untreated, diabetes increases the chance of developing other dangerous illnesses like heart disease, kidney disease and nerve damage. Early diagnosis of diabetes can assist a person in receiving the proper care and making the required lifestyle changes to prevent diabetesrelated complications. Due to improvements in image analysis, machine learning and deep learning approaches, the prediction of diabetes using images of the tongue has received a lot of interest recently. Researchers have explored the potential of tongue features as indicators of diabetes and have developed various prediction models based on tongue image analysis. This study presents a summary of the key findings of various researchers. This non-invasive diagnostic technique might provide accurate and speedy results, allowing early diagnosis and treatment for better patient outcomes. This study concludes that a noninvasive method of diagnosing diabetes can enhance patient outcomes and give medical professionals a useful tool.
An elegant intellectual engine towards automation of blockchain smart contract vulnerability detection Balachandar Raju, Gayathri Devi K Scientific Reports, 2025 To prevent vulnerabilities and ensure app security, smart contract vulnerability detection identifies flaws in blockchain code. To overcome the limitations of traditional detection methods, this study introduces a novel approach that combines Explainable Artificial Intelligence (XAI) with Deep Learning (DL) to detect vulnerabilities in smart contracts. The proposed intellectual engine operates in multiple stages. First, a smart contract is created, and the user provides a value during the runtime phase. XAI and DL then analyze the opcodes in high-value contracts to detect potentially risky processes. If violations such as security protocol failures, insufficient funds, or account restrictions are found, the engine halts the transaction and generates an error report. If the contract passes this vulnerability assessment, it continues executing without interruption. This ensures flagged transactions remain functional while being assessed. Our proposed Hybrid Boot Branch and Bound Long Short-Term Memory (HB 3 LSTM) approach achieves outstanding performance, with an accuracy of 99.68%, precision of 99.43%, recall of 99.54%, and an F1-score of 99.40%, which surpasses the performance of existing methods.
A Secure Access Framework for IoT–Cloud Integration With Blockchain and Bi-GCN Kavitha M. S., Gayathri Devi K. Iet Information Security, 2025 Digital advancements have made cloud computing and IoT essential for innovative environments such as healthcare and industry. Cloud platforms offer scalable compute and storage capabilities, whereas IoT devices generate real‐time data. However, there are significant challenges faced while integrating the IoT with cloud to achieve robust, scalable, and secure access control. Traditional centralized models, such as static rule‐based mechanisms and public key infrastructure (PKI), are prone to single points of failure and suffer from limited scalability and poor adaptability. To address these issues, this paper proposes a decentralized access control architecture that combines blockchain with a hybrid bidirectional graph convolutional network (Bi‐GCN). The framework integrates ciphertext policy‐attribute based encryption (CP‐ABE) with trusted platform module (TPM)–based pseudonymous identities and the blockchain smart contracts for fine‐ and hardware‐assisted access control. A generative adversarial network (GAN)‐assisted prevalidation layer filters sybil, tampering, and spoofing attempts before block inclusion, enhancing integrity and reducing overhead. Bi‐GCN supports real‐time anomaly detection, trust adaptation, and behavior profiling, while smart contracts enforce adaptive role‐attribute policies. Experimental results show that the proposed model outperforms existing methods across key metrics, including 0.97 accuracy, 0.98 F ‐measure, and minimal security overhead of 0.7%. Although it introduces slight latency due to advanced processing, the benefits of secure and intelligent access management outweigh the trade‐off. The integration of blockchain ensures decentralized and immutable policy enforcement, while Bi‐GCN facilitates self‐adaptive security, making the architecture suitable for dynamic IoT–cloud ecosystems.
Optimizing Sustainability in Deep Learning for Real-Time Banana Leaf Disease Detection using Densenet-201 and Alexnet Inception Network Gayathri Devi Krishnamoorthy, Sakthisudhan K, Surendiran B Proceedings of 2025 International Conference on Signal Processing Computation Electronics Power and Telecommunication Iconscept 2025, 2025 Bananas are a fruit crop grown globally and account for an important part of the global production of fruits. It is imperative to detect such diseases early and correctly so as to counteract their effects and enhance banana production. Here, this research introduces a deep learning methodology AlexNet-Inception network and DenseNet-201 model for the dentification and categorization of banana leaf. This approach has considered five classes of banana leaf diseases: Black Sigatoka, Fusarium Wilt, and Banana Bract Mosaic Virus (BBrMV), Banana Bunchy Top Virus (BBTV) and healthy leaves gathered from different platforms. The AlexNet-Inception network and DenseNet-201 model were trained with different learning rates and with Quasi-Hyperbolic Adam with decoupled Weight decay (QHAdamW) and ADAM optimizer. The hyperparameter tuning concludes that AlexNet-Inception model when trained with QHAdamW optimizer for a learning rate 0.0001 produces enhanced validation accuracy of 96% with corresponding validation loss of 0.21. The system was validated with parameters that produced results with 96% accuracy, indicating that the suggested model has successfully predicted and diagnosed banana diseases. This study is intended to help farmers of banana detect diseases at an early stage, eventually helping to enhance banana production as well as agricultural productivity.
A Hybrid Deep Learning Approach for Early Detection of Diabetic Retinopathy Mary Vespa M, Shajeena J, Shiny R M, Gayathri Devi K 3rd International Conference on Electronics and Renewable Systems Icears 2025 Proceedings, 2025 Diabetes is a malnutrition that results from elevated glucose levels. Diabetes eventually results in diabetic retinopathy (DR), a retinal condition that significantly impairs vision. It is an insulin-dependent difficulty that impacts ocular health. The receptive to cells at the back of the individual retina's veins gets injured, which is the cause of it. A favorable prognosis for this condition depends on its early identification. In this paper, the application of Convolutional Neural Network (CNN) with Long Short Term Memory (LSTM) on color fundus images is used for diabetic retinopathy is applied for understanding the task. The goal of the proposed DR identification method is to use deep learning to automatically identify the problem. An hybrid model that was trained and tested to distinguish between healthy and DR-affected fundi was able to achieve an accuracy of roughly 99.07% using fundus images from diabetic patients that were available in MESSIDOR.
Exploring Deep Learning Methods for Accurate Bridge Crack Detection: A Comparative Study Gayathri Devi Krishnamoorthy, Kishore B, Vinothini V R, Kanmani Ruby E. D, Sakthisudhan K, Thilagavathi K 2025 3rd International Conference on Advancements in Electrical Electronics Communication Computing and Automation Icaeca 2025, 2025 Bridges serve as an essential part in infrastructure and must undergo consistent inspection and maintenance to ensure safety and structural soundness. One common issue that bridges can face is the development of cracks, which can compromise their stability and safety. This study proposed a crack detection system with the Kaggle dataset of bridge images with and without cracks and trained using three architecture SqueezeNet, GoogLeNet and Alex-Net architecture. The images were pre-processed to improve their quality and to standardize their dimensions. A transfer learning approach was applied to a pre-trained network to classify cracked and non-cracked images. Its performance was evaluated using metrics including accuracy, precision, recall, and F1-score. The experimental findings indicated that the AlexNet-based system achieved remarkable crack detection accuracy exceeding 99% in bridge images. Furthermore, it showcased high precision, recall, and F1-score, emphasizing its capability to effectively identify cracks while minimizing both false positives and false negatives.
An efficient hybrid optimization of ETL process in data warehouse of cloud architecture Lina Dinesh, K. Gayathri Devi Journal of Cloud Computing, 2024 In big data, analysis data is collected from different sources in various formats, transforming into the aspect of cleansing the data, customization, and loading it into a Data Warehouse. Extracting data in other formats and transforming it to the required format requires transformation algorithms. This transformation stage has redundancy issues and is stored across any location in the data warehouse, which increases computation costs. The main issues in big data ETL are handling high-dimensional data and maintaining similar data for effective data warehouse usage. Therefore, Extract, Transform, Load (ETL) plays a vital role in extracting meaningful information from the data warehouse and trying to retain the users. This paper proposes hybrid optimization of Swarm Intelligence with a tabu search algorithm for handling big data in a cloud-based architecture-based ETL process. This proposed work overcomes many issues related to complex data storage and retrieval in the data warehouse. Swarm Intelligence algorithms can overcome problems like high dimensional data, dynamical change of huge data and cost optimization in the transformation stage. In this work for the swarm intelligence algorithm, a Grey-Wolf Optimizer (GWO) is implemented to reduce the high dimensionality of data. Tabu Search (TS) is used for clustering the relevant data as a group. Clustering means the segregation of relevant data accurately from the data warehouse. The cluster size in the ETL process can be optimized by the proposed work of (GWO-TS). Therefore, the huge data in the warehouse can be processed within an expected latency.
Brain computer interface for evaluation of mild cognitive impairment using eye blink Journal of Advanced Research in Dynamical and Control Systems, 2019
Segmentation of multiple organ from abdominal CT images using 3D region growing and gradient vector flow International Journal of Applied Engineering Research, 2014
