Enhancing Telemedicine Workflow Through Secure Image Transmission Niladri Maiti, Riddhi Chawla, T. Illakiya, Chinnem Rama Mohan, S. Meena, Souvik Sen, A. Shaji George Advanced Secure Transmission of Telemedicine Based Bio Medical Images, 2025 In the field of telemedicine, the incorporation of secure image transmission technologies and workflow automation, with a particular emphasis on the impact these technologies have on service delivery. Secure image transmission, which is accomplished through encryption protocols, virtual private networks (VPNs), and cloud-based platforms, makes it possible for medical professionals to share medical images in a manner that is both secure and fast. Through the use of real-time image sharing, diagnostic accuracy can be improved, delays can be reduced, and treatment decisions can be made more quickly and effectively. The automation of workflows also helps to streamline administrative and clinical tasks, which reduces the likelihood of errors caused by humans and increases operational efficiency.
A Hybrid Deep Learning Model for Lung Cancer Classification Using DenseNet169 and Convolutional Block Attention Module T. Illakiya, S Akhilesh, Dulam Satya Karthik Proceedings of the International Conference on Multi Agent Systems for Collaborative Intelligence Icmsci 2025, 2025 Lung cancer continues to rank among the leading causes of cancer-related deaths worldwide, underscoring the urgent need for more accurate diagnostic tools. Current methods face challenges such as limitations in feature extraction and a lack of focus on relevant image regions, which can affect diagnostic accuracy. This study presents an innovative approach to lung cancer classification that integrates the Convolutional Block Attention Module (CBAM) with the DenseNet169 architecture. DenseNet's robust feature extraction mitigates the vanishing gradient issue and enables the capture of complex spatial hierarchies, such as cellular shapes and tissue textures. The CBAM enhances this by applying spatial and channel attention mechanisms, allowing the model to focus on key areas within input images and improve classification precision. A dataset of 15,000 histopathological lung images (5,000 for each category: lung adenocarcinoma (LUAD), lung benign tissue (LUBEN), and lung squamous cell carcinoma (LUSC)) was used to evaluate the proposed model, which achieved an impressive 99.7% accuracy, outperforming traditional diagnostic methods. These findings underscore the potential of deep learning architectures and attention mechanisms to enhance diagnostic accuracy in medical imaging, potentially advancing lung cancer detection and treatment outcomes.
A Deep Learning Framework with Attention Mechanism for the Classification of Mild Cognitive Impairment using Brain MRI T. Illakiya, B. Vidhya, S. Prince Chelladurai, S. Hariprasad Proceedings of International Conference on Visual Analytics and Data Visualization Icvadv 2025, 2025 Mild Cognitive Impairment (MCI) refers to a neurological disorder marked by observable changes in cognitive decline. MCI signifies an intermediate phase linking normal aging and Alzheimer's Disease (AD). It is typically categorized into two types: Early MCI (EMCI) and Late MCI (LMCI), representing varying levels of cognitive impairment. An effective classification between EMCI and LMCI is vital, as it allows timely interventions that can potentially slow the progression of AD, improving patient outcomes and quality of life. Identifying the subtle features and patterns in EMCI and LMCI is essential for early diagnosis and effective intervention. This work proposes a novel Deep Learning (DL) network integrating EfficientNet-B0, a Global Context Network (GCN), and Neighborhood Attention blocks. The EfficientNet-B0 acts as the foundation for feature extraction in the proposed model. It uses its efficient architecture and pre-trained capabilities to capture meaningful patterns. To further enhance feature representation, a Global Context Network (GCN) is employed to capture long-range dependencies and global semantic information. Additionally, a Neighborhood Attention Module is used to refine local features by focusing on important regions in the MRI scans. The proposed framework balances global semantic understanding and localized feature extraction, resulting in improved classification performance. With systematic training and evaluation, the model achieves an accuracy of 95.3%, outperforming existing approaches and providing a better solution for neuroimaging-based MCI subtype classification.
An Attention-Based CNN and Transfer Learning Approach for Accurate Skin Lesion Classification S. Prince Chelladurai, Amirthasaravanan, E. Bharath, T. Pandiarajan, T. Illakiya 2025 6th International Conference on Data Intelligence and Cognitive Informatics Icdici 2025, 2025 The accurate classification of skin lesions is important for the early detection and effective treatment of skin cancer. However, the visual similarity among various lesion types poses a significant challenge to automated diagnostic systems. In this study, we propose a novel deep learning framework designed to improve the performance of skin lesion classification. The proposed model combines the strengths of DenseNet-169, a Group Shuffle with Depthwise Convolution (GSDW) block, and a Neighborhood Attention mechanism. The input image is passed simultaneously to DenseNet-169 and the GSDW block. The DenseNet-169 provides hierarchical feature extraction through densely connected layers. In parallel, the GSDW block enhances spatial feature representation by using channel-wise separability and group-wise shuffling, resulting in lightweight and effective local feature extraction. The feature maps generated from both DenseNet-169 and the GSDW block are concatenated to produce a unified feature representation. This combined feature map is subsequently refined through the Neighborhood Attention module, which applies spatial attention mechanisms to selectively weight the most informative regions. The proposed model is evaluated on DermaEvolve datasets, achieving an accuracy of 93.65 %. The results highlights the effectiveness of combining transfer learning and customized Convolutional Neural Network (CNN) techniques, offering a better solution for interpretable, scalable, and accurate automated skin lesion classification.
A Hybrid Deep Learning Model for Potato Leaf Disease Classification using Transfer Learning and Attention Mechanism T. Illakiya, Allen Vinster Joel, Namita Dushyant Nahata, Sai Sukumar, S. Prince Chelladurai Proceedings of 8th International Conference on Computing Methodologies and Communication Iccmc 2025, 2025 Potato leaf diseases pose a significant threat to crop yield and quality, necessitating accurate and timely classification for effective disease management. Deep learning has emerged as a powerful tool for automated disease detection, enabling precise classification of infected leaves. This work proposes a novel hybrid deep learning framework integrating DenseNet- 169, a Group Shuffle Depthwise convolution (GSDW) block, and Triplet Attention blocks to enhance feature extraction for better classification accuracy. DenseNet-169 serves as the backbone for deep feature extraction, using its dense connectivity for improved gradient flow and feature reuse. The GSDW captures cross- channel dependencies, modeling complex relationships between disease features. Additionally, the Triplet Attention module re- fines feature selection by focusing on relevant disease patterns, ensuring accurate classification. By combining global feature aggregation with localized attention mechanisms, the proposed model achieves better performance in distinguishing various potato leaf diseases. The proposed model attains an accuracy of 91.7%, outperforming existing methods and offering a reliable solution for automated potato leaf disease diagnosis.
Context-Aware Attention-based Deep Learning Model for Accurate Skin Cancer Detection using Dermoscopy Images S. Prince Chelladurai, Satheeshkumar. N, E. Bharath, S.Soorya, T. Illakiya 4th International Conference on Automation Computing and Renewable Systems Icacrs 2025 Proceedings, 2025 Early and accurate classification of medical images serves an important part in disease detection and planning treatments. Advanced deep learning approaches, particularly Convolutional Neural Networks (CNNs), have proven effective in analyzing medical images. However, these CNN architectures often fail to effectively capture spatial dependencies and contextual information within medical images. This study introduces an innovative deep learning framework merging DenseNet-121 and Non-Local Attention block to enhance feature representation and improve classification performance. The Non-Local Attention module allows the model to extract global contextual relationships across feature maps, addressing the limitations of local receptive fields in CNNs. The proposed method was tested on the ISIC dataset and obtained an accuracy of 89.3% with augmentation, outperforming the other pretrained CNN architectures. The findings highlight the capability and strength of the proposed approach for robust and reliable medical image classification.
E-voting system using biometric testament and cloud storage T. Illakiya, S. Karthikeyan, U. Maharaja Velayutham, N. T. Ravi Devan Iconstem 2017 Proceedings 3rd IEEE International Conference on Science Technology Engineering and Management, 2017
RECENT SCHOLAR PUBLICATIONS
Automated Breast Cancer Classification in Ultrasound Imaging Using Dense and Global Feature Fusion S Sukumar, AV Joel, ND Nahata, D Damania, T Illakiya 2026 9th International Conference on Intelligent Computing and Control … , 2026 2026
Classification of Alzheimer's Disease Through Deep Learning Approaches with Contextual T Illakiya, B Vidhya, K Jashvanth Advances in Artificial Intelligence and Machine Learning in Big Data … , 2026 2026
Data preprocessing and augmentation techniques for neuroinformatics T Illakiya, S Anand, B Vidhya Deep Learning Applications in Neuroinformatics, 21-47 , 2026 2026
Deep learning for Alzheimer’s disease and mild cognitive impairment detection SV Easwaramoorthy, T Illakiya, K Venkatachalam, S Hariprasad, ... Deep Learning Applications in Neuroinformatics, 81-103 , 2026 2026
Context-Aware Attention-based Deep Learning Model for Accurate Skin Cancer Detection using Dermoscopy Images SP Chelladurai, E Bharath, S Soorya, T Illakiya 2025 4th International Conference on Automation, Computing and Renewable … , 2025 2025
Deep Learning Models for Predictive Crop Water Stress Management using Real-Time Environmental Data T Illakiya, R Navyashree, A Aleeswari, G BhupalRaj, P Balaji, B Muni 2025 Third International Conference on Emerging Applications of Material … , 2025 2025
Next-Generation Blockchain: The Role of Quantum Protocols in Future Systems T Illakiya, K Randive, S Subramanian, G Prabaharan, K Prasanna Kumar, ... Quantum Protocols in Blockchain Security, 407-426 , 2025 2025
Classification of benign and malignant breast lesions in mammograms using dense-unified multiscale attention network and data-efficient image transformers S Paavankumar, R Karthik, G Idayachandiran, PPD Sri, T Illakiya The European Physical Journal Special Topics 234 (15), 4337-4355 , 2025 2025 Citations: 4
A Hybrid Deep Learning Model for Potato Leaf Disease Classification using Transfer Learning and Attention Mechanism T Illakiya, AV Joel, ND Nahata, S Sukumar, SP Chelladurai 2025 8th International Conference on Computing Methodologies and … , 2025 2025
An Attention-Based CNN and Transfer Learning Approach for Accurate Skin Lesion Classification SP Chelladurai, E Bharath, T Pandiarajan, T Illakiya 2025 6th International Conference on Data Intelligence and Cognitive … , 2025 2025
A deep learning framework with attention mechanism for the classification of mild cognitive impairment using brain mri T Illakiya, B Vidhya, SP Chelladurai, S Hariprasad 2025 International Conference on Visual Analytics and Data Visualization … , 2025 2025 Citations: 1
A Hybrid Deep Learning Model for Lung Cancer Classification Using DenseNet169 and Convolutional Block Attention Module T Illakiya, S Akhilesh, DS Karthik 2025 International Conference on Multi-Agent Systems for Collaborative … , 2025 2025 Citations: 7
Machine Learning for Consumer-Centric Safety in Automotive Commerce N Madhumithaa, TNS Rao, R Gupta, T Illakiya, I Imomov, V Bihade AI's Role in Enhanced Automotive Safety, 305-318 , 2025 2025
Classification of Alzheimer's Disease Through Deep Learning Approaches with Contextual and Inter-channel Features from Brain MRI T Illakiya, B Vidhya, K Jashvanth International Conference on Advances in Artificial Intelligence and Machine … , 2024 2024
A deep learning approach for crop disease and pest classification using swin transformer and dual-attention multi-scale fusion network R Karthik, A Ajay, AS Bisht, T Illakiya, K Suganthi IEEE access 12, 152639-152655 , 2024 2024 Citations: 52
Integration of localized, contextual, and hierarchical features in deep learning for improved skin lesion classification K Ramamurthy, I Thayumanaswamy, M Radhakrishnan, D Won, ... Diagnostics 14 (13), 1338 , 2024 2024 Citations: 20
A deep feature fusion network with global context and cross-dimensional dependencies for classification of mild cognitive impairment from brain MRI T Illakiya, R Karthik, Alzheimer's Disease Neuroimaging Initiative Image and Vision Computing 144, 104967 , 2024 2024 Citations: 32
A dimension centric proximate attention network and swin transformer for age-based classification of mild cognitive impairment from brain MRI T Illakiya, R Karthik IEEE Access 11, 128018-128031 , 2023 2023 Citations: 28
AHANet: Adaptive hybrid attention network for Alzheimer’s disease classification using brain magnetic resonance imaging T Illakiya, K Ramamurthy, MV Siddharth, R Mishra, A Udainiya Bioengineering 10 (6), 714 , 2023 2023 Citations: 69
Automatic detection of Alzheimer's disease using deep learning models and neuro-imaging: current trends and future perspectives T Illakiya, R Karthik Neuroinformatics 21 (2), 339-364 , 2023 2023 Citations: 81
MOST CITED SCHOLAR PUBLICATIONS
Automatic detection of Alzheimer's disease using deep learning models and neuro-imaging: current trends and future perspectives T Illakiya, R Karthik Neuroinformatics 21 (2), 339-364 , 2023 2023 Citations: 81
AHANet: Adaptive hybrid attention network for Alzheimer’s disease classification using brain magnetic resonance imaging T Illakiya, K Ramamurthy, MV Siddharth, R Mishra, A Udainiya Bioengineering 10 (6), 714 , 2023 2023 Citations: 69
A deep learning approach for crop disease and pest classification using swin transformer and dual-attention multi-scale fusion network R Karthik, A Ajay, AS Bisht, T Illakiya, K Suganthi IEEE access 12, 152639-152655 , 2024 2024 Citations: 52
A deep feature fusion network with global context and cross-dimensional dependencies for classification of mild cognitive impairment from brain MRI T Illakiya, R Karthik, Alzheimer's Disease Neuroimaging Initiative Image and Vision Computing 144, 104967 , 2024 2024 Citations: 32
Performance analysis of machine learning and deep learning models for classification of Alzheimer’s disease from brain MRI I Thayumanasamy, K Ramamurthy Traitement du Signal 39 (6), 1961 , 2022 2022 Citations: 32
A dimension centric proximate attention network and swin transformer for age-based classification of mild cognitive impairment from brain MRI T Illakiya, R Karthik IEEE Access 11, 128018-128031 , 2023 2023 Citations: 28
Integration of localized, contextual, and hierarchical features in deep learning for improved skin lesion classification K Ramamurthy, I Thayumanaswamy, M Radhakrishnan, D Won, ... Diagnostics 14 (13), 1338 , 2024 2024 Citations: 20
E-voting system using biometric testament and cloud storage T Illakiya, S Karthikeyan, UM Velayutham, NTR Devan 2017 Third International Conference on Science Technology Engineering … , 2017 2017 Citations: 9
A Hybrid Deep Learning Model for Lung Cancer Classification Using DenseNet169 and Convolutional Block Attention Module T Illakiya, S Akhilesh, DS Karthik 2025 International Conference on Multi-Agent Systems for Collaborative … , 2025 2025 Citations: 7
Classification of benign and malignant breast lesions in mammograms using dense-unified multiscale attention network and data-efficient image transformers S Paavankumar, R Karthik, G Idayachandiran, PPD Sri, T Illakiya The European Physical Journal Special Topics 234 (15), 4337-4355 , 2025 2025 Citations: 4
Improved genetic operators to handle uncertainty in medical image classification T Illakiya Int J Adv Comp Technol, 50-3 , 2013 2013 Citations: 2
A deep learning framework with attention mechanism for the classification of mild cognitive impairment using brain mri T Illakiya, B Vidhya, SP Chelladurai, S Hariprasad 2025 International Conference on Visual Analytics and Data Visualization … , 2025 2025 Citations: 1
Automated Breast Cancer Classification in Ultrasound Imaging Using Dense and Global Feature Fusion S Sukumar, AV Joel, ND Nahata, D Damania, T Illakiya 2026 9th International Conference on Intelligent Computing and Control … , 2026 2026
Classification of Alzheimer's Disease Through Deep Learning Approaches with Contextual T Illakiya, B Vidhya, K Jashvanth Advances in Artificial Intelligence and Machine Learning in Big Data … , 2026 2026
Data preprocessing and augmentation techniques for neuroinformatics T Illakiya, S Anand, B Vidhya Deep Learning Applications in Neuroinformatics, 21-47 , 2026 2026
Deep learning for Alzheimer’s disease and mild cognitive impairment detection SV Easwaramoorthy, T Illakiya, K Venkatachalam, S Hariprasad, ... Deep Learning Applications in Neuroinformatics, 81-103 , 2026 2026
Context-Aware Attention-based Deep Learning Model for Accurate Skin Cancer Detection using Dermoscopy Images SP Chelladurai, E Bharath, S Soorya, T Illakiya 2025 4th International Conference on Automation, Computing and Renewable … , 2025 2025
Deep Learning Models for Predictive Crop Water Stress Management using Real-Time Environmental Data T Illakiya, R Navyashree, A Aleeswari, G BhupalRaj, P Balaji, B Muni 2025 Third International Conference on Emerging Applications of Material … , 2025 2025
Next-Generation Blockchain: The Role of Quantum Protocols in Future Systems T Illakiya, K Randive, S Subramanian, G Prabaharan, K Prasanna Kumar, ... Quantum Protocols in Blockchain Security, 407-426 , 2025 2025
A Hybrid Deep Learning Model for Potato Leaf Disease Classification using Transfer Learning and Attention Mechanism T Illakiya, AV Joel, ND Nahata, S Sukumar, SP Chelladurai 2025 8th International Conference on Computing Methodologies and … , 2025 2025
