Artificial Intelligence, Human-Computer Interaction, Decision Sciences, Information Systems
8
Scopus Publications
11
Scholar Citations
3
Scholar h-index
Scopus Publications
A Robust Lemuria Framework for efficient crop prediction M. Tamilselvi, S. Vishnupriya, K. Ushanandhini, A. Dhanamathi Scientific Reports, 2026 Abstract Agriculture remains a critical pillar of the Indian economy, yet yield forecasting continues to be affected by climatic uncertainty and diverse environmental conditions. To address these challenges, this study introduces the Robust Lemuria Framework (RLF), a deep ensemble hybrid model that integrates a Deep Belief Network (DBN) for hierarchical and non-linear feature abstraction with a diversified ensemble of Random Forest (RF), J48 Decision Tree (DT), and Naïve Bayes (NB) classifiers for stable prediction consensus. The novelty of RLF lies in its two-stage optimized preprocessing pipeline, which applies DBN-based pre-training to eliminate noise, reconstruct missing values, and refine complex agricultural features through non-linear dimensionality reduction. The framework is trained and evaluated using a decade of multi-regional Indian agricultural data (2010–2020), capturing variations across climate zones, crops, and seasonal patterns. Experimental results show that RLF significantly outperforms existing machine learning and deep learning approaches, achieving 98.99% accuracy, 98.54% sensitivity, 99.35% specificity, and an R2 score of 0.9994 for yield prediction. These outcomes demonstrate the robustness, scalability, and real-world applicability of the model for agricultural forecasting. Overall, the proposed framework provides a reliable decision-support tool for precision agriculture, contributing to improved crop planning, resource allocation, and policy formulation.
Analysis of Brain Health Using Machine Learning and Artificial Intelligence Technology: Modern Drug Discovery Perspective Arunkumar Thirunagalingam, M. S. Usha, S. Geetha, A Dhanamathi, S. Dhivya, M.Tamil Thendral 1st International Conference on Advances in Computer Science Electrical Electronics and Communication Technologies Ce2ct 2025, 2025 The creation and discovery of pharmaceuticals may be considered the most important translational science activity that improves human invulnerability and happiness. In the pharmaceutical sector, strategies to reduce costs and speed up the development of new drugs have sparked a rigorous and fascinating brainstorming session. The use of classified big data in conjunction with remarkably improved computer power and cloud storage has enabled the application of artificial intelligence (AI), particularly the deep-learning (DL) component, in all domains.In healthy individuals, ML evaluation of neuroimaging data may accurately predict ordered age; illness and mental impairment have been linked to departures from normal brain maturation. Convolutional neural networks (CNN), a DL-based predictive display technique, were applied to both pre-handled and raw T1-weighted X-ray data in order to further evaluate the eligibility of “brain-predicted age” as a biomarker of individual contrasts in the brain ageing process. Brain-predicted age is a very accurate, remarkably stable, and genetically valid trait that exhibits assurance as a biomarker of brain maturation. Additionally, age may be accurately predicted from raw T1-MRI data, which greatly reduces the amount of time needed to compute fresh data and accelerates the process of delivering immediate data on brain health in clinical settings.
Securing the Cloud with AWS Shield for Comprehensive Protection of Cloud Infrastructure and Services Satheeshkumar Sekar, Pacha Shobha Rani, A. Dhanamathi, Ayalapogu Ratna Raju, Pramod Pandey, Bavaneeswari M Proceedings of the 2025 11th International Conference on Communication and Signal Processing Iccsp 2025, 2025 Cloud infrastructure requires strong, scalable, and intelligent security measures to combat advancing cyber threats. Amazon Web Services (AWS) Shield provides extensive security for cloud-hosted services via real-time mitigation of Distributed Denial of Service (DDoS) threats. This managed security solution, fully connected with AWS, guarantees continuous monitoring, fast threat detection, and automated response for all hosted applications. Utilizing AWS Shield’s sophisticated analytics and threat intelligence, organizations enhance their resistance against volumetric and application-layer threats autonomously. The solution's flawless integration with AWS CloudFront, Elastic Load Balancing, and Route 53 improves protection coverage while preserving performance and service availability. AWS Shield Advanced offers enhanced visibility, financial protection, and round-the-clock access to the AWS DDoS Response Team (DRT). The implementation ensures adherence to international security requirements, making it appropriate for industries such as healthcare, banking, and e-commerce. AWS Shield enhances cloud environments via layered security architecture, ensuring safe and continuous digital operations across many sectors.
On-Body Sensing Solutions for Automatic Health Monitoring Systems Using IoT A. Dhanamathi, C. Gunasundari Industry 5 0 for Smart Healthcare Technologies Utilizing Artificial Intelligence Internet of Medical Things and Blockchain, 2024 Nowadays, the healthcare market is experiencing rapid development and is accepted to be drastically enormous because of its up-and-coming worldwide maturation. The pervasive smartphone is the best data exchange station and is considered for the purpose of obtaining customized medical information. Here, medical data such as blood glucose and uric levels are displayed by the smartphone. The family specialist gets access to the related biomedical data of his patient and gives exact, customized, and preventive healthcare counsel. In the rising medical Internet of Things (IoT) applications, the proposed framework brings biosensors, internet communication, data processing, and family specialists together to provide comprehensive healthcare to every client. The use of IoT in conjunction with a global mobile communication system makes healthcare providers’ and patients’ lives easier. One of the key IoT innovations in the healthcare industry is body sensor networks, which use sensors, IoT, and cloud-based monitoring systems to continuously monitor patients’ health conditions. This chapter’s main emphasis is on web servers and applications to test and monitor various biological parameters. The intake (food, tablets) is analyzed by a sensor to measure the level of glucose and uric acid to predict diabetes.
Deep Reinforcement Learning for Autonomous Drone Navigation in Cluttered Environments A Chandrashekhar, Amit Rawate, A. Dhanamathi, Rakeshnag Dasari, Rajeshri Pravin Shinkar, Pavithra G 5th International Conference on Recent Trends in Computer Science and Technology Icrtcst 2024 Proceedings, 2024 The application of Deep Reinforcement Learning (DRL) to enhance the autonomous navigation capabilities of drones in environments that are complex and congested. The complications involved with guiding drones across restricted places, overcoming obstructions, and navigating among clutter are addressed in this article. Through the utilization of DRL techniques, the framework that has been proposed gives drones the ability to learn and alter their navigation strategies on their own through the process of trial and error, hence optimization of real-time decision-making. The incorporation of deep neural networks for the processing of sensory data makes it possible for drones to comprehend their environment, which in turn makes it easier for them to make educated judgments with regard to safe navigation. In order to demonstrate the potential of DRL in boosting the autonomy and robustness of drone navigation systems in demanding environments, the effectiveness of the technique is evaluated using simulations and experiments conducted in the real world. The findings make a contribution to the development of autonomous drone technology, which has implications for a variety of applications including environmental monitoring, search and rescue operations, and surveillance.
A Novel Approach for Driver Drowsiness Detection using Deep Neural Networks Sharon K V, Natarajan B, P. Madhumitha, A Dhanamathi, Prabu S, S Saranya Proceedings of Icwite 2024 IEEE International Conference for Women in Innovation Technology and Entrepreneurship, 2024 One major problem that contributes to many traffic accidents that cause injuries and fatalities all over the world is drowsy driving. This research introduces the novel approach for detecting driver drowsiness using deep networks and computer vision techniques aims to solve this issue and improve road safety. The Proposed system employs an InceptionV3-based Convolutional Neural Network (CNN) model to precisely determine whether the driver’s eyes are open or closed. A sizable dataset of eye images taken in actual driving situations is used to train the CNN model. Whenever the indicators of drowsiness are detected, the proposed system will identify them in real time and promptly notify the driver. The proposed model not only has strong real-time capabilities but also exhibits superior accuracy based on stringent evaluation metrics, which makes a significant contribution to efforts aimed at promoting road safety. The performance and adaptability of the system are improved and further integrates alarm activation for drowsiness detection in a variety of driving conditions.
Integrating and Interpreting Biomedical Analysis: A Comprehensive Analysis of Machine Learning Algorithms for Precision Medicine G. Sasikala, Sofia Bobby J, Dhanamathi A, C. L. Annapoorani, Prathisha M, V. Mythily 3rd International Conference on Advances in Computing Communication and Materials Icaccm 2024, 2024 A new era in healthcare has begun with precision medicine, which tailors medications to the specific characteristics of each individual patient. This shift is being driven by the advent of advanced machine learning (ML) algorithms that can parse and make sense of biological data culled from diverse sources like clinical records, proteomics, and genomes. This study aims to give a thorough evaluation of ML algorithms employed in biomedical analysis for precision medicine, with a particular emphasis on these algorithms' integration, interpretation, and practical uses. In this first step, we take stock of biological data and its current state, drawing attention to issues like data volume, privacy concerns, and data heterogeneity that pose obstacles to its integration. We continue by taking a look at the most recent developments in supervised and unsupervised learning as well as deep learning algorithms used in biological analysis. In the context of precision medicine, we discuss the pros and cons of these algorithms and emphasise their ability to handle complex data and extract valuable insights. Methods for feature selection, data preprocessing, and model validation are among the topics covered in this investigation of how to integrate ML algorithms with biological data. To make sure that healthcare providers and patients can understand and trust the results of machine learning (ML) models, we investigate how explainable AI (XAI) can help interpret these decisions. We also provide case examples that show how ML algorithms have been used for precision medicine to diagnose diseases, predict how treatments will work, and create individualised treatment plans. These examples show how ML has the ability to revolutionise healthcare by enhancing patient outcomes while decreasing expenses. Lastly, we discuss potential future developments and areas for future research in the field, such as improving XAI methods, integrating multi-omics data, and creating more sophisticated ML models. The research highlights the significance of integrating knowledge from several disciplines to progress precision medicine, specifically computer science, data science, and biomedical sciences.
AI-Driven Image Annotation for Plant Disease Detection Using Google Cloud Vision Platform Sabeetha Saraswathi S, Raju V, Dhanamathi A, Chitra J, Chandrasekar V, Rekha M, Thiruppathy Kesavan V International Journal of Experimental Research and Review, 2024 : Enabling visual plant disease diagnosis through deep learning that analyses big data is essential to diagnose diseases quickly. It helps the farmers and enables them to treat early, reducing the crop losses needed for a sustainable increase in agriculture. Farmers’ losses were also reduced using these technologies. However, deep learning still has great potential for plant disease diagnosis, though many challenges are associated with it. For example, it requires large, annotated data sets of symptoms and processing resources. This study proposes a novel Cloud-based Image Annotation Plant Disease Detection (C-IAPDD), which employs cloud platforms such as Google Cloud Vision API for image annotation and plant disease detection. Instead of creating such datasets manually or using those non-annotated ones saved by farmers onto their mobile phones since sensors in the device can detect disease on a particular leaf whenever placed close to it. The proposed solution provides a connection to the Internet and offline as well. The ability of C-IAPDD to simplify large-scale envision dataset collection and annotation enables powerful deep-learning models. Using cloud infrastructure’s processing power and scalability makes this a highly efficient method of identifying plant diseases without compromising accuracy. Several simulation experiments have proved that C-IAPDD could recognize a wide range of plant diseases across different types of crops. This simulation shows that C-IAPDD performs better than other methods in precision, swiftness, and expandability. The results indicate that C-IAPDD may improve plant disease detection and control, leading to healthier harvests. These findings endorse I-CIAPDD for artificial intelligence in agriculture.
RECENT SCHOLAR PUBLICATIONS
On-Body Sensing Solutions for Automatic Health Monitoring Systems Using IoT A Dhanamathi, C Gunasundari Industry 5.0 for Smart Healthcare Technologies, 153-160 , 2024 2024
A Framework for Wood Quality Assessment using DenseNet Algorithm A Dhanamathi, K Ajith, V Balamurugan, S Sridhar i-manager's Journal on Pattern Recognition 11 (1), 30 , 2024 2024
Deep reinforcement learning for autonomous drone navigation in cluttered environments A Chandrashekhar, A Rawate, A Dhanamathi, R Dasari, RP Shinkar 2024 5th International Conference on Recent Trends in Computer Science and … , 2024 2024 Citations: 3
A novel approach for driver drowsiness detection using deep neural networks KV Sharon, B Natarajan, S Prabu 2024 IEEE International Conference for Women in Innovation, Technology … , 2024 2024 Citations: 3
Sarcasm Sentiment Detection and Classification Model on Twitter S Ezhilmathi, A Dhanamathi, R Loganathan, E Elanchezhiyan Bioscience Biotechnology Research Communications Special Issue 13 (6), 147-152 , 2020 2020 Citations: 5
MOST CITED SCHOLAR PUBLICATIONS
Sarcasm Sentiment Detection and Classification Model on Twitter S Ezhilmathi, A Dhanamathi, R Loganathan, E Elanchezhiyan Bioscience Biotechnology Research Communications Special Issue 13 (6), 147-152 , 2020 2020 Citations: 5
Deep reinforcement learning for autonomous drone navigation in cluttered environments A Chandrashekhar, A Rawate, A Dhanamathi, R Dasari, RP Shinkar 2024 5th International Conference on Recent Trends in Computer Science and … , 2024 2024 Citations: 3
A novel approach for driver drowsiness detection using deep neural networks KV Sharon, B Natarajan, S Prabu 2024 IEEE International Conference for Women in Innovation, Technology … , 2024 2024 Citations: 3
On-Body Sensing Solutions for Automatic Health Monitoring Systems Using IoT A Dhanamathi, C Gunasundari Industry 5.0 for Smart Healthcare Technologies, 153-160 , 2024 2024
A Framework for Wood Quality Assessment using DenseNet Algorithm A Dhanamathi, K Ajith, V Balamurugan, S Sridhar i-manager's Journal on Pattern Recognition 11 (1), 30 , 2024 2024
