D SUBITHA

@veltech.edu.in

Assoociate Professor
Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology

D SUBITHA


               Download Compact PDF  
https://researchid.co/dsubitha

RESEARCH INTERESTS

Wireless Communication
Signal Processing
Antenna Design
50

Scopus Publications

284

Scholar Citations

9

Scholar h-index

9

Scholar i10-index

Scopus Publications

  • SQL Query Optimization Using Reinforcement Learning for Low-Power Computing Systems
    B. V. N. S. Diwakar, D. Subitha, J. C. Kavitha
    Lecture Notes in Networks and Systems, 2026
  • Inverter-Integrated ECC with Torsion Points as Black Box Alternatives in Aircraft Security
    Jasleen Kaur, Nilesh Tiwari, Nikhil Nair, D. Subitha
    Lecture Notes in Electrical Engineering, 2026
  • Decentralized secure multi-agent path planning using federated reinforcement learning and blockchain
    Hariram Pasupathy, Laleeth Adithya Sridhar, Poushikkumar Sivakumar, Subitha D., Kavitha J. C.
    Peerj Computer Science, 2026
    Multi-agent path planning in decentralized settings presents issues such as limited communication, security risk, and scalability issues. Centralized approaches have a single point of failure and are not ideal to depend on. Our proposed Decentralized and Secure Multi-Agent Path Planning framework is based on Federated Reinforcement Learning (FRL) with Proximal Policy Optimization (PPO) and blockchain. This FRL-PPO framework allows agents to learn how to navigate effectively without transmitting raw data or unnecessary information, protecting agent privacy. Smart contracts based on blockchain technologies also facilitate secure communication and guarantee trust among agents. We demonstrated the value of the FRL-PPO configuration through experiments in a simulated environment that showed the speed of the learning process was enhanced, attack resistance, and the overall speed of path planning and path efficiency improved. Our approach reduces the risk of data manipulation, making autonomous multi-agent systems more secure, scalable, and effective in decentralized environments.
  • Edge-optimized threat detection with Florence v2 for autonomous surveillance in resource-constrained environments
    Cynthia Konar, Diya Das, Subitha D., Kavitha Jc, Sweety Singh
    Peerj Computer Science, 2026
    This research presents a portable, edge-optimized system designed to overcome the limitations of traditional surveillance in detecting modern threats such as disguised individuals, hidden weapons, and flying drones, particularly in environments with limited resources. The system leverages a modified Florence v2 Vision-Language Transformer for military-grade object detection, with its core deployed on a Raspberry Pi 5. A separate ESP32-S2 DevKit handles wireless alerts using the ESP-NOW protocol for fast, local communication. To achieve high accuracy with low computational overhead, we adapted the Florence v2 model using Parameter Efficient Fine-Tuning (PEFT) and Low-Rank Adaptation (LoRA). The model was trained on a dataset of 12,000 images, augmented with manual annotations and synthetic images generated by Generative Adversarial Networks (GANs). The final model achieved an overall accuracy of 88.01%, outperforming other popular models such as You Only Look Once version 8 (YOLOv8) and Fast Region-based Convolutional Neural Network (FRCNN). Our model achieved a Mean Average Precision (mAP@50) score of 64.83, compared to YOLOv8 (64) and FRCNN (56). After training, the model was optimized through quantization and pruning to ensure efficient execution on edge hardware. It processes a frame in 16.6 s, utilizing only 38.4% of the Raspberry Pi’s RAM and 50.9% of its CPU. The integrated ESP32-S2 module enables the system to transmit critical alerts over long distances without the need for cloud connectivity or a central server. This system demonstrates the capability of autonomous, real-time surveillance across critical domains including military borders, urban airspaces, and civilian infrastructure.
  • Adaptive Multi-Layer Contrastive Graph Neural Network for Massive MIMO Under Imperfect CSIT
    Subitha D
    IETE Journal of Research, 2025
    Massive multiple-input multiple-output (MIMO) is the most important development in modern wireless systems. Massive MIMO systems have dramatically improved spectral and energy efficiency while also streamlining signal processing by outfitting base stations with an enormous number of antennas. To overcome this issue, an Adaptive Multi-layer Contrastive Graph Neural Network for Massive MIMO under Imperfect CSIT (AMCGNN-MIMO-CSIT) is proposed. Initially, uniform planar arrays (UPAs) at base stations in large multiple-input multiple-output communication systems, and look into downlink precoder design with poor channel status information (CSI). Initially, channel model indicates the quantitative depiction of a communication channel's propagation effects for wireless communications. Then, downlink transmission is the transmission path from the network side to mobile or fixed terminals. Later, Adaptive multi-layer contrastive graph neural network (AMCGNN) method requires an initialization parameter that decides the speed of convergence. The parameter is calculated from the Eigen value bounds. Generally, AMCGNN classifier does not adapt any optimization methods to detect optimal parameters for determining the speed of convergence. Therefore, Red Piranha Optimization Algorithm (RPOA) is proposed to enhance the weight parameters of AMCGNN, which accurately detects the speed of convergence. The proposed method performance assessed in presence of poor channel circumstances. The performance analysis is used as an alternative to measure the method's tolerance against channel state error. The simulation outputs demonstrate that the AMCGNN-MIMO-CSIT technique achieves 0.3%, 0.3% and 0.21% lower Normalized Mean Square Error (NMSE) while analyzed with existing techniques, such as DL-RPC-MIMO, DL-MU-MIMO, and MDDL-FDD-MIMO respectively.
  • Adaptive Machine Learning Models for Congestion Prediction Across Urban and Suburban Road Networks
    Mohita, Subitha D
    2025 IEEE 9th International Conference on Information and Communication Technology Cict 2025, 2025
    Urban and suburban traffic congestion remains a pressing challenge due to growing vehicle density and dynamic influencing factors such as weather conditions and peak hour patterns. Traditional traffic control systems, often static and inflexible, struggle to adapt to these variations, leading to inefficiencies and prolonged delays. This research presents a hybrid adaptive machine learning framework that integrates simulation-based traffic data with real-time visual detection to forecast congestion across varying geographical and temporal contexts. Leveraging OpenStreetMap and SUMO for simulation, and combining Random Forest and Neural Network models, the system adapts its predictive behavior based on area type and environmental conditions. Additionally, YOLO-based vehicle detection enhances congestion estimation by verifying vehicular density in real time. By dynamically adjusting to both structural and temporal traffic patterns, the model significantly contributes to intelligent transportation systems aimed at optimizing urban mobility and minimizing congestion-related losses.
  • Introduction to Network Sensing Systems in Society 5.0: Issues and Challenges
    Ankit Kumar, Anurag Kumar Kanojiya, D. Subitha
    Networked Sensing Systems, 2025
    Network Sensing System in Society 5.0 provides unprecedented connectivity and data-driven solutions to numerous societal problems. But they also raise many questions and problems that need to be resolved to ensure they are used effectively and fairly. This content explores the key issues and challenges of the Society 5.0 community. Since sensors collect and transmit a lot of data continuously, data privacy and security become an important issue. Strong protection and encryption are required to prevent data from leakage, unauthorized access, and misuse. The integration and data sharing of many sensors and protocols depend on the interoperability and standardization of the sensor. So, the systems can be made more scalable and efficient using different structures and procedures. Transparency, impartiality, and fairness are among some of the ethical concerns under data analysis and algorithmic decision making. So, it is necessary to take necessary actions to ensure fair results and get rid of biases to maintain trust and prevent bad outcomes. Network Detection System 5.0 focuses on reliable power plans and strong communication methods; therefore, infrastructure flexibility and dependability are very important. Such vulnerabilities in the systems might have the potential to cause disturbances and may interfere with vital activities. Hence, it is necessary to invest in redundancy and resilience in infrastructure. Energy and safety are important issues due to the environmental impact of sensors and data processing. Energy-efficient solutions and renewable energy sources can reduce these impacts and promote sustainability. The development of technology, policy, and business management creates uncertainty about responsibility and control. Guidelines and policies should be developed to address legal, ethical, and social issues while promoting innovation and community service. Public trust and acceptance are key to implementing Network Detection System 5.0. Transparent communication, community engagement, and meaningful feedback are critical to solving privacy, security, and consequence issues.
  • Improving Cancer Classification Through an Deep Learning Framework Using Transfer Learning
    Subitha D, Fayyaz Khalid, Kavitha J C, Gulisetty Abhinav
    2nd International Conference on Machine Learning and Autonomous Systems Icmlas 2025 Proceedings, 2025
    The primary objective of this work is to create an AI system that offers intelligible and transparent justifications for cancer classification. When it comes to medical imaging-based cancer detection, sophisticated image analysis techniques such as deep learning models are used to assess and interpret medical pictures while offering a transparent account of its reasoning. The performance of the three state-of-art pre-trained deep models: VGG-16, and EfficientNetB0 on a dataset of eight different cancer types obtained from Kaggle is analyzed in this work. Furthermore, a novel deep learning framework is proposed using the above mentioned three pre-trained models as the backbone network using transfer learning approach for each type of cancer. Each model's effectiveness is evaluated in classifying these cancers using metrics like accuracy, precision, recall, and F1-score. This work ultimately yields the best fit model that are tuned with the hyper parameters optimized using Powell's algorithm.
  • Explainable Credit Score Risk Analysis: Integrating Outlier Detection and Ensemble Modelling
    D Subitha, J C Kavitha, Karun Santosh, S G Rahul
    International Conference on Advanced Computing Technologies Icoact 2025, 2025
    In this research, we have explored the complex field of credit risk prediction using a various approach that integrates machine learning model for classification and model explainability. Accurate risk assessment, model performance evaluation, and open communication of predictions to stakeholders are the main goals. The project begins with descriptive statistics and exploratory data analysis (EDA), which reveals information on the financial and demographic makeup of credit applicants. Afterwards, outlier identification and elimination through Tukey's method and IsolationForest are done separately to guarantee the validity of ensuing analyses. Our predictive modelling is based on the use of many techniques, including random forest, XGBoost, LightGBM, logistic regression and finally ensemble model. Every model is fine-tuned for peak performance, and a comparative analysis provides a standard for forecast accuracy. We use methods such as SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) to improve the interpretability of our models. With the use of these techniques, we can better understand and convey the judgments rendered by intricate models, promoting openness in the evaluation of credit risk.
  • Self - adaptive canny edge detection with reinforcement learning and dominant texture color patterns for melanoma segmentation and classification in dermoscopic images
    Kavitha J C, Subitha D, Nagarajan D
    Engineering Research Express, 2024
    Melanoma, considered to be the most rapidly increasing cancer, has had great emphasis placed on its diagnosis. This paper proposes a powerful edge detection framework Self-adaptive Canny Edge Detection using Reinforcement Learning (CRL-Edge) that integrates Canny edge detection with reinforcement learning. This approach adaptively fine-tunes the threshold parameters of the canny so as to enhance the edge continuity particularly for images with weak boundaries. The research also focusses on proposing a feature extraction method Dominant Texture Color Patterns (DTCP) that effectively helps in classifying malignant melanoma from dermoscopic images. This method is proposed based on the extraction of texture and color features that are dominant in a particular local region. The RGB color channel that consists of texture patterns with more intensity variations is said to be a dominant texture feature and a color channel that has maximum color intensity variations is a dominant color feature. The texture-color patterns are combined together to form a pattern that is assigned a unique texture-color value that describes the image features. The proposed feature of texture and color is analyzed in dermoscopic color images to classify lesions as benign or malignant, using CatBoost, a gradient boosting technique. The CatBoost is compared with other gradient boosting algorithms like Random Forest, XGBoost and Light GBM. The experiments were conducted on two different databases, the ISIC Archive and the PH2 database. The images were evaluated, on the basis of performance metrics such as sensitivity, specificity, accuracy, precision, F1-score and AUC. The experiment results show that CRL-Edge segmentation provides better segmentation accuracy and the DTCP descriptor using CatBoost classifier provides enhanced classification accuracy for classifying malignant lesion. The new method is compared with different state-of-art methods and has demonstrated the best performance.
  • RETRACTION:Lesion detection and classification in dermoscopic images using optimal threshold based on Newton Raphson iterative method
    J.C. Kavitha, D. Subitha
    Journal of Intelligent and Fuzzy Systems, 2024
  • Performance Analysis of Near-Optimal Digital Precoding Algorithm for Massive MIMO Systems
    Journal of Communications, 2024
  • Enhancing Alzheimer’s disease classification through split federated learning and GANs for imbalanced datasets
    G Narayanee Nimeshika, Subitha D
    Peerj Computer Science, 2024
  • Performance Analysis of Machine Learning Algorithms for Covid-19 Detection using Cough Analysis
    Subitha D, Kavitha J.C
    2024 International Conference on Recent Innovation in Smart and Sustainable Technology Icrisst 2024, 2024
  • Mitigating Imbalance: Cost-Sensitive Learning for Enhanced Weather Prediction in Imbalanced Datasets
    Subitha D, G. Narayanee Nimeshika
    10th International Conference on Advanced Computing and Communication Systems Icaccs 2024, 2024
  • An Ensemble Model based on Deep Learning for Lung Disease Prediction using Chest XRay Images
    Sanchit Raj, J C Kavitha, D Subitha
    8th International Conference on Electronics Communication and Aerospace Technology Iceca 2024 Proceedings, 2024
  • Artificial Intelligence in Biometric Systems
    D. Subitha, S.G. Rahul, Palash Uddin
    AI Based Advancements in Biometrics and Its Applications, 2024
  • An ECC-Isogeny Cipher Shield for Navy Inverter Systems
    Nilesh Tiwari, Jasleen Kaur, D Subitha
    2024 15th International Conference on Computing Communication and Networking Technologies Icccnt 2024, 2024
  • Threat Analysis and Security Measures for the Internet of Medical Things (IoMT): A Study
    S. Velmurugan, G. Shanthi, L. Raja, D. Subitha
    Computational Intelligence and Blockchain in Biomedical and Health Informatics, 2024
  • Predicting Land Cover Changes with Convolutional LSTM Networks: A Case Study of Chatham, Massachusetts
    J C Kavitha, D Subitha, Divyansh Bhandari, Devesh Kumar Jaluka
    IEEE International Conference on Modeling Simulation and Intelligent Computing Mosicom 2024 Proceedings, 2024
  • Integrating IoT and Deep Learning for Smart Aquaculture Management in Freshwater Aquariums
    Rahul S G, Rajkumar R, Y. Kuswanth Reddy, N. Koushik, V. Srree Manikannta, Subitha D
    2nd International Conference on Sustainable Computing and Smart Systems Icscss 2024 Proceedings, 2024
  • Design and analysis of Circular microstrip patch antenna with SRR on modified and defected ground structures for UWB applications
    D. Subitha, I. Chandra, A. Raja
    Materials Today Proceedings, 2023
  • Hybrid precoding algorithm for massive MIMO system with imperfect channel knowledge
    D. Subitha, P. Poonkuzhali, I. Chandra, P. Venkata Hemanth
    Materials Today Proceedings, 2023
  • Smart Social Distancing Robot for COVID Safety
    S. G. Rahul, Velicheti Sravan Kumar, D. Subitha, Seeram Sai Sudheer, Amruthavalli Archakam, M. Nikhileswara Sri Venkat
    Lecture Notes in Mechanical Engineering, 2023
  • Slotted square microstrip patch antenna for 5G communication at 28 GHz with improved BW and gain
    D. Subitha, S. Velmurugan, S. Balasubramani
    Aip Conference Proceedings, 2022
  • Smart health assist for elder people using IoT
    V. Arulkumar, I. Chandra, D. Subitha, A. Raja, R. Ganesan, Rajasekhar Atla
    Aip Conference Proceedings, 2022
  • Wavelet Based Speech Enhancement Algorithm for Hearing Aid Application
    M. Vanithalakshmi, D. Subitha, S. Velmurugan
    8th International Conference on Advanced Computing and Communication Systems Icaccs 2022, 2022
  • Curing Free, Silver Nano Ink Based Inkjet Printed Fabrics for Bio-Medical Applications
    Subitha D, Rahul S G, Velmurugan S, Salveru Saiteja
    2022 IEEE International Conference on Nanoelectronics Nanophotonics Nanomaterials Nanobioscience and Nanotechnology 5nano 2022, 2022
  • SRR Loaded Dual Band Patch Antenna Array For Multi User Communication
    Subitha D, Nomula Harshit, Rahul S G, Bollineni Vinay, Velmurugan S, Yarravarapu Pavan
    8th International Conference on Advanced Computing and Communication Systems Icaccs 2022, 2022
  • Design and Development Of Graphical User Interface To Monitor and Control a Bioreactor: Design and Development of GUI for Bioreactor
    Rahul S G, Velmurugan S, Subitha D, M. Nikhileswara Sri Venkat, S V N Rupesh, Venkatesh D
    8th International Conference on Advanced Computing and Communication Systems Icaccs 2022, 2022
  • Development of Rogers RT/Duroid 5880 Substrate-Based MIMO Antenna Array for Automotive Radar Applications
    D. Subitha, S. Velmurugan, M. Vanitha Lakshmi, P. Poonkuzhali, T. Yuvaraja, Samson Alemayehu
    Advances in Materials Science and Engineering, 2022
  • Slotted. Dual Band 27/37 GHz MIMO Antenna for Millimeter Wave Applications
    Subitha D, R. Pavan Kumar, Velmurugan S, B.V. Sunil Babu, Rahul S G, S. Vinay Kumar
    8th International Conference on Advanced Computing and Communication Systems Icaccs 2022, 2022
  • Contactless Fog based Handwash Kit for COVID Safety
    Rahul S G, Neelamsetti Kiran Kumar, Sri Lekha Y, Velicheti Sravan Kumar, Subitha D, Siripireddy Venkateswarulu
    4th International Conference on Circuits Control Communication and Computing I4c 2022, 2022
  • Design of Microstrip Patch Antenna for Wearable Extravasation Detection Device for Intravenous (IV) Therapy
    Velmurugan S, Prabin Nyaupane, Subitha D, Saikiranreddy Sallarapu, Rahul S G, Satyanarayana Kathula
    8th International Conference on Advanced Computing and Communication Systems Icaccs 2022, 2022
  • Smart Access Control System For Covid Safety Smart Access Control System during Covid
    S G Rahul, D Subitha, S Velmurugan, R Chitra, Avinash Reddy, Grande Nishanth
    8th International Conference on Advanced Computing and Communication Systems Icaccs 2022, 2022
  • A Comparative Computational Analysis of VGG16and VGG19 in Prediction of Turmeric plant Disease
    S Velmurugan, K Ramdinesh Reddy, S G Rahul, S Vardhan, D Subitha, Sri Kamal Vignesh
    8th International Conference on Advanced Computing and Communication Systems Icaccs 2022, 2022
  • Android Application and SMS Alert Based Garbage Monitoring and Navigation System
    K Umapathy, T Mangayarkarasi, D Subitha, A Sivagami
    Journal of Physics Conference Series, 2021
  • An IoT Based Safe Assembly Point Alert System
    T Mangayarkarasi, K Umapathy, A Sivagami, D Subitha
    Journal of Physics Conference Series, 2021
  • Performance Analysis of Matrix Inversion Algorithms for Massive MIMO Precoding under Rural and Urban Scenarios
    D Subitha, S. Velmurugan, R Vani, E Nirmala
    2021 7th International Conference on Advanced Computing and Communication Systems Icaccs 2021, 2021
  • Novel approach for melanoma detection through iterative deep vector network
    R. Vani, J. C. Kavitha, D. Subitha
    Journal of Ambient Intelligence and Humanized Computing, 2021
  • Breast carcinoma analysis by broadband antennas with composite testbeds
    T.M. Amirthalakshmi, D. Subitha, A. Johnson Santhosh, Balachandra Pattanaik, Bharani Murugesan, K. Sakthisudhan
    Materials Today Proceedings, 2021
  • Development of Novel Nano-Silver-Based Antenna for Green Agriculture
    Subitha D., Vani R., Raja A., Balasubramani S., Manjunathan A., Kibebe Sahile
    Advances in Materials Science and Engineering, 2021
  • Automation of transportation process using iot for enhanced production
    Journal of Green Engineering, 2020
  • Poisonous gas detection by wireless sensor network based on ant lion optimization algorithm
    International Journal of Control and Automation, 2020
  • Automatic crop monitoring system using bluetooth module
    International Journal of Control and Automation, 2020
  • A novel low complexity downlink linear precoding algorithm for massive MIMO systems
    D. Subitha, J. M. Mathana
    Cluster Computing, 2019
  • Research on millimeter-wave microstrip patch antenna design for 5G
    B. Tech Scholar, Mohammad Muhammad Umar Khan, Raj Sharawi, Mittra, Wang Kun, et al.
    International Journal of Recent Technology and Engineering, 2019
  • Facing the callenges in 5G using DPA-MaIMaO architecture
    Praveen Boddu, Dr.I. Chandra, Ms.D. Subitha
    International Journal of Engineering and Advanced Technology, 2019
  • Design of Low-Complexity Hybrid Precoder and Inkjet-Printed Antenna Array for Massive MIMO Downlink Systems
    Subitha D, Mathana J M
    International Journal of Antennas and Propagation, 2018
  • Enhanced probe based admission control system for cellular traffic offloading
    International Journal of Applied Engineering Research, 2015

RECENT SCHOLAR PUBLICATIONS

  • Adaptive Machine Learning Models for Congestion Prediction Across Urban and Suburban Road Networks
    D Subitha
    2025 IEEE 9th International Conference on Information and Communication … , 2025
    2025
  • Inverter-Integrated ECC with Torsion
    J Kaur, N Tiwari, N Nair, D Subitha
    Soft Computing Applications in Modern Power and Energy Systems: Select … , 2025
    2025
  • SQL Query Optimization Using Reinforcement Learning for Low-Power Computing Systems
    B Diwakar, D Subitha, JC Kavitha
    International Conference on Emerging Trends and Technologies on Intelligent … , 2025
    2025
  • Explainable Credit Score Risk Analysis: Integrating Outlier Detection and Ensemble Modelling
    D Subitha, JC Kavitha, K Santosh, SG Rahul
    2025 International Conference on Advanced Computing Technologies (ICoACT), 1-7 , 2025
    2025
    Citations: 4
  • Improving Cancer Classification Through an Deep Learning Framework Using Transfer Learning
    D Subitha, F Khalid, JC Kavitha, G Abhinav
    2025 International Conference on Machine Learning and Autonomous Systems … , 2025
    2025
    Citations: 4
  • Introduction to Network Sensing Systems in Society 5.0: Issues and Challenges
    A Kumar, AK Kanojiya, D Subitha
    Networked Sensing Systems, 1-29 , 2025
    2025
    Citations: 1
  • Predicting Land Cover Changes with Convolutional LSTM Networks: A Case Study of Chatham, Massachusetts
    JC Kavitha, D Subitha, D Bhandari, DK Jaluka
    2024 International Conference on Modeling, Simulation & Intelligent … , 2024
    2024
    Citations: 2
  • Self-adaptive canny edge detection with reinforcement learning and dominant texture color patterns for melanoma segmentation and classification in dermoscopic images
    K JC
    Engineering Research Express 6 (4), 045254 , 2024
    2024
    Citations: 7
  • Enhancing Alzheimer’s disease classification through split federated learning and GANs for imbalanced datasets
    GN Nimeshika, D Subitha
    PeerJ Computer Science 10, e2459 , 2024
    2024
    Citations: 23
  • Artificial Intelligence in Biometric Systems
    D Subitha, SG Rahul, P Uddin
    AI Based Advancements in Biometrics and its Applications, 47-67 , 2024
    2024
    Citations: 2
  • An Ensemble Model based on Deep Learning for Lung Disease Prediction using Chest XRay Images
    S Raj, JC Kavitha, D Subitha
    2024 8th International Conference on Electronics, Communication and … , 2024
    2024
    Citations: 4
  • Integrating IoT and Deep Learning for Smart Aquaculture Management in Freshwater Aquariums
    SG Rahul, R Rajkumar, D Subitha
    2024 2nd International Conference on Sustainable Computing and Smart Systems … , 2024
    2024
    Citations: 7
  • An ECC-Isogeny Cipher Shield for Navy Inverter Systems
    N Tiwari, J Kaur, D Subitha
    2024 15th International Conference on Computing Communication and Networking … , 2024
    2024
  • 16 Threat Analysis and
    S Velmurugan, G Shanthi, L Raja, D Subitha
    Computational Intelligence and Blockchain in Biomedical and Health … , 2024
    2024
  • Threat analysis and security measures for the Internet of Medical Things (IoMT): A study
    S Velmurugan, G Shanthi, L Raja, D Subitha
    Computational Intelligence and Blockchain in Biomedical and Health … , 2024
    2024
    Citations: 2
  • Inverter-Integrated ECC with Torsion Points as Black Box Alternatives in Aircraft Security
    J Kaur, N Tiwari, N Nair, D Subitha
    International Conference on Electric Power and Renewable Energy, 201-217 , 2024
    2024
  • Performance Analysis of Machine Learning Algorithms for Covid-19 Detection using Cough Analysis
    D Subitha, JC Kavitha
    2024 International Conference on Recent Innovation in Smart and Sustainable … , 2024
    2024
    Citations: 1
  • Mitigating imbalance: Cost-sensitive learning for enhanced weather prediction in imbalanced datasets
    D Subitha, GN Nimeshika
    2024 10th International Conference on Advanced Computing and Communication … , 2024
    2024
    Citations: 5
  • RETRACTED: Lesion detection and classification in dermoscopic images using optimal threshold based on Newton Raphson iterative method
    JC Kavitha, D Subitha
    Journal of Intelligent & Fuzzy Systems 46 (1), 753-767 , 2024
    2024
  • Performance analysis of near-optimal digital precoding algorithm for massive MIMO systems
    D Subitha
    Journal of Communications 19 (7), 325-330 , 2024
    2024
    Citations: 5

MOST CITED SCHOLAR PUBLICATIONS

  • Development of Rogers RT/Duroid 5880 Substrate‐Based MIMO Antenna Array for Automotive Radar Applications
    D Subitha, S Velmurugan, MV Lakshmi, P Poonkuzhali, T Yuvaraja, ...
    Advances in Materials Science and Engineering 2022 (1), 4319549 , 2022
    2022
    Citations: 27
  • Enhancing Alzheimer’s disease classification through split federated learning and GANs for imbalanced datasets
    GN Nimeshika, D Subitha
    PeerJ Computer Science 10, e2459 , 2024
    2024
    Citations: 23
  • An IoT based safe assembly point alert system
    T Mangayarkarasi, K Umapathy, A Sivagami, D Subitha
    Journal of Physics: Conference Series 1964 (7), 072013 , 2021
    2021
    Citations: 19
  • Millimeter-wave microstrip patch antenna design for 5G
    MD Madhan, D Subitha
    international journal of innovative technology and exploring engineering … , 2019
    2019
    Citations: 19
  • Slotted square microstrip patch antenna for 5G communication at 28 GHz with improved BW and gain
    D Subitha, S Velmurugan, S Balasubramani
    AIP conference proceedings 2405 (1), 040017 , 2022
    2022
    Citations: 17
  • Analysis of linear precoding techniques for massive MIMO-OFDM systems under various scenarios
    D Subitha, R Vani
    IOP conference series: materials science and engineering 1084 (1), 012053 , 2021
    2021
    Citations: 17
  • Novel approach for melanoma detection through iterative deep vector network
    R Vani, JC Kavitha, D Subitha
    Journal of Ambient Intelligence and Humanized Computing, 1-10 , 2021
    2021
    Citations: 16
  • A novel low complexity downlink linear precoding algorithm for massive MIMO systems
    D Subitha, JM Mathana
    Cluster Computing 22 (Suppl 6), 13645-13652 , 2019
    2019
    Citations: 16
  • Design of Low-Complexity Hybrid Precoder and Inkjet-Printed Antenna Array for Massive MIMO Downlink Systems
    D SUBITHA, M JM
    International Journal of Antennas and Propagation 2018 (Article ID 4315128), 8 , 2018
    2018
    Citations: 16
  • A Comparative Computational Analysis of VGG16and VGG19 in Prediction of Turmeric plant Disease
    S Velmurugan, KR Reddy, SG Rahul, S Vardhan, D Subitha, SK Vignesh
    2022 8th International Conference on Advanced Computing and Communication … , 2022
    2022
    Citations: 8
  • Self-adaptive canny edge detection with reinforcement learning and dominant texture color patterns for melanoma segmentation and classification in dermoscopic images
    K JC
    Engineering Research Express 6 (4), 045254 , 2024
    2024
    Citations: 7
  • Integrating IoT and Deep Learning for Smart Aquaculture Management in Freshwater Aquariums
    SG Rahul, R Rajkumar, D Subitha
    2024 2nd International Conference on Sustainable Computing and Smart Systems … , 2024
    2024
    Citations: 7
  • Adaptive multi-layer contrastive graph neural network for massive MIMO under imperfect CSIT
    D Subitha
    IETE Journal of Research 71 (2), 594-602 , 2024
    2024
    Citations: 7
  • Android application and SMS alert based garbage monitoring and navigation system
    K Umapathy, T Mangayarkarasi, D Subitha, A Sivagami
    Journal of Physics: Conference Series 1964 (6), 062064 , 2021
    2021
    Citations: 6
  • Research on millimeter-wave microstrip patch antenna design for 5G
    MD Madhan, D Subitha, I Chandra
    International Journal of Recent Technology and Engineering 8 (2), 2841-2845 , 2019
    2019
    Citations: 6
  • Mitigating imbalance: Cost-sensitive learning for enhanced weather prediction in imbalanced datasets
    D Subitha, GN Nimeshika
    2024 10th International Conference on Advanced Computing and Communication … , 2024
    2024
    Citations: 5
  • Performance analysis of near-optimal digital precoding algorithm for massive MIMO systems
    D Subitha
    Journal of Communications 19 (7), 325-330 , 2024
    2024
    Citations: 5
  • Slotted. Dual Band 27/37 GHz MIMO Antenna for Millimeter Wave Applications
    D Subitha, RP Kumar, S Velmurugan, BVS Babu, SG Rahul, SV Kumar
    2022 8th International Conference on Advanced Computing and Communication … , 2022
    2022
    Citations: 5
  • An efficient privacy-preserving ranked keyword search method
    E Nirmala, S Muthurajkumar, D Subitha
    IOP Conference Series: Materials Science and Engineering 1084 (1), 012103 , 2021
    2021
    Citations: 5
  • Explainable Credit Score Risk Analysis: Integrating Outlier Detection and Ensemble Modelling
    D Subitha, JC Kavitha, K Santosh, SG Rahul
    2025 International Conference on Advanced Computing Technologies (ICoACT), 1-7 , 2025
    2025
    Citations: 4