Raj Kumar.J.S.

@karunya.edu

Assistant Professor in the Department of Computer Science and Engineering
Karunya Institute of Technology and Sciences

Raj Kumar.J.S.


                  Download Compact PDF  
https://researchid.co/rajkumar.j.s.

RESEARCH INTERESTS

Device Modelling
High power VLSI Design
HEMT
Nano electronics
31

Scopus Publications

185

Scholar Citations

7

Scholar h-index

4

Scholar i10-index

Scopus Publications

  • Deep Unfolding-Based Graph Transformer Framework for Early Detection of Diabetic Retinopathy Using OCT Images
    Aaron Bose, Nirmal Varghese Babu, J. S Rajkumar
    Proceedings of the 4th International Conference on Intelligent Data Communication Technologies and Internet of Things Idciot 2026, 2026
    Diabetic Retinopathy (DR) is a serious diabetes complication and a major cause of avoidable blindness, and hence its early and proper detection is important. The current research offers a smart risk prediction framework for DR from Optical Coherence Tomography (OCT) images, diagnosing the disease in four grades: Normal, Mild, Moderate, and Severe. In order to improve the image quality, a Deep Unfolding Network (DUN) removes speckle noise with maintaining retinal structures. To balance datasets, a Latent Diffusion Model (LDM) produces high-quality synthesized OCT images at all steps. Features are extracted by a Swin Transformer with Retinal Layer Attention (RLA-Swin), retaining both global patterns and subtle anatomical details. A Concrete Autoencoder (CAe) extracts important features, and a Graph Convolutional Network (GCN) classifies them final. Results show 98.5% accuracy with excellent precision, recall, and F1-scores. The model is able to efficiently deal with noise, data scarcity, and small stage differences, presenting a solid, interpretable, and clinically useful instrument for detecting DR early.
  • Multi-Domain EEG Fusion and Hybrid Ensembles for ADHD Subtype Intelligence
    Angela Ann Mathew, Nirmal Varghese Babu, J. S Rajkumar
    Proceedings of the 4th IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation Iatmsi 2026, 2026
    Identifying Attention Deficit Hyperactivity Disorder (ADHD) accurately by electroencephalography (EEG) signals remains a challenging task mostly because of the variability among subjects and the limited amount of data. The present study presents a novel framework for EEG-based ADHD analysis encompassing preprocessing, physiologically con- strained data augmentation, comprehensive feature extraction, feature selection, and hybrid ensemble classification steps towards precise subtype differentiation. EEG data from the Healthy Brain Network is preprocessed through the PERSONA pipeline, which consists of bandpass and notch filtering, adaptive artifact rejection, spectral-spatial reconstruction, wire referencing, and Z-normalization that together maintain the essential spectralcharacteristics. PHYS-AUG generates physiologically plausibleaugmentations in the temporal, spectral, and spatial areas usingsubject-aware mixup to keep the critical spectral ratios and soit takes care of data scarcity. Feature extraction with WIDE- BANK covers various domains such as temporal, spectral, decom- position, time-frequency, nonlinear, connectivity, cross-frequencycoupling, and microstate/topographic, capturing the aspects ofamplitude, complexity, oscillatory modes, synchronization, andhierarchical neural interactions respectively. TRI-SELECT cutsdown the high-dimensional feature set (20-40 features) byapplying low-variance filtering, correlation pruning, statisticalranking, mRMR, XGBoost importance, and genetic algorithmoptimization. STACK-MIND, a two-level ensemble combiningvarious base learners with a logistic regression meta-learner,achieve an accuracy of 96.0%, thus proving to be very robust,stable, and generalizable in detecting ADHD.
  • Adaptive Temporal-Spatial Attention Framework for Early Epileptic Seizure Prediction Using Multichannel EEG Signals
    Jeffrey Chris, Nirmal Varghese Babu, J. S Rajkumar
    2026 6th International Conference on Advances in Electrical Computing Communications and Sustainable Technologies Icaect 2026, 2026
    Epileptic seizure prediction from electroencephalogram (EEG) signals plays a critical role in improving the safety and quality of life of individuals living with epilepsy. This study proposes a robust multi-stage seizure prediction framework that integrates noise reduction, data enrichment, spectral decomposition, dynamic connectivity learning, optimal feature selection, and attention-driven classification. Initially, Adaptive Neuro-Clean Filtering (ANCF) removes noise components while preserving seizure-relevant neural dynamics. To mitigate class imbalance and enhance model generalization, a Temporal-Physiological Mixup (TPMix) strategy generates physiologically consistent synthetic EEG samples. The refined signals are further processed using the Multivariate Adaptive Synchro-Spectral Transform (MASST) to extract high-quality time-frequency representations. Dynamic Graph Spectral Connectivity (DGSC) features are derived to capture evolving inter-channel relationships, and Hybrid Quantum-Optimized Fisher Selection (HQFS) chooses compact yet discriminative feature subsets. Finally, a TemporalSpatial Attention Graph Neural Network (TSAGNN) jointly models long-range temporal dependencies and spatial brainregion interactions to classify EEG into pre-ictal, ictal, post-ictal, and normal states. Experimental evaluation on the CHB-MIT dataset achieved an overall accuracy of 95.9%, demonstrating the model's strong predictive capability and clinical relevance.
  • Few-Shot Urgency Classification of Crisis Tweets via Multi-View Feature Learning
    Renimol S, Nirmal Varghese Babu P, J. S Rajkumar
    Proceedings of the 4th IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation Iatmsi 2026, 2026
    The detection of crises through social media that is effective and timely is imperative for disaster response and humanitarian aid. The crisis tweet classification scheme proposed in this paper is a new urgency-aware crisis tweet classifier that combines multi-domain feature representations with few-shot learning to overcome the challenges of data scarcity and noisy user content. The authors collected the crisis tweets from Twitter and enriched them with CrisisLex, and CrisisNLP datasets annotated by their respective urgency levels (Critical, High, Moderate, Low) and types of help required which included temporal and geospatial metadata. Preprocessing takes advantage of Urgency-Preserving Contextual Encoding (UPCE) that successfully captures emojis, punctuation, capitalization, and temporal cues which express distress. Crisis-Adaptive MixUp (CAMU) creates new tweets to boost generalization of the underrepresented classes. Multi-Domain Urgency Feature Extraction Framework (MD-UFEF) is used in feature extraction whereby lexical, syntactic, semantic, and contextual signals are first encoded then followed by Urgency-Adaptive Feature Selection (UAFS) which retains the most salient features per class. Classification employs Urgency-Specific Few-Shot Learning (US-FSL), a combination of metric learning and attention-based weighting enabling accurate tweet categorization even with scant labeled data. The experimental results show that the UPCE+CAMU+US-FSL scheme developed is better than the baselines, with a 93.5% accuracy and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$91.6 \% \mathrm{F} 1$</tex>-score for urgency classification and a 91.0% accuracy for help-type classification. The few-shot experiments demonstrate that high performance can be achieved with only 20 support samples per class. The framework is so efficient in computation and at the same time reliable in prediction that it is well suited for real-time crisis detection and management.
  • Nanosheet transistors: materials, devices, systems and applications
    A. Angelin Delighta, J. S. Raj Kumar, I. V. Binola K Jebalin, D. Nirmal
    Journal of Materials Science, 2025
  • PREDICTIVE MODELS FOR EARLY DETECTION OF PARKINSON’S DISEASE: A MACHINE LEARNING APPROACH
    S. Jeyantha Jafna Juliet, D. Jasmine David, J. S. Raj Kumar, Angelin Jeba P., R. Golden Nancy, M. Selvarathi, T. Jemima Jebaseeli
    Journal of Mechanics of Continua and Mathematical Sciences, 2025
    Motor symptoms, such as tremors, bradykinesia, stiffness, and posture issues, are produced by the loss of dopamine-producing neurons in the spinal column portion of the brain, which is characteristic of Parkinson's disease (PD). To properly control and treat PD, the condition must be identified as soon as possible. Machine learning techniques, which use data-driven methodologies, provide intriguing possibilities for reaching this aim. These methods involve the analysis of various types of data, including clinical assessments, imaging scans, and genetic markers, to develop accurate predictive models. Even in the initial stages of the conditions, machine learning techniques can discriminate between patients who have and do not have PD by identifying minor variations and traits from such multivariate data. These models support early diagnosis and enable personalized treatment strategies tailored to the specific needs of patients. Additionally, integrating wearable sensors and mobile health technologies further enhances the feasibility of continuous monitoring and early detection, providing patients and healthcare practitioners with the tools they need to manage PD proactively. To identify diseases, one can access vast databases of medical information. To diagnose PD, the proposed method uses two different data sets. Algorithms for machine learning are also capable of helping in producing specific details from such data. The proposed research applies a few Machine Learning ways to anticipate Parkinson's disease by human guidance, with the dataset acting as the source of the process understanding. By applying the hyperparameter optimization process, the accuracy is estimated. When used to diagnose Parkinson's disease (PD), the proposed methods produce accuracy rates of 98.9% for Naive Bayes and 97.3% for Logistic Regression.
  • BERT-Based Agricultural Crop Prediction System Using Soil and Weather Parameters with Interactive Streamlit Deployment
    Naren L, Raj Kumar. J. S
    4th International Conference on Applied Artificial Intelligence and Computing Icaaic 2025, 2025
    Accurate crop selection plays a crucial role in improving agricultural productivity and resource utilization, especially under varying soil and climatic conditions. Traditional crop recommendation systems often rely on statistical or shallow learning models that fail to capture contextual relationships among agronomic parameters. This work proposes a BERT-Based Agricultural Crop Prediction System that converts numerical soil and weather parameters—Nitrogen, Phosphorus, Potassium (NPK), soil pH, temperature, humidity, rainfall, and soil type—into structured natural-language descriptors to leverage contextual embeddings from Bidirectional Encoder Representations from Transformers (BERT). The extracted embeddings are then passed to a custom classification head to recommend the most suitable crop among 22 crop types. The system is deployed using Streamlit, enabling interactive input, ranked top-3 recommendations, and explainability through SHAP visualizations. Experimental evaluation demonstrates that the proposed model achieves 92% accuracy, significantly outperforming baseline models including Random Forest, SVM, and LSTM. These results confirm the effectiveness of contextual language models for precision agriculture and decision support in field environments.
  • Enhanced Multi-Class Cardiac Sound Diagnosis using Advanced PCG Signal Analysis and Deep Learning Integration
    16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
  • MediScan: An AI-Powered Multi-Disease Diagnostic Support System Using Medical Imaging
    Abel Mathew Thomas, Rajkumar J S, Nirmal Varghese Babu
    4th International Conference on Applied Artificial Intelligence and Computing Icaaic 2025, 2025
    The rapid advancement of artificial intelligence (AI) in healthcare offers substantial potential for augmenting clinical decision-making and reducing diagnostic errors. Medical imaging, in particular, generates vast volumes of data that require expert interpretation, often leading to diagnostic delays due to a shortage of qualified radiologists and pathologists. To address these issues, this paper introduces MediScan, an AI-driven diagnostic framework that leverages deep learning models like Convolutional Neural Networks (CNNs) and U-Net to assist in multi-disease classification and segmentation of medical images. Evaluated on standard datasets including ChestX-ray14, ISIC 2018, and BraTS, the system demonstrates strong performance, achieving a 92.3 percent classification accuracy for thoracic conditions and a 0.87 Dice Similarity Coefficient for brain tumor segmentation. A key feature of the framework is the integration of explainable AI through Gradient-weighted Class Activation Mapping (Grad-CAM), which generates visual heatmaps to improve model transparency and foster clinician trust. By delivering fast, precise, and interpretable results, MediScan demonstrates the potential for a scalable and accessible diagnostic tool that can alleviate pressure on healthcare systems, promote early disease intervention, and improve patient outcomes.
  • Explainable Digital Twin Framework for Aircraft Engine Maintenance
    Chris Joseph George, J.S Rajkumar, Nirmal Varghese Babu
    International Conference on Nexgen Networks and Cybernetics Ic2nc 2025 Proceedings, 2025
    Growing dependence of modern aviation on aircraft engines underscores persistent challenges in balancing safety, reliability, and operational costs. Conventional maintenance practices, whether preventive or reactive, often prove inadequate, leading to premature component replacement, unscheduled downtime, and limited diagnostic transparency. To address these gaps, this study proposes an AI-driven digital twin framework that integrates predictive modeling, explainability, immersive visualization, and secure data management for aircraft engine maintenance. A Python-based simulator generates realistic IoT sensor streams replicating operational stresses, gradual degradation, and subtle anomalies, which are then analyzed using complementary machine learning models: an Isolation Forest for anomaly detection and a Random Forest Regressor for Remaining Useful Life (RUL) estimation. SHAP-based interpretability ensures that predictions remain transparent and traceable, a critical requirement for aviation applications. The framework further incorporates Unity 3D for interactive engine visualization and a Flutter mobile application for field-level accessibility, while blockchain-backed IoT logging and federated learning strengthen data integrity and collaborative scalability. Validation on synthetic datasets and the NASA C-MAPSS benchmark confirms improved robustness, with the Random Forest reducing RUL prediction error by over $30 \%$ and the Isolation Forest achieving an F1-score of 0.89 for anomaly detection. These results specify the framework’s potential as a transparent, scalable, and industry-ready solution for predictive maintenance in aviation, with adaptability to other safety-critical domains such as manufacturing and energy.
  • Semantic Kernel for Software Engineering: A Multi-Agent Framework for Autonomous Development Lifecycles
    Adithya B V, Raj Kumar.J.S., Nirmal Varghese Babu
    Proceedings of the 9th International Conference on Electronics Communication and Aerospace Technology Iceca 2025, 2025
  • Multi-Modal AI Personal Health Risk Prediction and Early Alert System
    Adhal Biju Abraham, Raj Kumar J S, Nirmal Varghese Babu, R Golden Nancy
    4th International Conference on Automation Computing and Renewable Systems Icacrs 2025 Proceedings, 2025
  • HematoScribe AI: A Transparent & Explainable System for Bone Marrow Cell Analysis
    Shebin Sam, Raj Kumar J S, Nirmal Varghese Babu, R Golden Nancy
    Proceedings of 6th International Conference on Iot Based Control Networks and Intelligent Systems Icicnis 2025, 2025
  • Forest Wildfire Detection from Satellite Image Using Deep Learning
    D Elizaroshan, J.S. Raj Kumar
    2024 International Conference on Communication Computing and Internet of Things Ic3iot 2024 Proceedings, 2024
  • Learning Disability Detection and Classification Analysis Between Two Classification Algorithms
    Darwin Roach D, Pearly Princess. J, V. Vijula, J. Raj Kumar, Anit Mary Shibu
    Proceedings 2024 International Conference on Expert Clouds and Applications Icoeca 2024, 2024
  • Monitoring Industrial Protection Gear Using Intelligent System
    Yakubraj M, Rajkumar J S, Sophas Samuel S, Matthew Palmer G, Ancy Jenifer J
    Proceedings of the 2nd IEEE International Conference on Networking and Communications 2024 Icnwc 2024, 2024
  • Investigations of ScAlN/AlGaN Split Barrier Inspired High Electron Mobility Transistor
    J. S. Raj Kumar, D. Nirmal, H. Victor Du John, K. Binola Jebalin
    Aip Conference Proceedings, 2023
  • A comprehensive review of AlGaN/GaN High electron mobility transistors: Architectures and field plate techniques for high power/ high frequency applications
    J.S. Raj Kumar, H. Victor Du John, Binola K Jebalin I.V, J. Ajayan, Angelin Delighta A, D. Nirmal
    Microelectronics Journal, 2023
  • Investigation on Fe-Doped AlGaN/GaN HEMT at 148 GHz Using E-FPL Technology for High-Frequency Communication Systems
    S. Angen Franklin, Binola K Jebalin I. V, Subhash Chander, Raj Kumar, J. Ajayan, D. Nirmal
    Ecs Journal of Solid State Science and Technology, 2023
  • Simulation Study of Stacked Oxide Layer NCFET for RF Applications
    Navya V S, H. Victor Du John, J.S. Raj Kumar, Angen Franklin, D. Nirmal
    Proceedings of the 8th International Conference on Communication and Electronics Systems Icces 2023, 2023
  • Investigation on LG = 50 nm Tapered T-Gated AlGaN/GaN HEMT on Silicon Wafer with a fT/fmax of 264/312 GHz for beyond 5G (B5G) Applications
    J. S. Raj Kumar, D. Nirmal, J. Ajayan, Shubham Tayal
    Silicon, 2022
  • Intensive Study of Field-Plated AlGaN/GaN HEMT on Silicon Substrate for High Power RF Applications
    J. S. Raj Kumar, D. Nirmal, Manish Kumar Hooda, Surinder Singh, J. Ajayan, L. Arivazhagan
    Silicon, 2022
  • Design and Simulation of a T-gated AlGaN/GaN HEMT with Added Mini Field Plate
    J.S. Raj Kumar, D. Nirmal, H. Victor Du John, S. Angen Franklin, G. Samuel
    3rd International Conference on Electronics and Sustainable Communication Systems Icesc 2022 Proceedings, 2022
  • Variable thermal resistance model of GaN-on-SiC with substrate scalability
    L. Arivazhagan, D. Nirmal, Subhash Chander, J. Ajayan, D. Godfrey, J. S. Rajkumar, S. Bhagya Lakshmi
    Journal of Computational Electronics, 2020
  • AlGaN/GaN HEMT for highly sensitive detection of Bio-molecules using transconductance method
    P Pavan Kumar Reddy, S Bhagya Lakshmi, L Arivazhgan, J S Raj Kumar, D Nirmal
    Iop Conference Series Materials Science and Engineering, 2020
  • Self-Heating Analysis of GaN-HEMT for Various Ambient Temperature and Substrate Thickness
    Arivazhagan L, Anwar Hasan Mohammed Jarndal, Subhash Chander, Godfrey D, Raj Kumar J S, S Bhagyalakshmi, Pavan Kumar Reddy, D. Nirmal
    Icdcs 2020 2020 5th International Conference on Devices Circuits and Systems, 2020
  • Modeling of self-heating for AlGaN/GaN HEMT with thermal conductivity degradation effect
    L. Arivazhagan, D. Nirmal, J. Ajayan, D. Godfrey, J. S. Rakkumar, S. Bhagya Lakshmi
    Aip Conference Proceedings, 2019
  • Enhancement of drain current in AlGaN/GaN HEMT using AlN passivation
    L. Arivazhagan, D. Nirmal, J. Ajayan, D. Godfrey, J. S. Rajkumar, S. Bhagya Lakshmi
    Aip Conference Proceedings, 2019
  • Improved RF and DC performance in AlGaN/GaN HEMT by P-type doping in GaN buffer for millimetre-wave applications
    L. Arivazhagan, D. Nirmal, D. Godfrey, J. Ajayan, P. Prajoon, A.S. Augustine Fletcher, A. Amir Anton Jone, J.S. Raj Kumar
    AEU International Journal of Electronics and Communications, 2019
  • DC and RF Analysis of AlGaN/GaN MOS-HEMT for High Power Application
    J. S. Raj Kumar, D. Nirmal, L. Arivazhagan, Pratik P Pandit
    2nd International Conference on Signal Processing and Communication Icspc 2019 Proceedings, 2019
  • DC Performance analysis of AlGaN/GaN HEMT for future High power applications
    Pratik P. Pandit, L. Arivazhagan, P. Prajoon, J.S. Rajkumar, J. Ajayan, D. Nirmal
    Proceedings of the 4th International Conference on Devices Circuits and Systems Icdcs 2018, 2019

RECENT SCHOLAR PUBLICATIONS

  • Few-Shot Urgency Classification of Crisis Tweets via Multi-View Feature Learning
    S Renimol, JS Rajkumar
    2026 IEEE International Conference on Interdisciplinary Approaches in … , 2026
    2026
  • Multi-Domain EEG Fusion and Hybrid Ensembles for ADHD Subtype Intelligence
    AA Mathew, NV Babu, JS Rajkumar
    2026 IEEE International Conference on Interdisciplinary Approaches in … , 2026
    2026
  • Deep Unfolding-Based Graph Transformer Framework for Early Detection of Diabetic Retinopathy Using OCT Images
    A Bose, NV Babu, JS Rajkumar
    2026 4th International Conference on Intelligent Data Communication … , 2026
    2026
  • Adaptive Temporal–Spatial Attention Framework for Early Epileptic Seizure Prediction Using Multichannel EEG Signals
    J Chris, NV Babu, JS Rajkumar
    2026 Sixth International Conference on Advances in Electrical, Computing … , 2026
    2026
  • MediScan: An AI-Powered Multi-Disease Diagnostic Support System Using Medical Imaging
    AM Thomas, JS Rajkumar, NV Babu
    2025 4th International Conference on Applied Artificial Intelligence and … , 2025
    2025
  • HematoScribe AI: A Transparent & Explainable System for Bone Marrow Cell Analysis
    S Sam, RK JS, NV Babu, RG Nancy
    2025 6th International Conference on IoT Based Control Networks and … , 2025
    2025
  • Multi-Modal AI Personal Health Risk Prediction and Early Alert System
    AB Abraham, RK JS, NV Babu, RG Nancy
    2025 4th International Conference on Automation, Computing and Renewable … , 2025
    2025
  • Explainable Digital Twin Framework for Aircraft Engine Maintenance
    CJ George, JS Rajkumar, NV Babu
    2025 International Conference on NexGen Networks and Cybernetics (IC2NC … , 2025
    2025
  • Semantic Kernel for Software Engineering: A Multi-Agent Framework for Autonomous Development Lifecycles
    BV Adithya, RK JS, NV Babu
    2025 9th International Conference on Electronics, Communication and … , 2025
    2025
  • Nanosheet transistors: materials, devices, systems and applications
    A Angelin Delighta, JS Raj Kumar, IV Binola K Jebalin, D Nirmal
    Journal of Materials Science 60 (16), 6769-6806 , 2025
    2025
    Citations: 3
  • Forest wildfire detection from satellite image using deep learning
    D Elizaroshan, JSR Kumar
    2024 International Conference on Communication, Computing and Internet of … , 2024
    2024
    Citations: 2
  • Monitoring industrial protection gear using intelligent system
    M Yakubraj, JS Rajkumar, S Sophas Samuel, G Matthew Palmer, ...
    2024 2nd International Conference on Networking and Communications (ICNWC), 1-6 , 2024
    2024
    Citations: 5
  • Investigations of ScAlN/AlGaN split barrier inspired high electron mobility transistor
    JSR Kumar, D Nirmal, HVD John, KB Jebalin
    AIP Conference Proceedings 2901 (1), 080018 , 2023
    2023
    Citations: 2
  • A comprehensive review of AlGaN/GaN High electron mobility transistors: Architectures and field plate techniques for high power/high frequency applications
    JSR Kumar, HV Du John, BKJ IV, J Ajayan, D Nirmal
    Microelectronics Journal 140, 105951 , 2023
    2023
    Citations: 43
  • Anesthetic Management in a 4-Year-Old Child Undergoing Removal of a Gemstone Tracheobronchial Foreign Body
    R Kumar, TK Jayakumar, A Sinha, S Kumar
    Journal of Indian Association of Pediatric Surgeons 28 (5), 448-449 , 2023
    2023
  • Simulation Study of Stacked Oxide Layer NCFET for RF Applications
    VS Navya, HV Du John, JSR Kumar, A Franklin, D Nirmal
    2023 8th International Conference on Communication and Electronics Systems … , 2023
    2023
  • Investigation on Fe-Doped AlGaN/GaN HEMT at 148 GHz Using E-FPL Technology for High-Frequency Communication Systems
    SA Franklin, S Chander, JSR Kumar, J Ajayan, D Nirmal
    ECS Journal of Solid State Science and Technology 12 (3), 035006 , 2023
    2023
    Citations: 4
  • Investigation on L G = 50 nm Tapered T-Gated AlGaN/GaN HEMT on Silicon Wafer with a f T /f max of 264/312 GHz for beyond 5G (B5G) Applications
    JSR Kumar, D Nirmal, J Ajayan, S Tayal
    Silicon 14 (17), 11315-11322 , 2022
    2022
    Citations: 10
  • Design and simulation of a T-gated AlGaN/GaN HEMT with added mini field plate
    JSR Kumar, D Nirmal, HV Du John, SA Franklin, G Samuel
    2022 3rd International Conference on Electronics and Sustainable … , 2022
    2022
    Citations: 3
  • Intensive study of field-plated AlGaN/GaN HEMT on silicon substrate for high power RF applications
    JSR Kumar, D Nirmal, MK Hooda, S Singh, J Ajayan, L Arivazhagan
    Silicon 14 (8), 4277-4282 , 2022
    2022
    Citations: 23

MOST CITED SCHOLAR PUBLICATIONS

  • Improved RF and DC performance in AlGaN/GaN HEMT by P-type doping in GaN buffer for millimetre-wave applications
    L Arivazhagan, D Nirmal, D Godfrey, J Ajayan, P Prajoon, ASA Fletcher, ...
    AEU-International Journal of Electronics and Communications 108, 189-194 , 2019
    2019
    Citations: 55
  • A comprehensive review of AlGaN/GaN High electron mobility transistors: Architectures and field plate techniques for high power/high frequency applications
    JSR Kumar, HV Du John, BKJ IV, J Ajayan, D Nirmal
    Microelectronics Journal 140, 105951 , 2023
    2023
    Citations: 43
  • Intensive study of field-plated AlGaN/GaN HEMT on silicon substrate for high power RF applications
    JSR Kumar, D Nirmal, MK Hooda, S Singh, J Ajayan, L Arivazhagan
    Silicon 14 (8), 4277-4282 , 2022
    2022
    Citations: 23
  • Investigation on L G = 50 nm Tapered T-Gated AlGaN/GaN HEMT on Silicon Wafer with a f T /f max of 264/312 GHz for beyond 5G (B5G) Applications
    JSR Kumar, D Nirmal, J Ajayan, S Tayal
    Silicon 14 (17), 11315-11322 , 2022
    2022
    Citations: 10
  • AlGaN/GaN HEMT for highly sensitive detection of Bio-molecules using transconductance method
    PP Kumar Reddy, SB Lakshmi, L Arivazhgan, JS Raj Kumar, D Nirmal
    IOP conference series: materials science and engineering 872 (1), 012048 , 2020
    2020
    Citations: 8
  • Modeling of self-heating for AlGaN/GaN HEMT with thermal conductivity degradation effect
    L Arivazhagan, D Nirmal, J Ajayan, D Godfrey, JS Rakkumar, SB Lakshmi
    AIP Conference Proceedings 2201 (1), 020010 , 2019
    2019
    Citations: 7
  • DC Performance analysis of AlGaN/GaN HEMT for future High power applications
    PP Pandit, L Arivazhagan, P Prajoon, JS Rajkumar, J Ajayan, D Nirmal
    2018 4th International Conference on Devices, Circuits and Systems (ICDCS … , 2018
    2018
    Citations: 7
  • Monitoring industrial protection gear using intelligent system
    M Yakubraj, JS Rajkumar, S Sophas Samuel, G Matthew Palmer, ...
    2024 2nd International Conference on Networking and Communications (ICNWC), 1-6 , 2024
    2024
    Citations: 5
  • Variable thermal resistance model of GaN-on-SiC with substrate scalability
    L Arivazhagan, D Nirmal, S Chander, J Ajayan, D Godfrey, JS Rajkumar, ...
    Journal of Computational Electronics 19 (4), 1546-1554 , 2020
    2020
    Citations: 5
  • Investigation on Fe-Doped AlGaN/GaN HEMT at 148 GHz Using E-FPL Technology for High-Frequency Communication Systems
    SA Franklin, S Chander, JSR Kumar, J Ajayan, D Nirmal
    ECS Journal of Solid State Science and Technology 12 (3), 035006 , 2023
    2023
    Citations: 4
  • Self-heating analysis of GaN-HEMT for various ambient temperature and substrate thickness
    L Arivazhagan, AHM Jarndal, S Chander, D Godfrey, RK JS, ...
    2020 5th International Conference on Devices, Circuits and Systems (ICDCS … , 2020
    2020
    Citations: 4
  • Nanosheet transistors: materials, devices, systems and applications
    A Angelin Delighta, JS Raj Kumar, IV Binola K Jebalin, D Nirmal
    Journal of Materials Science 60 (16), 6769-6806 , 2025
    2025
    Citations: 3
  • Design and simulation of a T-gated AlGaN/GaN HEMT with added mini field plate
    JSR Kumar, D Nirmal, HV Du John, SA Franklin, G Samuel
    2022 3rd International Conference on Electronics and Sustainable … , 2022
    2022
    Citations: 3
  • Forest wildfire detection from satellite image using deep learning
    D Elizaroshan, JSR Kumar
    2024 International Conference on Communication, Computing and Internet of … , 2024
    2024
    Citations: 2
  • Investigations of ScAlN/AlGaN split barrier inspired high electron mobility transistor
    JSR Kumar, D Nirmal, HVD John, KB Jebalin
    AIP Conference Proceedings 2901 (1), 080018 , 2023
    2023
    Citations: 2
  • Enhancement of drain current in AlGaN/GaN HEMT using AlN passivation
    L Arivazhagan, D Nirmal, J Ajayan, D Godfrey, JS Rajkumar, SB Lakshmi
    AIP Conference Proceedings 2201 (1), 020009 , 2019
    2019
    Citations: 2
  • DC and RF Analysis of AlGaN/GaN MOS-HEMT for High Power Application
    JSR Kumar, D Nirmal, L Arivazhagan, PP Pandit
    2019 2nd International Conference on Signal Processing and Communication … , 2019
    2019
    Citations: 2
  • Few-Shot Urgency Classification of Crisis Tweets via Multi-View Feature Learning
    S Renimol, JS Rajkumar
    2026 IEEE International Conference on Interdisciplinary Approaches in … , 2026
    2026
  • Multi-Domain EEG Fusion and Hybrid Ensembles for ADHD Subtype Intelligence
    AA Mathew, NV Babu, JS Rajkumar
    2026 IEEE International Conference on Interdisciplinary Approaches in … , 2026
    2026
  • Deep Unfolding-Based Graph Transformer Framework for Early Detection of Diabetic Retinopathy Using OCT Images
    A Bose, NV Babu, JS Rajkumar
    2026 4th International Conference on Intelligent Data Communication … , 2026
    2026