Dr. Padmashree G

@ajiet.edu.in

Associate Professor, Department of Computer Science and Engineering
A J Institute of Engineering and Technology

Dr. Padmashree G


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

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering, Computer Vision and Pattern Recognition, Artificial Intelligence, Computer Science Applications
17

Scopus Publications

63

Scholar Citations

3

Scholar h-index

1

Scholar i10-index

Scopus Publications

  • Foot Ulcer Classification: Demonstrating the Superiority of Hybrid Ensembles with Explainable AI
    Iaeng International Journal of Computer Science, 2026
  • Exploring and Contrasting Machine Learning Classifiers for Citrus Plant Disease Classification
    B. Mahima Shenoy, Sakshi S. Poojary, G. Padmashree
    Communications in Computer and Information Science, 2026
  • Unleashing Machine Learning for Accurate Weather Forecasts
    S. Amisha, Anusha, G. Padmashree
    Communications in Computer and Information Science, 2026
  • Dynamically Enhanced LSTM Framework for Diabetes Prediction With SMOTE-Based Balancing and Grid-Optimized Hyperparameters
    G. Padmashree, Meghana Nigam, K. R. Akshatha, G. Murali
    IEEE Access, 2026
    Diabetes mellitus is a chronic metabolic disorder that requires accurate and timely prediction for early diagnosis and intervention. Traditional machine learning methods often struggle to capture nonlinear interactions and temporal dependencies in clinical datasets. To address this, we propose a hybrid framework that integrates Dynamic Mode Decomposition (DMD) for feature augmentation with a bi-layer Long Short-Term Memory (LSTM) network for robust classification. DMD extracts latent dynamic patterns from static clinical attributes, transforming them into pseudo-sequential representations that the LSTM models use to capture long-term dependencies. The framework incorporates SMOTE-based class balancing and grid-optimized hyperparameters to improve robustness and generalization. Evaluation on the PIMA Indian Diabetes dataset shows that the proposed LSTM+DMD model outperforms standalone architectures, achieving 98.92% accuracy, 99.33% precision, 97.37% recall, and an F1-score of 98.34%. Ablation studies confirm the complementary roles of DMD and LSTM, while comparisons with state-of-the-art methods highlight the model’s novelty and effectiveness. These results demonstrate that the proposed framework provides a highly accurate and interpretable solution for diabetes prediction, with promising applicability in clinical decision support systems.
  • StealthFace:Transfer Learning-Based Ensemble Model for Disguised Face Recognition using Skin-Segmented Images
    Iaeng International Journal of Computer Science, 2025
  • Comparative Analysis of LSB, Phase Coding, and Spread Spectrum Techniques for Audio Steganography
    Padmashree G, Arun Krishna
    Proceedings of 2025 International Conference on Intelligent Systems and Pioneering Innovations in Robotics and Electric Mobility Transforming Mobility and Automation Through Intelligent Engineering Inspire 2025, 2025
    In the digital era, ensuring the secure transmission of confidential information is critically important. Audio steganography has emerged as an effective approach for concealing data within audio signals while preserving perceptual quality. This paper presents a comprehensive comparative study of three audio steganographic techniques: Least Significant Bit (LSB) modification, Phase Coding, and Spread Spectrum. Each method was experimentally implemented to embed text files of varying sizes (20 KB, 40 KB, 60 KB, and 80 KB) into digital audio signals using three different music files (rock, hip-hop, and EDM). Experimental evaluations were conducted to measure objective metrics such as Peak Signal-to-Noise Ratio (PSNR), Signal-to-Noise Ratio (SNR), and Bit Error Rate (BER). Results demonstrate that the LSB method, tested at different bit planes (5<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup>, 6<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup>, and 7<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> bits), achieves high embedding capacity and near-perfect extraction accuracy but is more vulnerable to signal processing distortions. Phase coding achieves a balance between perceptual transparency and capacity but shows moderate robustness under distortion. Spread spectrum, although offering lower embedding capacity, exhibits the highest robustness and signal fidelity, with superior PSNR and SNR values and acceptable error rates under noisy conditions. This comparative analysis provides practical insights into the trade-offs among capacity, imperceptibility, and robustness, guiding the selection of suitable audio steganography methods for diverse security and multimedia applications.
  • Performance Comparison of Machine Learning Techniques for Recognizing Disguised Faces
    Padmashree G, Ranjitha, Madhuri Herle
    Proceedings of 2025 International Conference on Intelligent Systems and Pioneering Innovations in Robotics and Electric Mobility Transforming Mobility and Automation Through Intelligent Engineering Inspire 2025, 2025
    Disguised face recognition poses significant challenges due to identity-obscuring factors such as masks, spectacles, cosmetics, and other occlusions. This study explores the effectiveness of machine learning approaches in addressing these challenges by evaluating multiple classifiers and systematically optimizing their performance through grid search. Individual models—including Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), and K-Nearest Neighbors (KNN)—were trained and assessed using metrics such as AUC-ROC, F1-score, accuracy, precision, and recall, with XGBoost serving as a benchmark. To enhance recognition accuracy, ensemble learning strategies were employed, examining all possible combinations of two-, three-, and four-model ensembles using both majority voting and weighted average techniques. The ensemble models consistently outperformed individual classifiers, with the KNN+RF+SVM ensemble achieving the highest accuracy and robustness. These results underscore the importance of feature fusion and model integration in improving disguised face recognition. By mitigating the effects of facial concealments, this work contributes to the development of more secure and reliable biometric authentication systems.
  • FutureGlycemics: A Comparative Study of Diverse Machine Learning Models for Diabetes Prognosis
    K. Vaishnavi Pai, Smitha, G. Padmashree
    Lecture Notes in Networks and Systems, 2025
  • Exploring Ensemble Learning Strategies for Robust Medical Deepfake Detection
    Padmashree G, Sinchana G Bhat, Vishweshwar Shinde
    2025 Control Instrumentation System Conference Ciscon 2025, 2025
  • Seismic and Geospatial Feature Integration for Earthquake Magnitude Prediction Using Machine Learning
    Padmashree G, Aman S Dsouza, P Adarsh
    2025 Control Instrumentation System Conference Ciscon 2025, 2025
  • Disguised face liveness detection: an ensemble approach using deep features
    Padmashree G., Karunakar A. K.
    Cogent Engineering, 2024
  • Skin Segmentation-Based Disguised Face Recognition Using Deep Learning
    G. Padmashree, Karunakar A. Kotegar
    IEEE Access, 2024
  • A Study on AI Applications for Orthodontics and Malocclusion Detection Approaches
    Ankitha A Nayak, Venugopala P S, Ashwini B, Padmashree G
    8th IEEE International Conference on Distributed Computing VLSI Electrical Circuits and Robotics Discover 2024 Proceedings, 2024
  • Exemplar-based facial attribute manipulation: a review
    G. Padmashree, A.K. Karunakar
    International Journal of Biometrics, 2023
  • Improved LBP Face Recognition Using Image Processing Techniques
    G. Padmashree, A. K. Karunakar
    Lecture Notes in Networks and Systems, 2023
  • Ensemble of Machine Learning Classifiers for Detecting Deepfake Videos using Deep Feature
    Iaeng International Journal of Computer Science, 2023
  • Disguise Face Classification Using EfficientNet Deep Learning
    G. Padmashree, Shruti G. Wagle, A. K. Karunakar
    Smart Innovation Systems and Technologies, 2023

RECENT SCHOLAR PUBLICATIONS

  • Dynamically Enhanced LSTM Framework for Diabetes Prediction with SMOTE-based Balancing and Grid-optimized Hyperparameters
    G Padmashree, M Nigam, KR Akshatha, G Murali
    IEEE Access , 2026
    2026
  • Seismic and Geospatial Feature Integration for Earthquake Magnitude Prediction Using Machine Learning
    G Padmashree, AS Dsouza, P Adarsh
    2025 Control Instrumentation System Conference (CISCON), 1-8 , 2026
    2026
  • Foot Ulcer Classification: Demonstrating the Superiority of Hybrid Ensembles with Explainable AI.
    P G., MG Rao
    IAENG International Journal of Applied Mathematics 56 (1) , 2026
    2026
  • Exploring Ensemble Learning Strategies for Robust Medical Deepfake Detection
    G Padmashree, SG Bhat, V Shinde
    2025 Control Instrumentation System Conference (CISCON), 1-9 , 2026
    2026
  • Local–Global Feature Fusion using CNN and Vision Transformer with Ensemble Post-Classification for Diabetic Retinopathy Diagnosis
    MGR Padmashree G.
    International Journal of Computer Applications 187 (71), 15-24 , 2026
    2026
  • Performance Comparison of Machine Learning Techniques for Recognizing Disguised Faces
    P G, Ranjitha, M Herle
    2025 International Conference on Intelligent Systems and Pioneering … , 2025
    2025
  • Comparative Analysis of LSB, Phase Coding, and Spread Spectrum Techniques for Audio Steganography
    G Padmashree, A Krishna
    2025 International Conference on Intelligent Systems and Pioneering … , 2025
    2025
  • FutureGlycemics: A Comparative Study of Diverse Machine Learning Models for Diabetes Prognosis.
    G Vaishnavi Pai, K., Smitha, Padmashree
    Advances in Health Informatics, Intelligent Systems, and Networking … , 2025
    2025
  • Unleashing Machine Learning for Accurate Weather Forecasts
    GP Amisha, S., Anusha
    Applications of Artificial Intelligence and Data Science: First Global … , 2025
    2025
  • Exploring and Contrasting Machine Learning Classifiers for Citrus Plant
    BM Shenoy, SS Poojary, G Padmashree
    Applications of Artificial Intelligence and Data Science: First Global … , 2025
    2025
  • StealthFace: Transfer Learning-Based Ensemble Model for Disguised Face Recognition using Skin-Segmented Images.
    G Padmashree, KA Kotegar
    IAENG International Journal of Computer Science 52 (4) , 2025
    2025
  • A Study on AI Applications for Orthodontics and Malocclusion Detection Approaches
    AA Nayak, PS Venugopala, B Ashwini, G Padmashree
    2024 IEEE International Conference on Distributed Computing, VLSI … , 2024
    2024
    Citations: 2
  • Skin segmentation-based disguised face recognition using deep learning
    G Padmashree, KA Kotegar
    IEEE Access 12, 51056-51072 , 2024
    2024
    Citations: 5
  • Disguised face liveness detection: an ensemble approach using deep features
    G Padmashree, KA Kotegar
    Cogent Engineering 11 (1) , 2024
    2024
    Citations: 2
  • Exemplar-based facial attribute manipulation: a review
    G Padmashree, AK Karunakar
    International Journal of Biometrics 16 (1), 68-111 , 2024
    2024
    Citations: 1
  • Ensemble of Machine Learning Classifiers for Detecting Deepfake Videos using Deep Feature.
    K AK
    IAENG International Journal of Computer Science 50 (4) , 2023
    2023
    Citations: 8
  • Disguise face classification using efficientnet deep learning
    G Padmashree, SG Wagle, AK Karunakar
    Human-Centric Smart Computing: Proceedings of ICHCSC 2022, 305-314 , 2022
    2022
    Citations: 3
  • Improved LBP Face Recognition Using Image Processing Techniques
    G Padmashree, AK Karunakar
    Amit Joshi· Mufti Mahmud·, 535 , 2022
    2022
    Citations: 2
  • “A Framework for Digitized Voting Mechanism in Centralized RMI Server (DVM)”
    PG Rudresh H M
    International Conference on Information Science and Technology … , 2015
    2015
  • Watermarking using Transformation domain Technique using Visual Cryptography
    Padmashree G, Jyothi V. Prasad, Venugopala P.S
    International Journal of Scientific and Engineering Research, 6 (3) , 2015
    2015

MOST CITED SCHOLAR PUBLICATIONS

  • “Audio Stegnography and Cryptography: Using LSB algorithm at 4th and 5th LSB layers”
    VPS Padmashree G
    International Conference on Evolutionary Trends in Information Technology … , 2012
    2012
    Citations: 38
  • Ensemble of Machine Learning Classifiers for Detecting Deepfake Videos using Deep Feature.
    K AK
    IAENG International Journal of Computer Science 50 (4) , 2023
    2023
    Citations: 8
  • Skin segmentation-based disguised face recognition using deep learning
    G Padmashree, KA Kotegar
    IEEE Access 12, 51056-51072 , 2024
    2024
    Citations: 5
  • Disguise face classification using efficientnet deep learning
    G Padmashree, SG Wagle, AK Karunakar
    Human-Centric Smart Computing: Proceedings of ICHCSC 2022, 305-314 , 2022
    2022
    Citations: 3
  • A Study on AI Applications for Orthodontics and Malocclusion Detection Approaches
    AA Nayak, PS Venugopala, B Ashwini, G Padmashree
    2024 IEEE International Conference on Distributed Computing, VLSI … , 2024
    2024
    Citations: 2
  • Disguised face liveness detection: an ensemble approach using deep features
    G Padmashree, KA Kotegar
    Cogent Engineering 11 (1) , 2024
    2024
    Citations: 2
  • Improved LBP Face Recognition Using Image Processing Techniques
    G Padmashree, AK Karunakar
    Amit Joshi· Mufti Mahmud·, 535 , 2022
    2022
    Citations: 2
  • Design of A DCT based watermarking approach using RGB color channels for an android device
    VM Pinto, G Padmashree, PS Venugopala, H Sarojadevi, NC Niranjan
    Proceedings of Second International Conference on ERCICA-14 , 2014
    2014
    Citations: 2
  • Exemplar-based facial attribute manipulation: a review
    G Padmashree, AK Karunakar
    International Journal of Biometrics 16 (1), 68-111 , 2024
    2024
    Citations: 1
  • Dynamically Enhanced LSTM Framework for Diabetes Prediction with SMOTE-based Balancing and Grid-optimized Hyperparameters
    G Padmashree, M Nigam, KR Akshatha, G Murali
    IEEE Access , 2026
    2026
  • Seismic and Geospatial Feature Integration for Earthquake Magnitude Prediction Using Machine Learning
    G Padmashree, AS Dsouza, P Adarsh
    2025 Control Instrumentation System Conference (CISCON), 1-8 , 2026
    2026
  • Foot Ulcer Classification: Demonstrating the Superiority of Hybrid Ensembles with Explainable AI.
    P G., MG Rao
    IAENG International Journal of Applied Mathematics 56 (1) , 2026
    2026
  • Exploring Ensemble Learning Strategies for Robust Medical Deepfake Detection
    G Padmashree, SG Bhat, V Shinde
    2025 Control Instrumentation System Conference (CISCON), 1-9 , 2026
    2026
  • Local–Global Feature Fusion using CNN and Vision Transformer with Ensemble Post-Classification for Diabetic Retinopathy Diagnosis
    MGR Padmashree G.
    International Journal of Computer Applications 187 (71), 15-24 , 2026
    2026
  • Performance Comparison of Machine Learning Techniques for Recognizing Disguised Faces
    P G, Ranjitha, M Herle
    2025 International Conference on Intelligent Systems and Pioneering … , 2025
    2025
  • Comparative Analysis of LSB, Phase Coding, and Spread Spectrum Techniques for Audio Steganography
    G Padmashree, A Krishna
    2025 International Conference on Intelligent Systems and Pioneering … , 2025
    2025
  • FutureGlycemics: A Comparative Study of Diverse Machine Learning Models for Diabetes Prognosis.
    G Vaishnavi Pai, K., Smitha, Padmashree
    Advances in Health Informatics, Intelligent Systems, and Networking … , 2025
    2025
  • Unleashing Machine Learning for Accurate Weather Forecasts
    GP Amisha, S., Anusha
    Applications of Artificial Intelligence and Data Science: First Global … , 2025
    2025
  • Exploring and Contrasting Machine Learning Classifiers for Citrus Plant
    BM Shenoy, SS Poojary, G Padmashree
    Applications of Artificial Intelligence and Data Science: First Global … , 2025
    2025
  • StealthFace: Transfer Learning-Based Ensemble Model for Disguised Face Recognition using Skin-Segmented Images.
    G Padmashree, KA Kotegar
    IAENG International Journal of Computer Science 52 (4) , 2025
    2025