Secure Hybrid Authentication Using Facial Biometrics, Liveness Verification, and Time-Based One-Time Passwords Kuldeep Vayadande, Praveenkumar Patel, Govinda Sambare, Prajakta Pawar, Premanand Ghadekar, Namrata Salgar, Vivek Kheradkar, Shlok Shinde, Aryan Shinde, Siddhant Shinde, Prathamesh Shinde, Samyak Lokhande International Journal of Safety and Security Engineering, 2026 Biometric authentication has become one of the topics that have attracted extensive interest because of its increased security and usability over the traditional systems that use passwords.Facial recognition is one of the common biometric modalities that has gained wide adoption due to its non-contact aspect.Nevertheless, it is susceptible to spoofing attacks, including printed images, replayed videos and deep fake-based impersonation.A hybrid authentication system called FaceOTP is suggested to counter these shortcomings, a system that combines face recognition, liveness and time-based one-time password (TOTP) authentication.The system uses MediaPipe Face Mesh to detect facial landmarks and extract geometric features of the face to build a normalized feature vector.Eye-blink and head-movement analysis are carried out to detect liveness in order to guarantee the existence of a legitimate user.The obtained feature vector is hash transformed to a secure biometric template with the help of hash SHA-256, which is then used in the production of a biometric-bound TOTP.The given system is tested in a controlled experimental setting with a number of users, and the genuine and attack cases were presented with photo-based and video replay spoofing.Experimental findings show face recognition accuracy of 95, liveness detection accuracy of 92 and 100 percent one-time password (OTP) verification success with an average authentication time of 4.5 seconds.
A Comprehensive Authenticated Dataset of Brahmi Script Characters for Recognition Tushar B. Kute, Premanand P. Ghadekar International Conference on Emerging Trends and Innovations in ICT Icei 2026, 2026 The Brahmi script is among the most ancient and historically prominent systems of writing in South Asia, with applications that warrant corresponding modern Indic scripts. Digitally recognizing Brahmi inscriptions holds the key to epigraphical studies, historical research, and cultural preservation. The efforts remained always undermined for the absence of a greater and authentic dataset. To meet this requirement, a new dataset is introduced, comprising 348 different classes of characters from the Brahmi script. The dataset contains a total of 7880 character images, each such image extracted from letter carvings over stone at seven salient archaeological sites in India: Naneghat Caves, Junnar Caves, Bhaje Caves, Karle Caves, Bedse Caves, Nashik Caves, and Pitalkhora Caves. The dataset design was an iterative and exhaustive process of image acquisition, segmentation of characters, and applications of preprocessing to increase visibility and recognizability of characters therein. The usability and robustness of the dataset were tested using four different deep learning models: a custom Deep Convolutional Neural Network (Deep CNN), InceptionNet, ResNet50, and XceptionNet. The best recognition accuracy of 98.07% was attained with a loss of 0.0958 using ResNet50, which shows the adequacy and quality of the dataset for the training of advanced machine learning models. This will help researchers by providing a valuable resource and accelerating the development of Brahmi script character recognition.
Identification of Diabetic Retinopathy Using Deep Regularized LSTM from Retinal Fundus Images Anita B. Dombale, Premanand P. Ghadekar Proceedings of the 5th International Conference on Sentiment Analysis and Deep Learning Icsadl 2026, 2026 The analysis of retinal fundus images through automation is very important in the early detection and assessment of risk of ocular and systemic complications related to diabetes. Though convolutional neural networks (CNNs) are useful in obtaining spatial information in fundus images, the fact that they model the structured feature sequence of the obtained images is a challenge to the shallow recurrent architectures. This paper compares the two (Long Short-Term Memory (LSTM)-based) models coded in binary risk classification based on fundus image-based features: a simple baseline model and a more detailed regularized proposed model. The standard model uses a two-layer LSTM with a lightweight and a single dense output layer, which is used in the computationally efficient standard model. The model proposed contains additional depth stacked LSTM layers, regularization by dropout, in-between layer normalization, and a dense layer in between layers to better represent temporal features and generalize. Both the architectures are tested in the same experimental conditions. Baseline model has an accuracy of 0.84 and the proposed architecture enhances the accuracy to 0.86, which proves that the risk prediction of risk is better by architecture modification using fundus images. The classification report analysis also validates better predictive balance in the proposed system. The findings suggest that more profound and regularized LSTM models are more able to discern sophisticated patterns in fundus image representations providing an avenue of path forward to powerful risk assessment systems in Diabetic Retinopathy.
Hybrid Fully Connected Neural-Bidirectional Long Short-Term Memory Networks for Diabetic Complication Risk Prediction , Anita B. Dombale, Premanand P. Ghadekar, and Engineered Science, 2025 Accurate estimation of the risk level of chronic diseases such as heart disease, kidney disease, and retinopathy is necessary for early detection and appropriate treatment planning for diabetic patients.The traditional machine learning models, i.e., Bidirectional long short-term memory (BiLSTM) and fully connected neural networks (FCNN), have been extensively used for disease prediction but are typically burdened with high computational complexity and redundant feature dependencies.In this research work, a new prediction model is proposed based on structured text data from CSV files to determine the levels of disease risk.The proposed method outperforms BiLSTM and FCNN in classification performance, with improved Performance Metrics.In addition, we also perform feature reduction using random forest (RF) and Explainable AI (XAI) techniques, such as SHAP (SHapley Additive exPlanations), with the objective of obtaining the most informative features.Regardless of feature reduction, the proposed system still maintains the best performance, confirming its efficacy and resilience in risk prediction.The outcomes reveal the potential for combining advanced deep learning models with feature selection techniques to improve diabetic complication disease risk assessment and prediction.
Deep Learning-based Art Authentication: A CNN-Model with Grad-CAM for AI-Generated Image Detection 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
Modified GANs Based on GNN for Anomaly Detection in Graphs Premanand Ghadekar, Ruchita Chaudhari, Kshitij Bisen, Ashish Biradar, Chetan Chaudhari, Aditya Bhosale Lecture Notes on Data Engineering and Communications Technologies, 2025
Resilient 3D Object Recognition using GR-Net in Sparse Point Clouds Premanand Ghadekar, Pratik Dhame, Soham Dixit, Arpit Patil, Rushikesh Sanjekar, Siddhesh Shinde Proceedings of 2025 3rd International Conference on Intelligent Systems Advanced Computing and Communication Isacc 2025, 2025
Dynamic Character Replacement in Videos using Motion-Guided Diffusion Techniques 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
Malicious QR Code Detection and Prevention Premanand Ghadekar, Faijan Momin, Tushar Nagre, Sanika Desai, Prathamesh Patil, Vinay Aher AI Driven Iot Systems for Industry 4 0, 2024
Early Diabetes Detection and its Effect on Heart using Random Forest 15th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2024, 2024
Bilinear Pooling with Hierarchical Structure for Precise Visual Recognition Premanand Ghadekar, Anushka Popalghat, Sarvesh Hadole, Sharvari Bawane, Sourav Jangral, Rushikesh Unde 2024 2nd International Conference on Advances in Computation Communication and Information Technology Icaiccit 2024, 2024
Prompt-based Generation of 3D Textured Human with Motion Rigging Premanand Ghadekar, Ajay Gonepuri, Prathamesh Deshpande, Mayuresh Dharwadkar, Vedant Dhole, Pranav Sonkamble 2024 8th International Conference on Computing Communication Control and Automation Iccubea 2024, 2024
Suspicious Activity Detection in Adverse Weather Conditions using YOLOv7 15th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2024, 2024
Transformer Based Text Summary Generation for Videos Premanand Ghadekar, Dhruva Khanwelkar, Harsh More, Chirag Vaswani, Nirvisha Soni, Juhi Rajani Proceedings 2024 International Conference on Current Trends in Advanced Computing Icctac 2024, 2024
Generating 3D Models for Prototyping of Virtual Environments using NeRF Premanand Ghadekar, Ajay Gonepuri, Prathamesh Deshpande, Vedant Dhole, Mayuresh Dharwadkar, Pranav Sonkamble, Chinmay Saraf 2nd International Conference on Emerging Trends in Information Technology and Engineering Ic Etite 2024, 2024
Efficient diagnosis and ICU patient monitoring model Machine Learning for Healthcare Systems Foundations and Applications, 2023
Video Regeneration Using Image Diffusion Model Premanand Ghadekar, Srushtiraj Patil, Hiranmayee Sant 2023 International Conference on Data Science Agents and Artificial Intelligence Icdsaai 2023, 2023
Waste Classification and Its Analysis Using RCNN Algorithm Premanand Ghadekar, Aniket Joshi, Prasanna Kshirsagar, Shubhankar Gupta, Mohammad Raza, Anagha Gajaralwar 2023 International Conference on Data Science Agents and Artificial Intelligence Icdsaai 2023, 2023
Voice Cloning and Forgery Detection Using WaveGAN and SpecGAN Premanand Ghadekar, Kartik Rajput, Harsh Dhabekar, Pushkar Helge, Harshit Mundhra, Chetanya Rathi 2023 7th International Conference on Computing Communication Control and Automation Iccubea 2023, 2023
Effective Mid-Day Meal Analysis Depending on Children’s Needs using Machine Learning 14th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2023, 2023
Fish Species Classification, Disease Prediction and Predictive Health Analytics 14th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2023, 2023
A Semi-Supervised GAN Architecture for Video Classification Premanand Ghadekar, Dhruva Khanwelkar, Nirvisha Soni, Harsh More, Juhi Rajani, Chirag Vaswani 2023 International Conference on Advances in Intelligent Computing and Applications Aicaps 2023, 2023
Unique Identification of Whales and Dolphins 14th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2023, 2023
3D Image Classification Based on Multi View CNN Using 2D Images Premanand Ghadekar, Mrugakshi Deshmukh, Shreyash Deshmukh, Devansh Jangid, Dhanashree Dewalkar, Rushikesh Dighole Proceedings 2023 3rd International Conference on Innovative Sustainable Computational Technologies Cisct 2023, 2023
Customer Transactional Analysis along with Customer Segmentation and Feedback Analysis 14th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2023, 2023
Improved Helmet Detection Model Using YOLOv5 Premanand Ghadekar, Shreyas Mendhekar, Vallabh Niturkar, Sanika Salunke, Abhinav Shambharkar, Kshitij Taley Lecture Notes in Networks and Systems, 2023
VR for automobile customization and its feedback analysis Premanand Ghadekar, Khushi Jhanwar, Ameya Karpe, Tanishka Shetty, Akash Sivanandan, Prannay Khushalani 2023 International Conference on Advances in Intelligent Computing and Applications Aicaps 2023, 2023
Sentence Meaning Similarity Detector Using FAISS Premanand P. Ghadekar, Sahil Mohite, Omkar More, Praiwal Patil, Sayantika, Shubham Mangrule 2023 7th International Conference on Computing Communication Control and Automation Iccubea 2023, 2023
Galaxy Classification Using Deep Learning Premanand Ghadekar, Kunal Chanda, Sakshi Manmode, Sanika Rawate, Shivam Chaudhary, Resham Suryawanshi Communications in Computer and Information Science, 2022
Web-Based Real-Time Gesture Recognition with Voice Ghadekar Premanand Pralhad, S. Abhishek, Tejas Kachare, Om Deshpande, Rushikesh Chounde, Prachi Tapadiya Communications in Computer and Information Science, 2021
Voice Controlled Augmented Reality for Real Estate Ghadekar Premanand Pralhad, S. Abhishek, Rushikesh Chounde, Tejas Kachare, Om Deshpande, Prachi Tapadiya Proceedings 2021 1st IEEE International Conference on Artificial Intelligence and Machine Vision Aimv 2021, 2021
Real-Time Hands-Free Mouse Control for Disabled Premanand Ghadekar, Pragya Korpal, Pooja Chendake, Raksha Bansal, Apurva Pawar, Siddhi Bhor Advances in Intelligent Systems and Computing, 2021
Efficient face and facial expression recognition model Premanand P Ghadekar, Hanan Ali Alrikabi, Nilkanth B Chopade Proceedings 2nd International Conference on Computing Communication Control and Automation Iccubea 2016, 2017
Handwritten Multistyle Multilingual Context Aware Resume Shortlisting with Social Score P Ghadekar, P Ahirrao, V Adhyapak, A Ainapur, S Ahire, A Nagdive, ... 2026 3rd International Conference on Emerging Trends in Engineering and … , 2026 2026
Identification of Diabetic Retinopathy Using Deep Regularized LSTM from Retinal Fundus Images AB Dombale, PP Ghadekar 2026 5th International Conference on Sentiment Analysis and Deep Learning … , 2026 2026 Citations: 1
Triplex attention enabled diffusion generative adversarial network for photorealistic image generation from text and images SS Fatangare, PP Ghadekar Engineering Applications of Artificial Intelligence 166, 113588 , 2026 2026
with Depth Inpainting and VR P Ghadekar, P Adav, N Mahajan, T Mali, S Kalaskar, A Kulkarni Evolution in Signal Processing and Telecommunication Networks: Proceedings … , 2026 2026
Secure Hybrid Authentication Using Facial Biometrics, Liveness Verification, and Time-Based One-Time Passwords K Vayadande, P Patel, G Sambare, P Pawar, P Ghadekar, N Salgar, ... Journal homepage: http://iieta. org/journals/ijsse 16 (2), 283-296 , 2026 2026
A Comprehensive Authenticated Dataset of Brahmi Script Characters for Recognition TB Kute, PP Ghadekar 2026 International Conference on Emerging Trends and Innovations in ICT … , 2026 2026
Multimodal Advanced Persistent Threat Detection and Attribution Using Heterogenous Graph Neural Network and Analysis Using Explainable AI P Ghadekar, P Jadhav, S Kulkarni, I Kulkarni, O Lohade, I Mahajan 2025 International Conference on Artificial Intelligence and Quantum … , 2025 2025
Unified Multimodal Knowledge Integration for A Secure Framework for Cross-Modal and Scalable Retrieval P Ghadekar, S Randhave, S Veer, P Gole, S Suntnure, S Pawar 2025 International Conference on Data, Energy and Communication Networks … , 2025 2025
Secure and Privacy-Preserving Machine Learning for Cloud Intrusion Detection with Federated Learning and Generated Attack Data P Ghadekar, N Gulhane, H Patil, I Ramdasi, G Hote, S Ghodke 2025 International Conference on Data, Energy and Communication Networks … , 2025 2025
Multimodal Oil Mining Prediction with LSGAT-Based DropEdge Regularization and Adaptive Training P Ghadekar, P Patange, R Paimode, S Pandav, P Patil, A Pardeshi 2025 International Conference on Data, Energy and Communication Networks … , 2025 2025
A Hybrid Multimodal Framework for Photorealistic Image Generation Using Text–Image Fusion Algorithms S Fatangare, P Ghadekar 2025 IEEE Pune Section International Conference (PuneCon), 1-6 , 2025 2025
Multimodal Learning with Spiking Neural Networks and Kolmogorov Arnold Networks Enhanced through Modified SHAP Visualization PP Ghadekar, SR Karandikar, KS Kalrao, JR Kale, ON Kapuskari, ... 2025 IEEE International Conference on Emerging Trends in Computing and … , 2025 2025
Realistic AI Based Mental Health Detection and Analysis Model Using AR Agentic AI & Conv-BiLSTM Architecture P Ghadekar, A Matre, P Pise, H Sawai, M Mule, S Shedbale 2025 IEEE 3rd International Symposium on Sustainable Energy, Signal … , 2025 2025
Multimodal Gut Microbiome based Personalized Nutrition Recommendation and Its Analysis using GNN P Ghadekar, P Wadile, A Patil, V Lakde, S Sagarkar, A Nimbolkar 2025 IEEE 3rd International Symposium on Sustainable Energy, Signal … , 2025 2025
Blockchain-Based Document Verification Using Cryptographic Hashing, QR Code, and Machine Learning P Ghadekar, I Mahajan, I Kulkarni, O Lohade, P Jadhav, S Kulkarni 2025 International Conference on Electrical, Electronics, and Computer … , 2025 2025
Transparent Clinical Support Through Cross-Modal Fusion and Aligned Explanations P Ghadekar, N Gupta, S Samgir, S Umbare, K Rathod, N Deshpande, ... 2025 Citations: 2
Autonomous Swarm Drone Surveillance System with AR Visualization for Military Patrolling and Intrusion Detection with AR Control Interface P Ghadekar, S Daga, R Sutrave, BS Bhande, V Sabale, S Gaikwad 2025 IEEE International Conference for Women in Innovation, Technology … , 2025 2025
A Multimodal Approach for Detection of Preeclampsia Risk Analysis using Reinforcement Learning and Agentic AI P Ghadekar, S Malode, M Girame, H Patil, H Patil, T Jagtap 2025 IEEE International Conference for Women in Innovation, Technology … , 2025 2025
A Real-Time GCN and AI Agent Framework for Sustainable Supply Chain Management Under Disaster Scenarios P Ghadekar, P Musne, I Naragude, M Girame 2025 IEEE International Conference for Women in Innovation, Technology … , 2025 2025
Fusion Attention-Driven Residual Generative Adversarial Networks for Realistic Image Generation S Fatangare, P Ghadekar 2025 International Conference on Electronics and Computing, Communication … , 2025 2025
MOST CITED SCHOLAR PUBLICATIONS
Handwritten Digit and Letter Recognition Using Hybrid DWT-DCT with KNN and SVM Classifier P Ghadekar, S Ingole, D Sonone SCOPUS indexed-2018 Fourth International Conference on Computing … , 2018 2018 Citations: 52
Sentence meaning similarity detector using FAISS PP Ghadekar, S Mohite, O More, P Patil, S Mangrule 2023 7th International Conference On Computing, Communication, Control And … , 2023 2023 Citations: 28
Predictive maintenance for industrial equipment: Using XGBoost and local outlier factor with explainable AI for analysis P Ghadekar, A Manakshe, S Madhikar, S Patil, M Mukadam, T Gambhir 2024 14th International Conference on Cloud Computing, Data Science … , 2024 2024 Citations: 22
EmoSecure: Enhancing smart home security with FisherFace emotion recognition and biometric access control P Ghadekar, MR Pradhan, D Swain, B Acharya IEEE Access 12, 93133-93144 , 2024 2024 Citations: 21
Secure Access Control to IoT Devices using Blockchain P Ghadekar, N Dhoke, S Kaneri, Z Varsha SCOPUS indexed Journal-International Journal of Recent Technology and … , 2019 2019 Citations: 16
Content based facial emotion recognition model using machine learning algorithm RS Jadhav, P Ghadekar SCOPUS indexed 2018 International Conference on Advanced Computation and … , 2018 2018 Citations: 16
Automatic Digitization of Engineering Diagrams using Intelligent Algorithms G Premanand, J Shaunak, S Debabrata, A Biswaranjan, RP Manas, ... SOCPUS indexed Journal of Computer Science 17 ((9)), 833 to 838 , 2021 2021 Citations: 13
Content based dynamic texture analysis and synthesis based on SPIHT with GPU PP Ghadekar, NB Chopade SCI Indexed-Journal of Information Processing System Korea, Thomson Reuters … , 2016 2016 Citations: 12
A comprehensive approach to aquatic environment monitoring: IoT-based smart aquarium system P Ghadekar, S Khare, D Sakharwade, C Saraf, P Sonkamble, A Amune 2023 International Conference on Advances in Computation, Communication and … , 2023 2023 Citations: 10
Improving image quality of noisy images through denoising and style GAN technique P Ghadekar, A Gundawar, S Kamnapure, D Manjramkar, I Gujarathi, ... 2023 7th International Conference On Computing, Communication, Control And … , 2023 2023 Citations: 10
Histopathological Cancer Detection using Deep Learning P Ghadekar, A Khandelwal, P Roy, A Gawas, C Joshi 2021 International Conference on Artificial Intelligence and Machine Vision … , 2021 2021 Citations: 10
A semantic approach for automated hiring using artificial intelligence & computer vision P Ghadekar, A Kabra, K Gangwal, A Kinage, K Agarwal, K Chaudhari 2023 IEEE 8th International Conference for Convergence in Technology (I2CT), 1-7 , 2023 2023 Citations: 9
Modelling Nonlinear Dynamic Textures using Hybrid DWT–DCT and Kernel PCA with GPU PP Ghadekar, NB Chopade Journal of The Institution of Engineers (India): Series B,Scopus … , 2016 2016 Citations: 9
Ensemble approach to solve multiple skin disease classification using deep learning P Ghadekar, A Bongulwar, A Jadhav, R Ahire, A Dumbre, S Ali 2023 International Conference on Device Intelligence, Computing and … , 2023 2023 Citations: 8
Image-Based Product Recommendations Using Market Basket Analysis P Ghadekar, A Dombe 2019 5th International Conference On Computing, Communication, Control And … , 2019 2019 Citations: 8
Multimodal PCOS detection: Combining XG boost for images with zero shot learning for textual data P Ghadekar, S Tekade, D Sakharwade, A Tripathi, S Tiwadi, S Zanzane 2024 Asia Pacific Conference on Innovation in Technology (APCIT), 1-8 , 2024 2024 Citations: 7
Text data augmentation using generative adversarial networks, back translation and eda P Ghadekar, M Jamble, A Jaybhay, B Jagtap, A Joshi, H More International Conference on Advances in Computing and Data Sciences, 391-401 , 2023 2023 Citations: 7
Predicting heart disease risk in diabetic patients using a pipeline of ensemble learning and xai-enhanced approaches P Ghadekar, U Shaikh, R Ner, S Patil, R Qazi 2024 1st international conference on cognitive, green and ubiquitous … , 2024 2024 Citations: 6
Suspicious Activity Detection in Adverse Weather Conditions using YOLOv7. P Ghadekar, S Jagtap, B Sadmake, N Mane, K Singh, B Chavan Grenze International Journal of Engineering & Technology (GIJET) 10 , 2024 2024 Citations: 6
SAGEConv graph neural network model for multivariate regression using Google quest dataset P Ghadekar, V Ingale, V Pungliya, R Bhonsle, A Raut, A Purohit Procedia Computer Science 235, 2027-2034 , 2024 2024 Citations: 6