Dr. Supriya Ashok Bhosale

@vupune.ac.in

Assistant Professor, Department of Artificial Intelligence, Faculty of Science & Technology
Vishwakarma University, Pune

Dr. Supriya Ashok Bhosale


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

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering, Artificial Intelligence, Computer Vision and Pattern Recognition, Human-Computer Interaction
11

Scopus Publications

24

Scholar Citations

2

Scholar h-index

1

Scholar i10-index

Scopus Publications

  • Mathematical analysis and numerical simulation of a fractional-order alcohol consumption model incorporating binge drinkers
    Supriya Bhosale, Chhaya Lande, Hossain Jafari, D. K. Raut
    Boundary Value Problems, 2026
    In this work, by the use of Caputo–Fabrizio fractional derivative, the fractional-order Alcoholism addiction dynamics model is formulated which capture memory effects inherent in addiction-related processes. The well-posedness of the proposed model is established by showing the existence and uniqueness of solutions under some conditions which suits to the model. Furthermore, there is a demonstration of the positivity and boundedness of the model solutions by ensuring the biological feasibility of the system and Reproduction number and endemic equilibrium with sensitivity analysis and analysis of Phase plane and bifurcation system. To assess the robustness of the solutions with respect to small perturbations, The Ulam–Hyers stability of the fractional model is investigated. To obtain approximate solutions, A suitable numerical technique is employed, and numerical simulations are carried out using MATLAB to support the theoretical findings. The influence of different fractional orders on the system dynamics is observed, which shows the accelerating progression of Recovery. The graph highlights the significant role of memory effects. The fractional-order framework provides a more flexible and realistic description of addiction dynamics compared to the classical integer-order model. The results obtained offer qualitative insights for understanding behavioral patterns of the system.
  • Hypertension Risk Prediction Using Support Vector Machines (SVM) in Electronic Health Record Data
    Harshvardhan Chunawala, Prabhudatta Behera, Supriya Bhosale, Yogesh Kumar Rathore, Zeenat Mir, Shipra Thapar
    Aip Conference Proceedings, 2026
  • Enhancing Tuberculosis Diagnosis with YOLOv5 for Real-Time X-Ray Image Detection
    Juginder Pal Singh, Supriya Bhosale, Shreya Chauhan, Ashutosh Pandey, Diksha Bhatt, Lowlesh Nandkishor Yadav
    Aip Conference Proceedings, 2026
  • Evaluating the Efficiency of the K-Nearest Neighbor Algorithm for Early Diabetes Prediction
    Supriya Ashok Bhosale, R. Krishna Kumari, Sundaresan B, Ranjeeth Kumar M, Jayaram Boga, S. Rukmani Devi
    Proceedings of 6th International Conference on Expert Clouds and Applications Icoeca 2026, 2026
    Early detection of a chronic disease like diabetes mellitus can lead to better outcomes for the patient and also help reduce healthcare expenditure. For identifying patterns in medical data, machine learning techniques have increasingly been applied to support clinical decisions. Among those techniques, the KNN algorithm stands out for its simplicity and effectiveness in classification tasks. This paper presents an exploratory and experimental study on the application of the KNN algorithm for diabetes prediction. The study involves bibliographic research and its experimental validation using a publicly available dataset on diabetes. The influence of the variation of the K parameter will also be analyzed on the performance of the model. The accuracy, recall, and F1-score performed well with variations in the value of K, especially in the diabetic class. These findings point to the importance of tuning parameters and preprocessing data in an attempt to achieve reliable predictions, which is connected to minimizing false negatives in clinical applications.
  • A Fractional Smoking Transmission Model Utilizing the Caputo-Fabrizio Operator: A Comprehensive Analysis and Simulation
    Supriya Bhosale, Chhaya Kiran Lande, Hossein Jafari, Dnyaneshwar Raut
    European Journal of Pure and Applied Mathematics, 2025
    Over the past few years, several novel formulations of fractional derivatives have emerged, facilitating the construction of mathematical models that can address a broad spectrum of real-world applications. This study presents and investigates a mathematical model for smoking behavior incorporating the Caputo–Fabrizio fractional differential operator, which is par-ticularly valued for its non-singular kernel and ability to capture memory effects in dynamic systems without the complexities of singularities. Here, the population is divided into six distinct compartments: mainly susceptible, snuffing, irregular, habitual, regular, and quit. To explore the model’s dynamics, the Laplace Adomian Decomposition Method (LADM) and the Aboodh Adomian Decomposition Method (AADM) are employed. A comparative analysis of LADM and AADM is carried out using MATLAB software, with numerical simulations conducted for various fractional orders to assess the accuracy and efficiency of both techniques. Both methodologies demonstrated a high level of accuracy and consistency in their results, highlighting their reliability for modeling complex systems.
  • Enhancing Automobile Design and Manufacturing Through VR and AR Integration
    P Sreenivas, M. Suresh Anand, Supriya Bhosale, T. V. V. Satyanarayana, Sampath Boopathi
    Virtual and Augmented Reality Applications in the Automobile Industry, 2025
    This chapter focuses on the integration of VR and AR technologies with automobile companies, especially through what transformative impacts they bring along for the design and process of automobile manufacturing. Therefore, with the use of these VR and AR technologies, the car manufacturers are facilitated in producing immersive, interactive experiences to streamline the designs thus producing better visions, prototypings, and testing cars as may be needed. These technologies allow designers and engineers, along with many other stakeholders, to provide collaborative working with real-time access to virtual environments that allow exploring and refining of concepts. Apart from this, AR increases efficiency in manufacturing by speeding up on-site assembly as well as reducing errors. This particular chapter includes case studies demonstrating the successful application of both VR and AR to improve workflow productivity, increase precision, as well as fuel innovation in auto-making.
  • Efficient Classification of Pomegranate Fruit Diseases Using MobileNetV3-Large
    Supriya Ashok Bhosale, M.Shanmugapriya, A Bhagyalakshmi, S.Nooray Sashmi, Deeya Julka, Girish Kumar
    2025 International Conference on Decision Aid Sciences and Applications Dasa 2025, 2025
    This research focuses on the development of a deep learning model for the classification of pomegranate fruit diseases, including Alternaria, Bacterial Blight, and Healthy fruits, using the MobileNetV3-large architecture. A dataset with 3,302 labeled images, acquired from Kaggle, was used for training and testing the model. Images were pre-processed with resizing, contrast enhancement, and histogram equalization to improve their quality for effective model training. Model training was done for 25 epochs with a high accuracy rate of 92% on the test set. Performance measures such as precision, recall, and F1-score showed good performance in all classes, with Healthy fruit being classified most accurately. Misclassifications were between Alternaria and Healthy most frequently, with scope for fine-tuning between them. Results show that deep learning models, in this example being MobileNetV3, can be used to accurately classify pomegranate diseases with an automated agricultural monitoring system. Data augmentation and employing more advanced models can be investigated for future enhancements, better performance, and generalizability.
  • Deep Learning for Predictive Maintenance in Power Systems
    Chintureena Thingom, Nmg Kumar, Sreenivasulu Gogula, Aparajita Mukherjee, Supriya Bhosale, Atul Sarojwal
    2024 2nd International Conference Computational and Characterization Techniques in Engineering and Sciences Ic3tes 2024, 2024
    The operation of deep learning ways for prophetic conservation in power systems, aiming to enhance trustability, effectiveness, and cost-effectiveness in conservation operations. Power systems, pivotal for icing nonstop electricity force, face challenges similar to growing structure, outfit declination, and unanticipated failures. Traditional conservation strategies frequently calculate on periodic examinations and preventative measures, which may be expensive and hamstrung. Deep learning offers a data-driven approach to prophetic conservation by using literal data from detectors and functional parameters. Convolutional Neural Networks( CNNs) and intermittent Neural Networks( RNNs) are employed to dissect time-series data and describe patterns reflective of implicit outfit failures or declination. By prognosticating conservation requirements in advance, serviceability can record interventions more effectively, reduce time-out, and optimize resource allocation. Through case studies and simulations, this exploration demonstrates the efficacity of deep learning models in perfecting prophetic conservation delicacy and trustability in power systems. The integration of AI-driven prophetic conservation holds a pledge for transubstantiating conservation practices, enhancing grid adaptability, and icing sustainable energy forces for unborn demands.
  • Optimizing Patient Flow and Resource Allocation in Hospitals using AI
    Yogesh Rathore, Upasana Sinha, Jaysing Pandurang Haladkar, Nilesh R. Mate, Supriya Ashok Bhosale, Santoshkumar Vaman Chobe
    International Conference on Artificial Intelligence for Innovations in Healthcare Industries Icaiihi 2023, 2023
    The present study investigates the incorporation of artificial intelligence (AI) into healthcare administration, with a specific focus on optimizing patient flow as well as allocating resources in various hospital environments. Using a descriptive research methodology with secondary data gathering, the study adopts an interpretivist philosophy and a deductive technique. The findings show that applying AI-driven techniques significantly improves patient wait times, the efficiency of resource utilization, and patient outcomes. The contrast between AI-enhanced practices and traditional procedures demonstrates how much better they are at optimizing patient flow. On the other hand, implementation-critical elements include initial investment expenses and ethical considerations. Investing in AI infrastructure, resolving algorithmic biases, including protecting data privacy are among the recommendations. Future research ought to concentrate on the scalability, long-term effects, and enhancements to AI systems for objective forecasts
  • Hybrid AI Model for Arthritis Prediction from Medical Image
    Vignesh Janarthanan, S. Pradeep, K. Vidhya, Roslin Dayana K, Supriya Ashok Bhosale, Ashok Kumar
    3rd International Conference on Smart Electronics and Communication Icosec 2022 Proceedings, 2022
    The most common type of arthritis is osteoarthritis (OA), particularly in the knee, which causes significant disability for all who suffer from this disease all over the world. Knee Osteoarthritis (KOA) is a degenerative joint ailment caused by the gradual deterioration of cartilage. Hand identification, classification, and annotation of knee joints are still used in clinical processes to detect OA, although they are time-consuming and extremely susceptible to the physician. Because of the complexity of KOA and the lack of understanding of its pathology, there is little requirement for accurate techniques which will minimize physician diagnostic errors. To overcome the limitation of the commonly used strategy, the research provides hybrid Artificial Intelligence (AI) approaches to automate OA prediction without expert assistance. Support Vector Machine (SVM), Naive Bayes (NB), Linear Discriminant Analysis (LDA), and a hybrid (SVM+NB) model were used in this work. To identify OA, AI models must be trained on labelled X-ray images. So, Kaggle is used to gather X-ray images of people without and with OA in various stages (Healthy, minimal, moderate, and severe). The collected image is not fed directly into the AI model for training. Before it can be utilized, the image must be processed. The preprocessed image is being applied for feature extraction to reduce the amount of memory required by the AI model to train. Following feature extraction, the data will be divided into two classes: training and testing. The AI model is trained using images from the training class with labels. The AI model is put to the test by giving unlabelled images of the testing class and asking it to estimate the label. The AI model is compared based on the test results, and the best model is identified using the positive and negative metrics values. The experimental results show that the hybrid AI model outperforms the other three AI models.
  • Usage of ML and IoT in Healthcare Diagnose During Pandemic
    Shashi, V. Srikanth, Prarthita Biswas, V. Chinnammal, Supriya Ashok Bhosale, Sheshang Degadwala
    Proceedings of 3rd International Conference on Intelligent Engineering and Management Iciem 2022, 2022

RECENT SCHOLAR PUBLICATIONS

  • AI-Driven Saliency-Guided Retinal Vessel Segmentation Framework for Sustainable Digital Pathology
    R Guha Thakurta, ME Seno, M Ur Rehman, SA Haider, MA Halwani, ...
    Frontiers in Medicine 13, 1801480 , 2026
    2026
  • Enhancing tuberculosis diagnosis with YOLOv5 for real-time x-ray image detection
    JP Singh, S Bhosale, S Chauhan, A Pandey, D Bhatt, LN Yadav
    AIP Conference Proceedings 3386 (1), 020144 , 2026
    2026
  • Hypertension risk prediction using support vector machines (SVM) in electronic health record data
    H Chunawala, P Behera, S Bhosale, YK Rathore, Z Mir, S Thapar
    AIP Conference Proceedings 3386 (1), 020134 , 2026
    2026
  • Evaluating the Efficiency of the K-Nearest Neighbor Algorithm for Early Diabetes Prediction
    SA Bhosale, RK Kumari, R Kumar, J Boga, SR Devi
    2026 6th International Conference on Expert Clouds and Applications (ICOECA … , 2026
    2026
  • Ultrasound Image De-noising and Feature Enhancement for Fetal Growth Monitoring
    M DEEPARANI, DM KRISHNA, M SHANMUGATHAI, SA BHOSALE, ...
    Journal of Environmental Protection and Ecology 26 (8), 3338-3347 , 2026
    2026
  • Federated AI-Driven Digital Twins in the Healthcare Metaverse: Architectures, Privacy, and Clinical Intelligence
    AS Budhewar, BK Patil, AS Tharayil, S Bhosale, S Suthadevan, N Patel, ...
    The Convergence of the Metaverse, AI, and Federated Learning in Healthcare … , 2026
    2026
  • Enhancing Credit Card Transaction Security Using Supervised and Unsupervised Machine Learning Techniques
    S Bhosal, V Aswini, C Thingom, SR Yendole, G Sheeba, SC Jency
    2025 IEEE International Conference on Recent Advances in Computing and … , 2025
    2025
  • Efficient Classification of Pomegranate Fruit Diseases Using MobileNetV3-Large
    SA Bhosale, M Shanmugapriya, A Bhagyalakshmi, SN Sashmi, D Julka, ...
    2025 International Conference on Decision Aid Sciences and Applications … , 2025
    2025
  • Enhancing Automobile Design and Manufacturing Through
    S Bhosale, TVV Satyanarayana, S Boopathi
    Virtual and Augmented Reality Applications in the Automobile Industry, 231 , 2025
    2025
  • Enhancing Automobile Design and Manufacturing Through VR and AR Integration
    P Sreenivas, MS Anand, S Bhosale, TVV Satyanarayana, S Boopathi
    Virtual and Augmented Reality Applications in the Automobile Industry, 231-256 , 2025
    2025
  • Deep Learning for Predictive Maintenance in Power Systems
    C Thingom, N Kumar, S Gogula, A Mukherjee, S Bhosale, A Sarojwal
    2024 Second International Conference Computational and Characterization … , 2024
    2024
  • Optimizing patient flow and resource allocation in hospitals using AI
    Y Rathore, U Sinha, JP Haladkar, NR Mate, SA Bhosale, SV Chobe
    2023 International Conference on artificial intelligence for innovations in … , 2023
    2023
    Citations: 15
  • Design and Detection of fake News in Social Plaforms using Machine Learning
    SA Bhosale, LS Songare
    Mathematical Statistician and Engineering Applications 71 (4), 9784-9796 , 2022
    2022
  • Detection of Fake News in Social Networks by Machine Learning
    DLSS Supriya Bhosale
    Journal of Northeastern University 25 (4), 540-547 , 2022
    2022
  • Hybrid AI Model for Arthritis Prediction from Medical Image
    V Janarthanan, S Pradeep, K Vidhya, SA Bhosale, A Kumar
    2022 3rd International Conference on Smart Electronics and Communication … , 2022
    2022
    Citations: 2
  • Usage of ML and IoT in Healthcare Diagnose During Pandemic
    V Srikanth, P Biswas, V Chinnammal, SA Bhosale, S Degadwala
    2022 3rd International Conference on Intelligent Engineering and Management … , 2022
    2022
    Citations: 1
  • JOURNAL OF NORTHEASTERN UNIVERSITY
    A Bose, N Khatoon
    Journal of Northeastern University 25 (04) , 2022
    2022
    Citations: 1
  • COVID-19: Face Mask Detector with Open CV and CNN Algorithm
    T Pragati, T Akshada, W Asmita, Z Prachi, SA Bhosale
    Recent Trends in Intensive Computing, 492-498 , 2021
    2021
  • Achieving Flatness: Selecting the Honeywords from Existing User Passwords
    MS Pawar, MS Dhoble, MN Soni, S Bhosale
    International Journal of Advance Research in Engineering, Science … , 2017
    2017
    Citations: 1
  • An explore to congestion control in wireless sensor network
    RA Ostwal, MB Kalkumbe, SA Bhosale
    International Journal of Engineering and Innovative Technology (IJEIT) 4 (7 … , 2015
    2015
    Citations: 2

MOST CITED SCHOLAR PUBLICATIONS

  • Optimizing patient flow and resource allocation in hospitals using AI
    Y Rathore, U Sinha, JP Haladkar, NR Mate, SA Bhosale, SV Chobe
    2023 International Conference on artificial intelligence for innovations in … , 2023
    2023
    Citations: 15
  • Hybrid AI Model for Arthritis Prediction from Medical Image
    V Janarthanan, S Pradeep, K Vidhya, SA Bhosale, A Kumar
    2022 3rd International Conference on Smart Electronics and Communication … , 2022
    2022
    Citations: 2
  • An explore to congestion control in wireless sensor network
    RA Ostwal, MB Kalkumbe, SA Bhosale
    International Journal of Engineering and Innovative Technology (IJEIT) 4 (7 … , 2015
    2015
    Citations: 2
  • A novel approach for Fingerprint Recognition
    PP Chouthmal, SA Bhosale, KV Kale
    Int. J. Adv. Res. Comput. Sci. Softw. Eng 4 (8) , 2014
    2014
    Citations: 2
  • Usage of ML and IoT in Healthcare Diagnose During Pandemic
    V Srikanth, P Biswas, V Chinnammal, SA Bhosale, S Degadwala
    2022 3rd International Conference on Intelligent Engineering and Management … , 2022
    2022
    Citations: 1
  • JOURNAL OF NORTHEASTERN UNIVERSITY
    A Bose, N Khatoon
    Journal of Northeastern University 25 (04) , 2022
    2022
    Citations: 1
  • Achieving Flatness: Selecting the Honeywords from Existing User Passwords
    MS Pawar, MS Dhoble, MN Soni, S Bhosale
    International Journal of Advance Research in Engineering, Science … , 2017
    2017
    Citations: 1
  • AI-Driven Saliency-Guided Retinal Vessel Segmentation Framework for Sustainable Digital Pathology
    R Guha Thakurta, ME Seno, M Ur Rehman, SA Haider, MA Halwani, ...
    Frontiers in Medicine 13, 1801480 , 2026
    2026
  • Enhancing tuberculosis diagnosis with YOLOv5 for real-time x-ray image detection
    JP Singh, S Bhosale, S Chauhan, A Pandey, D Bhatt, LN Yadav
    AIP Conference Proceedings 3386 (1), 020144 , 2026
    2026
  • Hypertension risk prediction using support vector machines (SVM) in electronic health record data
    H Chunawala, P Behera, S Bhosale, YK Rathore, Z Mir, S Thapar
    AIP Conference Proceedings 3386 (1), 020134 , 2026
    2026
  • Evaluating the Efficiency of the K-Nearest Neighbor Algorithm for Early Diabetes Prediction
    SA Bhosale, RK Kumari, R Kumar, J Boga, SR Devi
    2026 6th International Conference on Expert Clouds and Applications (ICOECA … , 2026
    2026
  • Ultrasound Image De-noising and Feature Enhancement for Fetal Growth Monitoring
    M DEEPARANI, DM KRISHNA, M SHANMUGATHAI, SA BHOSALE, ...
    Journal of Environmental Protection and Ecology 26 (8), 3338-3347 , 2026
    2026
  • Federated AI-Driven Digital Twins in the Healthcare Metaverse: Architectures, Privacy, and Clinical Intelligence
    AS Budhewar, BK Patil, AS Tharayil, S Bhosale, S Suthadevan, N Patel, ...
    The Convergence of the Metaverse, AI, and Federated Learning in Healthcare … , 2026
    2026
  • Enhancing Credit Card Transaction Security Using Supervised and Unsupervised Machine Learning Techniques
    S Bhosal, V Aswini, C Thingom, SR Yendole, G Sheeba, SC Jency
    2025 IEEE International Conference on Recent Advances in Computing and … , 2025
    2025
  • Efficient Classification of Pomegranate Fruit Diseases Using MobileNetV3-Large
    SA Bhosale, M Shanmugapriya, A Bhagyalakshmi, SN Sashmi, D Julka, ...
    2025 International Conference on Decision Aid Sciences and Applications … , 2025
    2025
  • Enhancing Automobile Design and Manufacturing Through
    S Bhosale, TVV Satyanarayana, S Boopathi
    Virtual and Augmented Reality Applications in the Automobile Industry, 231 , 2025
    2025
  • Enhancing Automobile Design and Manufacturing Through VR and AR Integration
    P Sreenivas, MS Anand, S Bhosale, TVV Satyanarayana, S Boopathi
    Virtual and Augmented Reality Applications in the Automobile Industry, 231-256 , 2025
    2025
  • Deep Learning for Predictive Maintenance in Power Systems
    C Thingom, N Kumar, S Gogula, A Mukherjee, S Bhosale, A Sarojwal
    2024 Second International Conference Computational and Characterization … , 2024
    2024
  • Design and Detection of fake News in Social Plaforms using Machine Learning
    SA Bhosale, LS Songare
    Mathematical Statistician and Engineering Applications 71 (4), 9784-9796 , 2022
    2022
  • Detection of Fake News in Social Networks by Machine Learning
    DLSS Supriya Bhosale
    Journal of Northeastern University 25 (4), 540-547 , 2022
    2022