Dr.Manjusha Tatiya

@indiraicem.ac.in

Assistant professor AI and DS
Indira College of Engineering and Management

Dr.Manjusha Tatiya


                        Download Compact PDF  
https://researchid.co/manjusha.tatiya

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering, Artificial Intelligence, Computer Science, Engineering
14

Scopus Publications

301

Scholar Citations

10

Scholar h-index

10

Scholar i10-index

Scopus Publications

  • SAR Image Colorization for Comprehensive Insight Using a Deep Learning Model – A Literature Survey
    Rakhi Bharadwaj, Minakshi N. Vharkate, Dipa Dattatray Dharmadhikari, Manjusha Tatiya
    Lecture Notes in Networks and Systems, 2026
  • The Role of AI in Reducing Environmental Impact in the Mining Sector
    Journal of Mines Metals and Fuels, 2025
  • Developing AI-Enhanced Forensic Tools to Combat Cognitive Cybercrimes
    Priya Matta, Atika Gupta, R.K. Saini, Sopan Talekar, Manjusha Tatiya
    Cognitive Cyber Crimes in the Era of Artificial Intelligence, 2025
    Cognitive cybercrimes—crimes aimed at manipulating human cognition through social engineering, deepfakes, misinformation, and synthetic identities—pose significant risks in today's digital ecosystem. This research introduces artificial intelligence–enhanced forensic tools that integrate machine learning and natural language processing (NLP) to detect, analyze, and mitigate cognitive cyberthreats. Utilizing the RealNews dataset (45 million tokens, 120K labeled articles), the FaceForensics++ dataset (1,000+ manipulated videos), and the SYN-ID dataset (synthetically generated identity profiles), we apply an ensemble approach combining BERT-based NLP classification, XceptionNet for deepfake detection, and gradient boosted decision trees for identity fraud classification. Our hybrid model achieved an accuracy of 97.6% in identifying misinformation, 96.3% for deepfake detection, and 95.1% in synthetic identity fraud detection. New performance metrics such as the Cognitive Threat Precision Index and Forensic Intervention Efficiency are proposed to measure detection depth and system responsiveness. These tools aim to empower cybersecurity teams with real-time decision-making support.
  • Enhancing Energy Efficiency in IoT Networks Using Deep Learning-Based Predictive Maintenance
    Pragati Choudhari, Manjusha Tatiya, R V S Praveen, Harmandeep Kaur, Hari Krishna Vemuri, Montater MuhsnHasan
    2025 World Skills Conference on Universal Data Analytics and Sciences Worldsuas 2025, 2025
    Energy consumption has increased dramatically due to the fast growth of the Internet of Things (IoT), particularly in large-scale IoT networks. This has the potential to compromise operational efficiency and sustainability. The goal of this project is to develop predictive maintenance techniques based on deep learning and apply them to IoT networks in order to increase their energy efficiency. Predictive maintenance allows Internet of Things devices to proactively detect and fix any problems, which in turn reduces energy use and system downtime. Predicting when equipment will break down and finding the best way to distribute network resources are two of the many uses of deep learning algorithms discussed in this article. To facilitate real-time tracking and forecasting, we suggest a hybrid paradigm that combines data collected by sensors embedded in IoT devices with analytics hosted on the cloud. Reliability, accuracy of predictions, and energy usage are some of the important performance measures used to assess the model's efficacy. The model has the ability to revolutionise energy management in IoT ecosystems, as shown by the results, which reveal a significant increase in energy efficiency and decreases in energy waste of up to 30%. This research lays the groundwork for future studies on energy-efficient Internet of Things (IoT) designs and sheds light on how deep learning might imp rove the sustainability of IoT networks.
  • AI Applications in Tailings and Waste Management: Improving Safety, Recycling, and Water Utilization
    Manjusha Tatiya, Milind Manikrao Darade, Babaso A. Shinde, Mahesh Prakash Kumbhare, Rupali Dineshwar Taware, Sukhadip Mhankali Chougule, Swati Mukesh Dixit, Anant Sidhappa Kurhade
    Applied Chemical Engineering, 2025
    Artificial Intelligence (AI) is transforming tailings and waste management in the mining sector by improving safety, enhancing recycling efficiency, and optimizing water utilization. Traditional monitoring and waste handling approaches often lack scalability, real-time responsiveness, and predictive accuracy, limiting their effectiveness in preventing environmental and operational failures. This review systematically examines AI-driven applications across tailings dam safety, waste recycling, and intelligent water management, drawing insights from over 80 recent studies. Quantitative evidence indicates that AI-based monitoring systems can detect potential dam failures up to 30–40% earlier than conventional methods, while reinforcement learning and neural-network models improve mineral recovery by 10–25% with reduced chemical consumption. In water reuse operations, machine learning optimization achieves up to 35% savings in freshwater demand through closed-loop control. The paper highlights emerging integrations of AI with Explainable AI (XAI), Federated Learning (FL), and Circular Economy (CE) models that collectively support sustainable and transparent mining practices. Persistent barriers such as poor data quality, inadequate infrastructure, and lack of regulatory clarity are also discussed, along with future research directions. The findings demonstrate AI’s potential to transition mining operations toward safer, more efficient, and environmentally responsible systems.
  • AI-Driven Process Control for Enhancing Safety and Efficiency in Oil Refining
    Manjusha Tatiya, Babaso A. Shinde, Navnath B. Pokale, Mahesh Sarada, Mahesh M. Bulhe, Govindrajan Murali, Vidhi Rajendra Kadam, Anant Sidhappa Kurhade, Shital Yashwant Waware
    Applied Chemical Engineering, 2025
    Artificial Intelligence (AI) is reshaping the oil refining sector by improving process safety, energy efficiency, and product quality. This work evaluates real-time AI applications such as predictive maintenance, anomaly detection, and autonomous process optimization using machine learning, deep learning, reinforcement learning, and natural language processing. A systematic review of recent industrial case studies and simulations shows AI can reduce equipment downtime, emissions, and operational costs while enhancing decision-making and regulatory compliance. Despite these advantages, the adoption of AI in refineries faces challenges such as cybersecurity risks, legacy system integration, and lack of explainable models. Future research should focus on scalable and transparent AI frameworks that align with industry-specific needs.
  • AI-based monitoring and management in smart aquaculture for ocean fish farming systems
    Pramod Dhamdhere, Swati Mukesh Dixit, Manjusha Tatiya, Babaso A. Shinde, Jyoti Deone, Anant Kaulage, Yogendra Patil, Rupesh Gangadhar Mahajan, Anant Sidhappa Kurhade, Shital Yashwant Waware
    Applied Chemical Engineering, 2025
    Background: The growing global demand for seafood and the limitations of conventional aquaculture practices have highlighted the need for sustainable and efficient alternatives. Ocean-based fish farming faces challenges such as inconsistent water quality, delayed disease detection, and inefficient feeding strategies. Artificial Intelligence (AI), integrated with the Internet of Things (IoT), computer vision, and machine learning, offers opportunities to address these issues and advance smart aquaculture systems. Methods: This review systematically synthesizes literature, industrial reports, and case studies from leading aquaculture regions including Norway, Japan, India, and Chile. The analysis focuses on AI applications in water quality monitoring, fish health management, feeding optimization, biomass estimation, and decision support. The study also evaluates commercial platforms and identifies technical, economic, and ethical challenges, alongside emerging research directions. Results: AI-based monitoring and management systems demonstrated significant improvements in aquaculture practices. Commercial solutions such as eFishery, Aquabyte, and Aquaai reported feed cost reductions of 15–30%, early disease detection leading to up to 20% lower mortality rates, and more accurate biomass estimation exceeding 90% prediction accuracy. These outcomes resulted in enhanced yield, cost savings, operational efficiency, and compliance with environmental standards. Conclusion: AI technologies have shown transformative potential in achieving sustainable, climate-resilient aquaculture. While challenges such as data scarcity, high setup costs, environmental variability, and ethical concerns persist, emerging approaches—including multimodal AI, digital twins, robotics, and explainable AI—can enhance robustness and transparency. Future research should emphasize scalable, adaptive, and standardized AI frameworks to support global seafood security and long-term sustainability in ocean-based fish farming.
  • Design of an Efficient Forensic Layer for IoT Network Traffic Analysis Engine Using Deep Packet Inspection via Recurrent Neural Networks
    Amol Dhumane, Nitin N. Sakhare, Pooja Dehankar, Jambi Ratna Raja Kumar, Sheetal S. Patil, Manjusha Tatiya
    International Journal of Safety and Security Engineering, 2024
    .
  • Security-aware analytical framework: A mathematical model and machine learning for dynamical system control in secure environments
    Jaya Chandwani, Gauri Dhopavkar, Manjusha Tatiya, Nitin Chakole, Shailesh V. Kulkarni, Nilesh Shelke
    Journal of Discrete Mathematical Sciences and Cryptography, 2024
    This study presents a Security-Aware Analytical Framework (SAAF) that is meant to make dynamic system control better in safe places. The framework uses a new mathematical model and advanced machine learning methods to make vital systems more resistant to possible security threats. The mathematical model gives a defined picture of how the system works and where its security holes are. This makes it possible to measure risks and come up with proactive control strategies. Using machine learning techniques, the system changes with changing danger scenarios, allowing for identification and reaction to threats in real time. A risk evaluation tool, a dynamic danger prediction model, and an adaptable control system are some of the most important parts of the SAAF. The risk assessment tool checks for weaknesses in the system, and the dynamic threat prediction model uses machine learning to guess when security might be broken. These guesses are used by the adaptive control method to change system settings on the fly, which improves security without lowering working efficiency. The suggested framework works well by being simulated in a number of safe settings. These settings show how it can reduce security risks and make sure that dynamic systems are strong even as threats change. This study helps to improve methods that focus on security for protecting key assets.
  • Optimizing Communication Systems with Applied Nonlinear Analysis Techniques
    Communications on Applied Nonlinear Analysis, 2023
  • Real-Time Patient Monitoring Using Deep Learning for Medical Diagnosis
    Himanshu Sharma, Manjusha Tatiya, Upendra Singh Aswal, K Laxminarayanamma, Nandita Tripathi, Dinesh Singh
    Proceedings of International Conference on Contemporary Computing and Informatics Ic3i 2023, 2023
  • Apply Agglomerative Algorithm and Vgg16 on Brain Tumor Segmentation (Dataset to be Used Brats)
    Lakshmi Namratha Vempaty, Manjusha Tatiya, Anurag Shrivastava, Gururaj L. Kulkarni, Pankaj Singh, Vijay Saxena
    Proceedings of International Conference on Contemporary Computing and Informatics Ic3i 2023, 2023
  • Detection of Alzheimer's Disease Using Deep Learning, Blockchain, and IoT Cognitive Data
    Balbir Singh, Manjush Tatiya, Anurag Shrivastava, Devvret Verma, Arun Pratap Srivastava, Ajay Rana
    Proceedings of International Conference on Technological Advancements in Computational Sciences Ictacs 2022, 2022
  • Web Mash-Up Development and Security Using AOP
    Manjusha Tatiya, Sharvari C. Tamane
    Smart Innovation Systems and Technologies, 2020

RECENT SCHOLAR PUBLICATIONS

  • AI-driven audio-to-video generation for dynamic content creation via stable diffusion and CNN-augmented transformers
    D Dharrao, M Dharrao, S Padgaonkar, S Kumari, PS Sreevaishnavi, ...
    Scientific Reports , 2026
    2026
  • Deep learning-based blood cell classification from microscopic images for haematological disorder identification
    NS Jagtap, V Bodade, V Kadrolli, H Mahajan, PP Kale, P Pise, A Hingmire
    Multimedia Tools and Applications 84 (20), 21917-21944 , 2025
    2025
    Citations: 14
  • Automated Detection of Defects in Solar Images Utilizing Integrated Deep Learning Frameworks
    D Kulkarni, PP Kale, HB Mahajan, P Pise, S Yadav, S Desai
    International Conference on Computer Vision and Robotics, 241-252 , 2025
    2025
  • Sentiment Analysis for E-Commerce Product Reviews Using CNN-LSTM
    P Paul, S Acharya, B Misra, S Majumder, N Dey, P Pise
    2024 First International Conference for Women in Computing (InCoWoCo), 1-7 , 2024
    2024
    Citations: 2
  • White Blood Cells Classification Model using Automatic Soft Computing
    PP Mahale, RK Deshmukh, P Pise, SR Rangari
    2024 Asia Pacific Conference on Innovation in Technology (APCIT), 1-6 , 2024
    2024
  • Summarizing business news: evaluating BART, T5, and PEGASUS for effective information extraction.
    D Dharrao, M Mishra, A Kazi, M Pangavhane, P Pise, AM Bongale
    Revue d'Intelligence Artificielle 38 (3) , 2024
    2024
    Citations: 16
  • Disease Classification Model Using Capsule Networks Based on White Blood Cells
    PS Gaikwad, RK Deshmukh, P Pise, SD Bhopale
    2024 5th International Conference for Emerging Technology (INCET), 1-5 , 2024
    2024
    Citations: 1
  • Efficient Feature Extraction for Classification of Alzheimer's Abnormalities Using Deep Learning
    MA Zope, RK Deshmukh, P Pise, SD Bhopale
    2024 5th International Conference for Emerging Technology (INCET), 1-6 , 2024
    2024
    Citations: 1
  • Object Detection and Classification in Human Rescue Operations: Deep Learning Strategies for Flooded Environments.
    PU Nehete, DS Dharrao, P Pise, A Bongale
    International Journal of Safety & Security Engineering 14 (2) , 2024
    2024
    Citations: 14
  • Multi-task convolutional neural network approach for automatic Alzheimer disease classification
    MA Zope, RK Deshmukh, P Pise, SD Bhopale
    2024 3rd International Conference for Innovation in Technology (INOCON), 1-5 , 2024
    2024
    Citations: 1
  • Automatic White Blood Cells Classification using Optimized Convulutional Neural Network
    PP Mahale, RK Deshmukh, P Pise, MS Gardi
    2024 3rd International Conference for Innovation in Technology (INOCON), 1-6 , 2024
    2024
    Citations: 1
  • Design and Investigate the Deep Learning Models for White Blood Cell Classification
    PS Gaikwad, RK Deshmukh, P Pise, SD Bhopale
    2024 3rd International Conference for Innovation in Technology (INOCON), 1-5 , 2024
    2024
  • Diabetic Condition Classification using Supervised and Unsupervised Machine Learning Techniques: A Use Case for HealthTech Industry
    AM Bongale, S Biradar, P Pise, AP Suke, N Uke, DS Dharrao
    2023 Fourth International Conference on Smart Technologies in Computing … , 2023
    2023
    Citations: 2
  • Computationally Efficient Blockchain-based Privacy Preservation Approach for Internet of Vehicle Things
    PK Shinde, RK Deshmukh, P Pise
    2023 Global Conference on Information Technologies and Communications (GCITC … , 2023
    2023
  • Lightweight Blockchain-based Secuirity Protocol for Internet of Vehicle Things
    PK Shinde, RK Deshmukh, P Pise
    2023 Global Conference on Information Technologies and Communications (GCITC … , 2023
    2023
    Citations: 1
  • SEMANTIC SEGMENTATION IN MEDICAL IMAGE ANALYSIS WITH CONVOLUTIONAL NEURAL NETWORKS.
    SN Jain, P Pise, A Mishra
    ICTACT Journal on Image & Video Processing 14 (2) , 2023
    2023
    Citations: 1
  • FEATURE EXTRACTION USING AT-CONVLSTM BASED CULTURAL ALGORITHM FOR IMAGE UNDERSTANDING.
    SN Jain, P Pise, A Mishra
    ICTACT Journal on Image & Video Processing 14 (1) , 2023
    2023
    Citations: 1
  • Comparative Analysis of Alzheimer's Disease Detection Using Machine Learning Techniques
    DAM Shweta Nishit Jain, Dr. Priya Pise
    European Chemical Bulletin 12 (7), 10.48047/ecb/2023.12.si7.437 , 2023
    2023
  • Feature Extraction Of Indicator Card Data For Sucker-Rod Pump Working Condition Diagnosis Using Machine Learning.
    DAKM Dr. Priya Pise, Mr. Ashish Dudhale,, Dr. Nilesh Uke
    Journal of Data Acquisition and Processing, 2023, 38 (3): 5060-5067 38 (3) , 2023
    2023
  • Machine Learning And Visual Computing Observation System
    DAKM Dr. Priya Pise, Mr. Ashish Dudhale,, Dr. Nilesh Uke
    Journal of Data Acquisition and Processing, 2023, 38 (3): 5060-5067 38 (3) , 2023
    2023

MOST CITED SCHOLAR PUBLICATIONS

  • Automatic robot Manoeuvres detection using computer vision and deep learning techniques: a perspective of internet of robotics things (IoRT)
    HB Mahajan, N Uke, P Pise, M Shahade, VG Dixit, S Bhavsar, ...
    Multimedia Tools and Applications 82 (15), 23251-23276 , 2023
    2023
    Citations: 88
  • Healthcare 4.0 Enabled Lightweight Security Provisions for Medical Data Processing
    SH Shailaja Uke Nilesh Uke, Priya Pise, Hemant B. Mahajan
    Turkish Journal of Computer and Mathematics Education 12 (11), 165-173 , 2021
    2021
    Citations: 48
  • A review on hybrid encryption in cloud computing
    L Kumar, N Badal
    2019 4th international conference on internet of things: smart innovation … , 2019
    2019
    Citations: 32
  • Summarizing business news: evaluating BART, T5, and PEGASUS for effective information extraction.
    D Dharrao, M Mishra, A Kazi, M Pangavhane, P Pise, AM Bongale
    Revue d'Intelligence Artificielle 38 (3) , 2024
    2024
    Citations: 16
  • Deep learning-based blood cell classification from microscopic images for haematological disorder identification
    NS Jagtap, V Bodade, V Kadrolli, H Mahajan, PP Kale, P Pise, A Hingmire
    Multimedia Tools and Applications 84 (20), 21917-21944 , 2025
    2025
    Citations: 14
  • Object Detection and Classification in Human Rescue Operations: Deep Learning Strategies for Flooded Environments.
    PU Nehete, DS Dharrao, P Pise, A Bongale
    International Journal of Safety & Security Engineering 14 (2) , 2024
    2024
    Citations: 14
  • Hybrid Encryption Techniques for Secure Sharing of a Sensitive Data for Banking Systems Over Cloud
    P More, S Chandugade, SMS Rafiq, P Pise
    2018 International Conference On Advances in Communication and Computing … , 2018
    2018
    Citations: 14
  • Efficient security framework for sensitive data sharing and privacy preserving on big-data and cloud platforms
    PD Pise, NJ Uke
    Proceedings of the International Conference on Internet of things and Cloud … , 2016
    2016
    Citations: 14
  • Smart shopping cart with automatic billing system through rfid and bluetooth
    P Aryan, P Pise, S Tamhane, R Patil, K Pittulwar
    International Journal of Emerging Technology and Computer Science 1 (02), 73-76 , 2016
    2016
    Citations: 13
  • Data collection and preparation
    PN Mahalle, GR Shinde, PD Pise, JY Deshmukh
    Foundations of data science for engineering problem solving, 15-31 , 2021
    2021
    Citations: 10
  • Foundations of data science for engineering problem solving
    PN Mahalle, GR Shinde, PD Pise, JY Deshmukh
    Springer , 2022
    2022
    Citations: 8
  • Compression technique using dct & fractal compression–a survey
    RM Gouda, P Pise
    Advances in Physics Theories and Applications, ISSN, 2225-0638 , 2012
    2012
    Citations: 4
  • Secure Login System using MD5 and AES Attribute Based Encryption Algorithm
    S Wakhare, DP Pise, R Khalate, S Birajdar, S Survase
    International Journal of Innovative Technology and Exploring Engineering 9 … , 2020
    2020
    Citations: 3
  • Efficient Security Protocol for Sensitive Data Sharing on Cloud Platforms
    PD Pise, NJ Uke
    2017 IEEE , 2017
    2017
    Citations: 3
  • Sentiment Analysis for E-Commerce Product Reviews Using CNN-LSTM
    P Paul, S Acharya, B Misra, S Majumder, N Dey, P Pise
    2024 First International Conference for Women in Computing (InCoWoCo), 1-7 , 2024
    2024
    Citations: 2
  • Diabetic Condition Classification using Supervised and Unsupervised Machine Learning Techniques: A Use Case for HealthTech Industry
    AM Bongale, S Biradar, P Pise, AP Suke, N Uke, DS Dharrao
    2023 Fourth International Conference on Smart Technologies in Computing … , 2023
    2023
    Citations: 2
  • Content-Based Deduplication of Data Using Erasure Technique for RTO Cloud
    S Pal, K More, P Pise
    2018 International Conference On Advances in Communication and Computing … , 2018
    2018
    Citations: 2
  • A Mechanism for Copyrighted Video Copy Detection and Identification
    V Dewar, P Pise
    International Journal of Science and Research (IJSR) , 2013
    2013
    Citations: 2
  • Disease Classification Model Using Capsule Networks Based on White Blood Cells
    PS Gaikwad, RK Deshmukh, P Pise, SD Bhopale
    2024 5th International Conference for Emerging Technology (INCET), 1-5 , 2024
    2024
    Citations: 1
  • Efficient Feature Extraction for Classification of Alzheimer's Abnormalities Using Deep Learning
    MA Zope, RK Deshmukh, P Pise, SD Bhopale
    2024 5th International Conference for Emerging Technology (INCET), 1-6 , 2024
    2024
    Citations: 1