Sujata P Pathak

@kjsce.somaiya.edu

Assistant Professor, IT
K J Somaiya College of Engineering, SVU, Vidyavihar, Mumbai

Sujata P Pathak


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

RESEARCH, TEACHING, or OTHER INTERESTS

Engineering, Computer Vision and Pattern Recognition, Renewable Energy, Sustainability and the Environment, Artificial Intelligence
11

Scopus Publications

168

Scholar Citations

5

Scholar h-index

4

Scholar i10-index

Scopus Publications

  • INPAINTING AND FORGERY DETECTION ON IMAGES USING DEEP LEARNING TECHNIQUES
    Revati Natu, Ruta Mangalampalli, Sanaya Parmar, Sujata Pathak, Sonali Patil
    Iet Conference Proceedings, 2026
    The need to identify altered or phony photos is greater than ever due to the increasing strength and accessibility of image editing and alteration tools, particularly in domains such as digital forensics, media verification, and image repair. This study explores a method that brings together two different techniques: one that modifies parts of an image (using a process known as Telea- based inpainting), and another that identifies forgeries through a machine learning approach called DCGAN. The inpainting tool helps simulate how real image tampering might happen by reconstructing damaged or manipulated areas in a realistic way. Next, the detection system is trained to recognize small inconsistencies in texture and structure, learning to tell the difference between real and fake by comparing them. After training on a dataset of 6,000 images over 50 learning cycles, the system reached an accuracy rate of 95.52%, showing strong potential for catching image forgeries automatically and accurately.
  • Enhanced Fault Identification in Solar Panels through Binary Cascaded Convolutional Classifiers with Thermal-Visual Image Augmentation
    and Sujata P. Pathak
    International Journal of Image Graphics and Signal Processing, 2025
    Solar power stands as a pivotal renewable energy source for the twenty-first century.However, the optimal functioning of solar panels is often hindered by various faults, necessitating accurate and early defect detection to maximize energy production.Existing solar panel fault identification models encounter challenges such as low precision, difficulty in distinguishing fault types, and poor generalization due to limited and unbalanced data samples.This paper introduces a novel and effective approach, leveraging a Binary Cascaded Convolutional Classifier augmented with visual and thermal image combinations to address these limitations.The proposed model adeptly classifies five distinct types of solar panel faults, including single cell hotspots, diode hotspots, dust/ shadow hotspots, multicell hotspots, and Potential-Induced Degradation (PID) hotspots.Through image augmentation techniques like rotation, shifting, sheering, resizing, jittering, and blurring applied to visual and thermal images, inter-class feature variance is increased.Binary Cascaded Convolutional Neural Network (BCCNN) classifiers are trained using an enriched dataset, each specifically designed to differentiate between dust/ shadow hotspots and other fault categories.The adoption of a binary method significantly enhances precision, allowing for focused fault identification and classification.The proposed model surpasses existing literature in terms of precision (99.8%), accuracy (98.5%) and recall (98.4%), underscoring its effectiveness across all five fault classes.In summary, this research marks a substantial advancement in the realm of solar panel fault identification, presenting a more precise and effective fault detection methodology that has the potential to significantly enhance the maintenance and longevity of solar energy systems.
  • Enhancing Solar Panel Fault Detection: An Efficient Multidomain Feature Analysis Model with Entropy-Guided Saliency Map Segmentation
    International Journal of Intelligent Engineering and Systems, 2024
    Solar panels are an increasingly popular and sustainable means of generating electricity.However, the efficiency and longevity of solar panels may get compromised by various types of faults, including diode hotspots, dust/shadow hotspots, multicell hotspots, PID hotspots, and single cell hotspots.Detecting these faults accurately is vital for maintaining optimal efficiency.Many existing methods for fault identification fall short due to inadequate feature representation and segmentation techniques.To address these limitations, an innovative approach is proposed involving entropy-based saliency map segmentation and multidomain feature analysis model for fault detection and classification in solar panels.Proposed saliency map segmentation method extracts the most relevant regions in solar panel images, improving fault detection.The entropy-driven saliency maps fault detection technique surpasses alternative approaches such as color thresholding and channel-based thresholding for fault detection in solar panels.A comprehensive set of feature representation models, including Fourier, Wavelet, DCT, Convolutional, and Gabor transformations is employed.To further enhance the precision and effectiveness of fault identification, we incorporate an Extra Trees feature selection mechanism.Classification is done with an ensemble of classification models, including k-Nearest Neighbors (kNN), Deep Forest, Support Vector Machines (SVM), Logical Regression, and Artificial Neural Networks (ANN).Empirical evaluation of the proposed model demonstrates exceptional performance, achieving F1 score of 94% for fault classification compared to existing machine learning models.Proposed multidomain analysis model gave an accuracy of 96.9% and recall of 93.5% in fault identification.Additionally, the proposed model exhibits computational efficiency, making it suitable for real-time fault detection scenarios.
  • Analysis and Evaluation of Pre-processing Techniques for Fault Detection in Thermal Images of Solar Panels
    Sujata P. Pathak, Sonali A. Patil
    Lecture Notes in Electrical Engineering, 2023
  • Evaluation of Effect of Pre-Processing Techniques in Solar Panel Fault Detection
    Sujata P. Pathak, Sonali A. Patil
    IEEE Access, 2023
    Solar energy is a clean and renewable source of energy produced by solar panels. Solar panels deteriorate over time, resulting in generation of faults. Faults reduce the overall power generation capacity of photovoltaic (PV) plants. A variety of atmospheric and functional conditions contribute to the formation of hotspots on solar panels, indicating an increase in temperature and resulting in lower efficiency. Early detection of faults during PV module inspection and monitoring is critical for improving the efficiency, reliability, and safety of PV systems. Thermal imaging is a non-contact, non-destructive, efficient, and effective technique. With thermal image analysis, probable problem areas can be identified and fixed before actual failures or problems occur, resulting in lower costs and less human labor. In this study, the effect of pre-processing techniques on fault detection in thermal images is studied and a comparative fault detection and demarcation method is proposed. Pre-processing is one of the steps in an automated fault detection system for removing noise or artefacts from thermal images. This study investigates the impact of pre-processing techniques such as filters and histogram equalization on fault detection and demarcation accuracy. Five different types of faults, such as single cell, multicell, diode, dust/shadow, and PID hotspot are detected. For fault detection, two segmentation techniques, histogram-based color thresholding and RGB color channel-based thresholding, are applied to thermal images of solar panels. Intersection over Union (IoU) is used to determine the efficiency of fault detection and demarcation techniques. Application of filters and histogram equalization on the dataset provided increased contrast and highlighted the faulty area of the thermal image more prominently. Overall, images processed with a bilateral filter and histogram equalization performed better for fault detection and demarcation than other filters. This technique resulted in IoU values of 0.35, 0.14, 0.31, 0.54 and 0.32 for diode, dust, multicell, single cell and PID hotspots respectively.
  • Solar panel hotspot localization and fault classification using deep learning approach
    Sujata P. Pathak, Dr.Sonali Patil, Shailee Patel
    Procedia Computer Science, 2022
    There has been an exponential increase in Photovoltaic energy over the last decade. The size and the complexity of photovoltaic solar power plants are increasing, and it requires advanced and robust condition monitoring systems for ensuring their reliability. To this aim, a novel method is addressed for fault detection in photovoltaic panels through processing of thermal images of solar panels captured by a thermographic camera. In this paper, two advanced convolutional neural network models are used wherein the task of the first model is to classify the type of fault affecting the panel and the task of the second model is to identify the region of interest of the faulty panel. Proposed approach uses F1 score as a metric to compare several classification models of which the ResNet-50 transfer learning model achieves the highest score of 85.37 %. Mean Average Precision is used as an evaluation metric for object detection models wherein the highest scoring model is Faster R-CNN with a score of 67 %. This paper puts forth an approach to facilitate early identification and fault localization in Solar Panels by minimizing the amount of manual labour involved in the process.
  • Secure E-Voting System using Blockchain technology and authentication via Face recognition and Mobile OTP
    Abhishek Parmar, Sagar Gada, Trunesh Loke, Yash Jain, Sujata Pathak, Sonali Patil
    2021 12th International Conference on Computing Communication and Networking Technologies Icccnt 2021, 2021
    In the digital era where hacking and bypassing a system is easy, tampering of data is always possible leading to bad situations. Blockchain is used to store data which is near impossible to change or tamper with as it is very secure in nature. Voting as a process in any nation is an essential event and if votes get miscalculated by any external source it will be harmful. To avoid such kinds of situations and making it more comfortable blockchain technology comes in acknowledgment. This paper proposes a decentralized national e-voting system based on blockchain technology. It includes an admin panel to schedule the voting, manage candidates and declare the results. The web application will provide the users with an interface to enter their Aadhar card ID (text input) and a photo of themselves at the time of voting. The eligibility of the voter will be checked at the time they enter their Aadhar card ID. Eligible voter's phone numbers will be verified via One Time Password (OTP). After voter verification, individual voters will be considered eligible for voting. During voting, voters will be monitored through a webcam/front camera. The votes will be stored in a blockchain and any tampering would be detected easily. The address and the corresponding constituency will be checked in the backend. Voting results will be declared on a specified date and will be handled by the admin. The results will be displayed graphically with various options to choose from and will also include past results and statistics.
  • Threat Modeling for Breaking of CAPTCHA System
    Divya Suvarna, Sujata Pathak
    Advances in Intelligent Systems and Computing, 2020
  • Secured Vehicle Toll Payment System Using NFC
    Rugnesh Rameshram Kanojia, Sujata Pathak
    Proceedings 2018 4th International Conference on Computing Communication Control and Automation Iccubea 2018, 2018
    Nowadays, uses for NFC technology have been emerging day by day, the best application of NFC technology is in the contactless payment system. Similarly, due to various advantages of web application such as ease of maintenance and various user-friendly released version, the demand for new web applications supporting distinctive kinds of gadgets and intentions are persistently. Now different technologies such as Bluetooth, NFC, and BLE are being used for initiating the online payment. Considering the parameters such as cost, more reliability, and increased security, NFC technology is a best-fitted option for initiating the online vehicle toll payment system. Thus, the application of Cloud-based web application along with different IoT devices like Smartphone (having NFC feature) and NFC tag (ISO/IEC 14443) is explained in this paper. Paper the online vehicle toll payment system developed by using NFC technology is used for triggering the vehicle toll payment system supported by the web application.
  • HTML Voice
    Hashmeet Chadha, Satyam Mhatre, Unnati Ganatra, Sujata Pathak
    Proceedings 2018 4th International Conference on Computing Communication Control and Automation Iccubea 2018, 2018
    Creating web pages is a tiresome job for experts as well as new users. In this project web pages are developed using voice commands. Voice command input from the user is converted into text commands using available speech-to-text API. Using Natural Language Processing, knowledge is extracted from these text commands and web pages are generated using intelligent system support. The proposed hardware and software for the project will be a microphone as an input device, Python programming language, voice recognition API and other required libraries for webpage development. The user is thus relieved from worrying about writing the code and can instantly build desired web pages. This voice-driven system thus saves users' time to design and build web pages.
  • Recognizing emotions from speech
    Sujata Pathak, Arun Kulkarni
    Icect 2011 2011 3rd International Conference on Electronics Computer Technology, 2011

RECENT SCHOLAR PUBLICATIONS

  • Inpainting and forgery detection on images using deep learning techniques
    R Natu, R Mangalampalli, S Parmar, S Pathak, S Patil
    IET Conference Proceedings CP967 2025 (43), 437-442 , 2025
    2025
  • Enhanced Fault Identification in Solar Panels through Binary Cascaded Convolutional Classifiers with Thermal-Visual Image Augmentation
    SAP Sujata P. Pathak
    International Journal of Image, Graphics and Signal Processing(IJIGSP), 17 … , 2025
    2025
  • Enhancing Solar Panel Fault Detection: An Efficient Multidomain Feature Analysis Model with Entropy-Guided Saliency Map Segmentation.
    SP Pathak, SA Patil, D Mishra
    International Journal of Intelligent Engineering & Systems 17 (4) , 2024
    2024
    Citations: 2
  • Evaluation of effect of pre-processing techniques in solar panel fault detection
    SP Pathak, SA Patil
    IEEE Access 11, 72848-72860 , 2023
    2023
    Citations: 34
  • Analysis and Evaluation of Pre-processing Techniques for Fault Detection in Thermal Images of Solar Panels
    SP Pathak, SA Patil
    Emerging Research in Computing, Information, Communication and Applications … , 2022
    2022
    Citations: 2
  • Applied Intelligence for Mental Health Detection: ManoVaidya–A Mental Health Therapist
    KP Desai, MA Shah, MC Lapasia, SA Patil, SP Pathak
    Handbook of Research on Applied Intelligence for Health and Clinical … , 2022
    2022
    Citations: 3
  • Solar panel hotspot localization and fault classification using deep learning approach
    SP Pathak, S Patil, S Patel
    Procedia Computer Science 204, 698-705 , 2022
    2022
    Citations: 55
  • Secure E-Voting System using Blockchain technology and authentication via Face recognition and Mobile OTP
    A Parmar, S Gada, T Loke, Y Jain, S Pathak, S Patil
    2021 12th International Conference on Computing Communication and Networking … , 2021
    2021
    Citations: 24
  • of CAPTCHA System
    D Suvarna, S Pathak
    Intelligent Computing, Information and Control Systems: ICICCS 2019, 94 , 2019
    2019
  • Threat Modeling for Breaking of CAPTCHA System
    D Suvarna, S Pathak
    International Conference on Intelligent Computing, Information and Control … , 2019
    2019
    Citations: 3
  • Automated Fire Evacuation System with Congestion Control
    S Pathak, S Parikh, A Bhat, AS Chabada, A Ganesh
    2nd International Conference on Advances in Science & Technology (ICAST) , 2019
    2019
    Citations: 3
  • Farmer awareness and cost estimation
    S Pathak, D Shah, N Shah, V Shah, S Ughade
    2nd International Conference on Advances in Science & Technology (ICAST) , 2019
    2019
    Citations: 1
  • Html voice
    H Chadha, S Mhatre, U Ganatra, S Pathak
    2018 Fourth International Conference on Computing Communication Control and … , 2018
    2018
    Citations: 8
  • Secured Vehicle Toll Payment System using NFC
    PSP Rugnesh Rameshram Kanojia
    Fourth International Conference on Computing Communication Control and … , 2018
    2018
    Citations: 3
  • Hybrid cryptosystem for secure data storage
    M Shah, S Pathak
    Int. J. Innov. Res. Inf. Secur 4 (11), 1-4 , 2017
    2017
    Citations: 4
  • Privilege Identity Management- Cyberark
    PS Prof. Sujata Pathak
    International Journal of Technical Research and Applications 4 (3) , 2016
    2016
  • Location Tracking with Safe Paths and Safe Zones in Android
    MMB Prof. Sujata Pathak
    International Journal on Recent and Innovation Trends in Computing and … , 2016
    2016
  • Automatic Evaluation System for Student Code
    SP Prof Sujata Pathak, Pratik Saraf, Shankar Ramesh
    International Journal of Computer Science and Information Technologies 6 , 2015
    2015
    Citations: 4
  • Recognizing emotions from speech
    S Pathak, A Kulkarni
    2011 3rd International Conference on Electronics Computer Technology 4, 107-109 , 2011
    2011
    Citations: 22
  • Multimodal approaches for emotional features in speech: A survey
    PSP Prof. Arun Kulkarni
    National, 155-160 , 2009
    2009

MOST CITED SCHOLAR PUBLICATIONS

  • Solar panel hotspot localization and fault classification using deep learning approach
    SP Pathak, S Patil, S Patel
    Procedia Computer Science 204, 698-705 , 2022
    2022
    Citations: 55
  • Evaluation of effect of pre-processing techniques in solar panel fault detection
    SP Pathak, SA Patil
    IEEE Access 11, 72848-72860 , 2023
    2023
    Citations: 34
  • Secure E-Voting System using Blockchain technology and authentication via Face recognition and Mobile OTP
    A Parmar, S Gada, T Loke, Y Jain, S Pathak, S Patil
    2021 12th International Conference on Computing Communication and Networking … , 2021
    2021
    Citations: 24
  • Recognizing emotions from speech
    S Pathak, A Kulkarni
    2011 3rd International Conference on Electronics Computer Technology 4, 107-109 , 2011
    2011
    Citations: 22
  • Html voice
    H Chadha, S Mhatre, U Ganatra, S Pathak
    2018 Fourth International Conference on Computing Communication Control and … , 2018
    2018
    Citations: 8
  • Hybrid cryptosystem for secure data storage
    M Shah, S Pathak
    Int. J. Innov. Res. Inf. Secur 4 (11), 1-4 , 2017
    2017
    Citations: 4
  • Automatic Evaluation System for Student Code
    SP Prof Sujata Pathak, Pratik Saraf, Shankar Ramesh
    International Journal of Computer Science and Information Technologies 6 , 2015
    2015
    Citations: 4
  • Applied Intelligence for Mental Health Detection: ManoVaidya–A Mental Health Therapist
    KP Desai, MA Shah, MC Lapasia, SA Patil, SP Pathak
    Handbook of Research on Applied Intelligence for Health and Clinical … , 2022
    2022
    Citations: 3
  • Threat Modeling for Breaking of CAPTCHA System
    D Suvarna, S Pathak
    International Conference on Intelligent Computing, Information and Control … , 2019
    2019
    Citations: 3
  • Automated Fire Evacuation System with Congestion Control
    S Pathak, S Parikh, A Bhat, AS Chabada, A Ganesh
    2nd International Conference on Advances in Science & Technology (ICAST) , 2019
    2019
    Citations: 3
  • Secured Vehicle Toll Payment System using NFC
    PSP Rugnesh Rameshram Kanojia
    Fourth International Conference on Computing Communication Control and … , 2018
    2018
    Citations: 3
  • Enhancing Solar Panel Fault Detection: An Efficient Multidomain Feature Analysis Model with Entropy-Guided Saliency Map Segmentation.
    SP Pathak, SA Patil, D Mishra
    International Journal of Intelligent Engineering & Systems 17 (4) , 2024
    2024
    Citations: 2
  • Analysis and Evaluation of Pre-processing Techniques for Fault Detection in Thermal Images of Solar Panels
    SP Pathak, SA Patil
    Emerging Research in Computing, Information, Communication and Applications … , 2022
    2022
    Citations: 2
  • Farmer awareness and cost estimation
    S Pathak, D Shah, N Shah, V Shah, S Ughade
    2nd International Conference on Advances in Science & Technology (ICAST) , 2019
    2019
    Citations: 1
  • Inpainting and forgery detection on images using deep learning techniques
    R Natu, R Mangalampalli, S Parmar, S Pathak, S Patil
    IET Conference Proceedings CP967 2025 (43), 437-442 , 2025
    2025
  • Enhanced Fault Identification in Solar Panels through Binary Cascaded Convolutional Classifiers with Thermal-Visual Image Augmentation
    SAP Sujata P. Pathak
    International Journal of Image, Graphics and Signal Processing(IJIGSP), 17 … , 2025
    2025
  • of CAPTCHA System
    D Suvarna, S Pathak
    Intelligent Computing, Information and Control Systems: ICICCS 2019, 94 , 2019
    2019
  • Privilege Identity Management- Cyberark
    PS Prof. Sujata Pathak
    International Journal of Technical Research and Applications 4 (3) , 2016
    2016
  • Location Tracking with Safe Paths and Safe Zones in Android
    MMB Prof. Sujata Pathak
    International Journal on Recent and Innovation Trends in Computing and … , 2016
    2016
  • Multimodal approaches for emotional features in speech: A survey
    PSP Prof. Arun Kulkarni
    National, 155-160 , 2009
    2009