Lynette

@djsce.ac.in

Assistant Professor Computer Department
Dwarkadas J. Sanghvi College of Engineering

Lynette


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

RESEARCH INTERESTS

NLP
CV
Data Mining
12

Scopus Publications

142

Scholar Citations

6

Scholar h-index

3

Scholar i10-index

Scopus Publications

  • Exercise Video Analysis for Health Monitoring
    Divyam Dedhia, Tanay Parikh, Dev Patel, Aayush Bhagat, Lynette D’mello
    Iet Conference Proceedings, 2026
    Our paper explores the development of machine learning techniques for a fitness solution utilizing computer vision and deep learning. The solution addresses two main goals: real-time exercise tracking and also pose classification. The paper discusses the increasing need for real-time fitness applications that actively guide and evaluate users, and the issues individuals face in consistently tracking their health. The developed system uses pose estimation and classification to evaluate exercise form and count repetitions. This paper includes an evaluation of various models for exercise classification using pose estimation.
  • Exception handling in distributed systems
    Pranav Desai, Apoorva Ambulgekar, Rishi Parekh, Lynette Dmello
    Aip Conference Proceedings, 2025
  • Getaway Guide—ML Powered Travel Itinerary Curation
    Medha Shah, Tanay Dave, Devarshee Thopte, Lynette Dmello
    Lecture Notes in Networks and Systems, 2025
  • Enhancing Scholarship Opportunities: A Multi-label Classification Approach
    Vaishnavi Padiya, Vidit Gala, Shubham Mehta, Pratham Shah, Lynette DMello
    Lecture Notes in Networks and Systems, 2025
  • Track Learning Agent Using Multi-objective Reinforcement Learning
    Rushabh Shah, Vidhi Ruparel, Mukul Prabhu, Lynette D’mello
    Lecture Notes in Networks and Systems, 2024
  • Flowchart Generation and Mind Map Creation using Extracted Summarized Text
    Aditya Kulkarni, Hetansh Shah, Lynette D’Mello, Krish Shah
    International Conference on Recent Advances in Science and Engineering Technology Icraset 2023, 2023
    The technology discussed in this research study aims to transform text into a variety of visual representations, including mind maps, flowcharts, and summaries. The research underlines the usefulness of graphical representations and summaries for greater retention, starting with the challenges of remembering and digesting information from numerous sources. The project uses machine learning and deep learning algorithms to extract text from user-provided images or PDFs and transform it into mind maps or flowcharts based on user preferences. The capability of this research spans both the business and academic areas, allowing for the concise summarization of lengthy, complex documents. An overview of the literature on text extraction, summarization, and conversion techniques is given in the article. These techniques covered include OCR, network text analysis, deep learning-based summarization, keyword extraction, and data flow diagrams. The suggested method involves extracting text using OCR, summarising text using the T5 transformer model, creating flowcharts based on phrase relationships, and creating mind maps using NLTK and NetworkX modules. The conclusion of the study discusses the advantages and implementation specifics of each technique. The project offers a powerful way for converting text into visual representations in both academic and professional contexts, encouraging better comprehension, information retention, and improved learning and problem-solving skills.
  • Stock Market Graph Prediction using LSTM
    Raj Gandhi, Guransh Anand, Varun Vekaria, Tarasha Ahuja, Lynette D’Mello
    2023 14th International Conference on Computing Communication and Networking Technologies Icccnt 2023, 2023
    There has been a rapid growth in the number of traders and investors in the stock market. A lot of them are beginners and young adults with little to no knowledge about the stock market. So it is essential to help these people out to minimise their losses and increase their profits while investing. A predicted graph of a particular stock in the stock market can help them do so. This paper focuses on the machine learning algorithm: Long Short-Term Memory to predict the graphs of a particular stock. The data is fetched from Yahoo Finance to get accurate results from the historic data. The website that has been made is very accessible for all kinds of users. It provides them with a simple input field to enter the stock to generate the predicted graph of the stock they wish to look for. It also shows the users if a stock is bullish (prices will rise) or bearish (prices will fall) for the particular week and month for their better understanding. The website also features a news section which highlights news and information related to the stock market and also the factors that affect the trends in the stock market.
  • Towards a Multi-Modular Decentralized System for Dealing with EHR Data
    Jay Mehta, Rishi Desai, Jash Mehta, Deep Gandhi, Lynette D'Mello
    8th International Conference on Advanced Computing and Communication Systems Icaccs 2022, 2022
    With the rise of “big data”, finding computationally efficient and privacy-preserving solutions for large-scale machine learning problems has gained paramount importance, especially in the case of medical data which is collected in huge volumes by modern healthcare systems. Since a large amount of data resides in different locations and owned by different entities, accessing sufficient data while keeping ethical, legal, economic, and technical challenges related to privacy in mind, precludes the medical data from being fully exploited by ML. Thus, to counter these challenges, we propose a novel blockchain-based Federated Learning architecture for healthcare consortia, which provides a solution to the current problems while highlighting the challenges and considerations that need to be addressed. The authors suggest a multi-modular system that can be broken down into three main modules - decentralized medical history module, differentially private institutional analytics module, and Federated Learning based patient prognosis. We conduct extensive experimentation using Logistic Regression and TabNet and receive an accuracy of 83.82 under IID settings with a client fraction of 10%. Further, we show that TabNet outperforms Logistic Regression under conditions of showing less data.
  • Emulation of Intel's 8086 Microprocessor using Rust and Web Assembly
    Yashodhan Joshi, Yatharth Vyas, Tejas Ghone, Vatsal Soni, Lynette D'Mello
    2022 3rd International Conference for Emerging Technology Incet 2022, 2022
    The existing Intel’s 8086 microprocessor emulators are hampered by significant short falling that includes : The existing emulator software does not support operating systems such Linux and mac OS. Students could not use the emulator on devices other than desktops since the emulator required was bundled as an installer file for Windows. The emulator required several disparate windows to read the execution of programs along with values of registers, flags, and memory, thus hampering the overall user experience. The 8086 Emulator with Rust and WASM improves upon these issues by providing a web platform with a simple and adjustable interface compatible across various screen sizes and operating systems and a command-line platform for the accustomed programmers and SSH command line users. In a world where many devices support web browsers, a web version makes it very convenient for the global user base, especially when it performs without sacrificing speed or correctness; allowing students to test and run their programs on any device, at any place, as long as they have a web browser.
  • A Federated Approach to Predicting Emojis in Hindi Tweets
    Deep Gandhi, Jash Mehta, Nirali Parekh, Karan Waghela, Lynette D’Mello, Zeerak Talat
    Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing Emnlp 2022, 2022
    The use of emojis affords a visual modality to, often private, textual communication.The task of predicting emojis however provides a challenge for machine learning as emoji use tends to cluster into the frequently used and the rarely used emojis.Much of the machine learning research on emoji use has focused on high resource languages and has conceptualised the task of predicting emojis around traditional server-side machine learning approaches.However, traditional machine learning approaches for private communication can introduce privacy concerns, as these approaches require all data to be transmitted to a central storage.In this paper, we seek to address the dual concerns of emphasising high resource languages for emoji prediction and risking the privacy of people’s data.We introduce a new dataset of 118k tweets (augmented from 25k unique tweets) for emoji prediction in Hindi, and propose a modification to the federated learning algorithm, CausalFedGSD, which aims to strike a balance between model performance and user privacy. We show that our approach obtains comparative scores with more complex centralised models while reducing the amount of data required to optimise the models and minimising risks to user privacy.
  • ChaDRaL: RGB Image Encryption based on 3D Chaotic Map, DNA, RSA and LSB
    Nirali Parekh, Lynette D'Mello
    Proceedings 2021 1st IEEE International Conference on Artificial Intelligence and Machine Vision Aimv 2021, 2021
  • Using Universal Sentence Encoder for Semantic Search of Employee Data
    Divyam Sheth, Ankit Rishi Gupta, Lynette D'Mello
    2021 International Conference on Computational Intelligence and Computing Applications Iccica 2021, 2021

RECENT SCHOLAR PUBLICATIONS

  • Exercise video analysis for health monitoring
    D Dedhia, T Parikh, D Patel, A Bhagat, L D’mello
    IET Conference Proceedings CP967 2025 (43), 211-218 , 2025
    2025
  • Exception handling in distributed systems
    P Desai, A Ambulgekar, R Parekh, L Dmello
    AIP Conference Proceedings 3162 (1), 020084 , 2025
    2025
  • Enhancing Stock Price Prediction: Improvising in KNN
    P Bari, L D'mello, M Daftary, P Shah, H Patel, A Bhatt
    International Journal of Communication Networks and Information Security 16 … , 2024
    2024
  • Enhancing Scholarship Opportunities: A Multi-label Classification Approach
    V Padiya, V Gala, S Mehta, P Shah, L DMello
    International Conference on Artificial Intelligence on Textile and Apparel … , 2024
    2024
  • Getaway Guide—ML Powered Travel Itinerary Curation
    M Shah, T Dave, D Thopte, L Dmello
    International Conference on Artificial Intelligence on Textile and Apparel … , 2024
    2024
  • Flowchart generation and mind map creation using extracted summarized text
    A Kulkarni, H Shah, L D’Mello, K Shah
    2023 International Conference on Recent Advances in Science and Engineering … , 2023
    2023
    Citations: 7
  • Track Learning Agent Using Multi-objective Reinforcement Learning
    R Shah, V Ruparel, M Prabhu, L D’mello
    Congress on Intelligent Systems, 27-40 , 2023
    2023
  • Stock Market Graph Prediction using LSTM
    R Gandhi, G Anand, V Vekaria, T Ahuja, L D’mello
    2023 14th International Conference on Computing Communication and Networking … , 2023
    2023
    Citations: 1
  • Screen-Time Data Analysis
    P Mehta, P Shah, R Lakhani, N Pocha, L D’mello
    2022
  • A federated approach to predicting emojis in Hindi tweets
    D Gandhi, J Mehta, N Parekh, K Waghela, L D’Mello, Z Talat
    Proceedings of the 2022 Conference on Empirical Methods in Natural Language … , 2022
    2022
    Citations: 8
  • A Federated Approach to Predicting Emojis in Hindi Tweets
    ZT Deep Gandhi*1 , Jash Mehta*2 , Nirali Parekh3 , Karan Waghela4 , Lynette ...
    Proceedings of the 2022 Conference on Empirical Methods in Natural Language … , 2022
    2022
  • Emulation of Intel’s 8086 Microprocessor using Rust and Web Assembly
    Y Joshi, Y Vyas, T Ghone, V Soni, L D’Mello
    2022 3rd International Conference for Emerging Technology (INCET), 1-8 , 2022
    2022
    Citations: 2
  • A novel dual model approach for categorization of unbalanced skin lesion image classes
    S Dedhia, S Trivedi, S Salvi, J Jani, L D’mello
    Computational Vision and Bio-Inspired Computing: Proceedings of ICCVBIC 2021 … , 2022
    2022
    Citations: 2
  • Towards a multi-modular decentralized system for dealing with EHR data
    J Mehta, R Desai, J Mehta, D Gandhi, L D'Mello
    2022 8th International Conference on Advanced Computing and Communication … , 2022
    2022
    Citations: 5
  • Using universal sentence encoder for semantic search of employee data
    D Sheth, AR Gupta, L D’Mello
    2021 International Conference on Computational Intelligence and Computing … , 2021
    2021
    Citations: 5
  • ChaDRaL: RGB Image Encryption based on 3D Chaotic Map, DNA, RSA and LSB
    N Parekh, L D’Mello
    2021 International Conference on Artificial Intelligence and Machine Vision … , 2021
    2021
    Citations: 4
  • Visual and Auditory Assistant for people with various cognitive impairments
    H Gala, J Hirpara, M Shah, J Shah, L D'Mello
    2021 International Conference on Innovative Computing, Intelligent … , 2021
    2021
  • SpecGrav--Detection of Gravitational Waves using Deep Learning
    H Dodia, H Tandel, L D'Mello
    arXiv preprint arXiv:2107.03607 , 2021
    2021
  • Airline Delay Prediction using Machine Learning and Deep Learning Techniques
    LDM Devansh Shah, Ayushi Lodaria, Danish Jain
    International Journal of Recent Technology and Engineering (IJRTE) 9 (2 … , 2020
    2020
    Citations: 7
  • Attribute Reduction for Medical Data Analysis Using Rough Set Theory
    P Bhavsar, P Jhunjhunwala, L D’Mello
    Advanced Computing Technologies and Applications, 325-335 , 2020
    2020
    Citations: 3

MOST CITED SCHOLAR PUBLICATIONS

  • Use of ID3 decision tree algorithm for placement prediction
    H Bhatt, S Mehta, LR D'mello
    Int J Comput Sci Inform Technol 6 (5), 4785-9 , 2015
    2015
    Citations: 42
  • A comparative study of different data mining algorithms
    S Bavisi, J Mehta, L Lopes
    International Journal of Current Engineering and Technology 4 (5), 3248-3252 , 2014
    2014
    Citations: 23
  • Density based clustering algorithms
    LD Harsh shah,Karan Napanda
    international journal of computer science and engineering 3 (11), 54-57 , 2015
    2015
    Citations: 14
  • A federated approach to predicting emojis in Hindi tweets
    D Gandhi, J Mehta, N Parekh, K Waghela, L D’Mello, Z Talat
    Proceedings of the 2022 Conference on Empirical Methods in Natural Language … , 2022
    2022
    Citations: 8
  • Flowchart generation and mind map creation using extracted summarized text
    A Kulkarni, H Shah, L D’Mello, K Shah
    2023 International Conference on Recent Advances in Science and Engineering … , 2023
    2023
    Citations: 7
  • Airline Delay Prediction using Machine Learning and Deep Learning Techniques
    LDM Devansh Shah, Ayushi Lodaria, Danish Jain
    International Journal of Recent Technology and Engineering (IJRTE) 9 (2 … , 2020
    2020
    Citations: 7
  • Advanced computing technologies and applications
    M Mhapsekar, P Mhapsekar, A Mhatre, V Sawant
    Springer , 2020
    2020
    Citations: 6
  • Towards a multi-modular decentralized system for dealing with EHR data
    J Mehta, R Desai, J Mehta, D Gandhi, L D'Mello
    2022 8th International Conference on Advanced Computing and Communication … , 2022
    2022
    Citations: 5
  • Using universal sentence encoder for semantic search of employee data
    D Sheth, AR Gupta, L D’Mello
    2021 International Conference on Computational Intelligence and Computing … , 2021
    2021
    Citations: 5
  • ChaDRaL: RGB Image Encryption based on 3D Chaotic Map, DNA, RSA and LSB
    N Parekh, L D’Mello
    2021 International Conference on Artificial Intelligence and Machine Vision … , 2021
    2021
    Citations: 4
  • Cryptocurrency: The Future of Currencies?
    K Nayak, D Kotak, L D’mello
    International Journal of Computer Technology & Applications 5 (5), 1703-1706 , 2014
    2014
    Citations: 4
  • Attribute Reduction for Medical Data Analysis Using Rough Set Theory
    P Bhavsar, P Jhunjhunwala, L D’Mello
    Advanced Computing Technologies and Applications, 325-335 , 2020
    2020
    Citations: 3
  • Hybrid approach for query expansion using query log
    L Lopes, J Gadge
    Int. J. Appl. Inf. Syst 7 (6), 30-35 , 2014
    2014
    Citations: 3
  • Emulation of Intel’s 8086 Microprocessor using Rust and Web Assembly
    Y Joshi, Y Vyas, T Ghone, V Soni, L D’Mello
    2022 3rd International Conference for Emerging Technology (INCET), 1-8 , 2022
    2022
    Citations: 2
  • A novel dual model approach for categorization of unbalanced skin lesion image classes
    S Dedhia, S Trivedi, S Salvi, J Jani, L D’mello
    Computational Vision and Bio-Inspired Computing: Proceedings of ICCVBIC 2021 … , 2022
    2022
    Citations: 2
  • Movie Attendance Prediction
    K Gevaria, R Wagh, L D’Mello
    International Journal of Computer Applications 130 (3), 14-17 , 2015
    2015
    Citations: 2
  • Stock Market Graph Prediction using LSTM
    R Gandhi, G Anand, V Vekaria, T Ahuja, L D’mello
    2023 14th International Conference on Computing Communication and Networking … , 2023
    2023
    Citations: 1
  • A Study of Sequential Pattern Mining Algorithms
    M Shah, L D’mello
    IJIACS, ISSN, 2347-8616 , 2015
    2015
    Citations: 1
  • A Survey on Cross Domain Sentiment Classification Techniques
    K Ajmera, LR D'mello
    International Journal of Computer Science and Information Technologies 6 (6 … , 2015
    2015
    Citations: 1
  • Conversion of 2D Images to 3D Using Data Mining Algorithm
    Z Ganatra, R Chavda, L D’mello
    Academic Press , 2014
    2014
    Citations: 1