About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Broadband Communications, Networks, and Systems. 14th EAI International Conference, BROADNETS 2024, Hyderabad, India, February 16–17, 2024, Proceedings, Part I

Research Article

IoT-Based Classification of COVID-19 Cases with Cardiovascular Disease Using Deep Convolutional Decision Trees

Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-031-81168-5_19,
        author={R. Amudha and M. S. Kavitha and S. Karthik and Balakrishnan Biju},
        title={IoT-Based Classification of COVID-19 Cases with Cardiovascular Disease Using Deep Convolutional Decision Trees},
        proceedings={Broadband Communications, Networks, and Systems. 14th EAI International Conference, BROADNETS 2024, Hyderabad, India, February 16--17, 2024, Proceedings, Part I},
        proceedings_a={BROADNETS},
        year={2025},
        month={2},
        keywords={IoT COVID-19 cardiovascular disease deep learning convolutional decision trees},
        doi={10.1007/978-3-031-81168-5_19}
    }
    
  • R. Amudha
    M. S. Kavitha
    S. Karthik
    Balakrishnan Biju
    Year: 2025
    IoT-Based Classification of COVID-19 Cases with Cardiovascular Disease Using Deep Convolutional Decision Trees
    BROADNETS
    Springer
    DOI: 10.1007/978-3-031-81168-5_19
R. Amudha1,*, M. S. Kavitha2, S. Karthik2, Balakrishnan Biju3
  • 1: Department of Information Technology, Hindusthan College of Engineering and Technology, Coimbatore
  • 2: Department of Computer Science and Engineering, SNS College of Technology, Coimbatore
  • 3: Department of Computer Science and Engineering, Chennai Institute of Technology, Kundrathur
*Contact email: amudha.ramamoorthy@gmail.com

Abstract

The COVID-19 has underscored the need for advanced healthcare solutions. This research addresses the intersection of COVID-19 and cardiovascular disease (CVD) through the lens of Internet of Things (IoT) and deep learning. Patients with pre- existing cardiovascular conditions face elevated risks when infected with COVID-19. Current diagnostic methods often lack the precision required to identify specific health risks in this vulnerable population. This research aims to bridge this gap by developing a sophisticated model that combines IoT data and deep learning techniques for robust classification of COVID-19 cases with concurrent cardiovascular disease. While existing studies explore either COVID-19 classification or the relationship with cardiovascular conditions separately, there is a noticeable research gap in the integration of IoT and deep convolutional decision trees for a comprehensive analysis. This study fills this void by proposing a novel approach that harnesses the potential of both technologies to improve diagnostic accuracy. With the aim of enhancing classification accuracy, we propose an IoT-based framework that leverages deep convolutional decision trees. Our methodology involves the collection of diverse IoT data streams, including vital signs and patient activity, to create a comprehensive dataset. Deep convolutional decision trees are then employed to extract intricate patterns and relationships from the data. The model is trained on a well-curated dataset, optimizing its ability to accurately classify COVID-19 cases in individuals with pre-existing cardiovascular conditions. The results demonstrate a significant improvement in classification accuracy compared to traditional methods. The model exhibits enhanced sensitivity and specificity, showcasing its potential for early and precise identification of COVID-19 cases in individuals with cardiovascular disease.

Keywords
IoT COVID-19 cardiovascular disease deep learning convolutional decision trees
Published
2025-02-07
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-031-81168-5_19
Copyright © 2024–2025 ICST
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL