Thesis
Unlocking Identity: Robust Individual Identification through Electrocardiogram Analysis
Washington State University
Master of Science (MS), Washington State University
05/2024
DOI:
https://doi.org/10.7273/000006964
Abstract
In an era characterized by escalating cybersecurity threats and growing concerns over data privacy, the quest for robust and secure methods of individual identification has become paramount. Biometric authentication, leveraging distinctive physiological or behavioral traits, has emerged as a promising solution, offering enhanced security and user convenience compared to traditional authentication methods like passwords and PINs. However, conventional biometric modalities are not immune to vulnerabilities, with concerns ranging from theft to replication of biometric data. In this context, Electrocardiogram (ECG) signals capture the heart's electrical activity to establish unique patterns for individual identification. Unlike static biometrics, ECG offers continuous data, enabling dynamic authentication and anomaly detection, thereby fortifying security measures. The non-invasive nature of ECG data collection, often facilitated by wearables or contactless sensors, further enhances user comfort and privacy. This paper proposes a novel approach to person identification using ECG data, leveraging deep learning techniques to exploit the distinctive features of heartbeat patterns for reliable identification. Through a series of experiments, we demonstrate the effectiveness of our methodology.
Metrics
1 File views/ downloads
14 Record Views
Details
- Title
- Unlocking Identity
- Creators
- Diwas Pandey
- Contributors
- Scott Wallace (Chair)Xinghui Zhao (Committee Member)Anna Wisniewska (Committee Member)
- Awarding Institution
- Washington State University
- Academic Unit
- School of Engineering and Computer Science (VANC)
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University
- Number of pages
- 85
- Identifiers
- 99901125140701842
- Language
- English
- Resource Type
- Thesis