Result: Machine Learning-Based Multimodal Biometric Authentication System (Facial and Fingerprint Recognition) for Online Voting Systems.

Online voting systems offer many advantages over traditional voting methods, such as paper ballots, this is because paper ballots face some well-known challenges, ranging from logistics, susceptibility to tampering, and the requirement for voters to be physically present at polling stations. In contrast, online voting systems offer the potential to overcome these challenges by providing a convenient and accessible means for citizens to cast their votes from anywhere. However, online voting systems must address significant security and authentication challenges to ensure that each vote is cast by a legitimate and unique voter, maintaining the integrity of the electoral process. This project proposes the development of a machine learning authentication module that can be integrated into an online voting system using facial recognition and fingerprint recognition to enhance the security of online voting. The system therefore consists of two main components; the machine learning-based authentication component and the web-based voting platform. The authentication component uses machine learning algorithms to accurately and reliably verify the identities of voters based on their biometric data. The web-based platform facilitates voter registration, authentication, and voting processes, ensuring a seamless and secure user experience. These two components were implemented first by obtaining a comprehensive database of user biometric data, training the machine learning module, and implementing a user-friendly web interface using Java Server Pages (JSP) and a MySQL database. The system's performance was evaluated using established metrics, including accuracy, precision, recall, and R2 Score with the following values 98%, 1.0, 0.8 and 0.78 respectively. [ABSTRACT FROM AUTHOR]

Copyright of ABUAD Journal of Engineering Research & Development is the property of Afe Babalola University, College of Engineering and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)