Access to this thesis is limited to Boise State University students and employees or persons using Boise State University facilities.
Off-campus Boise State University users: To download Boise State University access-only theses/dissertations, please select the "Off-Campus Download" button and enter your Boise State username and password when prompted.
Publication Date
12-2021
Date of Final Oral Examination (Defense)
7-2-2021
Type of Culminating Activity
Thesis - Boise State University Access Only
Degree Title
Master of Science in Electrical and Computer Engineering
Department
Electrical and Computer Engineering
Supervisory Committee Chair
Sin Ming Loo, Ph.D.
Supervisory Committee Member
Liljana Babinkostova, Ph.D.
Supervisory Committee Member
Charmaine C. Sample, Ph.D.
Abstract
As technology evolves, we need better tools to secure our sensitive data on our smartphones. The common method is two factor authentication. This thesis offers a unique biometric authentication method. This authentication method was utilized by solving a simple maze. It is based on the idea that abnormal hand gestures could be flagged as a security threat. The maze is just a simple tool designed to limit the user's hand movements and compare it against the same user's machine learning model. The maze captures the uniqueness of writing - graphology. This thesis shows two different maze configurations. Maze A is wider and each participant solves the maze three time periods throughout the day (i.e., morning, afternoon, night). Maze B is narrower and each participant solved the maze within one sitting. The data collected by this thesis shows 93:66% model prediction accuracy for maze A, and 94% model prediction accuracy on maze B.
DOI
https://doi.org/10.18122/td/1885/boisestate
Recommended Citation
Kesem, Liron, "AI Hand Pattern Authentication Method" (2021). Boise State University Theses and Dissertations. 1885.
https://doi.org/10.18122/td/1885/boisestate