| Title |
Child, Daniel_MCS_2023 |
| Alternative Title |
Comparing Classifiers vs Clustering Algorithms on an Audio Gait Dataset |
| Creator |
Child, Daniel |
| Collection Name |
Master of Computer Science |
| Description |
The following masters of computer science thesis explores the use of machine learning to identify individuals based upon their gait. |
| Abstract |
Researchers have explored different methods for the identification of persons by the sound generated when they walk (i.e., gait). Using machine learning they can train a system to identify individuals. In buildings where only authorized personnel are allowed a system like this could provide an additional layer of authentication. In this thesis, audio was captured by participants walking past a series of microphones to capture their gait. The Fast Fourier Transform algorithm was used to process the data into a form usable by machine learning algorithms. A comparison is made between classification and clustering algorithms, and several machine learning algorithms are tested in each category. Also mentioned are three methods for feature elimination and their impact on performance. Lastly, tests are conducted to see how including a backpack can alter the results, which tests the ability for the algorithms to generalize under normal human behavioral changes. |
| Subject |
Algorithms; Computer programming; Machine learning; Computer science |
| Keywords |
gait; machine learning; classification; cluster; unsupervised; python; raspberry pi; Fourier; fast fourier transform |
| Digital Publisher |
Stewart Library, Weber State University, Ogden, Utah, United States of America |
| Date |
2023 |
| Medium |
Thesis |
| Type |
Text |
| Access Extent |
49 page PDF; 2.6 MB |
| Language |
eng |
| Rights |
The author has granted Weber State University Archives a limited, non-exclusive, royalty-free license to reproduce their theses, in whole or in part, in electronic or paper form and to make it available to the general public at no charge. The author retains all other rights. |
| Source |
University Archives Electronic Records: Master of Computer Science. Stewart Library, Weber State University |
| Format |
application/pdf |
| ARK |
ark:/87278/s6mbp3mx |
| Setname |
wsu_smt |
| ID |
96897 |
| Reference URL |
https://digital.weber.edu/ark:/87278/s6mbp3mx |
