Predicting Sex and Age Using Swipe-Gesture Data from a Mobile Device
dc.access.option | Open Access | |
dc.contributor.advisor | Tabrizi, Nasseh | |
dc.contributor.author | Davis, Storm Pierce | |
dc.contributor.department | Computer Science | |
dc.date.accessioned | 2022-07-19T14:40:13Z | |
dc.date.available | 2022-07-19T14:40:13Z | |
dc.date.created | 2020-05 | |
dc.date.issued | 2022-05-09 | |
dc.date.submitted | May 2020 | |
dc.date.updated | 2022-07-12T14:47:29Z | |
dc.degree.department | Computer Science | |
dc.degree.discipline | Computer Science | |
dc.degree.grantor | East Carolina University | |
dc.degree.level | Undergraduate | |
dc.degree.name | BS | |
dc.description.abstract | Swipe-gestures are by far the most common way to interact with mobile devices such as phones, tablets, and even some computers. As touch-screen technology has improved, the possibility of obtaining high-quality swipe-gesture data from touch-screen devices has become more and more prevalent. This has led to the exploration of its use in further improving authentication systems, and more recently, as the basis for soft biometrics prediction. This paper discusses the process of using swipe-gesture data for prediction of sex and age of individuals using mobile devices. The software used to obtain the data is presented, the features collected from the swipe data are detailed, and the machine learning classifiers are displayed in a way that the experiment can be replicated. During this experiment, a total of ten well-known classifiers have been used. The results of this analysis have further confirmed the possibility of predicting sex, obtaining an accuracy rate of 79% for a single classifier as well as a group average of almost 70%. Moreover, in the prediction of age category, the results are even more encouraging, obtaining an accuracy rate of nearly 80% on average as well as several of the classifiers performing well above the average. | |
dc.format.mimetype | application/pdf | |
dc.identifier.uri | http://hdl.handle.net/10342/10825 | |
dc.publisher | East Carolina University | |
dc.subject | soft-biometrics | |
dc.subject | swipe-gestures | |
dc.subject | machine learning | |
dc.subject | mobile device | |
dc.title | Predicting Sex and Age Using Swipe-Gesture Data from a Mobile Device | |
dc.type | Honors Thesis | |
dc.type.material | text |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- DAVIS-HONORSTHESIS-2020.pdf
- Size:
- 527.56 KB
- Format:
- Adobe Portable Document Format