| Download | - View accepted manuscript: Identity verification based on haptic handwritten signature: novel fitness functions for GP framework (PDF, 297 KiB)
|
|---|
| DOI | Resolve DOI: https://doi.org/10.1109/HAVE.2013.6679618 |
|---|
| Author | Search for: Alsulaiman, Fawaz A.; Search for: Valdes, Julio J.1; Search for: El Saddik, Abdulmotaleb |
|---|
| Affiliation | - National Research Council of Canada. Information and Communication Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | 2013 IEEE International Symposium on Haptic Audio Visual Environments and Games (HAVE 2013), Oct 26-27, 2013, Istanbul, Turkey |
|---|
| Abstract | Fitness functions are the evaluation measures driving evolutionary processes towards solutions. In this paper, three fitness functions are proposed for solving the unbalanced dataset problem in Haptic-based handwritten signatures using genetic programming (GP). The use of these specifically designed fitness functions produced simpler analytical expressions than those obtained with currently available fitness measures, while keeping comparable classification accuracy. The functions introduced in this paper capture explicitly the nature of unbalanced data, exhibit better dimensionality reduction and have better False Rejection Rate. |
|---|
| Publication date | 2013-11-01 |
|---|
| Publisher | IEEE |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| NPARC number | 21270500 |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 71ef8fa7-ac7f-4144-b873-1ae61c9c3d5b |
|---|
| Record created | 2014-02-14 |
|---|
| Record modified | 2020-06-05 |
|---|
