| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Industrial and Systems Engineering | - |
| dc.contributor | Department of Aeronautical and Aviation Engineering | - |
| dc.creator | Lee, CKM | - |
| dc.creator | Ng, KKH | - |
| dc.creator | Chen, CH | - |
| dc.creator | Lau, HCW | - |
| dc.creator | Chung, SY | - |
| dc.creator | Tsoi, T | - |
| dc.date.accessioned | 2021-05-13T08:31:25Z | - |
| dc.date.available | 2021-05-13T08:31:25Z | - |
| dc.identifier.issn | 0957-4174 | - |
| dc.identifier.uri | http://hdl.handle.net/10397/89807 | - |
| dc.language.iso | en | en_US |
| dc.publisher | Pergamon Press | en_US |
| dc.subject | American sign language | en_US |
| dc.subject | Leap motion controller | en_US |
| dc.subject | Learning application | en_US |
| dc.subject | Sign recognition system | en_US |
| dc.title | American sign language recognition and training method with recurrent neural network | en_US |
| dc.type | Journal/Magazine Article | en_US |
| dc.identifier.volume | 167 | - |
| dc.identifier.doi | 10.1016/j.eswa.2020.114403 | - |
| dcterms.abstract | Though American sign language (ASL) has gained recognition from the American society, few ASL applications have been developed with educational purposes. Those designed with real-time sign recognition systems are also lacking. Leap motion controller facilitates the real-time and accurate recognition of ASL signs. It allows an opportunity for designing a learning application with a real-time sign recognition system that seeks to improve the effectiveness of ASL learning. The project proposes an ASL learning application prototype. The application would be a whack-a-mole game with a real-time sign recognition system embedded. Since both static and dynamic signs (J, Z) exist in ASL alphabets, Long-Short Term Memory Recurrent Neural Network with k-Nearest-Neighbour method is adopted as the classification method is based on handling of sequences of input. Characteristics such as sphere radius, angles between fingers and distance between finger positions are extracted as input for the classification model. The model is trained with 2600 samples, 100 samples taken for each alphabet. The experimental results revealed that the recognition rate for 26 ASL alphabets yields an average of 99.44% accuracy rate and 91.82% in 5-fold cross-validation with the use of leap motion controller. | - |
| dcterms.accessRights | embargoed access | - |
| dcterms.bibliographicCitation | Expert systems with applications, 1 Apr. 2021, v. 167, 114403 | - |
| dcterms.isPartOf | Expert systems with applications | - |
| dcterms.issued | 2021-04-01 | - |
| dc.identifier.scopus | 2-s2.0-85097552443 | - |
| dc.identifier.eissn | 1873-6793 | - |
| dc.identifier.artn | 114403 | - |
| dc.description.validate | 202105 bchy | - |
| dc.description.oa | Not applicable | - |
| dc.identifier.FolderNumber | a0768-n12 | - |
| dc.identifier.SubFormID | 1581 | - |
| dc.description.fundingSource | Self-funded | - |
| dc.description.pubStatus | Early release | - |
| dc.date.embargo | 2023.04.01 | en_US |
| Appears in Collections: | Journal/Magazine Article | |
Access
View full-text via PolyU eLinks 
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.