Name
Title | ||
|---|---|---|
Automated assessment of Parkinsonian finger-tapping tests through a vision-based fine-grained classification model |
Abstract | ||
|---|---|---|
•A vision-based fine-grained classification model is proposed for automated assessment of Parkinsonian finger-tapping tests.•A skeleton-based three-stream fine-grained classification network with Markov chained fusion is developed.•A mini-batch-based balanced algorithm is proposed to ensure that each mini-batch is inter-class balanced, thus reducing the effect of imbalanced data. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1016/j.neucom.2021.02.011 | Neurocomputing |
Keywords | DocType | Volume |
Parkinson’s disease,Finger-tapping tests,Fine-grained action recognition,Imbalanced data learning,Three-stream model | Journal | 441 |
ISSN | Citations | PageRank |
0925-2312 | 2 | 0.38 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hao Li | 1 | 261 | 85.92 |
| Xiangxin Shao | 2 | 2 | 0.38 |
| Chencheng Zhang | 3 | 16 | 2.48 |
| Xiaohua Qian | 4 | 4 | 3.78 |