Name
Abstract | ||
|---|---|---|
Wearable sensor technology has the potential to transform the treatment of Parkinson's Disease (PD) by providing objective analysis about the frequency and severity of symptoms in everyday life. However, many challenges remain to developing a system that can robustly distinguish PD motor symptoms from normal motion. Stronger feature sets may help to improve the detection accuracy of such a system. In this work, we explore several feature sets compared across two classification algorithms for PD tremor detection. We find that features automatically learned by a Convolutional Neural Network (CNN) lead to the best performance, although our handcrafted features are close behind. We also find that CNNs benefit from training on data decomposed into tremor and activity spectra as opposed to raw data. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1145/3278576.3278582 | 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE) |
Keywords | Field | DocType |
Parkinson's disease,Feature extraction,Accelerometers,Radio frequency,Classification algorithms,Deep learning,Standards | Parkinson's disease,Systems engineering,Pattern recognition,Accelerometer,Convolutional neural network,Wearable computer,Feature extraction,Artificial intelligence,Deep learning,Engineering,Statistical classification | Conference |
ISBN | Citations | PageRank |
978-1-5386-7206-8 | 0 | 0.34 |
References | Authors | |
0 | 8 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ada Zhang | 1 | 15 | 3.12 |
| R. SAN-SEGUNDO | 2 | 139 | 14.28 |
| Stanislav Panev | 3 | 0 | 0.34 |
| Griffin Tabor | 4 | 0 | 0.34 |
| Katelyn Stebbins | 5 | 0 | 0.34 |
| Andrew Whitford | 6 | 0 | 0.34 |
| Fernando De La Torre | 7 | 3832 | 181.17 |
| Jessica K. Hodgins | 8 | 6121 | 550.56 |