Multi-view representation learning via gcca for multimodal analysis of Parkinson's disease
| Autor: | Maria Yancheva, Juan Rafael Orozco-Arroyave, Raman Arora, Najim Dehak, Frank Rudzicz, Julius Hannink, Nikolai Vogler, Elmar Nöth, Milos Cernak, Phani Sankar Nidadavolu, Juan Camilo Vásquez-Correa, Heidi Christensen, Alyssa Vann, Hamidreza Chinaei, Tobias Bocklet |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Parkinson's disease
Computer science business.industry Speech recognition Feature extraction 020206 networking & telecommunications 02 engineering and technology computer.software_genre medicine.disease Dysarthria Gait (human) Handwriting 0202 electrical engineering electronic engineering information engineering medicine 020201 artificial intelligence & image processing Artificial intelligence medicine.symptom Representation (mathematics) business Feature learning computer Natural language processing |
| Zdroj: | ICASSP |
| DOI: | 10.1109/icassp.2017.7952700 |
| Popis: | Information from different bio-signals such as speech, handwriting, and gait have been used to monitor the state of Parkinson's disease (PD) patients, however, all the multimodal bio-signals may not always be available. We propose a method based on multi-view representation learning via generalized canonical correlation analysis (GCCA) for learning a representation of features extracted from handwriting and gait that can be used as a complement to speech-based features. Three different problems are addressed: classification of PD patients vs. healthy controls, prediction of the neurological state of PD patients according to the UPDRS score, and the prediction of a modified version of the Frenchay dysarthria assessment (m-FDA). According to the results, the proposed approach is suitable to improve the results in the addressed problems, specially in the prediction of the UPDRS, and m-FDA scores. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|