Szczegóły publikacji
Opis bibliograficzny
Deep learning approach to Parkinson’s disease detection using voice recordings and Convolutional Neural Network dedicated to image classification / Marek WODZIŃSKI, Andrzej SKALSKI, Daria HEMMERLING, Juan Rafael Orozco-Arroyave, Elmar Nöth // W: EMBC 2019 [Dokument elektroniczny] : 41st annual international conference of the IEEE Engineering in Medicine and Biology Society : 23-27 July 2019, Berlin, Germany. — Wersja do Windows. — Dane tekstowe. — [Piscataway] : IEEE, cop. 2019. — (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society ; ISSN 1094-687X). — ISBN: 978-1-5386-1312-2; e-ISBN: 978-1-5386-1311-5. — S. 717–720. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 720, Abstr.
Autorzy (5)
- AGHWodziński Marek
- AGHSkalski Andrzej
- AGHHemmerling Daria
- Orozco-Arroyave Juan Rafael
- Nöth Elmar
Dane bibliometryczne
| ID BaDAP | 125192 |
|---|---|
| Data dodania do BaDAP | 2019-10-16 |
| Tekst źródłowy | URL |
| DOI | 10.1109/EMBC.2019.8856972 |
| Rok publikacji | 2019 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
| Konferencja | The Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2019 |
| Czasopismo/seria | Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society |
Abstract
This study presents an approach to Parkinson’s disease detection using vowels with sustained phonation and a ResNet architecture dedicated originally to image classification. We calculated spectrum of the audio recordings and used them as an image input to the ResNet architecture pre-trained using the ImageNet and SVD databases. To prevent overfitting the dataset was strongly augmented in the time domain. The Parkinson’s dataset (from PC-GITA database) consists of 100 patients (50 were healthy / 50 were diagnosed with Parkinson’s disease). Each patient was recorded 3 times. The obtained accuracy on the validation set is above 90% which is comparable to the current state-of-the-art methods. The results are promising because it turned out that features learned on natural images are able to transfer the knowledge to artificial images representing the spectrogram of the voice signal. What is more, we showed that it is possible to perform a successful detection of Parkinson’s disease using only frequency-based features. A spectrogram enables visual representation of frequencies spectrum of a signal. It allows to follow the frequencies changes of a signal in time.
