English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper presents an efficient deep neural network model for diagnosingParkinson's disease from gait. More specifically, we introduce a hybridConvNet-Transformer architecture to accurately diagnose the disease bydetecting the severity stage. The proposed architecture exploits the strengthsof both Convolutional Neural Networks and Transformers in a single end-to-endmodel, where the former is able to extract relevant local features fromVertical Ground Reaction Force (VGRF) signal, while the latter allows tocapture long-term spatio-temporal dependencies in data. In this manner, ourhybrid architecture achieves an improved performance compared to using eithermodels individually. Our experimental results show that our approach iseffective for detecting the different stages of Parkinson's disease from gaitdata, with a final accuracy of 88%, outperforming other state-of-the-art AImethods on the Physionet gait dataset. Moreover, our method can be generalizedand adapted for other classification problems to jointly address the featurerelevance and spatio-temporal dependency problems in 1D signals. Our sourcecode and pre-trained models are publicly available athttps://github.com/SafwenNaimi/1D-Convolutional-transformer-for-Parkinson-disease-diagnosis-from-gait.

1D-Convolutional transformer for Parkinson disease diagnosis from gait