InceptoFormer: A Multi-Signal Neural Framework for Parkinson's Disease Severity Evaluation from Gait
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909725111615488 |
|---|---|
| author | Naimi, Safwen Said, Arij Bouachir, Wassim Bilodeau, Guillaume-Alexandre |
| author_facet | Naimi, Safwen Said, Arij Bouachir, Wassim Bilodeau, Guillaume-Alexandre |
| contents | We present InceptoFormer, a multi-signal neural framework designed for Parkinson's Disease (PD) severity evaluation via gait dynamics analysis. Our architecture introduces a 1D adaptation of the Inception model, which we refer to as Inception1D, along with a Transformer-based framework to stage PD severity according to the Hoehn and Yahr (H&Y) scale. The Inception1D component captures multi-scale temporal features by employing parallel 1D convolutional filters with varying kernel sizes, thereby extracting features across multiple temporal scales. The transformer component efficiently models long-range dependencies within gait sequences, providing a comprehensive understanding of both local and global patterns. To address the issue of class imbalance in PD severity staging, we propose a data structuring and preprocessing strategy based on oversampling to enhance the representation of underrepresented severity levels. The overall design enables to capture fine-grained temporal variations and global dynamics in gait signal, significantly improving classification performance for PD severity evaluation. Through extensive experimentation, InceptoFormer achieves an accuracy of 96.6%, outperforming existing state-of-the-art methods in PD severity assessment. The source code for our implementation is publicly available at https://github.com/SafwenNaimi/InceptoFormer |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04540 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InceptoFormer: A Multi-Signal Neural Framework for Parkinson's Disease Severity Evaluation from Gait Naimi, Safwen Said, Arij Bouachir, Wassim Bilodeau, Guillaume-Alexandre Computer Vision and Pattern Recognition We present InceptoFormer, a multi-signal neural framework designed for Parkinson's Disease (PD) severity evaluation via gait dynamics analysis. Our architecture introduces a 1D adaptation of the Inception model, which we refer to as Inception1D, along with a Transformer-based framework to stage PD severity according to the Hoehn and Yahr (H&Y) scale. The Inception1D component captures multi-scale temporal features by employing parallel 1D convolutional filters with varying kernel sizes, thereby extracting features across multiple temporal scales. The transformer component efficiently models long-range dependencies within gait sequences, providing a comprehensive understanding of both local and global patterns. To address the issue of class imbalance in PD severity staging, we propose a data structuring and preprocessing strategy based on oversampling to enhance the representation of underrepresented severity levels. The overall design enables to capture fine-grained temporal variations and global dynamics in gait signal, significantly improving classification performance for PD severity evaluation. Through extensive experimentation, InceptoFormer achieves an accuracy of 96.6%, outperforming existing state-of-the-art methods in PD severity assessment. The source code for our implementation is publicly available at https://github.com/SafwenNaimi/InceptoFormer |
| title | InceptoFormer: A Multi-Signal Neural Framework for Parkinson's Disease Severity Evaluation from Gait |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.04540 |