{"ID":2885850,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.04540","arxiv_id":"2508.04540","title":"InceptoFormer: A Multi-Signal Neural Framework for Parkinson's Disease Severity Evaluation from Gait","abstract":"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\u0026Y) 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","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2508.04540","url_pdf":"https://arxiv.org/pdf/2508.04540v1","authors":"[\"Safwen Naimi\",\"Arij Said\",\"Wassim Bouachir\",\"Guillaume-Alexandre Bilodeau\"]","published":"2025-08-06T15:27:11Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false,"code_links":[{"ID":611250,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2885850,"paper_url":"https://arxiv.org/abs/2508.04540","paper_title":"InceptoFormer: A Multi-Signal Neural Framework for Parkinson's Disease Severity Evaluation from Gait","repo_url":"https://github.com/SafwenNaimi/InceptoFormer","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}