Scholarlink

<p>Parkinson’s disease (PD) is a neurodegenerative disorder characterized by progressive motor impairments, prominently reflected in gait abnormalities. This study presents a preliminary investigation using the newly developed Parkinson’s Disease Gait Video (PDGV) dataset to evaluate the discriminative capacity of gait features to distinguish PD patients from healthy controls. The goal is to support the development of noninvasive, vision-based diagnostic tools through effective feature extraction and classification techniques. Experiments conducted on Gait Energy Images derived from PDGV demonstrate that appearance-based representations combined with deep convolutional neural networks can effectively capture pathological gait patterns. The investigation of the performance of VGG, AlexNet, DenseNet, and ResNet from <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(0^{\circ }\)</EquationSource> <EquationSource Format="MATHML"><math> <msup> <mn>0</mn> <mo>∘</mo> </msup> </math></EquationSource> </InlineEquation>, <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(90^{\circ }\)</EquationSource> <EquationSource Format="MATHML"><math> <msup> <mn>90</mn> <mo>∘</mo> </msup> </math></EquationSource> </InlineEquation>, and <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(180^{\circ }\)</EquationSource> <EquationSource Format="MATHML"><math> <msup> <mn>180</mn> <mo>∘</mo> </msup> </math></EquationSource> </InlineEquation> view angles showed that ResNet-101 is the most performant model, achieving accuracy, precision, recall, and F1-score of 0.81, 0.84, 0.64, and 0.73, respectively, from the <InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(90^{\circ }\)</EquationSource> <EquationSource Format="MATHML"><math> <msup> <mn>90</mn> <mo>∘</mo> </msup> </math></EquationSource> </InlineEquation> view angle. These findings underscore the potential of gait-based analysis for automated PD screening and provide a foundation for future intelligent assistive diagnostic systems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PDGV Dataset: Investigating Deep Learning CNN for Gait-Based Parkinson’s Disease Recognition

  • 期刊论文

  • 发表日期：

    2025年12月10日

查看全文
  • Zohra Mahfouf,
  • Islem Jarraya,
  • Thameur Dhieb,
  • Mohamed Neji,
  • Nouha Farhat,
  • Emna Smaoui,
  • Tarek M. Hamdani,
  • Mariem Damak,
  • Chokri Mhiri,
  • Adel M. Alimi

摘要

Parkinson’s disease (PD) is a neurodegenerative disorder characterized by progressive motor impairments, prominently reflected in gait abnormalities. This study presents a preliminary investigation using the newly developed Parkinson’s Disease Gait Video (PDGV) dataset to evaluate the discriminative capacity of gait features to distinguish PD patients from healthy controls. The goal is to support the development of noninvasive, vision-based diagnostic tools through effective feature extraction and classification techniques. Experiments conducted on Gait Energy Images derived from PDGV demonstrate that appearance-based representations combined with deep convolutional neural networks can effectively capture pathological gait patterns. The investigation of the performance of VGG, AlexNet, DenseNet, and ResNet from \(0^{\circ }\) 0 ∘ , \(90^{\circ }\) 90 ∘ , and \(180^{\circ }\) 180 ∘ view angles showed that ResNet-101 is the most performant model, achieving accuracy, precision, recall, and F1-score of 0.81, 0.84, 0.64, and 0.73, respectively, from the \(90^{\circ }\) 90 ∘ view angle. These findings underscore the potential of gait-based analysis for automated PD screening and provide a foundation for future intelligent assistive diagnostic systems.