发表机构
Begum Rokeya University; Texas State University; Asian Institute of Technology; National Center for Geriatrics and Gerontology（贝古姆罗基亚大学; 德克萨斯州立大学; 亚洲理工学院; 国立长寿医疗研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出注意力增强Transformer框架，利用3D步态特征进行自闭症分类，在公开基准和私有数据集上分别达到99%和95%的准确率，并验证了跨折叠稳定性。
AI 中文摘要
自闭症谱系障碍（ASD）是一种神经发育性疾病，其早期诊断仍具挑战性，因为常规临床评估往往主观、耗时且需要专家评估。步态为自动化ASD筛查提供了一种有前景的非侵入性行为生物标志物；然而，现有研究主要依赖单一数据集评估、卷积架构以及交叉验证性能的描述性总结，而未正式评估折叠间稳定性。本研究通过一种注意力增强的Transformer框架来解决这些不足，用于ASD分类，并在两种结构不同的3D步态特征表示上进行评估：预计算的统计步态描述符和原始生物力学地面反作用力测量。在五折交叉验证下，所提出的框架在公开的基于Kinect的基准上达到了99.00%的准确率、99.02%的精确率、99.00%的召回率、99.00%的F1分数和99.00%的特异性，超过了所比较的最先进方法。在独立的私有测力台数据集上，它达到了95.00%的准确率、93.81%的精确率、96.67%的召回率、95.13%的F1分数和93.33%的特异性的平均值。
英文摘要
Autism Spectrum Disorder (ASD) is a neurodevelopmental condition whose early diagnosis remains challenging because conventional clinical assessments are often subjective, time-consuming, and require expert evaluation. Gait provides a promising non-invasive behavioral biomarker for auto- mated ASD screening; however, existing studies have primarily relied on single-dataset evaluations, convolutional architectures, and descriptive summaries of cross-validation performance without formally assessing fold-to-fold stability. This study addresses these gaps with an attention-enhanced Transformer framework for ASD classification, evaluated on two structurally different 3D gait feature representations: precomputed statistical gait descriptors and raw biomechanical ground-reaction- force measurements. Under five-fold cross-validation, the proposed framework achieved 99.00% accuracy, 99.02% precision, 99.00% recall, 99.00% F1-score, and 99.00% specificity on the public Kinect-based benchmark, exceeding the performance of the compared state-of-the-art methods. On the independent private force-plate dataset, it achieved mean values of 95.00% accuracy, 93.81% precision, 96.67% recall, 95.13% F1-score, and 93.33% specificity.
CommentsWithdrawn by the authors because the manuscript requires substantial correction of the provenance, attribution, authorization, ethics reporting, and contributor recognition associated with the UiTM force-plate gait dataset. The authors will address these matters before any future dissemination of the work
