arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.02772cs.LGcs.AIcs.CVcs.CY
收藏

通过结合硬负样本与软负样本的监督对比学习进行康复运动质量评估

Rehabilitation Exercise Quality Assessment through Supervised Contrastive Learning with Hard and Soft Negatives

University of Toronto(多伦多大学);KITE Research Institute, University Health Network(大学健康网络KITE研究所)

Mark Karlov, Ali Abedi, Shehroz S. Khan

AI总结:

针对康复数据集中各运动类型样本稀少的问题,提出融合硬、软负样本的监督对比学习框架,基于ST-GCN训练单一通用模型,并在UI-PRMD、IRDS和KIMORE上取得最优性能。

摘要:

基于运动的康复计划已被证明可有效提升生活质量,并降低死亡率和再住院率。由AI驱动的虚拟康复允许患者在家中独立完成运动,它利用AI算法分析运动数据,向患者提供反馈,并向临床医生更新患者的进展。这些计划通常会规定多种运动类型,从而在康复运动评估数据集中带来一个明显挑战:尽管总体训练样本丰富,但这些数据集在每种单独运动类型上的样本数量往往有限。这种不均衡削弱了现有方法在每种运动类型样本量如此之小的情况下训练可泛化模型的能力。为解决这一问题,本文提出一种新颖的、包含硬负样本与软负样本的监督对比学习框架,该框架有效利用整个数据集来训练一个适用于所有运动类型的单一模型。该模型采用时空图卷积网络(Spatial-Temporal Graph Convolutional Network,ST-GCN)架构,在不同运动之间表现出更强的泛化能力,并降低了整体复杂度。通过在三个公开可用的康复运动评估数据集 UI-PRMD、IRDS 和 KIMORE 上进行大量实验,我们的方法被证明优于现有方法,在康复运动质量评估方面树立了新的基准。

英文摘要:

Exercise-based rehabilitation programs have proven to be effective in enhancing the quality of life and reducing mortality and rehospitalization rates. AI-driven virtual rehabilitation, which allows patients to independently complete exercises at home, utilizes AI algorithms to analyze exercise data, providing feedback to patients and updating clinicians on their progress. These programs commonly prescribe a variety of exercise types, leading to a distinct challenge in rehabilitation exercise assessment datasets: while abundant in overall training samples, these datasets often have a limited number of samples for each individual exercise type. This disparity hampers the ability of existing approaches to train generalizable models with such a small sample size per exercise type. Addressing this issue, this paper introduces a novel supervised contrastive learning framework with hard and soft negative samples that effectively utilizes the entire dataset to train a single model applicable to all exercise types. This model, with a Spatial-Temporal Graph Convolutional Network (ST-GCN) architecture, demonstrated enhanced generalizability across exercises and a decrease in overall complexity. Through extensive experiments on three publicly available rehabilitation exercise assessment datasets, UI-PRMD, IRDS, and KIMORE, our method has proven to surpass existing methods, setting a new benchmark in rehabilitation exercise quality assessment.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑