使用 Kolmogorov-Arnold Networks 实现下肢假肢的个性化控制
Personalized Control for Lower Limb Prosthesis Using Kolmogorov-Arnold Networks
AI总结：
本文针对下肢假肢转弯意图预测，比较 KAN、FKAN 与 MLP、CNN，并评估用户专属和混合训练数据，发现可学习激活函数未显著提升性能，而深度学习模型可有效利用多参与者数据。
摘要：
目的：本文研究 Kolmogorov-Arnold Networks（KAN）中可学习激活函数在下肢假肢个性化控制中的潜力。此外，还评估了用户专属训练数据与混合训练数据，以提升机器学习（ML）和深度学习（DL）在转弯意图预测方面的性能。方法：在实验室环境中，从五名执行转弯任务的下肢截肢者处采集小腿惯性测量单元（IMU）数据。研究评估了多层感知机（MLP）、Kolmogorov-Arnold Network（KAN）、卷积神经网络（CNN）和分数阶 Kolmogorov-Arnold Networks（FKAN）对即将发生的转弯进行分类的能力。通过比较 MLP 与 KAN（针对 ML 模型）以及 FKAN 与 CNN（针对 DL 模型），评估可学习激活函数的有效性。模型分别使用用户专属数据和混合数据进行训练，以评估训练数据对其性能的影响。结果：KAN 和 FKAN 中的可学习激活函数分别相较 MLP 和 CNN 未产生显著提升。对于 ML 模型，使用用户专属数据训练取得了优于混合数据的结果（p < 0.05）。相比之下，DL 模型在用户专属训练与混合训练之间未观察到显著差异。意义：这些发现表明，可学习激活函数可能在涉及更复杂任务和更大数据量的数据集中展现出明显优势。此外，混合训练在 DL 模型中表现出与用户专属训练相当的性能，表明假肢控制的模型训练可以利用来自多名参与者的数据。
英文摘要：
Objective: This paper investigates the potential of learnable activation functions in Kolmogorov-Arnold Networks (KANs) for personalized control in a lower-limb prosthesis. In addition, user-specific vs. pooled training data is evaluated to improve machine learning (ML) and Deep Learning (DL) performance for turn intent prediction. Method: Inertial measurement unit (IMU) data from the shank were collected from five individuals with lower-limb amputation performing turning tasks in a laboratory setting. Ability to classify an upcoming turn was evaluated for Multilayer Perceptron (MLP), Kolmogorov-Arnold Network (KAN), convolutional neural network (CNN), and fractional Kolmogorov-Arnold Networks (FKAN). The comparison of MLP and KAN (for ML models) and FKAN and CNN (for DL models) assessed the effectiveness of learnable activation functions. Models were trained separately on user-specific and pooled data to evaluate the impact of training data on their performance. Results: Learnable activation functions in KAN and FKAN did not yield significant improvement compared to MLP and CNN, respectively. Training on user-specific data yielded superior results compared to pooled data for ML models ($p < 0.05$). In contrast, no significant difference was observed between user-specific and pooled training for DL models. Significance: These findings suggest that learnable activation functions may demonstrate distinct advantages in datasets involving more complex tasks and larger volumes. In addition, pooled training showed comparable performance to user-specific training in DL models, indicating that model training for prosthesis control can utilize data from multiple participants.
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。
