Sarwat Hussein, Alkhashab Amr, Song Xinyu, Jiang Shuo, Jia Jie, Shull Peter B
School of Mechanical Engineering, Shanghai Jiao Tong University, Dongchuan Road, Shanghai, 200240, China.
Robot Offline Programming, Visual Components, Vänrikinkuja, Espoo, 02600, Finland.
J Neuroeng Rehabil. 2024 Jun 12;21(1):100. doi: 10.1186/s12984-024-01398-7.
In-home rehabilitation systems are a promising, potential alternative to conventional therapy for stroke survivors. Unfortunately, physiological differences between participants and sensor displacement in wearable sensors pose a significant challenge to classifier performance, particularly for people with stroke who may encounter difficulties repeatedly performing trials. This makes it challenging to create reliable in-home rehabilitation systems that can accurately classify gestures.
Twenty individuals who suffered a stroke performed seven different gestures (mass flexion, mass extension, wrist volar flexion, wrist dorsiflexion, forearm pronation, forearm supination, and rest) related to activities of daily living. They performed these gestures while wearing EMG sensors on the forearm, as well as FMG sensors and an IMU on the wrist. We developed a model based on prototypical networks for one-shot transfer learning, K-Best feature selection, and increased window size to improve model accuracy. Our model was evaluated against conventional transfer learning with neural networks, as well as subject-dependent and subject-independent classifiers: neural networks, LGBM, LDA, and SVM.
Our proposed model achieved 82.2% hand-gesture classification accuracy, which was better (P<0.05) than one-shot transfer learning with neural networks (63.17%), neural networks (59.72%), LGBM (65.09%), LDA (63.35%), and SVM (54.5%). In addition, our model performed similarly to subject-dependent classifiers, slightly lower than SVM (83.84%) but higher than neural networks (81.62%), LGBM (80.79%), and LDA (74.89%). Using K-Best features improved the accuracy in 3 of the 6 classifiers used for evaluation, while not affecting the accuracy in the other classifiers. Increasing the window size improved the accuracy of all the classifiers by an average of 4.28%.
Our proposed model showed significant improvements in hand-gesture recognition accuracy in individuals who have had a stroke as compared with conventional transfer learning, neural networks and traditional machine learning approaches. In addition, K-Best feature selection and increased window size can further improve the accuracy. This approach could help to alleviate the impact of physiological differences and create a subject-independent model for stroke survivors that improves the classification accuracy of wearable sensors.
The study was registered in Chinese Clinical Trial Registry with registration number CHiCTR1800017568 in 2018/08/04.
居家康复系统是中风幸存者传统治疗的一种有前景的潜在替代方案。不幸的是，参与者之间的生理差异以及可穿戴传感器中的传感器位移对分类器性能构成了重大挑战，特别是对于中风患者而言，他们可能在反复进行试验时遇到困难。这使得创建能够准确对手势进行分类的可靠居家康复系统具有挑战性。
20名中风患者进行了七种与日常生活活动相关的不同手势（大量屈曲、大量伸展、腕掌屈、腕背屈、前臂旋前、前臂旋后和休息）。他们在前臂佩戴肌电图（EMG）传感器、在手腕佩戴功能性肌电图（FMG）传感器和惯性测量单元（IMU）的同时执行这些手势。我们基于用于一次性迁移学习的原型网络、K最优特征选择和增加窗口大小开发了一个模型，以提高模型准确性。我们的模型与使用神经网络的传统迁移学习以及依赖个体和不依赖个体的分类器（神经网络、LightGBM、线性判别分析和支持向量机）进行了比较评估。
我们提出的模型实现了82.2%的手势分类准确率，这比使用神经网络的一次性迁移学习（63.17%）、神经网络（59.72%）、LightGBM（65.09%）、线性判别分析（63.35%）和支持向量机（54.5%）更好（P<0.05）。此外，我们的模型表现与依赖个体的分类器相似，略低于支持向量机（83.84%）但高于神经网络（81.62%）、LightGBM（80.79%）和线性判别分析（74.89%）。使用K最优特征提高了用于评估的6个分类器中3个的准确率，同时不影响其他分类器的准确率。增加窗口大小使所有分类器的准确率平均提高了4.28%。
与传统迁移学习、神经网络和传统机器学习方法相比，我们提出的模型在中风患者的手势识别准确率方面有显著提高。此外，K最优特征选择和增加窗口大小可以进一步提高准确率。这种方法有助于减轻生理差异的影响，并为中风幸存者创建一个不依赖个体的模型，提高可穿戴传感器的分类准确率。
该研究于2018年8月4日在中国临床试验注册中心注册，注册号为CHiCTR1800017568。
