Author:
Sarwat Hussein,Alkhashab Amr,Song Xinyu,Jiang Shuo,Jia Jie,Shull Peter B.
Abstract
Abstract
Background
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.
Methods
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.
Results
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%.
Conclusion
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.
Trial registration number: The study was registered in Chinese Clinical Trial Registry with registration number CHiCTR1800017568 in 2018/08/04
Funder
The National Natural Science Foundation of China
The Chenguang Program by Shanghai Municipal Education Commission
Fujian Province Science and Technology Innovation Joint Fund Project
Publisher
Springer Science and Business Media LLC
Reference47 articles.
1. Murphy SJ, Werring DJ. Stroke: causes and clinical features. Medicine. 2020;48(9):561–6.
2. Johnson CO, Nguyen M, Roth GA, Nichols E, Alam T, Abate D, et al. Global, regional, and national burden of stroke, 1990–2016: a systematic analysis for the Global Burden of Disease Study 2016. Lancet Neurol. 2019;18(5):439–58.
3. Feigin VL, Brainin M, Norrving B, Martins S, Sacco RL, Hacke W, et al. World Stroke Organization (WSO): global stroke fact sheet 2022. Int J Stroke. 2022;17(1):18–29.
4. Lo K, Stephenson M, Lockwood C. The economic cost of robotic rehabilitation for adult stroke patients: a systematic review. JBI Evid Synth. 2019;17(4):520–47.
5. Ao D, Sun R, Song R, Comparison of complexity of EMG signals between a normal subject and a patient after stroke-a case study. In: 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE. 2013;2013:4965–8.