1. Intuitive real-time control strategy for high-density myoelectric hand prosthesis using deep and transfer learning
- Author
-
Benoit Gosselin, Alexandre Campeau-Lecours, Mounir Boukadoum, and Simon Tam
- Subjects
Quality of life ,Computer science ,Interface (computing) ,Science ,0206 medical engineering ,Skeletal muscle ,Artificial Limbs ,02 engineering and technology ,Prosthesis Design ,Convolutional neural network ,Article ,Machine Learning ,03 medical and health sciences ,0302 clinical medicine ,Amputees ,Real-time Control System ,Computational models ,Humans ,Simulation ,Computational model ,Multidisciplinary ,Gestures ,Hand Strength ,Electromyography ,Prostheses and Implants ,Hand ,020601 biomedical engineering ,Data processing ,Gesture recognition ,Unique user ,Medicine ,Neural Networks, Computer ,Transfer of learning ,030217 neurology & neurosurgery ,Algorithms ,Gesture ,Muscle Contraction - Abstract
Myoelectric hand prostheses offer a way for upper-limb amputees to recover gesture and prehensile abilities to ease rehabilitation and daily life activities. However, studies with prosthesis users found that a lack of intuitiveness and ease-of-use in the human-machine control interface are among the main driving factors in the low user acceptance of these devices. This paper proposes a highly intuitive, responsive and reliable real-time myoelectric hand prosthesis control strategy with an emphasis on the demonstration and report of real-time evaluation metrics. The presented solution leverages surface high-density electromyography (HD-EMG) and a convolutional neural network (CNN) to adapt itself to each unique user and his/her specific voluntary muscle contraction patterns. Furthermore, a transfer learning approach is presented to drastically reduce the training time and allow for easy installation and calibration processes. The CNN-based gesture recognition system was evaluated in real-time with a group of 12 able-bodied users. A real-time test for 6 classes/grip modes resulted in mean and median positive predictive values (PPV) of 93.43% and 100%, respectively. Each gesture state is instantly accessible from any other state, with no mode switching required for increased responsiveness and natural seamless control. The system is able to output a correct prediction within less than 116 ms latency. 100% PPV has been attained in many trials and is realistically achievable consistently with user practice and/or employing a thresholded majority vote inference. Using transfer learning, these results are achievable after a sensor installation, data recording and network training/fine-tuning routine taking less than 10 min to complete, a reduction of 89.4% in the setup time of the traditional, non-transfer learning approach.
- Published
- 2021