This paper presents a real-time fine gesture recognition system for multi-articulating hand prosthesis control, using an embedded convolutional neural network (CNN) to classify hand-muscle contractions sensed at the forearm. The sensor consists in a custom non-intrusive, compact, and easy-to-install 32-channel high-density surface electromyography (HDsEMG) electrode array, built on a flexible printed circuit board (PCB) to allow wrapping around the forearm. The sensor provides a low-noise digitization interface with wireless data transmission through an industrial, scientific and medical (ISM) radio link. An original frequency-time-space cross-domain preprocessing method is proposed to enhance gesture-specific data homogeneity and generate reliable muscle activation maps, leading to 98.15% accuracy when using a majority vote over 5 subsequent inferences by the proposed CNN. The obtained real-time gesture recognition, within 100 to 200 ms, and CNN properties show reliable and promising results to improve on the state-of-the-art of commercial hand prostheses. Moreover, edge computing using a specialized embedded artificial intelligence (AI) platform ensures reliable, secure and low latency real-time operation as well as quick and easy access to training, fine-tuning and calibration of the neural network. Co-design of the signal processing, AI algorithms and sensing hardware ensures a reliable and power-efficient embedded gesture recognition system.

中文翻译：

---

利用HD-sEMG和深度学习的全嵌入式自适应实时手势分类器。

本文提出了一种用于多关节手假体控制的实时精细手势识别系统，该系统使用嵌入式卷积神经网络（CNN）对前臂感觉到的手部肌肉收缩进行分类。该传感器包含一个定制的非侵入式，紧凑且易于安装的32通道高密度表面肌电（HDsEMG）电极阵列，该电极阵列构建在柔性印刷电路板（PCB）上，从而可以缠绕在前臂上。该传感器提供低噪声数字化接口，并通过工业，科学和医学（ISM）无线电链路进行无线数据传输。提出了一种原始的频率-时间-空间跨域预处理方法，以增强特定于手势的数据同质性并生成可靠的肌肉激活图，从而得出98。当提议的CNN对5个后续推论使用多数票时，准确性为15％。在100到200毫秒内获得的实时手势识别以及CNN属性显示出可靠和有希望的结果，可以改进最新的商业手部假体。此外，使用专用嵌入式人工智能（AI）平台的边缘计算可确保可靠，安全和低延迟的实时操作，以及对神经网络的训练，微调和校准的快速便捷访问。信号处理，AI算法和传感硬件的共同设计确保了可靠且节能的嵌入式手势识别系统。CNN的性能显示出可靠和有希望的结果，可以改进最新的商用手用假体。此外，使用专用嵌入式人工智能（AI）平台的边缘计算可确保可靠，安全和低延迟的实时操作，以及对神经网络的训练，微调和校准的快速便捷访问。信号处理，AI算法和传感硬件的共同设计确保了可靠且节能的嵌入式手势识别系统。CNN的性能显示出可靠和有希望的结果，可以改进最新的商用手用假体。此外，使用专用嵌入式人工智能（AI）平台的边缘计算可确保可靠，安全和低延迟的实时操作，以及对神经网络的训练，微调和校准的快速便捷访问。信号处理，AI算法和传感硬件的共同设计确保了可靠且节能的嵌入式手势识别系统。