Striving for more robust and natural control of multi-fingered hand prostheses, we are studying electrical impedance tomography (EIT) as a method to monitor residual muscle activations. Previous work has shown promising results for hand gesture recognition, but also lacks generalization across multiple sessions and users. Thus, the present paper aims for a detailed analysis of an existing EIT dataset acquired with a 16-electrode wrist band as a prerequisite for further improvements of machine learning results on this type of signal. The performed t-SNE analysis confirms a much stronger inter-session and inter-user variance compared to the expected in-class variance. Additionally, we observe a strong drift of signals within a session. To handle these challenging problems, we propose new machine learning architectures based on deep learning, which allow to separate undesired from desired variation and thus significantly improve the classification accuracy. With these new architectures we increased cross-session classification accuracy on 12 gestures from 19.55 to 30.45%. Based on a fundamental data analysis we developed three calibration methods and thus were able to further increase cross-session classification accuracy to 39.01, 55.37, and 56.34%, respectively.

中文翻译：

---

在 EIT 数据上实现更强大的手势识别。

为了对多指手假肢进行更稳健和自然的控制，我们正在研究电阻抗断层扫描 (EIT) 作为监测残余肌肉活动的一种方法。以前的工作在手势识别方面显示出有希望的结果，但也缺乏跨多个会话和用户的泛化。因此，本文旨在详细分析使用 16 电极腕带获取的现有 EIT 数据集，作为进一步改进此类信号的机器学习结果的先决条件。与预期的类内方差相比，执行的 t-SNE 分析证实了更强的会话间和用户间方差。此外，我们观察到一个会话中信号的强烈漂移。为了处理这些具有挑战性的问题，我们提出了基于深度学习的新机器学习架构，这允许将不想要的变化与期望的变化分开，从而显着提高分类精度。通过这些新架构，我们将 12 个手势的跨会话分类准确度从 19.55% 提高到 30.45%。基于基本数据分析，我们开发了三种校准方法，从而能够进一步将跨会话分类准确率分别提高到 39.01、55.37 和 56.34%。