Towards Integration of Domain Knowledge-Guided Feature Engineering and Deep Feature Learning in Surface Electromyography-Based Hand Movement Recognition

<div>Average hand movement recognition accuracies achieved by the FLonly architecture, the DKonly architecture, and our proposed PFNet on NinaProDB1–NinaProDB5, when the sliding window length was set to 200 ms.</div>

Computational Intelligence and Neuroscience

fig5

Figure 5

Figure 5: Towards Integration of Domain Knowledge-Guided Feature Engineering and Deep Feature Learning in Surface Electromyography-Based Hand Movement Recognition 

Figure 5 | Towards Integration of Domain Knowledge-Guided Feature Engineering and Deep Feature Learning in Surface Electromyography-Based Hand Movement Recognition 