MyoTac: Real-Time Recognition of Tactical Sign Language Based on Lightweight Deep Neural Network

Algorithm 1

Data processing algorithm.

Input: Real time EMG data S_EMG, IMU data S_IMU, short time energy threshold H

Output: Fused matrix R^17x400

1: For each t >0.05 s do

2:   E(t):=

3:   If E(t) > H then

4:      :=S_EMG(t-0.05:t +1.95)

5:      :=S_EMG(t-0.05:t +1.95)

6:      :=Interp

7:      :=merge

8:      Return

9:   End

10: End for