Table 7 The comparisons of inference time, training time, model params of different models on 4 joint angles on I9-139000H(CPU), NVIDIA RTX4060(GPU), and Raspberry Pi 4B(ARM).

From: A linear-attention based network for estimating continuous upper limb movement from surface electromyography

Model name

CPU (ms)

GPU (ms)

ARM (ms)

Training (s)

Params (MB)

MLP

4.00

1.00

20.52

1.49

1.14

TCN

7.59

1.02

33.50

1.95

2.19

LSTM

23.59

9.02

121.50

5.64

5.83

DABD

10.46

1.01

57.14

4.64

1.48

LABD

8.36

0.99

22.97

2.43

0.68

  1. The used device is CPU: I9-139000H, GPU: NVIDIA RTX4060, ARM: Raspberry Pi 4B and training: NVIDIA RTX4060
Back to article page