Multi-Attention Feature Fusion Network for Accurate Estimation of Finger Kinematics from Surface Electromyographic Signals

Weiyu Guo, Ning Jiang, Dario Farina, Jingyong Su, Zheng Wang, Chuang Lin, Hui Xiong

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


Simultaneous and proportional control (SPC) based on surface electromyographic (sEMG) signals has led to a broad range of applications. However, due to the limitation in the generalization and stability of current machine learning algorithms, these methods can only estimate less than 15 simultaneuous and proportional (SP) categories of finger movement. In this article, a novel deep learning algorithm, named multiattention feature fusion network (MAFN), is proposed to estimate comprehensive finger movement (up to 28 categories SP movements) from sEMG signals. MAFN is based on the multihead attention mechanism, which adaptively extracts essential features for analyzing the joint angles from the extracted sEMG features. Furthermore, a real-time exponential smoothing algorithm is designed for further improvement of the prediction stability. MAFN was evaluated on 28 finger movements of 38 subjects in the Ninapro_db2 dataset, and benchmarked with the state-of-the-art methods, such as temporal convolutional network (TCN) and long short term memory network (LSTM). The results demonstrated that the average Pearson correlation coefficient, root mean squared error of MAFN (0.84 ± 0.03,0.09 ± 0.01) were significantly higher than those of TCN (0.52 ± 0.06, p < 0.001;0.16 ± 0.02, p < 0.001) and LSTM (0.62 ± 0.06, p < 0.001;0.13 ± 0.01, p < 0.001). These improvements led to more stable and accurate movement predictions. Additionally, the time delay and power consumption of MAFN when applied to sEMG signals on a portable device are only 83.4 ms and 3 W, which implies prospective commercial applications.

Original languageEnglish (US)
Pages (from-to)512-519
Number of pages8
JournalIEEE Transactions on Human-Machine Systems
Issue number3
StatePublished - Jun 1 2023

All Science Journal Classification (ASJC) codes

  • Human Factors and Ergonomics
  • Control and Systems Engineering
  • Signal Processing
  • Human-Computer Interaction
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence


  • Deep learning
  • figner kinematics
  • simultaneous and proportional control (SPC)
  • surface EMG


Dive into the research topics of 'Multi-Attention Feature Fusion Network for Accurate Estimation of Finger Kinematics from Surface Electromyographic Signals'. Together they form a unique fingerprint.

Cite this