Answers are grounded in this paper and cite their sources.
Emerging technology improves hand gesture recognition in industrial robotics, indicating more efficient human-robot interaction.
In the rapidly developing setting of smart factories, human‐robot interaction (HRI) systems have emerged as a pivotal solution, facilitating seamless communication between humans and machines. Hand gesture‐based surface electromyography signals are widely used for robot control applications. This study proposes an innovative framework intended at improving the efficiency and accuracy of gesture‐based control systems within industrial robotics settings. The proposed system leverages edge artificial intelligence platforms to empower users with intuitive control mechanisms. Ensuring accurate classification of hand gestures is essential for proper operation in a smart factory environment. To address this, a novel approach using graph spiking attention neural networks (GSANN) to recognize hand gestures with surface electromyography sensors is introduced. Initially, a data set comprising 900 hand gesture samples is generated. A sliding window‐based segmentation technique, the surface electromyography signals are efficiently processed, preparing the data for feature extraction. The transformer attention network is then deployed to extract spatial and global features from the segmented signals, facilitating robust gesture representation. The GSANN technique is then employed to recognize six different hand gestures. Additionally, the enhanced circle‐inspired optimization algorithm is executed to decrease the neural network's loss function. Comparative analysis against existing methods revealed the superior performance of the developed GSANN technique, reaching a notable accuracy rate of 99.43%. Experimental results validate the efficiency of the developed strategy in precisely recognizing hand gestures.
No takes yet. Share an insight, caveat, or question.
Arsamy et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: