Young Peyton R, Hong Kihun, Winslow Eden J, Sagastume Giancarlo K, Battraw Marcus A, Whittle Richard S, Schofield Jonathon S
Department of Mechanical and Aerospace Engineering, University of California-Davis, Davis, California, United States of America.
Department of Biomedical Engineering, University of California-Davis, Davis, California, United States of America.
PLoS One. 2025 Apr 10;20(4):e0321319. doi: 10.1371/journal.pone.0321319. eCollection 2025.
Hand gesture classification is crucial for the control of many modern technologies, ranging from virtual and augmented reality systems to assistive mechatronic devices. A prominent control technique employs surface electromyography (EMG) and pattern recognition algorithms to identify specific patterns in muscle electrical activity and translate these to device commands. While being well established in consumer, clinical, and research applications, this technique suffers from misclassification errors caused by limb movements and the weight of manipulated objects, both vital aspects of how we use our hands in daily life. An emerging alternative control technique is force myography (FMG) which uses pattern recognition algorithms to predict hand gestures from the axial forces present at the skin's surface created by contractions of the underlying muscles. As EMG and FMG capture different physiological signals associated with muscle contraction, we hypothesized that each may offer unique additional information for gesture classification, potentially improving classification accuracy in the presence of limb position and object loading effects. Thus, we tested the effect of limb position and grasped load on 3 different sensing modalities: EMG, FMG, and the fused combination of the two. 27 able-bodied participants performed a grasp and release task with 4 hand gestures at 8 positions and under 5 object weight conditions. We then examined the effects of limb position and grasped load on gesture classification accuracy across each sensing modality. It was found that position and grasped load had statistically significant effects on the classification performance of the 3 sensing modalities and that the combination of EMG and FMG provided the highest classification accuracy of hand gesture, limb position, and grasped load combinations (97.34%) followed by FMG (92.27%) and then EMG (82.84%). This points to the fact that the addition of FMG to traditional EMG control systems offers unique additional data for more effective device control and can help accommodate different limb positions and grasped object loads.
手势分类对于许多现代技术的控制至关重要，从虚拟现实和增强现实系统到辅助机电设备。一种突出的控制技术采用表面肌电图（EMG）和模式识别算法来识别肌肉电活动中的特定模式，并将这些模式转换为设备命令。虽然该技术在消费、临床和研究应用中已得到广泛应用，但它会因肢体运动和被操作物体的重量而产生误分类错误，而这两个因素在我们日常生活中使用双手的方式中都至关重要。一种新兴的替代控制技术是力描记法（FMG），它使用模式识别算法从由底层肌肉收缩在皮肤表面产生的轴向力来预测手势。由于EMG和FMG捕获与肌肉收缩相关的不同生理信号，我们推测每种技术可能为手势分类提供独特的额外信息，在存在肢体位置和物体负载影响的情况下可能提高分类准确性。因此，我们测试了肢体位置和握持负载对三种不同传感模式的影响：EMG、FMG以及两者的融合组合。27名身体健全的参与者在8个位置和5种物体重量条件下，用4种手势执行抓握和释放任务。然后，我们研究了肢体位置和握持负载对每种传感模式下手势分类准确性的影响。结果发现，位置和握持负载对三种传感模式的分类性能具有统计学上的显著影响，并且EMG和FMG的组合提供了手势、肢体位置和握持负载组合的最高分类准确率（97.34%），其次是FMG（92.27%），然后是EMG（82.84%）。这表明在传统的EMG控制系统中添加FMG可为更有效的设备控制提供独特的额外数据，并有助于适应不同的肢体位置和握持物体负载。
