Effect of Segmentation Parameters on Classification Accuracy of High-Density EMG recordings

Muscle-Specific High-Density Electromyography Arrays for Hand Gesture Classification

OBJECTIVE

Dexterous hand motion is critical for object manipulation. Electrophysiological studies of the hand are key to understanding its underlying mechanisms. High-density electromyography (HD-EMG) provides spatio-temporal information about the underlying electrical activity of muscles, which can be used in neurophysiological research, rehabilitation and control applications. However, existing EMG electrodes platforms are not muscle-specific, which makes the assessment of intrinsic hand muscles difficult.

METHODS

Muscle-specific flexible HD-EMG electrode arrays were developed to capture intrinsic hand muscle myoelectric activity during manipulation tasks. The arrays consist of 60 individual electrodes targeting 10 intrinsic hand muscles. Myoelectric activity was displayed as spatio-temporal amplitude maps to visualize muscle activation. Time-domain and temporal-spatial HD-EMG features were extracted to train cubic support vector machine machine-learning classifiers to classify the intended user motion.

RESULTS

Experimental data was collected from 5 subjects performing a range of 10 common hand motions. Spatio-temporal EMG maps showed distinct activation areas correlated to the muscles recruited during each movement. The thenar muscle fiber conduction velocity (CV) was estimated to be at 4.70.3 m/s for all subjects. Hand motions were successfully classified and average accuracy for all subjects was directly related to spatial resolution based on the number of channels used as inputs; ranging from 744% when using only 5 channels and up to 922% when using 41 channels. Temporal-spatial features were shown to provide increased motion-specific accuracy when similar muscles were recruited for different gestures.

CONCLUSIONS

Muscle-specific electrodes were capable of accurately recording HD-EMG signals from intrinsic hand muscles and accurately predicting motion.

SIGNIFICANCE

The muscle-specific electrode arrays could improve electrophysiological research studies using EMG decomposition techniques to assess motor unit activity and in applications involving the analysis of dexterous hand motions.

Quantification of Gastric Slow Wave Velocity using Bipolar High-Resolution Recordings

OBJECTIVE

Gastric bio-electrical slow waves are, in part, responsible for coordinating motility. High-resolution (HR) in vivo recordings can be used to capture the wavefront velocity of the propagating slow waves. A standard marking-and-grouping approach is typically employed along with manual review. Here, a bipolar velocity estimation (BVE) method was developed, which utilized local directional information to estimate the wavefront velocity in an efficient manner.

METHODS

With this approach, unipolar in vivo HR recordings were used to construct bipolar recordings in different directions. Then, the local directionality of the slow wave was extracted by calculating time delay information. The accuracy of the method was verified using synthetic data and then validated with in vivo HR pig experimental recordings.

RESULTS

Against ventilator noise amplitude of 0% - 70% of the average slow wave amplitude, the direction and speed error increased from 4.4 and 0.9 mm/s to 8.6 and 1.4 mm/s. For signals added with high-frequency noise with signal-to-noise ratios of 60 dB - 12 dB, the error increased from 8.0 and 1.0 mm/s to 9.8 and 1.2 mm/s. For experimental signals, the BVE algorithm resulted in 19.2 1.7 of direction error and 2.0 0.2 mm/s of speed error, when compared to the standard marking-and-grouping method.

CONCLUSION

Gastric slow wave wavefront velocities were estimated rapidly using the BVE algorithm with minimal errors.

SIGNIFICANCE

The BVE algorithm enables the ability to estimate wavefront velocities in HR recordings in an efficient manner.

HD-EMG Electrode Count and Feature Selection Influence on Pattern-based Movement Classification Accuracy

Control schemes that rely on electromyography (EMG) pattern classification have shown to improve their accuracy when coupled with an increasing number of electrodes. In this study, HD-EMG signals from the hand and forearm of volunteers performing a series of movements were recorded. Different amounts of input EMG channels were selected and time-domain features were extracted to train several SVM classifiers. Detailed comparisons were made to evaluate the impact of electrode count and feature selection over the overall classification accuracy of 17 different movements. The increased resolution achieved from higher electrode counts yielded significant improvements in classification accuracy; however, these improvements were marginal when the number of channels utilized surpassed 100 electrodes.Clinical relevance- Pattern-based EMG classification is a widely used control method for a range of prosthetic devices and robotic interfaces. This work studies the optimal number of simultaneous HD-EMG channels and features that must be considered for accurate myoelectric control using this method.