Linear regression with frequency division technique for robust simultaneous and proportional myoelectric control during medium and high contraction-level variation

Pradhan, Ashirbad; Jiang, Ning; Chester, Victoria; Kuruganti, Usha

doi:10.1016/j.bspc.2020.101984

Cited by 15 publications

(10 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Another approach is treating these segments as classes of their own [17], [18]. Similar trends and performance values have been observed previously [54], however, only two DOFs of the wrist have been considered. Barsotti et.…”

Section: Discussionmentioning

confidence: 71%

Simultaneous and Proportional Real-Time Myocontrol of Up to Three Degrees of Freedom of the Wrist and Hand

Nowak

Vujaklija

Sturma

et al. 2023

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Achieving robust, intuitive, simultaneous and proportional control over multiple degrees of freedom (DOFs) is an outstanding challenge in the development of myoelectric prosthetic systems. Since the priority in myoelectric prosthesis solutions is robustness and stability, their number of functions is usually limited. Objective: Here, we introduce a system for intuitive concurrent hand and wrist control, based on a robust feature-extraction protocol and machine-learning. Methods: Using the mean absolute value of high-density EMG, we train a ridgeregressor (RR) on only the sustained portions of the single-DOF contractions and leverage the regressor's inherent ability to provide simultaneous multi-DOF estimates. In this way, we robustly capture the amplitude information of the inputs while harnessing the power of the RR to extrapolate otherwise noisy and often overfitted estimations of dynamic portions of movements. Results: The real-time evaluation of the system on 13 able-bodied participants and an amputee shows that almost all single-DOF tasks could be reached (96% success rate), while at the same time users were able to complete most of the two-DOF (62%) and even some of the very challenging three-DOF tasks (37%).To further investigate the translational potential of the approach, we reduced the original 192-channel setup to a 16channel configuration and the observed performance did not deteriorate. Notably, the amputee performed similarly well to the other participants, according to all considered metrics. Conclusion: This is the first real-time operated myocontrol system that consistently provides intuitive simultaneous and proportional control over 3-DOFs of wrist and hand, relying on only surface EMG signals from theThe study was partially funded by the DFG project Tact Hand (CA-1389/1-1), Academy of Finland project Hi-Fi BiNDIng (#333149), and the ERC Synergy project NaturalBionicS (#810346).M. Nowak and C. Castellini are with the German Aerospace Center (DLR),

show abstract

Section: Discussionmentioning

confidence: 71%

Simultaneous and Proportional Real-Time Myocontrol of Up to Three Degrees of Freedom of the Wrist and Hand

Nowak

Vujaklija

Sturma

et al. 2023

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…For instance, entropy and CoV differed between handle designs, offering insight on the spatial differences between each handle design and trunk muscles. Both entropy and CoV have been characterized as indicators of heterogeneity in the spatial distribution of muscle fibers [ 16 , 21 , 22 ]. Moreover, this clustering of fibers has been suggested to indicate low heterogeneity of muscle fibers [ 21 ].…”

Section: Discussionmentioning

confidence: 99%

“…It is estimated that approximately 9–18% of all low back injuries are associated with pushing and pulling tasks [ 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 ]. While the activity of pushing and pulling can contribute to low back injuries in workers, the design of the cart has not changed significantly over the years despite the understanding that inappropriate design and/or use can lead to worker injuries.…”

Section: Introductionmentioning

confidence: 99%

Alteration in HDEMG Spatial Parameters of Trunk Muscle Due to Handle Design during Pushing

Toner

Rickards

Seaman

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Previous research identifies that pushing and pulling is responsible for approximately 9–18% of all low back injuries. Additionally, the handle design of a cart being pushed can dramatically alter a worker’s capacity to push (≅9.5%). Surprisingly little research has examined muscle activation of the low back and its role in muscle function. Therefore, the purpose of this study was to examine the effects of handle design combination of pushing a platform truck cart on trunk muscle activity. Twenty participants (10 males and 10 females, mean age = 24.3 ± 4.3 years) pushed 475 lbs using six different handle combinations involving handle orientation (vertical/horizontal/semi-pronated) and handle height (hip/shoulder). Multichannel high-density EMG (HDsEMG) was recorded for left and right rectus abdominis, erector spinae, and external obliques. Pushing at hip height with a horizontal handle orientation design (HH) resulted in significantly less (p < 0.05) muscle activity compared to the majority of other handle designs, as well as a significantly higher entropy than the shoulder handle height involving either the semi-pronated (p = 0.023) or vertical handle orientation (p = 0.028). The current research suggests that the combination of a hip height and horizontal orientation handle design may require increased muscle demand of the trunk and alter the overall muscle heterogeneity and pattern of the muscle activity.

show abstract

“…Due to their relatively lower computational cost, they have been preferred as a feature set in multitudes of pattern recognition-based research [13]. The frequency-domain category of features is based on the principle that the sEMG spectrum varies with limb movements and has shown robustness in real-time myoelectric control of prosthetic functions [34,35]. The AR feature set includes the coefficients of the nth order autoregressive model of the sEMG signal [27,33,36] and has shown to be stable over varying muscle force levels and shifts in electrode location [37].…”

Section: A Feature Extraction Methodsmentioning

confidence: 99%

Performance Optimization of Surface Electromyography Based Biometric Sensing System for Both Verification and Identification

Pradhan

Jiang

2021

IEEE Sensors J.

Self Cite

View full text Add to dashboard Cite

Recently, surface electromyography (sEMG) emerged as a novel biometric authentication method. EMG system parameters, such as the feature sets and channel numbers, have been known to affect system performances. Therefore, it is crucial to investigate these effects on the performance of the sEMG-based biometric system to determine optimal system parameters. In this study, three robust feature sets, Time-domain (TD) feature, Frequency Division Technique (FDT), and Autoregressive (AR) feature, and their combinations were investigated, while the number of channels varying from one to eight. For these system parameters, the performance of sixteen static wrist and hand gestures was systematically investigated in two authentication modes: verification and identification. The results from 24 participants showed that the TD features significantly (p<0.05) and consistently outperformed FDT and AR features for all channel numbers. The results also showed that the performance of a four-channel setup was not significantly different from those with higher numbers of channels. The average equal error rate (EER) for a four-channel sEMG verification system was 4% for TD features, 5.3% for FDT features, and 10% for AR features. For an identification system, the average Rank-1 error (R1E) for a four-channel configuration was 3% for TD features, 12.4% for FDT features, and 36.3% for AR features. The electrode position on the flexor carpi ulnaris (FCU) muscle had a critical contribution to the authentication performance. Thus, the combination of the TD feature set and a four-channel sEMG system with one of the electrodes positioned on the FCU are recommended for optimal authentication performance.

show abstract

Linear regression with frequency division technique for robust simultaneous and proportional myoelectric control during medium and high contraction-level variation

Cited by 15 publications

References 32 publications

Simultaneous and Proportional Real-Time Myocontrol of Up to Three Degrees of Freedom of the Wrist and Hand

Simultaneous and Proportional Real-Time Myocontrol of Up to Three Degrees of Freedom of the Wrist and Hand

Alteration in HDEMG Spatial Parameters of Trunk Muscle Due to Handle Design during Pushing

Performance Optimization of Surface Electromyography Based Biometric Sensing System for Both Verification and Identification

Contact Info

Product

Resources

About