Selecting the appropriate input variables in a regression approach to estimate actively generated muscle moments around L5/S1 for exoskeleton control

Tabasi, Ali; Kingma, Idsart; Looze, M.P. de; Dijk, W. van; Koopman, Axel S.; Dieën, Jaap H. van

doi:10.1016/j.jbiomech.2020.109650

Cited by 8 publications

(13 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, the RegMod was trained using data from four EMG channels (bilateral longissimus thoracis pars lumborum and pars thoracis) together with pelvic and trunk kinematics as predictor variables and the active moment, predicted using the calibrated EMGMod, as the response variable. The selection of these specific EMG channels was shown to provide the best performance of the regression model [ 14 ]. Third, the calibrated EMGMod and RegMod were applied on the test trials to predict the active moment, i.e.,

and

, respectively.…”

Section: Methodsmentioning

confidence: 99%

“…The use of multiple surface EMG electrodes will increase preparation time, may be limited by interference with the exoskeleton, and may cause discomfort and thus limit the practical feasibility of EMG-based trunk muscle models in exoskeleton control. To reduce the number of required EMG channels, an additional calibration step has been suggested [ 14 ]. This step follows the calibration of the EMG-based trunk muscle model by fitting a regression model on data from the same set of calibration trials.…”

Section: Introductionmentioning

confidence: 99%

“…A challenge of this approach is to design an optimal calibration procedure. Previously, EMG-based trunk muscle models and the regression model were calibrated for each user using data obtained during several lifting trials with a range of characteristics, i.e., mass lifted, technique, and velocity [ 14 , 15 ]. However, the time and cost involved with performing an extensive calibration procedure limits practical feasibility as well.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimizing Calibration Procedure to Train a Regression-Based Prediction Model of Actively Generated Lumbar Muscle Moments for Exoskeleton Control

Tabasi

Lazzaroni

Brouwer

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

The risk of low-back pain in manual material handling could potentially be reduced by back-support exoskeletons. Preferably, the level of exoskeleton support relates to the required muscular effort, and therefore should be proportional to the moment generated by trunk muscle activities. To this end, a regression-based prediction model of this moment could be implemented in exoskeleton control. Such a model must be calibrated to each user according to subject-specific musculoskeletal properties and lifting technique variability through several calibration tasks. Given that an extensive calibration limits the practical feasibility of implementing this approach in the workspace, we aimed to optimize the calibration for obtaining appropriate predictive accuracy during work-related tasks, i.e., symmetric lifting from the ground, box stacking, lifting from a shelf, and pulling/pushing. The root-mean-square error (RMSE) of prediction for the extensive calibration was 21.9 Nm (9% of peak moment) and increased up to 35.0 Nm for limited calibrations. The results suggest that a set of three optimally selected calibration trials suffice to approach the extensive calibration accuracy. An optimal calibration set should cover each extreme of the relevant lifting characteristics, i.e., mass lifted, lifting technique, and lifting velocity. The RMSEs for the optimal calibration sets were below 24.8 Nm (10% of peak moment), and not substantially different than that of the extensive calibration.

show abstract

and

, respectively.…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimizing Calibration Procedure to Train a Regression-Based Prediction Model of Actively Generated Lumbar Muscle Moments for Exoskeleton Control

Tabasi

Lazzaroni

Brouwer

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…According to Taylor, Dabnichki, and Strike (2005), the nature of the strategies for the step turn and spin turn are quite different. There are more advantages to the step turn than the spin turn because it has a wide base of support, small angle variations and turning force (requiring muscle), and is more similar to straight walking.…”

Section: Turning Methods When Changing Directionmentioning

confidence: 99%

“…There are more advantages to the step turn than the spin turn because it has a wide base of support, small angle variations and turning force (requiring muscle), and is more similar to straight walking. Additionally, the shortest distance between the toes is smaller in the spin turn than in the step turn, and there is a greater danger of tripping when lower limb coordination is impaired (Taylor et al, 2005). Since both legs are crossed in the spin turn, it is easy for the base of support to be reduced.…”

Section: Turning Methods When Changing Directionmentioning

confidence: 99%

Examining directional changes when walking with an intravenous pole: A comparison of turning methods with and without stopping

Hachigasaki

2020

Japan Journal Nursing Sci

View full text Add to dashboard Cite

Aim: This study aimed to examine safer turning methods by focusing on and comparing gait and turn methods in relation to stopping when executing a turn while walking with an intravenous (IV) pole. Methods: The study participants included 33 healthy men. A situation was recreated in which an IV drip was placed in the peripheral vein of the left forearm of the participants and the IV pole was maneuvered using the left hand. A series of six movements was executed, including turn left and right, stopping. Gait was measured (by observing turning motion, stride, walking speed and head tilt angle), and subjective assessments were performed. Results: Compared with walking normally, walking with an IV pole and executing turns resulted in a decrease in the walking speed, an increase in the time required for walking, a decrease in the stride and a forward tilting in the head angle. Turning left without stopping was mostly accompanied by a spin turn, and the probability of the pole legs coming into contact with participants' legs (15.2%) was higher than that in other assessed movements of walking with a pole. In the subjective assessment, turning left without stopping displayed a lower sense of security (p < .05) than turning left with stopping. Conclusions: When turning while using an IV pole, the pole itself poses a risk of falling. Therefore, momentary stopping and checking the safety of one's footing is a preventive measure against falling. K E Y W O R D S fall, gait, IV pole, turning, walking 1 | INTRODUCTION Over 21% of Japan's population is aged >65 years, which is the highest proportion worldwide. Additionally, the number of hospitalized patients has increased, and the proportion of inpatients among individuals aged ≥65 years has increased from 52.1% in 1996 to 71.1% in 2014. The promotion of early postoperative ambulation and shortened hospital stay has recently increased, and an upward trend can be observed in the percentage of patients using intravenous (IV) poles on a daily basis. According to Hiyama and Nakamura (2017), medical instruments, such as IV drip routes, tubes, and IV poles, restrict patient movement and increase the risk of falling during hospitalization. Moreover, in a nationwide survey conducted by Hachigasaki (2015) on 629 nurses with a minimum of 3 years of experience, 85.7% of respondents felt there is a risk of falling when patients use IV poles.

show abstract

Calibrating an EMG-Driven Muscle Model and a Regression Model to Estimate Moments Generated Actively by Back Muscles for Controlling an Actuated Exoskeleton with Limited Data

Tabasi

Lazzaroni

Brouwer

et al. 2021

Biosystems &Amp; Biorobotics

Self Cite

View full text Add to dashboard Cite

General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.• Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal ? Take down policyIf you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

show abstract

Selecting the appropriate input variables in a regression approach to estimate actively generated muscle moments around L5/S1 for exoskeleton control

Cited by 8 publications

References 28 publications

Optimizing Calibration Procedure to Train a Regression-Based Prediction Model of Actively Generated Lumbar Muscle Moments for Exoskeleton Control

Optimizing Calibration Procedure to Train a Regression-Based Prediction Model of Actively Generated Lumbar Muscle Moments for Exoskeleton Control

Examining directional changes when walking with an intravenous pole: A comparison of turning methods with and without stopping

Calibrating an EMG-Driven Muscle Model and a Regression Model to Estimate Moments Generated Actively by Back Muscles for Controlling an Actuated Exoskeleton with Limited Data

Contact Info

Product

Resources

About