Optimization of Sensor Number for Lower Limb Prosthetics using Genetic Algorithm

Halim, Ahmed A. El Baset A. El; Ibrahim, Ahmed Abdellatif Hamed; Awad, Mohammed I.; Atia, Mostafa R. A.

doi:10.1109/itce48509.2020.9047780

Cited by 3 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Su et al (2019) used a convolutional neural network for classification and reached an overall error rate of 5.85% in ten able-bodied subjects. Halim et al (2020) reached an average overall error of 6.0% using a random forest classifier on the ENABL3S dataset. Hu et al (2018b) reported an average error rate of 2.09 ± 0.27% and 5.94 ± 0.84 for overall and transitional errors, respectively, using an ipsilateral sensor setup.…”

Section: Discussionmentioning

confidence: 99%

“…Another limitation of our study is that we did not investigate the influence of sensor selection on the error rate. One could expect based on the literature that, by using sensor selection, the error rate could be reduced even further, such as shown by Young et al (2014) , or that the computational time can be reduced while not decreasing the error rate as shown by Halim et al (2020) . Sensor selection next to feature selection could be performed by a genetic algorithm, but this would greatly increase the search space, and thus, the question would arise again whether this search space is not too large.…”

Section: Discussionmentioning

confidence: 99%

“…They concluded that a genetic algorithm can optimize support vector machine parameters to increase classification accuracy, from 66.1% up to 97.6%. Halim et al (2020) used a genetic algorithm to reduce the number of sensors necessary to reach similar performance versus all sensors in the lower limb. They showed that, with only a decrease of 0.9% in accuracy from 94.0 to 93.1%, they could reduce the number of sensors necessary by 54%.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Genetic Algorithm for Feature Selection in Lower Limb Pattern Recognition

et al. 2021

View full text Add to dashboard Cite

Choosing the right features is important to optimize lower limb pattern recognition, such as in prosthetic control. EMG signals are noisy in nature, which makes it more challenging to extract useful information. Many features are used in the literature, which raises the question which features are most suited for use in lower limb myoelectric control. Therefore, it is important to find combinations of best performing features. One way to achieve this is by using a genetic algorithm, a meta-heuristic capable of searching vast feature spaces. The goal of this research is to demonstrate the capabilities of a genetic algorithm and come up with a feature set that has a better performance than the state-of-the-art feature set. In this study, we collected a dataset containing ten able-bodied subjects who performed various gait-related activities while measuring EMG and kinematics. The genetic algorithm selected features based on the performance on the training partition of this dataset. The selected feature sets were evaluated on the remaining test set and on the online benchmark dataset ENABL3S, against a state-of-the-art feature set. The results show that a feature set based on the selected features of a genetic algorithm outperforms the state-of-the-art set. The overall error decreased up to 0.54% and the transitional error by 2.44%, which represent a relative decrease in overall errors up to 11.6% and transitional errors up to 14.1%, although these results were not significant. This study showed that a genetic algorithm is capable of searching a large feature space and that systematic feature selection shows promising results for lower limb myoelectric control.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Genetic Algorithm for Feature Selection in Lower Limb Pattern Recognition

et al. 2021

View full text Add to dashboard Cite

show abstract

“…This dataset was used in several types of research. 12,31–33 This dataset contains neuromechanical signals of the lower body for 10 healthy subjects. For the work in this paper, only raw data are used.…”

Section: Methodsmentioning

confidence: 99%

Prediction of human gait activities using wearable sensors

Halim

Abdellatif

Awad

et al. 2021

Proc Inst Mech Eng H

View full text Add to dashboard Cite

This paper aims to enhance the accuracy of human gait prediction using machine learning algorithms. Three classifiers are used in this paper: XGBoost, Random Forest, and SVM. A predefined dataset is used for feature extraction and classification. Gait prediction is determined during several locomotion activities: sitting (S), level walking (LW), ramp ascend (RA), ramp descend (RD), stair ascend (SA), stair descend (SD), and standing (ST). The results are gained for steady-state (SS) and overall (full) gait cycle. Two sets of sensors are used. The first set uses inertial measurement units only. The second set uses inertial measurement units, electromyography, and electro-goniometers. The comparison is based on prediction accuracy and prediction time. In addition, a comparison between the prediction times of XGBoost with CPU and GPU is introduced due to the easiness of using XGBoost with GPU. The results of this paper can help to choose a classifier for gait prediction that can obtain acceptable accuracy with fewer types of sensors.

show abstract

“…They concluded that a genetic algorithm can optimize support vector machine parameters to increase Introduction classification accuracy, from 66.1% up to 97.6%. Halim et al [92] used a genetic algorithm to reduce the number of sensors necessary to reach similar performance versus all sensors in the lower limb. They showed that with only a decrease of 0.9% in accuracy from 94.0% to 93.1% they could reduce the number of sensors necessary by 54%.…”

Section: Introductionmentioning

confidence: 99%

Up to one's knees in data : data-driven intent recognition using electromyography for the lower limb

Schulte¹

View full text Add to dashboard Cite

Approximately two thousand people undergo a major lower-limb amputation in the Netherlands per year. Reasons for amputation vary, but in high income countries vascular diseases are the main cause for amputation [1-5], followed by trauma [1, 6].A lower-limb amputation can drastically change a person's functional abilities, which leads to a lower quality of life [1, 7]. Individuals with an amputation regain some of those functional abilities by learning to use a prosthesis [8]. Most of the prosthetic components are passive and are adequate for most walking scenarios in daily life.However, these devices are not capable of generating power to provide support during standing up and stair walking for instance [8][9][10]. This means that the residual leg Chapter 2

show abstract

Optimization of Sensor Number for Lower Limb Prosthetics using Genetic Algorithm

Cited by 3 publications

References 10 publications

Genetic Algorithm for Feature Selection in Lower Limb Pattern Recognition

Genetic Algorithm for Feature Selection in Lower Limb Pattern Recognition

Prediction of human gait activities using wearable sensors

Up to one's knees in data : data-driven intent recognition using electromyography for the lower limb

Contact Info

Product

Resources

About