Upper Limb Movement Classification Via Electromyographic Signals and an Enhanced Probabilistic Network

Burns, Alexis; Adeli, Hojjat; Buford, John A.

doi:10.1007/s10916-020-01639-x

Cited by 44 publications

(11 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These approaches are well suited, often superior to traditional means-based statistics, for handling the relatively large number of measurements possible from biomechanics [ 51 ]. Machine learning approaches have proven successful at detecting upper limb movement patterns from electromyography (EMG) with wearable sensors [ 52 ]. They have also proven useful to predict outcomes from CIMT rehabilitation in adults after stroke [ 53 ].…”

Section: Discussionmentioning

confidence: 99%

3D Motion Capture May Detect Spatiotemporal Changes in Pre-Reaching Upper Extremity Movements with and without a Real-Time Constraint Condition in Infants with Perinatal Stroke and Cerebral Palsy: A Longitudinal Case Series

Mazzarella

McNally

Richie

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Perinatal stroke (PS), occurring between 20 weeks of gestation and 28 days of life, is a leading cause of hemiplegic cerebral palsy (HCP). Hallmarks of HCP are motor and sensory impairments on one side of the body—especially the arm and hand contralateral to the stroke (involved side). HCP is diagnosed months or years after the original brain injury. One effective early intervention for this population is constraint-induced movement therapy (CIMT), where the uninvolved arm is constrained by a mitt or cast, and therapeutic activities are performed with the involved arm. In this preliminary investigation, we used 3D motion capture to measure the spatiotemporal characteristics of pre-reaching upper extremity movements and any changes that occurred when constraint was applied in a real-time laboratory simulation. Participants were N = 14 full-term infants: N = six infants with typical development; and N = eight infants with PS (N = three infants with PS were later diagnosed with cerebral palsy (CP)) followed longitudinally from 2 to 6 months of age. We aimed to evaluate the feasibility of using 3D motion capture to identify the differences in the spatiotemporal characteristics of the pre-reaching upper extremity movements between the diagnosis group, involved versus uninvolved side, and with versus and without constraint applied in real time. This would be an excellent application of wearable sensors, allowing some of these measurements to be taken in a clinical or home setting.

show abstract

Section: Discussionmentioning

confidence: 99%

3D Motion Capture May Detect Spatiotemporal Changes in Pre-Reaching Upper Extremity Movements with and without a Real-Time Constraint Condition in Infants with Perinatal Stroke and Cerebral Palsy: A Longitudinal Case Series

Mazzarella

McNally

Richie

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Burns et al proposes a classification method combining discrete wavelet transform and enhanced probabilistic neural network (EPNN). Compared with SVM, k-Nearest Neighbor (KNN), and probabilistic neural network, it is proved that the performance of the proposed method is better than that of machine learning algorithm alone (Burns et al, 2020). Atzori et al (2016) applied convolutional neural network to sEMG data classification, and the proposed framework classification accuracy was higher than the average accuracy obtained by classical methods, with the highest accuracy reaching 87.8%.…”

Section: Semg-based Hri Related Studymentioning

confidence: 98%

“…In fact, deep convolutional neural networks (CNNs) can automatically extract appropriate features from the data. Some researchers have designed deep learning-based HRIs, which can achieve higher lower limb movement prediction performance than hand-crafted features (Atzori et al, 2016;Hartwell et al, 2018;Duan et al, 2019;Burns et al, 2020). However, due to the large amount of data required by deep learning, when predicting small datasets (such as the lower extremity motion dataset for a single hemiplegic patient), the lower-limb movement prediction method based on deep learning often suffers from overfitting.…”

Section: Introductionmentioning

confidence: 99%

An sEMG-Based Human-Exoskeleton Interface Fusing Convolutional Neural Networks With Hand-Crafted Features

Yang

et al. 2022

Front. Neurorobot.

View full text Add to dashboard Cite

In recent years, the human-robot interfaces (HRIs) based on surface electromyography (sEMG) have been widely used in lower-limb exoskeleton robots for movement prediction during rehabilitation training for patients with hemiplegia. However, accurate and efficient lower-limb movement prediction for patients with hemiplegia remains a challenge due to complex movement information and individual differences. Traditional movement prediction methods usually use hand-crafted features, which are computationally cheap but can only extract some shallow heuristic information. Deep learning-based methods have a stronger feature expression ability, but it is easy to fall into the dilemma of local features, resulting in poor generalization performance of the method. In this article, a human-exoskeleton interface fusing convolutional neural networks with hand-crafted features is proposed. On the basis of our previous study, a lower-limb movement prediction framework (HCSNet) in patients with hemiplegia is constructed by fusing time and frequency domain hand-crafted features and channel synergy learning-based features. An sEMG data acquisition experiment is designed to compare and analyze the effectiveness of HCSNet. Experimental results show that the method can achieve 95.93 and 90.37% prediction accuracy in both within-subject and cross-subject cases, respectively. Compared with related lower-limb movement prediction methods, the proposed method has better prediction performance.

show abstract

“…As a crucial branch of machine learning, classification has received great attention [1,2,3]. The models used for classification are often referred to as classifiers [4,5].…”

Section: Introductionmentioning

confidence: 99%

“…To better solve the classification problems, a large amount of features are often included, however, most of them are irrelevant or redundant in many cases, resulting in the possibility of reduction of classification accuracy, model complexity, etc [6,7,8]. Classification is a fundamental task in machine learning [9,10] which enables a range of applications such as medicine [11,12,13,14] with numerous 1 Corresponding Author: F. Neri, School of Computer Science, Jubilee Campus, Wollaton Road, Nottingham NG8 1BB, UK; Email: ferrante.neri@nottingham.ac.uk Y. Xue and H. Zhu equally contributed to this work and should be considered co-first authors application in diagnostics based on electroencephalogram [15,16,17]. Other studies, more broadly, focus on neurobiology [18,19].…”

Section: Introductionmentioning

confidence: 99%

A self-adaptive multi-objective feature selection approach for classification problems

Xue

Zhu

Neri

2021

ICA

View full text Add to dashboard Cite

In classification tasks, feature selection (FS) can reduce the data dimensionality and may also improve classification accuracy, both of which are commonly treated as the two objectives in FS problems. Many meta-heuristic algorithms have been applied to solve the FS problems and they perform satisfactorily when the problem is relatively simple. However, once the dimensionality of the datasets grows, their performance drops dramatically. This paper proposes a self-adaptive multi-objective genetic algorithm (SaMOGA) for FS, which is designed to maintain a high performance even when the dimensionality of the datasets grows. The main concept of SaMOGA lies in the dynamic selection of five different crossover operators in different evolution process by applying a self-adaptive mechanism. Meanwhile, a search stagnation detection mechanism is also proposed to prevent premature convergence. In the experiments, we compare SaMOGA with five multi-objective FS algorithms on sixteen datasets. According to the experimental results, SaMOGA yields a set of well converged and well distributed solutions on most data sets, indicating that SaMOGA can guarantee classification performance while removing many features, and the advantage over its counterparts is more obvious when the dimensionality of datasets grows.

show abstract

Upper Limb Movement Classification Via Electromyographic Signals and an Enhanced Probabilistic Network

Cited by 44 publications

References 65 publications

3D Motion Capture May Detect Spatiotemporal Changes in Pre-Reaching Upper Extremity Movements with and without a Real-Time Constraint Condition in Infants with Perinatal Stroke and Cerebral Palsy: A Longitudinal Case Series

3D Motion Capture May Detect Spatiotemporal Changes in Pre-Reaching Upper Extremity Movements with and without a Real-Time Constraint Condition in Infants with Perinatal Stroke and Cerebral Palsy: A Longitudinal Case Series

An sEMG-Based Human-Exoskeleton Interface Fusing Convolutional Neural Networks With Hand-Crafted Features

A self-adaptive multi-objective feature selection approach for classification problems

Contact Info

Product

Resources

About