scholarly journals Classification Performance and Feature Space Characteristics in Individuals with Upper Limb Loss Using Sonomyography

2022 ◽  
pp. 1-1
Author(s):  
Susannah Engdahl ◽  
Ananya Dhawan ◽  
Ahmed Bashatah ◽  
Guoqing Diao ◽  
Biswarup Mukherjee ◽  
...  
Keyword(s):  
Upper Limb ◽  
Feature Space ◽  
Classification Performance ◽  
Limb Loss

Classification Performance and Feature Space Characteristics in Individuals with Upper Limb Loss Using Sonomyography

2021 ◽  
Author(s):  
Susannah Engdahl ◽  
Ananya Dhawan ◽  
Ahmed Bashatah ◽  
Guoqing Diao ◽  
Biswarup Mukherjee ◽  
...  
Keyword(s):  
Upper Limb ◽  
Classification Accuracy ◽  
Feature Space ◽  
Classification Performance ◽  
Limb Loss ◽  
User Performance ◽  
Initial Exposure ◽  
Upper Limb Prosthesis ◽  
Subsequent Exposure ◽  
Training Protocol

Abstract Objective: Sonomyography, or ultrasound-based sensing of muscle deformation, is an emerging modality for upper limb prosthesis control. Although prior studies have shown that individuals with upper limb loss can achieve successful motion classification with sonomyography, it is important to better understand the time-course over which proficiency develops. In this study, we characterized user performance during their initial and subsequent exposures to sonomyography. Method: Ultrasound images corresponding to a series of hand gestures were collected from individuals with transradial limb loss under three scenarios: during their initial exposure to sonomyography (Experiment 1), during a subsequent exposure to sonomyography where they were provided biofeedback as part of a training protocol (Experiment 2), and during testing sessions held on different days (Experiment 3). User performance was characterized by offline classification accuracy, as well as metrics describing the consistency and separability of the sonomyography signal patterns in feature space. Results: Classification accuracy was high during initial exposure to sonomyography (96.2 ± 5.9%) and did not systematically change with the provision of biofeedback or on different days. Despite this stable classification performance, some of the feature space metrics changed. Conclusions: User performance was strong upon their initial exposure to sonomyography and did not improve with subsequent exposure. Clinical Impact: Prosthetists may be able to quickly assess if a patient will be successful with sonomyography without submitting them to an extensive training protocol, leading to earlier socket fabrication and delivery.

scholarly journals Individuals With Upper Limb Loss Require Minimal Training to Achieve Robust Motion Classification Using Sonomyography

2020 ◽  
Author(s):  
Susannah Engdahl ◽  
Ananya Dhawan ◽  
Ahmed Bashatah ◽  
Guoqing Diao ◽  
Biswarup Mukherjee ◽  
...  
Keyword(s):  
Upper Limb ◽  
Cross Validation ◽  
Positive Association ◽  
Classification Performance ◽  
Limb Loss ◽  
Ultrasound Images ◽  
Motion Classification ◽  
Initial Exposure ◽  
Motion Patterns ◽  
Upper Limb Prostheses

Abstract Background: Although surface electromyography is commonly used as a sensing strategy for upper limb prostheses, it remains difficult to reliably decode the recorded signals for controlling multi-articulated hands. Sonomyography, or ultrasound-based sensing of muscle deformation, overcomes some of these issues and allows individuals with upper limb loss to reliably perform multiple motion patterns. The purposes of this study were to determine 1) the effect of training on classification performance with sonomyographic control and 2) the effect of training on the underlying muscle deformation patterns.Methods: A series of motion pattern datasets were collected from five individuals with transradial limb loss. Each dataset contained five ultrasound images corresponding each of the following five motions: power grasp, wrist pronation, key grasp, tripod, point. Participants initially performed the motions for the datasets without receiving feedback on their performance (baseline phase), then with visual and verbal feedback (feedback phase), and finally again without feedback (retention phase). Cross-validation accuracy and metrics describing the consistency and separability of the muscle deformation patters were computed for each dataset. Changes in classification performance over the course of the study were assessed using linear mixed models. Associations between classification performance and the consistency and separability metrics were evaluated using Pearson correlations.Results: The average cross-validation accuracy for each phase was 92% or greater and there was no significant change in cross-validation accuracy throughout training. Misclassifications of one motion as another did not persist systematically across datasets. Few of the correlations were significant, although many were moderate or greater in strength and showed a positive association between accuracy and improved consistency and separability metrics.Conclusions: Participants were able to achieve high classification rates upon their initial exposure to sonomyography and training did not affect their performance. Thus, motion classification using sonomyography may be highly intuitive and is unlikely to require a structured training protocol to gain proficiency.

scholarly journals Motion prediction using electromyography and sonomyography for an individual with transhumeral limb loss

2020 ◽  
Author(s):  
Susannah Engdahl ◽  
Ananya Dhawan ◽  
György Lévay ◽  
Ahmed Bashatah ◽  
Rahul Kaliki ◽  
...  
Keyword(s):  
Upper Limb ◽  
Cross Validation ◽  
Classification Performance ◽  
Limb Loss ◽  
Single Individual ◽  
Motion Classification ◽  
Motion Patterns ◽  
Prosthetic Hands ◽  
Upper Limb Prosthesis ◽  
Power Grasp

AbstractControlling multi-articulated prosthetic hands with surface electromyography can be challenging for users. Sonomyography, or ultrasound-based sensing of muscle deformation, avoids some of the problems of electromyography and enables classification of multiple motion patterns in individuals with upper limb loss. Because sonomyography has been previously studied only in individuals with transradial limb loss, the purpose of this study was to assess the feasibility of an individual with transhumeral limb loss using this modality for motion classification. A secondary aim was to compare motion classification performance between electromyography and sonomyography. A single individual with transhumeral limb loss created two datasets containing 11 motions each (individual flexion of each finger, thumb abduction, power grasp, key grasp, tripod, point, pinch, wrist pronation). Electromyography or sonomyography signals associated with every motion were acquired and cross-validation accuracy was computed for each dataset. While all motions were usually predicted successfully with both electromyography and sonomyography, the cross-validation accuracies were typically higher for sonomyography. Although this was an exploratory study, the results suggest that controlling an upper limb prosthesis using sonomyography may be feasible for individuals with transhumeral limb loss.

Variability in Muscle Recruitment Strategy Between Operators During Assisted Assembly Tasks

2018 ◽  
Author(s):  
Yingxin Qiu ◽  
Keerthana Murali ◽  
Jun Ueda ◽  
Atsushi Okabe ◽  
Dalong Gao
Keyword(s):  
Upper Limb ◽  
Lower Limb ◽  
Wrist Joint ◽  
Principal Component ◽  
Classification Performance ◽  
Body Motion ◽  
Recruitment Strategy ◽  
Support Vector ◽  
Recruitment Strategies ◽  
Muscle Recruitment

This paper reports the variability in muscle recruitment strategies among individuals who operate a non-powered lifting device for general assembly (GA) tasks. Support vector machine (SVM) was applied to the classification of motion states of operators using electromyography (EMG) signals collected from a total of 15 upper limb, lower limb, shoulder, and torso muscles. By comparing the classification performance and muscle activity features, variability in muscle recruitment strategy was observed from lower limb and torso muscles, while the recruitment strategies of upper limb and shoulder muscles were relatively consistent across subjects. Principal component analysis (PCA) was applied to identify key muscles that are highly correlated with body movements. Selected muscles at the wrist joint, ankle joint and scapula are considered to have greater significance in characterizing the muscle recruitment strategies than other investigated muscles. PCA loading factors also indicate the existence of body motion redundancy during typical pick-and-place tasks.

A systematical approach to classification problems with feature space heterogeneity

Kybernetes ◽  
2019 ◽  
Vol 48 (9) ◽  
pp. 2006-2029
Author(s):  
Hongshan Xiao ◽  
Yu Wang
Keyword(s):  
Factor Analysis ◽  
Meta Analysis ◽  
Feature Space ◽  
Classification Performance ◽  
Classification Algorithm ◽  
Significant Feature ◽  
Data Sets ◽  
Data Set ◽  
Classification Techniques ◽  
Content Type

Purpose Feature space heterogeneity exists widely in various application fields of classification techniques, such as customs inspection decision, credit scoring and medical diagnosis. This paper aims to study the relationship between feature space heterogeneity and classification performance. Design/methodology/approach A measurement is first developed for measuring and identifying any significant heterogeneity that exists in the feature space of a data set. The main idea of this measurement is derived from a meta-analysis. For the data set with significant feature space heterogeneity, a classification algorithm based on factor analysis and clustering is proposed to learn the data patterns, which, in turn, are used for data classification. Findings The proposed approach has two main advantages over the previous methods. The first advantage lies in feature transform using orthogonal factor analysis, which results in new features without redundancy and irrelevance. The second advantage rests on samples partitioning to capture the feature space heterogeneity reflected by differences of factor scores. The validity and effectiveness of the proposed approach is verified on a number of benchmarking data sets. Research limitations/implications Measurement should be used to guide the heterogeneity elimination process, which is an interesting topic in future research. In addition, to develop a classification algorithm that enables scalable and incremental learning for large data sets with significant feature space heterogeneity is also an important issue. Practical implications Measuring and eliminating the feature space heterogeneity possibly existing in the data are important for accurate classification. This study provides a systematical approach to feature space heterogeneity measurement and elimination for better classification performance, which is favorable for applications of classification techniques in real-word problems. Originality/value A measurement based on meta-analysis for measuring and identifying any significant feature space heterogeneity in a classification problem is developed, and an ensemble classification framework is proposed to deal with the feature space heterogeneity and improve the classification accuracy.

scholarly journals Kernel Joint Sparse Representation Based on Self-Paced Learning for Hyperspectral Image Classification

2019 ◽  
Vol 11 (9) ◽  
pp. 1114
Author(s):  
Sixiu Hu ◽  
Jiangtao Peng ◽  
Yingxiong Fu ◽  
Luoqing Li
Keyword(s):  
Sparse Representation ◽  
Hyperspectral Image ◽  
Feature Space ◽  
Classification Performance ◽  
Hyperspectral Data ◽  
Data Sets ◽  
Neighborhood Structure ◽  
Joint Sparse Representation ◽  
Negative Effect ◽  
Sparse Coefficient

By means of joint sparse representation (JSR) and kernel representation, kernel joint sparse representation (KJSR) models can effectively model the intrinsic nonlinear relations of hyperspectral data and better exploit spatial neighborhood structure to improve the classification performance of hyperspectral images. However, due to the presence of noisy or inhomogeneous pixels around the central testing pixel in the spatial domain, the performance of KJSR is greatly affected. Motivated by the idea of self-paced learning (SPL), this paper proposes a self-paced KJSR (SPKJSR) model to adaptively learn weights and sparse coefficient vectors for different neighboring pixels in the kernel-based feature space. SPL strateges can learn a weight to indicate the difficulty of feature pixels within a spatial neighborhood. By assigning small weights for unimportant or complex pixels, the negative effect of inhomogeneous or noisy neighboring pixels can be suppressed. Hence, SPKJSR is usually much more robust. Experimental results on Indian Pines and Salinas hyperspectral data sets demonstrate that SPKJSR is much more effective than traditional JSR and KJSR models.

scholarly journals Finer Resolution Mapping of Marine Aquaculture Areas Using WorldView-2 Imagery and a Hierarchical Cascade Convolutional Neural Network

2019 ◽  
Vol 11 (14) ◽  
pp. 1678 ◽  
Author(s):  
Yongyong Fu ◽  
Ziran Ye ◽  
Jinsong Deng ◽  
Xinyu Zheng ◽  
Yibo Huang ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Contextual Information ◽  
Feature Space ◽  
Classification Performance ◽  
Support Vector ◽  
Marine Resources ◽  
Marine Aquaculture ◽  
Multi Scale ◽  
Coastal Marine

Marine aquaculture plays an important role in seafood supplement, economic development, and coastal ecosystem service provision. The precise delineation of marine aquaculture areas from high spatial resolution (HSR) imagery is vital for the sustainable development and management of coastal marine resources. However, various sizes and detailed structures of marine objects make it difficult for accurate mapping from HSR images by using conventional methods. Therefore, this study attempts to extract marine aquaculture areas by using an automatic labeling method based on the convolutional neural network (CNN), i.e., an end-to-end hierarchical cascade network (HCNet). Specifically, for marine objects of various sizes, we propose to improve the classification performance by utilizing multi-scale contextual information. Technically, based on the output of a CNN encoder, we employ atrous convolutions to capture multi-scale contextual information and aggregate them in a hierarchical cascade way. Meanwhile, for marine objects with detailed structures, we propose to refine the detailed information gradually by using a series of long-span connections with fine resolution features from the shallow layers. In addition, to decrease the semantic gaps between features in different levels, we propose to refine the feature space (i.e., channel and spatial dimensions) using an attention-based module. Experimental results show that our proposed HCNet can effectively identify and distinguish different kinds of marine aquaculture, with 98% of overall accuracy. It also achieves better classification performance compared with object-based support vector machine and state-of-the-art CNN-based methods, such as FCN-32s, U-Net, and DeeplabV2. Our developed method lays a solid foundation for the intelligent monitoring and management of coastal marine resources.

Shift-Invariance of Pattern Recognition in the Visual Field?

Perception ◽  
1996 ◽  
Vol 25 (1_suppl) ◽  
pp. 78-78 ◽  
Author(s):  
M Jüttner ◽  
I Rentschler ◽  
A Unzicker
Keyword(s):  
Visual Field ◽  
Feature Space ◽  
Classification Performance ◽  
Classification Model ◽  
Perceptual Dimension ◽  
Internal Representations ◽  
Visual Hemifield ◽  
Shift Invariance ◽  
Hemispheric Specialisation ◽  
The Individual

The classification behaviour of human observers with respect to compound Gabor signals was tested at foveal and extrafoveal retinal positions. Classification performance was analysed in terms of a probabilistic classification model recently proposed by Rentschler, Jüttner, and Caelli (1994 Vision Research34 669 – 687). The analysis allows inferences about structure and dimensionality of the individual internal representations underlying the classification task and their temporal evolution during the learning process. With this technique it was found that the internal representations of direct and eccentric viewing are intrinsically incommensurable in the sense that extrafoveal pattern representations are characterised by a lower perceptual dimension in feature space relative to the corresponding physical input signals, whereas foveal representations are not (Jüttner and Rentschler, 1996 Vision Research in press). We then addressed the question to what extent observers are capable of generalising class concepts that have been acquired at one particular retinal location to other retinal sites. We found partial generalisation with respect to spatial translation across the visual field. Moreover, there is, in the case of extrafoveal learning, a distinct asymmetry in performance with respect to the visual hemifield in which the signals were originally learned. The latter finding can be related to functional hemispheric specialisation in pattern learning and recognition.

scholarly journals Fault Diagnosis for Rolling Element Bearings Based on Feature Space Reconstruction and Multiscale Permutation Entropy

Entropy ◽  
2019 ◽  
Vol 21 (5) ◽  
pp. 519 ◽  
Author(s):  
Weibo Zhang ◽  
Jianzhong Zhou
Keyword(s):  
Diagnostic Algorithm ◽  
Feature Space ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Ensemble Empirical Mode Decomposition ◽  
Classification Performance ◽  
Fault Classification ◽  
Permutation Entropy ◽  
Support Vector ◽  
Intrinsic Mode Functions

Aimed at distinguishing different fault categories of severity of rolling bearings, a novel method based on feature space reconstruction and multiscale permutation entropy is proposed in the study. Firstly, the ensemble empirical mode decomposition algorithm (EEMD) was employed to adaptively decompose the vibration signal into multiple intrinsic mode functions (IMFs), and the representative IMFs which contained rich fault information were selected to reconstruct a feature vector space. Secondly, the multiscale permutation entropy (MPE) was used to calculate the complexity of reconstructed feature space. Finally, the value of multiscale permutation entropy was presented to a support vector machine for fault classification. The proposed diagnostic algorithm was applied to three groups of rolling bearing experiments. The experimental results indicate that the proposed method has better classification performance and robustness than other traditional methods.

Sign in / Sign up

Export Citation Format

Share Document