• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

使用非线性特征增强肌电模式识别性能。

Myoelectric Pattern Recognition Performance Enhancement Using Nonlinear Features.

机构信息

Department of Electrical and Electronic Engineering, University of Rajshahi, Rajshahi 6205, Bangladesh.

Department of Physics, Rajshahi University of Engineering and Technology, Rajshahi 6204, Bangladesh.

出版信息

Comput Intell Neurosci. 2022 Apr 29;2022:6414664. doi: 10.1155/2022/6414664. eCollection 2022.

DOI:10.1155/2022/6414664
PMID:35528339
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9076314/
Abstract

The multichannel electrode array used for electromyogram (EMG) pattern recognition provides good performance, but it has a high cost, is computationally expensive, and is inconvenient to wear. Therefore, researchers try to use as few channels as possible while maintaining improved pattern recognition performance. However, minimizing the number of channels affects the performance due to the least separable margin among the movements possessing weak signal strengths. To meet these challenges, two time-domain features based on nonlinear scaling, the log of the mean absolute value (LMAV) and the nonlinear scaled value (NSV), are proposed. In this study, we validate the proposed features on two datasets, the existing four feature extraction methods, variable window size, and various signal-to-noise ratios (SNR). In addition, we also propose a feature extraction method where the LMAV and NSV are grouped with the existing 11 time-domain features. The proposed feature extraction method enhances accuracy, sensitivity, specificity, precision, and F1 score by 1.00%, 5.01%, 0.55%, 4.71%, and 5.06% for dataset 1, and 1.18%, 5.90%, 0.66%, 5.63%, and 6.04% for dataset 2, respectively. Therefore, the experimental results strongly suggest the proposed feature extraction method, for taking a step forward with regard to improved myoelectric pattern recognition performance.

摘要

用于肌电图 (EMG) 模式识别的多通道电极阵列提供了良好的性能，但成本高、计算量大且佩戴不便。因此，研究人员试图在保持改进的模式识别性能的同时，使用尽可能少的通道。然而，由于具有较弱信号强度的运动之间的最小可分离间隙，最小化通道数量会影响性能。为了应对这些挑战，提出了两种基于非线性缩放的时域特征，即对数均绝对值 (LMAV) 和非线性缩放值 (NSV)。在这项研究中，我们在两个数据集上验证了所提出的特征，即现有的四种特征提取方法、可变窗口大小和各种信噪比 (SNR)。此外，我们还提出了一种特征提取方法，其中 LMAV 和 NSV 与现有的 11 个时域特征组合在一起。所提出的特征提取方法将数据集 1 的准确性、灵敏度、特异性、精度和 F1 评分分别提高了 1.00%、5.01%、0.55%、4.71%和 5.06%，将数据集 2 的准确性、灵敏度、特异性、精度和 F1 评分分别提高了 1.18%、5.90%、0.66%、5.63%和 6.04%。因此，实验结果强烈表明所提出的特征提取方法在提高肌电模式识别性能方面向前迈进了一步。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/c51e55c5bfad/CIN2022-6414664.015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/50136f531adf/CIN2022-6414664.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/d18e7ec43aa6/CIN2022-6414664.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/ae9d3b70bcfe/CIN2022-6414664.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/ed57615beca0/CIN2022-6414664.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/9aaa108995c9/CIN2022-6414664.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/bb48a895389a/CIN2022-6414664.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/cb40e6ed2b49/CIN2022-6414664.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/0ffa6cc2fb2d/CIN2022-6414664.008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/dfd08978d60a/CIN2022-6414664.009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/8abbd9d2c8f2/CIN2022-6414664.010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/73c40fcf7ca0/CIN2022-6414664.011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/11d1943e770f/CIN2022-6414664.012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/52bf3d5a1f6c/CIN2022-6414664.013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/9f81c53b9b1f/CIN2022-6414664.014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/c51e55c5bfad/CIN2022-6414664.015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/50136f531adf/CIN2022-6414664.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/d18e7ec43aa6/CIN2022-6414664.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/ae9d3b70bcfe/CIN2022-6414664.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/ed57615beca0/CIN2022-6414664.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/9aaa108995c9/CIN2022-6414664.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/bb48a895389a/CIN2022-6414664.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/cb40e6ed2b49/CIN2022-6414664.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/0ffa6cc2fb2d/CIN2022-6414664.008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/dfd08978d60a/CIN2022-6414664.009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/8abbd9d2c8f2/CIN2022-6414664.010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/73c40fcf7ca0/CIN2022-6414664.011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/11d1943e770f/CIN2022-6414664.012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/52bf3d5a1f6c/CIN2022-6414664.013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/9f81c53b9b1f/CIN2022-6414664.014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d0de/9076314/c51e55c5bfad/CIN2022-6414664.015.jpg

相似文献

1
Myoelectric Pattern Recognition Performance Enhancement Using Nonlinear Features.使用非线性特征增强肌电模式识别性能。
Comput Intell Neurosci. 2022 Apr 29;2022:6414664. doi: 10.1155/2022/6414664. eCollection 2022.
2
A novel channel selection method for multiple motion classification using high-density electromyography.一种使用高密度肌电图进行多运动分类的新型通道选择方法。
Biomed Eng Online. 2014 Jul 25;13:102. doi: 10.1186/1475-925X-13-102.
3
EMG feature assessment for myoelectric pattern recognition and channel selection: a study with incomplete spinal cord injury.用于肌电模式识别和通道选择的肌电图特征评估：一项关于不完全性脊髓损伤的研究。
Med Eng Phys. 2014 Jul;36(7):975-80. doi: 10.1016/j.medengphy.2014.04.003. Epub 2014 May 17.
4
Spatial correlation of high density EMG signals provides features robust to electrode number and shift in pattern recognition for myocontrol.高密度肌电图信号的空间相关性为肌电控制的模式识别提供了对电极数量和偏移具有鲁棒性的特征。
IEEE Trans Neural Syst Rehabil Eng. 2015 Mar;23(2):189-98. doi: 10.1109/TNSRE.2014.2366752. Epub 2014 Nov 6.
5
A Framework of Temporal-Spatial Descriptors-Based Feature Extraction for Improved Myoelectric Pattern Recognition.基于时空描述符的特征提取框架，提高肌电模式识别性能。
IEEE Trans Neural Syst Rehabil Eng. 2017 Oct;25(10):1821-1831. doi: 10.1109/TNSRE.2017.2687520. Epub 2017 Mar 24.
6
Improving robustness against electrode shift of high density EMG for myoelectric control through common spatial patterns.通过共同空间模式提高用于肌电控制的高密度肌电图对电极移位的鲁棒性。
J Neuroeng Rehabil. 2015 Dec 2;12:110. doi: 10.1186/s12984-015-0102-9.
7
Feature dimensionality reduction for myoelectric pattern recognition: a comparison study of feature selection and feature projection methods.用于肌电模式识别的特征降维：特征选择与特征投影方法的比较研究
Med Eng Phys. 2014 Dec;36(12):1716-20. doi: 10.1016/j.medengphy.2014.09.011. Epub 2014 Oct 5.
8
Real-time intelligent pattern recognition algorithm for surface EMG signals.用于表面肌电信号的实时智能模式识别算法
Biomed Eng Online. 2007 Dec 3;6:45. doi: 10.1186/1475-925X-6-45.
9
Identification of a feature selection based pattern recognition scheme for finger movement recognition from multichannel EMG signals.基于特征选择的模式识别方案用于从多通道肌电信号中识别手指运动
Australas Phys Eng Sci Med. 2018 Jun;41(2):549-559. doi: 10.1007/s13246-018-0646-7. Epub 2018 May 9.
10
Towards limb position invariant myoelectric pattern recognition using time-dependent spectral features.利用时变光谱特征实现肢体位置不变的肌电模式识别。
Neural Netw. 2014 Jul;55:42-58. doi: 10.1016/j.neunet.2014.03.010. Epub 2014 Mar 28.

引用本文的文献

1
Empirical Myoelectric Feature Extraction and Pattern Recognition in Hemiplegic Distal Movement Decoding.偏瘫远端运动解码中的经验性肌电特征提取与模式识别
Bioengineering (Basel). 2023 Jul 21;10(7):866. doi: 10.3390/bioengineering10070866.
2
Supervised Myoelectrical Hand Gesture Recognition in Post-Acute Stroke Patients with Upper Limb Paresis on Affected and Non-Affected Sides.上肢瘫痪的脑卒中后患者患侧和非患侧的肌电手动作的监督识别。
Sensors (Basel). 2022 Nov 11;22(22):8733. doi: 10.3390/s22228733.
3
Machine Learning-Based Diabetic Neuropathy and Previous Foot Ulceration Patients Detection Using Electromyography and Ground Reaction Forces during Gait.

本文引用的文献

1
A Hierarchical View Pooling Network for Multichannel Surface Electromyography-Based Gesture Recognition.基于多通道表面肌电信号的手势识别的分层视图池网络。
Comput Intell Neurosci. 2021 Aug 26;2021:6591035. doi: 10.1155/2021/6591035. eCollection 2021.
2
Improvement of EMG Pattern Recognition Model Performance in Repeated Uses by Combining Feature Selection and Incremental Transfer Learning.通过结合特征选择和增量迁移学习提高肌电图模式识别模型在重复使用中的性能
Front Neurorobot. 2021 Jun 14;15:699174. doi: 10.3389/fnbot.2021.699174. eCollection 2021.
3
Force-Invariant Improved Feature Extraction Method for Upper-Limb Prostheses of Transradial Amputees.
基于机器学习的肌电图和步态中地面反力检测糖尿病周围神经病变和既往足部溃疡患者
Sensors (Basel). 2022 May 5;22(9):3507. doi: 10.3390/s22093507.
经桡骨截肢者上肢假肢的力不变改进特征提取方法
Diagnostics (Basel). 2021 May 7;11(5):843. doi: 10.3390/diagnostics11050843.
4
Lw-CNN-Based Myoelectric Signal Recognition and Real-Time Control of Robotic Arm for Upper-Limb Rehabilitation.基于轻量化卷积神经网络的上肢康复用肌电信号识别与机器人手臂实时控制
Comput Intell Neurosci. 2020 Dec 28;2020:8846021. doi: 10.1155/2020/8846021. eCollection 2020.
5
Classification of forearm EMG signals for 10 motions using optimum feature-channel combinations.使用最优特征-通道组合对 10 种运动的前臂肌电信号进行分类。
Comput Methods Biomech Biomed Engin. 2021 Jul;24(9):945-955. doi: 10.1080/10255842.2020.1861256. Epub 2020 Dec 27.
6
Performance analysis of noninvasive electrophysiological methods for the assessment of diabetic sensorimotor polyneuropathy in clinical research: a systematic review and meta-analysis with trial sequential analysis.非侵入性电生理方法评估糖尿病感觉运动多发性神经病的临床研究中的性能分析：系统评价和试验序贯分析荟萃分析。
Sci Rep. 2020 Dec 10;10(1):21770. doi: 10.1038/s41598-020-78787-0.
7
An Energy-Based Method for Orientation Correction of EMG Bracelet Sensors in Hand Gesture Recognition Systems.基于能量的方法用于手势识别系统中肌电手环传感器的方向校正。
Sensors (Basel). 2020 Nov 6;20(21):6327. doi: 10.3390/s20216327.
8
Hand Gesture Recognition based on Surface Electromyography using Convolutional Neural Network with Transfer Learning Method.基于卷积神经网络的迁移学习方法的表面肌电手势识别。
IEEE J Biomed Health Inform. 2021 Apr;25(4):1292-1304. doi: 10.1109/JBHI.2020.3009383. Epub 2021 Apr 6.
9
Cross-Subject and Cross-Modal Transfer for Generalized Abnormal Gait Pattern Recognition.跨主题和跨模态转移的广义异常步态模式识别。
IEEE Trans Neural Netw Learn Syst. 2021 Feb;32(2):546-560. doi: 10.1109/TNNLS.2020.3009448. Epub 2021 Feb 4.
10
An Improved Performance of Deep Learning Based on Convolution Neural Network to Classify the Hand Motion by Evaluating Hyper Parameter.基于卷积神经网络的深度学习在通过评估超参数对手部运动进行分类方面的性能改进。
IEEE Trans Neural Syst Rehabil Eng. 2020 Jul;28(7):1678-1688. doi: 10.1109/TNSRE.2020.2999505.