检索结果-内蒙古大学图书馆

Myoelectric Pattern Recognition Using Gramian Angular Field and Convolutional Neural Networks for muscle-computer interface

引用

SENSORS 2023年第5期23卷 2715-2715页

作者： Fan, Junjun Wen, Jiajun Lai, Zhihui Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Shenzhen Univ Guangdong Lab Artificial Intelligence & Cyber Econ Shenzhen 518060 Peoples R China

In the field of the muscle-computer interface, the most challenging task is extracting patterns from complex surface electromyography (sEMG) signals to improve the performance of myoelectric pattern recognition. To address this problem, a two-stage architecture, consisting of Gramian angular field (GAF)-based 2D representation and convolutional neural network (CNN)-based classification (GAF-CNN), is proposed. To explore discriminant channel features from sEMG signals, sEMG-GAF transformation is proposed for time sequence signal representation and feature modeling, in which the instantaneous values of multichannel sEMG signals are encoded in image form. A deep CNN model is introduced to extract high-level semantic features lying in image-form-based time sequence signals concerning instantaneous values for image classification. An insight analysis explains the rationale behind the advantages of the proposed method. Extensive experiments are conducted on benchmark publicly available sEMG datasets, i.e., NinaPro and CagpMyo, whose experimental results validate that the proposed GAF-CNN method is comparable to the state-of-the-art methods, as reported by previous work incorporating CNN models.

关键词： muscle-computer interface surface electromyography myoelectric pattern recognition Gramian angular field convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CApG-Myo: A muscle-computer interface supporting user-defined gesture recognition 21

CApG-Myo: A muscle-computer interface supporting user-define...

引用

9th International Conference on computer and Communications Management, ICCCM 2021

作者： Dai, Qingfeng Li, Xiangdong Geng, Weidong Jin, Wenguang Liang, Xiubo Zhejiang University China

ISBN: (纸本)9781450390071

The recent progress in sEMG-based hand gesture detection has developed a set of predefined hand gestures for interaction. However, customized hand gestures are less concerned due to the lack of supporting tools for training alternative hand gestures. To fill the gap, we present a training system, called CAPG-MYO, for user-defined hand gesture interaction. An armband named CAPG was used to simultaneously capture sEMG and IMU signals from the participants to construct a small-scale dataset with the customized hand gestures. To predict the customized hand gestures, we developed a multiview convolutional neural network to handle the dataset and consequently shaped a gesture recognition model that effectively transferred a model of 8-hand gesture recognition into a model of the customized hand gesture recognition. We conducted technical validation of the system and the results demonstrate the system's accuracy of hand gesture recognition, which reached 84.71% after a 2min training. © 2021 Association for Computing Machinery.

关键词： deep learning muscle-computer interface gesture recognition user-defined sEMG

来源：评论

学校读者我要写书评

暂无评论

Sparsity Analysis of a Sonomyographic muscle-computer interface

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2020年第3期67卷 688-696页

作者： Akhlaghi, Nima Dhawan, Ananya Khan, Amir A. Mukherjee, Biswarup Diao, Guoqing Truong, Cecile Sikdar, Siddhartha George Mason Univ Dept Bioengn Fairfax VA 22030 USA George Mason Univ Dept Comp Sci Fairfax VA 22030 USA George Mason Univ Ctr Adapt Syst Brain Body Interact Fairfax VA 22030 USA George Mason Univ Dept Stat Fairfax VA 22030 USA

Objective: Sonomyography has been shown to be a promising method for decoding volitional motor intent from analysis of ultrasound images of the forearm musculature. The objectives of this paper are to determine the optimal location for ultrasound transducer placement on the anterior forearm for imaging maximum muscle deformations during different hand motions, and to investigate the effect of using a sparse set of ultrasound scanlines for motion classification for ultrasound-based muscle-computer interfaces (MCIs). Methods: The optimal placement of the ultrasound transducer along the forearm was identified using freehand three-dimensional reconstructions of the muscle thickness during rest and motion completion. Based on the ultrasound images acquired from the optimally placed transducer, classification accuracy with equally spaced scanlines across the cross-sectional field of view was determined. Furthermore, the unique contribution of each scanline to class discrimination using Fisher criterion (FC) and mutual information (MI) with respect to motion discriminability was determined. Results: Experiments with five able-bodied subjects show that the maximum muscle deformation occurred between 40%-50% of the forearm length for multiple degrees-of-freedom. The average classification accuracy was 94% +/- 6% with the entire 128-scanline image and 94% +/- 5% with four equally spaced scanlines. However, no significant improvement in classification accuracy was observed with optimal scanline selection using FC and MI. Conclusion: For an optimally placed transducer, a small subset of ultrasound scanlines can be used instead of a full imaging array without sacrificing performance in terms of classification accuracy for multiple degrees-of-freedom. Significance: The selection of a small subset of transducer elements can enable the reduction of computation, and simplification of the instrumentation and power consumption of wearable sonomyographic MCIs, particularly for rehabili

关键词： Ultrasonic imaging Imaging muscles Transducers Probes Sensors Three-dimensional displays muscle-computer interface ultrasound imaging wearable system prosthesis control mutual information Fisher criterion

来源：评论

学校读者我要写书评

暂无评论

A multi-stream convolutional neural network for sEMG-based gesture recognition in muscle-computer interface

引用

PATTERN RECOGNITION LETTERS 2019年第Mar.期119卷 131-138页

作者： Wei, Wentao Wong, Yongkang Du, Yu Hu, Yu Kankanhalli, Mohan Geng, Weidong Zhejiang Univ Coll Comp Sci & Technol Zheda Rd 38 Hangzhou 310027 Zhejiang Peoples R China Natl Univ Singapore Smart Syst Inst 21 Heng Mui Keng Terrace Singapore 119613 Singapore Natl Univ Singapore Sch Comp 13 Comp Dr Singapore 117417 Singapore

In muscle-computer interface (MCI), deep learning is a promising technology to build-up classifiers for recognizing gestures from surface electromyography (sEMG) signals. Motivated by the observation that a small group of muscles play significant roles in specific hand movements, we propose a multi-stream convolutional neural network (CNN) framework to improve the recognition accuracy of gestures by learning the correlation between individual muscles and specific gestures with a "divide-and-conquer" strategy. Its pipeline consists of two stages, namely the multi-stream decomposition stage and the fusion stage. During the multi-stream decomposition stage, it first decomposes the original sEMG image into equalsized patches (streams) by the layout of electrodes on muscles, and for each stream, it independently learns representative features by a CNN. Then during the fusion stage, it fuses the features learned from all streams into a unified feature map, which is subsequently fed into a fusion network to recognize gestures. Evaluations on three benchmark sEMG databases showed that our proposed multi-stream CNN framework outperformed the state-of-the-arts on sEMG-based gesture recognition. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Surface electromyography muscle-computer interface Gesture recognition Deep learning Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Improving Unimodal sEMG-Based Pattern Recognition Through Multimodal Generative Adversarial Learning

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Wei, Wentao Ren, Linyan Zhou, Ming Ma, Zhaoyi Zhao, Kexin Xu, Xun Nanjing Univ Sci & Technol Sch Design Arts & Media Dept Ind Design Nanjing 210094 Peoples R China

Surface electromyography (sEMG)-based pattern recognition system is a kind of instrumentation and measurement system that captures, processes, and recognizes bioelectrical signals, like other pattern recognition systems, it can benefit from multimodal data to enhance its recognition performance. However, acquiring multimodal data typically requires additional sensors, thereby increasing hardware complexity and costs. This article proposes a novel generative auxiliary modality (GAM) method. It improves the overall performance of unimodal sEMG-based hand gesture recognition (HGR) by integrating a multimodal generative adversarial learning process into the HGR model training phase. Specifically, we trained a deep generative model using real sEMG and inertial measurement unit (IMU) signals, which is able to generate corresponding virtual IMU signals from the input real sEMG signals. During gesture recognition, the generated virtual IMU signals were used as the auxiliary modality alongside sEMG signals to provide multimodal information for unimodal sEMG-based gesture recognition, both of which are subsequently fed into a multimodal convolutional neural network (CNN) for gesture recognition. Evaluations were conducted on six databases, including five publicly available databases and our collected database containing sEMG and IMU data from 28 subjects performing 38 gestures. Results demonstrate that by incorporating generated virtual IMU signals, our method can significantly improve unimodal sEMG-based HGR accuracy (with increases of 2.15%-11.43% and 2.54%-8.29% in intrasubject and intersubject HGR accuracy, respectively) while only incurring an acceptable increase in computational cost. This improvement is particularly evident in distinguishing gestures with identical hand gestures across different forearm postures. Moreover, the accuracy of our proposed GAM method is comparable to multimodal HGR systems using both real sEMG and IMU signals as their inputs. This work repr

关键词： Accuracy Hands Gesture recognition Databases Hardware Sensors Deep learning Training Feature extraction Data models Auxiliary modality generative adversarial learning hand gesture recognition (HGR) muscle-computer interface virtual inertial measurement unit (IMU) signals

来源：评论

学校读者我要写书评

暂无评论

Electromyography-Based Gesture Recognition: Is It Time to Change Focus From the Forearm to the Wrist?

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2022年第1期18卷 174-184页

作者： Botros, Fady S. Phinyomark, Angkoon Scheme, Erik J. Univ New Brunswick Dept Elect & Comp Engn Fredericton NB E3B 5A3 Canada Univ New Brunswick Inst Biomed Engn Fredericton NB E3B 5A3 Canada

Despite a historical focus on prosthetics, the incorporation of electromyography (EMG) sensors into less obtrusive wearable designs has recently gained attention as a potential human-computer interaction scheme for general consumer use. Because consumers are more used to wrist-worn devices, this article presents a comprehensive and systematic investigation of the feasibility of hand gesture recognition using EMG signals recorded at the wrist. A direct comparison of signal and information quality is conducted between concurrently recorded wrist and forearm signals. Both signals were collected simultaneously from 21 subjects while they performed a selection of 17 different single-finger gestures, multifinger gestures, and wrist gestures. Wrist EMG signals yielded consistently higher (p < 0.05) signal quality metrics than forearm signals for gestures that involved fine finger movements, while maintaining comparable quality for wrist gestures. Similarly, the performance of both individual state-of-the-art EMG features and a standard feature set was found to be significantly better when using wrist signals for single and multifinger gestures, and comparable for wrist gestures. Classifiers trained and tested using wrist EMG signals achieved average accuracy levels of 92.1% for single-finger gestures, 91.2% for multifinger gestures, and 94.7% for the conventional wrist gestures. In conclusion, this article clearly demonstrates the feasibility of using wrist EMG signals for hand gesture recognition. Results highlight not only the promise of this approach, but also the viability of incorporating prior knowledge from the prosthetics field in the design of wrist-based EMG pattern recognition systems.

关键词： Electromyography Wrist muscles Electrodes Gesture recognition Wearable computers Prosthetics Electromyography (EMG) finger gestures forearm gesture recognition hand gestures human-computer interaction (HCI) muscle-computer interface myoelectric control wearables wrist

来源：评论

学校读者我要写书评

暂无评论

Analysis and Considerations of the Controllability of EMG-Based Force Input

Analysis and Considerations of the Controllability of EMG-Ba...

引用

Human-computer Interaction Thematic Area Conference (HCI) Held as Part of the 25th International Conference on Human-computer Interaction (HCII)

作者： Nozaki, Hayato Kataoka, Yuta Cruz, Christian Arzate Shibata, Fumihisa Kimura, Asako Ritsumeikan Univ Grad Sch Informat Sci & Engn Kusatsu Shiga Japan Ritsumeikan Univ Global Innovat Res Org Ibaraki Osaka Japan Ritsumeikan Univ Coll Informat Sci & Engn Kusatsu Shiga Japan

ISBN: (纸本)9783031355950;9783031355967

Using electromyography (EMG) measurements for user interfaces (UIs) is widely employed as an interaction method. Some advantages of using EMG-based input are that it does not require a physical controller and can be operated intuitively with small body movements. Existing work has explored different novel interaction methods for UIs using EMG. However, it is still unclear how precisely users can control the force and what kind of control pattern is easier for them to use. Thus, this paper analyzes the effect of EMG-based force input on control accuracy and mental workload. We constructed a pointer-tracking application that inputs force strength from forearm EMG. Tracking accuracy and mental workload were evaluated under the conditions of multiple tracking patterns and hand gestures. The results showed that EMG-based input accuracy was affected by the way in which the force was applied (e.g., strengthened, weakened, or fluctuated). We also found that hand gesture type did not influence accuracy or mental workload.

关键词： muscle-computer interface Electromyography Force Input Performance Evaluation

来源：评论

学校读者我要写书评

暂无评论

Acoustic Nonlinearity Parameter Estimation for Exoskeleton Control

IEEE TRANSACTIONS ON MEDICAL ROBOTICS AND BIONICS

引用

IEEE TRANSACTIONS ON MEDICAL ROBOTICS AND BIONICS 2021年第4期3卷 1002-1010页

作者： Yan, Jipeng Yang, Xingchen Zeng, Jia Liu, Honghai Shanghai Jiao Tong Univ Sch Mech Engn State Key Lab Mech Syst & Vibrat Shanghai 200240 Peoples R China Harbin Inst Technol Sch Mech Engn & Automat State Key Lab Robot & Syst Shenzhen 518052 Peoples R China Univ Portsmouth Sch Comp Portsmouth PO1 3HE Hants England

The acoustic nonlinearity parameter of skeletal muscles changes with their contractions and has the potential to be utilized for exoskeleton control. In our previous work, a system comprising a wearable ultrasound probe was developed to estimate the acoustic nonlinearity parameter in vivo by measuring amplitudes of second-harmonic ultrasound. The estimating accuracy was found to be significantly affected by the corruption between echoes due to the limited axial resolution of ultrasound. As both frequency components of the single echo and the extent of corruption are unknown, a method based on a bi-directional deconvolution is proposed in this paper to decompose corrupted echoes, and integrated into the measuring system. Eight subjects were recruited for the in vivo measurement of the biceps brachii acoustic nonlinearity parameter, thickness, and elbow torque. Linear regression between the elbow torque and (1) the estimated acoustic nonlinearity parameter, (2) the thickness demonstrated the correlations, with average coefficients of determinations (R-2) of 0.861 and 0.633 respectively. This work paves a way for estimating the acoustic nonlinearity parameter of skeletal muscles in vivo.

关键词： Acoustic signal processing force estimation muscle-computer interface signal decomposition

来源：评论

学校读者我要写书评

暂无评论

All-ConvNet: A Lightweight All CNN for Neuromuscular Activity Recognition Using Instantaneous High-Density Surface EMG Images

All-ConvNet: A Lightweight All CNN for Neuromuscular Activit...

引用

2020 International Instrumentation and Measurement Technology Conference

作者： Islam, Md Rabiul Massicotte, Daniel Zhu, Wei-Ping Univ Quebec Trois Rivieres Dept Elect & Comp Engn Trois Rivieres PQ Canada Concordia Univ Dept Elect & Comp Engn Montreal PQ Canada

ISBN: (纸本)9781728144610;9781728144603

Neuromuscular activity recognition using low-resolution instantaneous high-density surface electromyography (HD-sEMG) images present a great challenge. The recent result shows the high potentiality and hence opens up new avenues for the development of more fluid and natural muscle-computer interfaces. However, the existing approaches employed a very large deep ConvNet, which requires learning >5.63 million training parameters only during fine-tuning and pre-trained on a very large-scale labeled HD-sEMG training datasets, as a result, it makes high-end resource bounded and computationally expensive. To overcome this problem, we propose a lightweight All-ConvNet model that consists solely of convolutional layers, a simple yet efficient framework for learning instantaneous HD-sEMG images from scratch through random initialization. Without using any pre-trained models, our proposed lightweight All-ConvNet demonstrate very competitive or even state of the art performance on a current benchmarks HD-sEMG dataset, while requires learning only approximate to 460k training parameters and using approximate to 12xsmaller dataset. The experimental results proved that the proposed lightweight All-ConvNet is highly effective for learning discriminative features for low-resolution instantaneous HD-sEMG image recognition and low-latency processing especially in the data and high-end resource constrained scenarios.

关键词： Neuromuscular activity recognition All convolutional neural networks Feature learning HD-sEMG Gesture recognition muscle-computer interface Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

S-CONVNET: A SHALLOW CONVOLUTIONAL NEURAL NETWORK ARCHITECTURE FOR NEUROMUSCULAR ACTIVITY RECOGNITION USING INSTANTANEOUS HIGH-DENSITY SURFACE EMG IMAGES 42

S-CONVNET: A SHALLOW CONVOLUTIONAL NEURAL NETWORK ARCHITECTU...

引用

42nd Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC)

作者： Islam, Md. Rabiul Massicotte, Daniel Nougarou, Francois Massicotte, Philippe Zhu, Wei-Ping Univ Quebec Trois Rivieres Dept Elect & Comp Engn Trois Rivieres PQ Canada Concordia Univ Dept Elect & Comp Engn Montreal PQ Canada

ISBN: (纸本)9781728119908

The recent progress in recognizing low-resolution instantaneous high-density surface electromyography (HD-sEMG) images opens up new avenues for the development of more fluid and natural muscle-computer interfaces. However, the existing approaches employed a very large deep convolutional neural network (ConvNet) architecture and complex training schemes for HD-sEMG image recognition, which requires learning of >5.63 million(M) training parameters only during fine-tuning and pre-trained on a very large-scale labeled HD-sEMG training dataset, as a result, it makes high-end resource-bounded and computationally expensive. To overcome this problem, we propose S-ConvNet models, a simple yet efficient framework for learning instantaneous HD-sEMG images from scratch using random-initialization. Without using any pre-trained models, our proposed S-ConvNet demonstrate very competitive recognition accuracy to the more complex state of the art, while reducing learning parameters to only approximate to 2M and using approximate to 12 x smallest dataset. The experimental results proved that the proposed S-ConvNet is highly effective for learning discriminative features for instantaneous HD-sEMG image recognition, especially in the data and high-end resource-constrained scenarios.

关键词： Neuromuscular activity recognition Shallow convolutional neural networks Feature learning HD-sEMG Gesture recognition muscle-computer interface Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：