中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
DeepCS: Training a deep learning model for cervical spondylosis recognition on small-labeled sensor data

文献类型：期刊论文

作者Wang, Nana1,2,3,5; Luo, Chunjie1,3; Huang, Xi4; Huang, Yunyou5; Zhan, Jianfeng1,3
刊名NEUROCOMPUTING
出版日期2022-02-01
卷号472页码:24-34
ISSN号0925-2312
关键词Cervical spondylosis recognition High-dimensional time series sensor data Convolutional neural network Network architecture search Feature extraction
DOI10.1016/j.neucom.2021.11.008
英文摘要Cervical spondylosis (CS) recognition systems provide regular screening services outside of a hospital and promote early detection and treatment of CS. However, in this paper, we propose a deep learning-based CS recognition system. Concerning the state-of-the-art and state-of-the-practice systems, the innovations of our approaches and algorithms are as follows: First, to elevate the reliance upon the sample number required for training the high-quality model, we reduce sample dimension and find optimal neural net-work architectures to reduce the number of model parameters to fit. Second, we incorporate multi-stream parallel network architecture search with multi-view feature extraction by converting time series classification into an image classification task. Specifically, five feature extraction methods (time-domain, frequency-domain, time-frequency domain, model-based, nonlinear feature extraction) are firstly uti-lized to extract features from multiple perspectives and form low-dimensional data set with multi-properties. Third, we reorganize low-dimensional data into image one representing the spatio-temporal relationship of muscle activity pattern. Finally, a multi-stream parallel network architecture search is proposed to use a bypass mechanism for optimal neural network architecture, each of which processes a kind of features mentioned above with an idea of the sparse connection of convolution neural network. The results on the real-world data set show that our CS recognition system achieves the average accuracy of 95.54%, average sensitivity of 99.09%, and average specificity of 90.00%, outperforming the state-of-the-art ones. (c) 2021 Elsevier B.V. All rights reserved.
资助项目Project of Guangxi Science and Technology[GuiKeAD20297004]
WOS研究方向Computer Science
语种英语
出版者ELSEVIER
WOS记录号WOS:000761893000003
源URL[http://119.78.100.204/handle/2XEOYT63/18964]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhan, Jianfeng
作者单位1.Chinese Acad Sci, Inst Comp Technol ICT, State Key Lab Comp Architecture, Beijing 100080, Peoples R China
2.Univ Chinese Acad Sci, 19A Yuquan Rd, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Software Syst Lab, ICT, ACS, Beijing 100080, Peoples R China
4.Chinese Acad Sci, Wireless Sensor Network Lab, ICT, Beijing, Peoples R China
5.Guangxi Normal Univ, Guilin, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Nana,Luo, Chunjie,Huang, Xi,et al. DeepCS: Training a deep learning model for cervical spondylosis recognition on small-labeled sensor data[J]. NEUROCOMPUTING,2022,472:24-34.
APA Wang, Nana,Luo, Chunjie,Huang, Xi,Huang, Yunyou,&Zhan, Jianfeng.(2022).DeepCS: Training a deep learning model for cervical spondylosis recognition on small-labeled sensor data.NEUROCOMPUTING,472,24-34.
MLA Wang, Nana,et al."DeepCS: Training a deep learning model for cervical spondylosis recognition on small-labeled sensor data".NEUROCOMPUTING 472(2022):24-34.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。