Home Journals Articles Updates About
CN
image
收藏切换
Multi-period Pulse Recognition Based on Convolutional and Self-Attention Model
收藏切换
Wei DENG1, Xuanji LIU1, Longhui HAO1, Zijian ZHU2, Fei LI3, Rui WANG4, Keqin LIU4, Pengyu GUO2, Hua ZHOU2, Weiguang WANG5, Zhanchun CHEN1
Chinese Archives of Traditional Chinese Medicine | 2025, 43(8) : 13 - 17
Less
收藏切换
Chinese Archives of Traditional Chinese Medicine | 2025, 43(8): 13-17
• Digital Traditional Chinese Medicine •
Multi-period Pulse Recognition Based on Convolutional and Self-Attention Model
Full
Wei DENG1, Xuanji LIU1, Longhui HAO1, Zijian ZHU2, Fei LI3, Rui WANG4, Keqin LIU4, Pengyu GUO2, Hua ZHOU2, Weiguang WANG5, Zhanchun CHEN1
Affiliations
  • 1.College of Mechanical Engineering，Taiyuan University of Technology，Taiyuan 030024，Shanxi，China
  • 2.Shanghai Beyers Health Technology Co.Ltd，Shanghai 201600，China
  • 3.Shanxi Acupuncture and Moxibustion Hospital，Taiyuan 030006，Shanxi，China
  • 4.Taiyuan Traditional Chinese Medicine Hospital，Taiyuan 030009，Shanxi，China
  • 5.Institute of Basic Research in Clinical Medicine，China Academy of Chinese Medical Sciences，Beijing University of Chinese Medicine，Beijing 100029，China
Published: 2025-08-10 doi: 10.13193/j.issn.1673-7717.2025.08.004
Outline
收藏切换
Objective

The traditional single-cycle pulse recognition methods encounter significant limitations in practical applications due to the morphological diversity，cycle variability and individual differences inherent in the wrist pulse signals.In this study，it focused on solving the classification problem of multi-period pulse recognition，and constructed an image-based dataset by integrating the amplitude and temporal information of pulse signal through the Markov Transition Field（MTF）.Building upon this foundation，it set up new deep-learning network model，TCANet（Temporal Convolutional Attention Network），which leveraged the depth-wise separable convolutions and self-attention mechanisms to markedly improve the accuracy and efficiency of pulse image classification.The experimental outcomes revealed that TCANet achieved the impressive performance metrics，including 94.74% accuracy，94.79% precision，94.74% recall and 94.76% F1 score in recognizing the slippery，stringy and normal wrist pulses.This indicated that it had excellent performance and wide application potential in the field of multi cycle pulse recognition.

multi-period pulse  /  pulse classification  /  MTF  /  depth-wise separable convolution  /  self-attention
邓威, 刘轩吉, 郝龙辉, 朱子简, 李飞, 王蕊, 刘克勤, 郭鹏宇, 周华, 王维广, 陈占春. 基于卷积-自注意力机制对多周期脉象识别分类. 中华中医药学刊, 2025 , 43 (8) : 13 -17 . DOI: 10.13193/j.issn.1673-7717.2025.08.004
Wei DENG, Xuanji LIU, Longhui HAO, Zijian ZHU, Fei LI, Rui WANG, Keqin LIU, Pengyu GUO, Hua ZHOU, Weiguang WANG, Zhanchun CHEN. Multi-period Pulse Recognition Based on Convolutional and Self-Attention Model[J]. Chinese Archives of Traditional Chinese Medicine, 2025 , 43 (8) : 13 -17 . DOI: 10.13193/j.issn.1673-7717.2025.08.004
Appendix
Less
Year 2025 volume 43 Issue 8
36
15
Cite this Article
BibTeX
Article Info
doi: 10.13193/j.issn.1673-7717.2025.08.004
  • Online Date：2026-10-30
  • Published：2025-08-10
Article Data
Affiliations
History
Funding
Affiliations
    1.College of Mechanical Engineering，Taiyuan University of Technology，Taiyuan 030024，Shanxi，China
    2.Shanghai Beyers Health Technology Co.Ltd，Shanghai 201600，China
    3.Shanxi Acupuncture and Moxibustion Hospital，Taiyuan 030006，Shanxi，China
    4.Taiyuan Traditional Chinese Medicine Hospital，Taiyuan 030009，Shanxi，China
    5.Institute of Basic Research in Clinical Medicine，China Academy of Chinese Medical Sciences，Beijing University of Chinese Medicine，Beijing 100029，China
References
Share
https://castjournals.cast.org.cn/joweb/zhzyyxk/EN/10.13193/j.issn.1673-7717.2025.08.004
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT
Links
Articles
Latest Articles
Most Read
Collections
Updates
Events
News
Multimedia
About
About Us
Contact
No. 86 Xueyuan South Road, Haidian District, Beijing
100081
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn

Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House