Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (11): 3402-3408.DOI: 10.11772/j.issn.1001-9081.2021010008
• Frontier and comprehensive applications • Previous Articles
Jiaqi ZHANG, Yueqin ZHANG(), Jian CHEN
Received:
2021-01-05
Revised:
2021-04-12
Accepted:
2021-04-21
Online:
2021-04-29
Published:
2021-11-10
Contact:
Yueqin ZHANG
About author:
ZHANG Jiaqi,born in 1994,M. S,candidate. Her research
interests include data mining通讯作者:
张月琴
作者简介:
张嘉琪(1994-),女,山西大同人,硕士研究生,主要研究方向:数据挖掘CLC Number:
Jiaqi ZHANG, Yueqin ZHANG, Jian CHEN. Pulse condition recognition method based on optimized reinforcement learning path feature classification[J]. Journal of Computer Applications, 2021, 41(11): 3402-3408.
张嘉琪, 张月琴, 陈健. 优化强化学习路径特征分类的脉象识别法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3402-3408.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2021010008
名称 | 脉位 | 节律 | 脉力 | 脉型 | 脉势 | 脉率 | 脉搏 | U角 | P波 | t1 | T波 | V波 | D波 | t |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
平脉 | 中 | 齐 | 中 | abc | 正常 | 中 | 70~90 | 80~87 | 9~22 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | 0.43~0.88 |
结脉 | 中 | 不齐 | 中 | abc | 正常 | 慢 | 70~90 | 80~87 | 9~22 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | 0.43~0.88 |
促脉 | 中 | 不齐 | 中 | abc | 正常 | 快 | >120 | 80~87 | 9~22 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | 0.43~0.88 |
数脉 | 中 | 齐 | 中 | abc | 正常 | 快 | 90~120 | 80~87 | 9~22 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | 0.06~0.43 |
疾脉 | 中 | 齐 | 中 | abc | 正常 | 快 | >120 | 80~87 | 9~22 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | 0.33~0.43 |
迟脉 | 中 | 齐 | 中 | abc | 正常 | 慢 | <60 | 80~87 | >22 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | 1.00~1.50 |
浮脉 | 浮 | 齐 | 都可能 | abc | 正常 | 中 | 70~90 | 80~87 | 9~22 | <0.11 | <1 | <30 | 0.5~2.0 | 0.43~0.88 |
芤脉 | 浮 | 齐 | 软 | abc | 正常 | 中 | 70~90 | 80~87 | 9~22 | 0.06~0.09 | <1 | <15 | 0.5~2.0 | 0.43~0.88 |
洪脉 | 浮 | 齐 | 有力 | abc | 强 | 中 | 70~90 | 80~87 | >22 | ≤0.07 | <1 | <30 | 0.5~2.0 | 0.43~0.88 |
沉脉 | 沉 | 齐 | 中 | abc | 正常 | 中 | 70~90 | 80~87 | <9 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | 0.43~0.88 |
伏脉 | 沉 | 齐 | 中 | abc | 正常 | 中 | 70~90 | 80~87 | <7 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | <0.60 |
短脉 | 中 | 齐 | 中 | b | 正常 | 中 | 70~90 | <78 | <5 | >0.11 | <1 | <25 | <0.5 | 0.43~0.88 |
滑脉 | 中 | 齐 | 有力 | abc | 强 | 中 | 70~90 | 80~87 | 9~22 | 0.07~0.09 | <1 | >70 | >2.0 | 0.43~0.88 |
弦脉 | 中 | 齐 | 有力 | abc | 强 | 中 | 70~90 | <84 | 9~22 | >0.09 | >6 | >50 | <0.5 | 0.43~0.88 |
涩脉 | 中 | 不齐 | 不匀 | abc | 正常 | 中 | 70~90 | 80~87 | <22 | 0.09~0.16 | <1 | <25 | <2.0 | 0.43~0.88 |
细脉 | 中 | 齐 | 中 | abc | 正常 | 中 | 70~90 | 80~87 | <8 | 0.07~0.11 | <1 | <55 | <2.0 | 0.43~0.88 |
Tab. 1 Pulse condition thresholds
名称 | 脉位 | 节律 | 脉力 | 脉型 | 脉势 | 脉率 | 脉搏 | U角 | P波 | t1 | T波 | V波 | D波 | t |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
平脉 | 中 | 齐 | 中 | abc | 正常 | 中 | 70~90 | 80~87 | 9~22 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | 0.43~0.88 |
结脉 | 中 | 不齐 | 中 | abc | 正常 | 慢 | 70~90 | 80~87 | 9~22 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | 0.43~0.88 |
促脉 | 中 | 不齐 | 中 | abc | 正常 | 快 | >120 | 80~87 | 9~22 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | 0.43~0.88 |
数脉 | 中 | 齐 | 中 | abc | 正常 | 快 | 90~120 | 80~87 | 9~22 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | 0.06~0.43 |
疾脉 | 中 | 齐 | 中 | abc | 正常 | 快 | >120 | 80~87 | 9~22 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | 0.33~0.43 |
迟脉 | 中 | 齐 | 中 | abc | 正常 | 慢 | <60 | 80~87 | >22 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | 1.00~1.50 |
浮脉 | 浮 | 齐 | 都可能 | abc | 正常 | 中 | 70~90 | 80~87 | 9~22 | <0.11 | <1 | <30 | 0.5~2.0 | 0.43~0.88 |
芤脉 | 浮 | 齐 | 软 | abc | 正常 | 中 | 70~90 | 80~87 | 9~22 | 0.06~0.09 | <1 | <15 | 0.5~2.0 | 0.43~0.88 |
洪脉 | 浮 | 齐 | 有力 | abc | 强 | 中 | 70~90 | 80~87 | >22 | ≤0.07 | <1 | <30 | 0.5~2.0 | 0.43~0.88 |
沉脉 | 沉 | 齐 | 中 | abc | 正常 | 中 | 70~90 | 80~87 | <9 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | 0.43~0.88 |
伏脉 | 沉 | 齐 | 中 | abc | 正常 | 中 | 70~90 | 80~87 | <7 | 0.07~0.11 | <1 | 25~57 | 0.5~2.0 | <0.60 |
短脉 | 中 | 齐 | 中 | b | 正常 | 中 | 70~90 | <78 | <5 | >0.11 | <1 | <25 | <0.5 | 0.43~0.88 |
滑脉 | 中 | 齐 | 有力 | abc | 强 | 中 | 70~90 | 80~87 | 9~22 | 0.07~0.09 | <1 | >70 | >2.0 | 0.43~0.88 |
弦脉 | 中 | 齐 | 有力 | abc | 强 | 中 | 70~90 | <84 | 9~22 | >0.09 | >6 | >50 | <0.5 | 0.43~0.88 |
涩脉 | 中 | 不齐 | 不匀 | abc | 正常 | 中 | 70~90 | 80~87 | <22 | 0.09~0.16 | <1 | <25 | <2.0 | 0.43~0.88 |
细脉 | 中 | 齐 | 中 | abc | 正常 | 中 | 70~90 | 80~87 | <8 | 0.07~0.11 | <1 | <55 | <2.0 | 0.43~0.88 |
K | 分类模型 | TPR/% | TNR/% | Accuracy/% |
---|---|---|---|---|
0.1 | 优化路径特征分类 | 97.76 | 97.26 | 95.51 |
PNN | 65.92 | 95.27 | 66.41 | |
RNN | 86.05 | 93.81 | 82.35 | |
0.2 | 优化路径特征分类 | 96.71 | 86.81 | 89.16 |
PNN | 63.83 | 84.39 | 60.53 | |
RNN | 85.29 | 86.30 | 77.39 | |
0.3 | 优化路径特征分类 | 94.25 | 90.83 | 90.87 |
PNN | 63.49 | 84.16 | 66.10 | |
RNN | 85.62 | 85.05 | 79.41 | |
0.5 | 优化路径特征分类 | 92.88 | 66.37 | 72.91 |
PNN | 47.47 | 43.71 | 44.74 | |
RNN | 62.23 | 54.32 | 54.12 |
Tab. 2 Comparison of diagnostic performance of different models
K | 分类模型 | TPR/% | TNR/% | Accuracy/% |
---|---|---|---|---|
0.1 | 优化路径特征分类 | 97.76 | 97.26 | 95.51 |
PNN | 65.92 | 95.27 | 66.41 | |
RNN | 86.05 | 93.81 | 82.35 | |
0.2 | 优化路径特征分类 | 96.71 | 86.81 | 89.16 |
PNN | 63.83 | 84.39 | 60.53 | |
RNN | 85.29 | 86.30 | 77.39 | |
0.3 | 优化路径特征分类 | 94.25 | 90.83 | 90.87 |
PNN | 63.49 | 84.16 | 66.10 | |
RNN | 85.62 | 85.05 | 79.41 | |
0.5 | 优化路径特征分类 | 92.88 | 66.37 | 72.91 |
PNN | 47.47 | 43.71 | 44.74 | |
RNN | 62.23 | 54.32 | 54.12 |
分类模型 | K | |||
---|---|---|---|---|
0.1 | 0.2 | 0.3 | 0.5 | |
优化路径特征分类 | 98.72 | 96.71 | 95.12 | 82.06 |
PNN | 79.20 | 70.58 | 74.58 | 46.60 |
RNN | 92.16 | 90.38 | 89.18 | 59.90 |
Tab. 3 F1 comparison of different model diagnosis
分类模型 | K | |||
---|---|---|---|---|
0.1 | 0.2 | 0.3 | 0.5 | |
优化路径特征分类 | 98.72 | 96.71 | 95.12 | 82.06 |
PNN | 79.20 | 70.58 | 74.58 | 46.60 |
RNN | 92.16 | 90.38 | 89.18 | 59.90 |
1 | 唐亚平.刍议当前脉诊存在的问题[J].医学与哲学(人文社会医学版),2008,29(17):79-79. |
TANG Y P. Opinion on the problems existing in current pulse diagnosis [J]. Medicine and Philosophy (Humanistic and Social Medicine Edition), 2008, 29(17): 79-79. | |
2 | 欧阳珊婷.扁鹊医学之研究[D].北京:中国中医科学院,2013:50-63. |
OCHS S D. The medical tradition of the legendary physician Bian Que [D]. Beijing: China Academy of Chinese Medical Sciences, 2013: 50-63. | |
3 | 陈欣然.中医脉诊起源及《脉经》以前各脉诊法本义研究[D].北京:北京中医药大学,2017:1-185. 10.37360/blacpma.21.20.3.23 |
CHEN X R. Study on the origin of pulse diagnosis in traditional Chinese medicine and the original meaning of pulse diagnosis methods before Mai Jing [D]. Beijing: Beijing University of Chinese Medicine, 2017: 1-185. 10.37360/blacpma.21.20.3.23 | |
4 | 王柳.在“互联网+”时代“悬丝诊脉”[J].软件和集成电路,2015(5):28-33. JournalArticle/5b3bce03c095d70f0090c6ac |
WANG L. “Hanging silk to diagnose pulse” in the “internet+” era [J]. Software and Integrated Circuits, 2015(5): 28-33. JournalArticle/5b3bce03c095d70f0090c6ac | |
5 | 徐黎明,宿明良,张广福,等.中医脉象图形数学分析法[J].中华现代中西医杂志,2004,10(2):875-879. |
XU L M, SU M L, ZHANG G F, et al. Mathematical analysis of traditional Chinese medicine pulse tracings [J]. Chinese Journal Current Traditional Western Medicine, 2004, 10(2): 875-879. | |
6 | 郭红霞,王炳和,郑思仪,等.基于概率神经网络的中医脉象识别方法研究[J].计算机工程与应用,2007,43(20):194-196,203. 10.3321/j.issn:1002-8331.2007.20.057 |
GUO H X, WANG B H, ZHENG S Y, et al. Recognition method of traditional Chinese medicine pulse conditions based on probabilistic neural network [J]. Computer Engineering and Applications, 2007, 43(20): 194-196, 203. 10.3321/j.issn:1002-8331.2007.20.057 | |
7 | 李磊.基于大数据分析的中医脉象辨别智能判断[J].科技通报,2016,32(8):41-45. |
LI L. Traditional Chinese medicine pulse condition recognition intelligent judgement based on large data analysis [J]. Bulletin of Science and Technology, 2016, 32(8): 41-45. | |
8 | 陈星池,黄淑春,赵海,等.基于极限学习机的中医脉象识别方法[J].东北大学学报(自然科学版),2017,38(9):1226-1229. 10.12068/j.issn.1005-3026.2017.09.003 |
CHEN X C, HUANG S C, ZHAO H, et al. Recognition method of traditional Chinese medicine pulse conditions based on extreme learning machine [J]. Journal of Northeastern University (Natural Science), 2017, 38(9): 1226-1229. 10.12068/j.issn.1005-3026.2017.09.003 | |
9 | 郭彦杰.基于循环神经网络的脉搏信号分析研究[D].北京:北京邮电大学,2018: 1-64. |
GUO Y J. Pulse signal analysis based on recurrent neural network [D]. Beijing: Beijing University of Posts and Telecommunications, 2018: 1-64. | |
10 | 胡阳生.基于卷积神经网络的脉搏分析方法研究[D].北京:北京邮电大学,2018:1-59. |
HU Y S. Study on pulse analysis method based on convolution neural network [D]. Beijing: Beijing University of Posts and Telecommunications, 2018: 1-59. | |
11 | 颜建军,陈松晔,燕海霞,等.基于递归图和卷积神经网络的脉象分析识别[J].计算机工程与应用,2020,56(7):170-175. 10.3778/j.issn.1002-8331.1901-0441 |
YAN J J, CHEN S Y, YAN H X, et al. Wrist pulse analysis and recognition based on recurrence plot and convolution neutral network [J]. Computer Engineering and Applications, 2020, 56(7): 170-175. 10.3778/j.issn.1002-8331.1901-0441 | |
12 | 费兆馥.现代中医诊断学讲稿[M].北京:人民卫生出版社,2009:33-163. |
FEI J F. Lecture Notes on Modern Diagnostics of Traditional Chinese Medicine [M]. Beijing: People’s Medical Publishing House, 2009: 33-163. | |
13 | 陈忠铭,何明.深度强化学习:原理与实践[M].北京:人民邮电出版社,2019:3-186. 10.1007/978-3-030-10546-4_2 |
CHEN Z M, HE M. Deep Reinforcement Learning: Principles and Practices [M]. Beijing: Posts and Telecom Press, 2019: 3-186. 10.1007/978-3-030-10546-4_2 | |
14 | MOWBRAY F I, FOX-WASYLYSHYM S M, EI-MASRI M M. Univariate outliers: a conceptual for the nurse researcher [J]. Canadian Journal of Nursing Research, 2019, 51(1): 31-37. 10.1177/0844562118786647 |
15 | 徐徐.循环神经网络改进方法研究[D].上海:上海交通大学,2017:1-166. |
XU X. Research and improvement of recurrent neural network [D]. Shanghai: Shanghai Jiao Tong University, 2017: 1-166. |
[1] | Rui TANG, Chuanlin PANG, Ruizhi ZHANG, Chuan LIU, Shibo YUE. DDPG-based resource allocation in D2D communication-empowered cellular network [J]. Journal of Computer Applications, 2024, 44(5): 1562-1569. |
[2] | Fei LUO, Mengwei BAI. Decision optimization of traffic scenario problem based on reinforcement learning [J]. Journal of Computer Applications, 2022, 42(8): 2361-2368. |
[3] | Xueming LI, Guohao WU, Shangbo ZHOU, Xiaoran LIN, Hongbin XIE. Image instance segmentation model based on fractional-order network and reinforcement learning [J]. Journal of Computer Applications, 2022, 42(2): 574-583. |
[4] | Bing SHI, Xizi HUANG, Zhaoxiang SONG, Jianqiao XU. User incentive based bike‑sharing dispatching strategy [J]. Journal of Computer Applications, 2022, 42(11): 3395-3403. |
[5] | SHANG Fangjian, LI Xin, Di ZHAI, LU Yang, ZHANG Donglei, QIAN Yuwen. Two-phase resource allocation technology for network slices in smart grid [J]. Journal of Computer Applications, 2021, 41(7): 2033-2038. |
[6] | ZHOU Shuo, QIU Runhe, TANG Minjun. Power allocation algorithm for CR-NOMA system based on tabu search and Q-learning [J]. Journal of Computer Applications, 2021, 41(7): 2026-2032. |
[7] | WANG Qi, QIN Jin. Automatic hierarchical approach of MAXQ based on action space partition [J]. Journal of Computer Applications, 2017, 37(5): 1357-1362. |
[8] | CAO Hao, YIN Baoqun, CAO Jie, LU Xiaonong. Admission control of media delivery network based on software defined network [J]. Journal of Computer Applications, 2016, 36(7): 1767-1771. |
[9] | YAN Chengyu, LI Zhihua, YU Xinrong. Virtual machine dynamic consolidation method based on adaptive overloaded threshold selection [J]. Journal of Computer Applications, 2016, 36(10): 2698-2703. |
[10] | ZHANG Rubo, MENG Lei, SHI Changting. Self-repair method for autonomous underwater vehicle software based on micro-reboot and partially observable Markov decision process model [J]. Journal of Computer Applications, 2015, 35(8): 2375-2379. |
[11] | HUANG Hao, TANG Hao, ZHOU Lei, CHENG Wenjuan. Robust optimal control of single conveyor-serviced production station with uncertain service rate [J]. Journal of Computer Applications, 2015, 35(7): 2067-2072. |
[12] | XU Ming, LIU Guangzhong. Medium access control protocol based on partially observable Markov decision process in underwater acoustic sensor networks [J]. Journal of Computer Applications, 2015, 35(11): 3047-3050. |
[13] | ZHU Jiang PENG Zhenzhen ZHANG Yuping. Transmission and scheduling scheme based on W-learning algorithm in wireless networks [J]. Journal of Computer Applications, 2013, 33(11): 3005-3009. |
[14] | ZHENG Yan-bin GUO Ling-yun LIU Jing-jing. Research on decentralized communication decision in multi-Agent system [J]. Journal of Computer Applications, 2012, 32(10): 2875-2878. |
[15] | Fang-Yi SUN . CMAC application using triangulation in reinforcement learning [J]. Journal of Computer Applications, 2009, 29(3): 871-873. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||