2.765

2022影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

融合混合知识与MCTS的针灸排序方案设定方法

姜秉序 宿翀 刘存志 陈捷

姜秉序, 宿翀, 刘存志, 陈捷. 融合混合知识与MCTS的针灸排序方案设定方法. 自动化学报, 2020, 46(6): 1240−1254 doi: 10.16383/j.aas.c180120
引用本文: 姜秉序, 宿翀, 刘存志, 陈捷. 融合混合知识与MCTS的针灸排序方案设定方法. 自动化学报, 2020, 46(6): 1240−1254 doi: 10.16383/j.aas.c180120
Jiang Bing-Xu, Su Chong, Liu Cun-Zhi, Chen Jie. Acupuncture sequential scheming method with hybrid knowledge and MCTS. Acta Automatica Sinica, 2020, 46(6): 1240−1254 doi: 10.16383/j.aas.c180120
Citation: Jiang Bing-Xu, Su Chong, Liu Cun-Zhi, Chen Jie. Acupuncture sequential scheming method with hybrid knowledge and MCTS. Acta Automatica Sinica, 2020, 46(6): 1240−1254 doi: 10.16383/j.aas.c180120

融合混合知识与MCTS的针灸排序方案设定方法

doi: 10.16383/j.aas.c180120
基金项目: 国家自然科学基金(61603023)资助
详细信息
    作者简介:

    姜秉序:北京化工大学信息学院硕士研究生. 主要研究方向为智能决策. E-mail: yizhoutanjian@126.com

    宿翀:北京化工大学信息学院副教授. 主要研究方向为人工智能, 情感计算和智能医疗. 本文通信作者.E-mail: suchong@mail.buct.edu.cn

    刘存志:北京中医药大学东方医院副院长. 主要研究方向为针灸的临床疗效评价与作用机理研究.E-mail: lcz623780@126.com

    陈捷:北京中关村医院针灸推拿科主治医师. 主要研究方向为中医学, 针灸推拿学及智慧医学. E-mail: chenjie0128@126.com

Acupuncture Sequential Scheming Method With Hybrid Knowledge and MCTS

Funds: Supported by National Natural Science Foundation of China (61603023)
  • 摘要: 传统的序列决策方法旨在对决策过程与决策步骤进行建模, 以求解得到最优的决策序列. 然而, 序列决策建模过程对目标函数的确定性要求高, 且序列搜索的算法多以深度优先或广度优先等遍历搜索为主, 鲜有考虑搜索过程的随机性. 蒙特卡洛树搜索算法(Monte Carlo tree search, MCTS)虽然适合求解随机序列搜索问题, 但目前仅应用于博弈型搜索过程, 鲜有探讨需要专家参与的知识约束序列决策的搜索策略, 另外, 传统MCTS算法往往存在搜索范围过大、收敛不及时等问题. 为此, 提出一种融合群决策经验型知识和部分确定型决策序列片段的混合知识约束的MCTS 序列决策方法, 并给出了详细的求解流程. 最后, 将所提方法应用于一类中风后吞咽功能障碍针灸穴位排序方案制订问题, 给出了融合混合知识与MCTS的针灸排序方案设定方法, 并与其他方法进行对比, 验证了所提方法的可行性和有效性, 为年轻医师的针灸方案制订技能的标准化培训工作奠定了方法基础.
  • 图  1  完整决策序列的评价流程图

    Fig.  1  Evaluation flow chart of complete decision sequence

    图  2  序列分割示意图

    Fig.  2  Sequence segmentation diagram

    图  3  传统MCTS流程图[20]

    Fig.  3  Traditional MCTS flow chart[20]

    图  4  基于混合知识的UCT-max算法的序列决策流程图

    Fig.  4  Sequential decision flow chart of UCT-max algorithm based on mixed knowledge

    图  5  MCTS多次实验结果显示

    Fig.  5  The results of multiple experiments of MCTS

    图  6  基于GA算法的5次针灸排序序列搜索的数据图

    Fig.  6  The data flowchart of acupuncture sequence searching in five times based on GA

    表  1  针灸治疗脑卒中后吞咽障碍腧穴运用频次统计

    Table  1  Acupuncture treatment of dysphagia after stroke

    序号腧穴名频次频率 (%)
    1廉泉22111.16
    2风池21911.06
    3翳风1316.61
    4金津1125.65
    5玉液1115.60
    6完骨824.14
    7内关763.84
    8风府713.58
    9人中613.08
    10人迎582.93
    11三阴交532.68
    12合谷532.68
    13旁廉泉492.47
    $\vdots$$\vdots$$\vdots$$\vdots$
    下载: 导出CSV

    表  2  针灸序列长度为5的不同分割方式

    Table  2  Different segmentation patterns of acupuncture sequence in depth of 5

    序列长度序列分割方式
    1维×5a1, a2, a3, a4, a5
    1维×3+2维×1a1, a2, a3, a4a5; a1, a2, a3a4, a5
    a1, a2a3, a4, a5; a1a2, a3, a4, a5
    1维×1+2维×2a1, a2a3, a4a5; a1a2, a3, a4a5
    a1a2, a3a4, a5
    2维×1+3维×1a1a2, a3a4a5; a1a2a3, a4a5
    1维×2+3维×1a1, a2, a3a4a5; a1, a2a3a4, a5
    a1a2a3, a4, a5
    1维×1+4维×1a1, a2a3a4a5; a1a2a3a4, a5
    5维×1a1a2a3a4a5
    下载: 导出CSV

    表  3  长度为5的序列优先度量化表

    Table  3  Sequence priority quantization table with sequence length 5

    序列长度序列分割方式 序列优先度
    1维×5a1,a2,a3,a4,a5(a1+0.08)(a2+0.06)×
    (a3+0.04)(a4+0.02)(a5)
    1维×3+
    2维×1
    a1,a2,a3,a4a5(a1+0.075)(a2+0.05)(a3+0.025)(a4a5)
    a1,a2,a3a4,a5(a1+0.075)(a2+0.05)(a3a4+0.025)(a5)
    a1,a2a3,a4,a5(a1+0.075)(a2a3+0.05)(a4+0.025)(a5)
    a1a2,a3,a4,a5(a1a2+0.075)(a3+0.05)(a4+0.025)(a5)
    1维×1+
    2维×2
    a1,a2a3,a4a5(a1+0.067)a2a3+0.033)(a4a5)
    a1a2,a3,a4a5(a1a2+0.067)(a3+0.033)(a4a5)
    a1a2,a3a4,a5(a1a2+0.067)(a3a4+0.033)(a5)
    2维×1+
    3维×1
    a1a2,a3a4a5(a1a2+0.05)(a3a4a5)
    a1a2a3,a4a5(a1a2a3+0.05)(a4a5)
    1维×2+
    3维×1
    a1,a2,a3a4a5(a1+0.067)(a2+0.033)(a3a4a5)
    a1,a2a3a4,a5(a1+0.067)(a2a3a4+0.033)(a5)
    a1a2a3,a4,a5(a1a2a3+0.067)(a4+0.033)(a5)
    1维×1+
    4维×1
    a1,a2a3a4a5(a1+0.05)(a2a3a4aa5)
    a1a2a3a4,a5(a1a2a3a4+0.05)(a5)
    5维×1a1a2a3a4a5(a1a2a3a4a5)
    下载: 导出CSV

    表  4  各层节点的评价值及访问次数

    Table  4  Evaluation value and visiting numbers of nodes in each layer

    层次节点编号评价值访问次数
    第1层10.8812 550
    20.8310 050
    $\vdots $$\vdots $$\vdots $
    760.0950
    770.1250
    第2层$\vdots $$\vdots $$\vdots $
    $\vdots $$\vdots $$\vdots $$\vdots $
    第5层6117.9250
    73.0350
    $\vdots $$\vdots $$\vdots $
    763.0350
    771.5250
    下载: 导出CSV

    表  5  针灸治疗次序(方案)的优异性验证数据

    Table  5  Acupuncture treatment order (plan) superiority verification data

    跟踪治疗时机例数痊愈数优异数非优异数
    3周以内351064
    6周以内256172
    3个月以内9522
    6个月以内7124
    下载: 导出CSV

    表  6  算法对比汇总

    Table  6  Comparison between four algorithms

    评价算法复杂度实验100次得分评价率 (%)
    传统MCTS12 50017.13068.14
    基于混合知识的MCTS-max12 50021.62386.01
    基于混合知识的遗传算法120 00011.46848.51
    基于混合知识的贪心算法50021.24984.52
    下载: 导出CSV

    表  B.1  吞咽障碍针刺穴位统计表

    Table  B.1  Statistical table of acupuncture points for dysphagia

    出现次数出现频率归一化处理穴位序号单个穴位的优先度 (java)最终评价值
    廉泉2210.111561a10.78340.8917
    风池2190.110550.99090909a20.70010.845504545
    翳风1310.0661280.59090909a300.590909091
    金津1120.0565370.50454545a40.50560.505072727
    玉液1110.0560320.5a500.5
    完骨820.0413930.36818182a60.3390.353590909
    风府710.035840.31818182a70.4260.372090909
    人中610.0307930.27272727a80.28340.278063636
    人迎580.0292780.25909091a90.72790.493495455
    旁廉泉490.0247350.21818182a100.75560.486890909
    天突450.0227160.2a110.67230.43615
    百会430.0217060.19090909a1200.190909091
    上廉泉340.0171630.15a1300.15
    天柱300.0151440.13181818a140.42980.280809091
    外玉液270.0136290.11818182a1500.118181818
    外金津270.0136290.11818182a1600.118181818
    哑门250.012620.10909091a170.36680.237945455
    翳明200.0100960.08636364a1800.086363636
    吞咽170.0085820.07272727a1900.072727273
    地仓160.0080770.06818182a2000.068181818
    $\vdots $$\vdots $$\vdots $$\vdots $$\vdots $$\vdots $$\vdots $
    三阴交530.0267540.2363664a7400.236363636
    足三里270.0136290.11818182a7500.118181818
    照海240.0121150.10454545a7600.104545455
    太冲230.011610.1a7700.1
    丰隆190.0095910.08181818a7800.081818182
    太溪130.0065620.05454545a7900.054545455
    委中50.0025240.01818182a8000.018181818
    公孙50.0025240.01818182a8100.018181818
    然谷30.0015140.00909091a8200.009090909
    下巨虚30.0015140.00909091a8300.009090909
    上巨虚30.0015140.00909091a8400.009090909
    血海20.001010.00454545a8500.004545455
    足临泣10.0005050a8600
    阳陵泉10.0005050a8700
    地机10.0005050a8800
    大抒30.0015140.00909091a8900.009090909
    心俞20.001010.00454545a9000.004545455
    脾俞10.0005050a9100
    膈俞10.0005050a9200
    膻中穴30.0015140.00909091a9300.009090909
    关元20.001010.00454545a9400.004545455
    神阙10.0005050a9500
    下载: 导出CSV

    表  D.1  混合知识库

    Table  D.1  Hybrid knowledge base

    (穴位代号, 评价值)
    (1, 0.891700000)(34, 0.013636364)(67, 0.054545455)(11011, 0.088440506)
    (2, 0.845504545)(35, 0.013636364)(68, 0.018181818)(90102, 0.139526954)
    (3, 0.590909091)(36, 0.238168182)(69, 0.018181818)(100902, 0.15563375)
    (4, 0.505072727)(37, 0.013636364)(70, 0.009090909)(90111, 0.074267505)
    (5, 0.5000000)(38, 0.013636364)(71, 0.009090909)(21001, 0.13419066)
    (6, 0.353590909)(39, 0.013636364)(72, 0.009090909)(20901, 0.095735074)
    (7, 0.372090909)(40, 0.013636364)(73, 0.004545455)(100109, 0.173870168)
    (8, 0.278063636)(41, 0.013636364)(74, 0.009090909)(20110, 0.175216481)
    (9, 0.493495455)(42, 0.009090909)(75, 0.004545455)(20109, 0.112918919)
    (10, 0.486890909)(43, 0.292045455)(76, 0.009090909)(100209, 0.099847447)
    (11, 0.436150000)(44, 0.009090909)(77, 0.004545455)(10910, 0.119356742)
    (12, 0.190909091)(45, 0.009090909)(110, 0.419621)(10902, 0.158522203)
    (13, 0.150000000)(46, 0.009090909)(1001, 0.405419)(91001, 0.143002889)
    (14, 0.280809091)(47, 0.004545455)(109, 0.391218)(11002, 0.185644285)
    (15, 0.118181818)(48, 0.281772727)(102, 0.37572)(100111, 0.080705328)
    (16, 0.118181818)(49, 0.004545455)(201, 0.364057)(91101, 0.067829683)
    (17, 0.237945455)(50, 0.278072727)(210, 0.357253)(90110, 0.161165872)
    (18, 0.086363636)(51, 0.004545455)(1009, 0.328796)(100901, 0.105697788)
    (19, 0.072727273)(52, 0.639200000)(1002, 0.327662)(2011009, 0.131238458)
    (20, 0.068181818)(53, 0.340909091)(111, 0.306954)(1090211, 0.06947019)
    (21, 0.068181818)(54, 0.273781818)(1011, 0.291753)(1100902, 0.148610784)
    (22, 0.050000000)(55, 0.172727273)(901, 0.277497)(1100211, 0.092690625)
    (23, 0.045454545)(56, 0.081818182)(910, 0.263296)(9020110, 0.139915065)
    (24, 0.040909091)(57, 0.040909091)(209, 0.24823)(1100911, 0.109088265)
    (25, 0.036363636)(58, 0.031818182)(211, 0.236621)(2011011, 0.092747959)
    (26, 0.031818182)(59, 0.004545455)(902, 0.220691)(2090110, 0.114630591)
    (27, 0.027272727)(60, 0.004545455)(1110, 0.20649)(9011002, 0.121701835)
    (28, 0.022727273)(61, 0.004545455)(1101, 0.192288)(9100211, 0.053053438)
    (29, 0.022727273)(62, 0.236363636)(1102, 0.17679)(2110110, 0.079102370)
    (30, 0.018181818)(63, 0.118181818)(911, 0.157189)(2090111, 0.063698526)
    (31, 0.018181818)(64, 0.104545455)(1109, 0.160267)
    (32, 0.018181818)(65, 0.100000000)(11009, 0.188802)
    (33, 0.312590909)(66, 0.081818182)(10210, 0.125794565)
    下载: 导出CSV

    表  C.1  穴位组合评价值

    Table  C.1  Acupoint combination evaluation value

    两个穴位排序优先度最终评价值三个穴位排序优先度最终评价值四个穴位排序优先度最终评价值
    a10a10.75080.405419a1a10a90.77130.188802a1a10a9a20.77760.148611
    a1a90.72450.391218a1a9a100.75840.185644a1a2a9a100.73210.139915
    a1a20.69580.37572a1a2a90.71580.175216a1a2a10a90.68670.131238
    a2a10.67420.364057a1a2a100.71030.17387a2a1a9a100.63680.121702
    a1a110.66160.357253a1a9a20.65840.161166a2a1a10a90.59980.114631
    a9a10.60890.328796a1a10a20.64760.158522a1a9a2a100.57080.109088
    a9a100.60680.327662a2a1a90.63580.155634a1a9a10a20.48530.092748
    a2a90.56660.305954a2a1a100.58420.143003a2a9a1a100.4850.092691
    a2a110.54030.291753a2a9a10.570.139527a2a9a10a10.41390.079102
    a2a100.51390.277497a2a9a100.54820.134191a9a1a2a100.36350.06947
    a11a10.48760.263296a2a10a110.51390.125795a9a2a1a100.33330.063699
    a10a20.45970.24823a1a11a20.48760.119357a10a1a2a90.27760.053053
    a9a20.43820.236621a9a10a110.46130.112919
    a10a90.40870.220691a2a11a10.43180.105698
    a10a10.38240.20649a2a11a100.39110.095735
    a11a20.35610.192288a9a1a20.40790.099847
    a9a110.32740.17679a9a2a10.36130.088441
    a11a100.29110.157189a10a11a10.30340.074268
    a10a110.29680.160267a10a1a110.27710.06783
    下载: 导出CSV
  • [1] Arnold T, Wooders M H. Dynamic club formation with coordination. Journal of Dynamics and Games, 2017, 2(3–4): 341−361
    [2] L Zhang. Artificial neural network model design and topology analysis for FPGA implementation of Lorenz Chaotic generator. In: Proceedings of the 30th IEEE Canadaian Conference on Electrical and Computer Engineering, Windsor, ON, Canada: IEEE, 2017. 1−4
    [3] Chen M, Zhou R Q, Zhang R, Zhu X Z. Application of artificial neural network to failure diagnosis on process industry equipments. In: Proceedings of the 6th International Conference on Natural Computation, Yantai, China IEEE, 2010. 1190−1193
    [4] 孔令智, 高迎彬, 李红增, 张华鹏. 一种快速的多个主成分并行提取算法. 自动化学报, 2017, 43(5): 835−842

    Kong Ling-Zhi, Gao Ying-Bin, Li Hong-Zeng, Zhang Hua-Peng. A fast algorithm that extracts multiple principle components in parallel. Acta Automatica Sinica, 2017, 43(5): 835−842
    [5] Tan S F, Mavrovouniotis M L. Reducing data dimensionality through optimizing neural network inputs. Aiche Journal, 1995, 41(6): 1471−1480 doi: 10.1002/(ISSN)1547-5905
    [6] Hnida M, Idrissi M K, Bennani S. Adaptive teaching learning sequence based on Instructional design and evolutionary computation. In: Proceedings of the 15th International Conference on Information Technology Based Higher Education and Training, Intanbul,Turkey: IEEE, 2016. 1−6
    [7] Zhang W, Shi J W, Tang G F, Wu W J, Yue X, Li D F. Predicting small RNAs in bacteria via sequence learning ensemble method. In: Proceedings of the 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Denver-Broomfield, CO, USA: IEEE, 2017. 643−647
    [8] Reed M, Yiannakou A, Evering R. An ant colony algorithm for the multi-compartment vehicle routing problem. Elsevier Science Publishers B.V., 2014, 15(2): 169−176
    [9] Novoaab C. An approximate dynamic programming approach for the vehicle routing problem with stochastic demands. European Journal of Operational Research, 2009, 196(2): 509−515 doi: 10.1016/j.ejor.2008.03.023
    [10] 肖云涛, 欧林林, 俞立. 基于线性时序逻辑的最优巡回路径规划. 自动化学报, 2014, 40(10): 2126−2133

    Xiao Yun-Tao, Ou Lin-Lin, Yu Li. Optimal patrolling path planning via linear temporal logic. Acta Automatica Sinica, 2014, 40(10): 2126−2133
    [11] Bosansky B, Lisy V, Lanctot M, Cermak J, Winands M H M. Algorithms for computing strategies in two player simultaneous move games. Artificial Intelligence, 2016, 237: 1−40 doi: 10.1016/j.artint.2016.03.005
    [12] Conway R. T. Sangaline E. W. A Monte Carlo simulation approach for quantitatively evaluating keyboard layouts for gesture input. International Journal of Human-Computer Studies, 2017, 99: 37−47
    [13] Kato H, Takaya M, Yamamura A. Analysis of a Monte Carlo tree search in Knight-Amazons. Procedia Computer Science, 2015, 62: 31−38 doi: 10.1016/j.procs.2015.08.406
    [14] Powley E J, Cowling P I, Whitehouse D. Information capture and reuse strategies in Monte Carlo tree search with applications to games of hidden information. Artificial Intelligence, 2014, 217(C): 92−116
    [15] Gelly S, Wang Y. Exploration exploitation in go. UCT for Monte-Carlo go, 2006, 1−8
    [16] Chaslot J B, Winands M H M, Herik H J V D, Uiterwijk J W H M, Bouzy B. Progressive strategies for Monte-Carlo tree search. New Mathematics and Natural Computation, 2008, 4(3): 343−357 doi: 10.1142/S1793005708001094
    [17] 田渊栋. 阿法狗围棋系统的简要分析. 自动化学报, 2016, 42(5): 671−675

    Tian Yuan-Dong. A simple analysis of AlphaGo. Acta Automatica Sinica, 2016, 42(5): 671−675
    [18] Kocsis L, Szepesvári C. Bandit based Monte-Carlo planning. In: Proceedings of the 2006 European Conference on Machine Learning Bertin, Heidetberg, Germany: Springer-Vertag, 2006. 4212: 282−293
    [19] Mandai Y, Kaneko T. Lin-UCB applied to Monte Carlo tree search. Theoretical Computer Science, 2016, 644: 114−126 doi: 10.1016/j.tcs.2016.06.035
    [20] Browne C B, Powley E, Whitehouse D, Lucas S M, Cowling P I. A survey of Monte Carlo tree search methods. IEEE Transactions on Computational Intelligence and AI in Games, 2012, 4(1): 1−43 doi: 10.1109/TCIAIG.2012.2186810
    [21] Lorentz R. Using evaluation functions in Monte-Carlo tree search. Theoretical Computer Science, 2016, 644(1): 106−113
    [22] Ohmoto Y, Kataoka M, Nishida T. Extended methods to dynamically estimate emphasizing points for group decision-making and their evaluation. Procedia–Social and Behavioral Sciences, 2013, 97: 147−155 doi: 10.1016/j.sbspro.2013.10.215
    [23] Meng F Y, Zhang Q. Induced continuous Choquet integral operators and their application to group decision making. Computers and Industrial Engineering, 2014, 68(1): 42−53
    [24] Xu Z S, Cai X Q. Dynamic intuitionistic fuzzy multi-attribute decision making. International Journal of Approximate Reasoning, 2008, 48(1): 246−262 doi: 10.1016/j.ijar.2007.08.008
    [25] Wilson R D, Howe E C. A cost-effectiveness analysis of screening methods for dysphagia after stroke. PM & R, 2012, 4(4): 273−282
    [26] 黄伟新. 针灸联合康复训练治疗卒中后吞咽障碍的文献及临床研究[博士学位论文]. 广州中医药大学, 中国, 2016.

    Huang Wei–Xin. The Study of Literature and Clinical Research on Acupuncture Treatment Combined with Rehabilitation Training of Dysphagia after Stroke [Ph.D. dissertation]. Guangzhou University of Chinese Medicine, China, 2016.
    [27] Huang W T, Chen P S, Liu J J, Chen Y R, Chen Y H. Dynamic configuration scheduling problem for stochastic medical resources. Journal of Biomedical Informaticsl, 2018, 4(80): 96−105
    [28] Chen P S, Lin Y J, Peng N C. A two-stage method to determine the allocation and scheduling of medical staff in uncertain environments. Computer and Inolustrial Engineering, 2016, 99: 174−188
    [29] 刘惊雷, 张伟, 童向荣, 张振荣. 一种O(2.983n)时间复杂度的最优联盟结构生成算法. 软件学报, 2011, 22(5): 938−950

    Liu Jing-Lei, Zhang Wei, Tong Xiang-Rong, Zhang Zhen-Rong. O(2.983n) time complexity algorithm for optimal coalition structure generation. Journal of Software, 2011, 22(5): 938−950
    [30] 张新良, 石纯一. 多Agent联盟结构动态生成算法. 软件学报, 2007, 18(3): 574−581

    Zhang Xin-Liang, Shi Chun-Yi. A dynamic formation algorithm of multi-agent coalition structure. Journal of Software, 2007, 18(3): 574−581
    [31] Michalak T, Rahwan T, Elkind E, Wooldridge M, Jennings N R. A hybrid exact algorithm for complete set partitioning. Artificial Intelligence, 2016, 230(C): 14−50
    [32] Aurangzeb M, Lewis F L. Internal structure of coalitions in competitive and altruistic graphical coalitional games. Automatica, 2014, 50(2): 335−348 doi: 10.1016/j.automatica.2013.11.002
    [33] 时恩早, 张先哲. 基于直觉模糊偏好关系的多属性群决策方法. 控制工程, 2017, 24(7): 1352−1358

    Shi En-Zao, Zhang Xian-Zhe. Intuitionist fuzzy preference relations and their applications to multi-attribute decision making. Control Engineering of China, 2017, 24(7): 1352−1358
    [34] Liu P D, Chen S M. Multiattribute group decision making based on intuitionistic 2-tuple linguistic information. Information Sciences, 2018, 430: 599−619
    [35] Graf T, Platzner M. Adaptive playouts for online learning of policies during Monte Carlo tree search. Theoretical Computer Science, 2016, 644: 53−62 doi: 10.1016/j.tcs.2016.06.029
    [36] 倪延延, 张晋昕. 向量自回归模型拟合与预测效果评价. 中国卫生统计, 2014, 31(1): 53−56

    Ni Yan-Yan, Zhang Jin-Xin. Modeling and forecasting for multivariate time series using a vector autoregression model. Chinese Journal of Health Statistics, 2014, 31(1): 53−56
    [37] Xu B, Peng Z P, Yu J P, Ke W D. Quantum coding genetic algorithm based on frog leaping. Engineering Sciences, 2014, 16(3): 108−112
  • 加载中
图(6) / 表(9)
计量
  • 文章访问数:  1288
  • HTML全文浏览量:  208
  • PDF下载量:  71
  • 被引次数: 0
出版历程
  • 收稿日期:  2018-03-03
  • 录用日期:  2018-07-16
  • 网络出版日期:  2020-07-10
  • 刊出日期:  2020-07-10

目录

    /

    返回文章
    返回