一级黄色片免费播放|中国黄色视频播放片|日本三级a|可以直接考播黄片影视免费一级毛片

高級搜索

留言板

尊敬的讀者、作者、審稿人, 關(guān)于本刊的投稿、審稿、編輯和出版的任何問題, 您可以本頁添加留言。我們將盡快給您答復(fù)。謝謝您的支持!

姓名
郵箱
手機(jī)號碼
標(biāo)題
留言內(nèi)容
驗證碼

差異區(qū)域平衡法探索時間序列變化的因果關(guān)系

王開軍 曾元鵬 繆忠劍

王開軍, 曾元鵬, 繆忠劍. 差異區(qū)域平衡法探索時間序列變化的因果關(guān)系[J]. 電子與信息學(xué)報, 2021, 43(8): 2414-2420. doi: 10.11999/JEIT200756
引用本文: 王開軍, 曾元鵬, 繆忠劍. 差異區(qū)域平衡法探索時間序列變化的因果關(guān)系[J]. 電子與信息學(xué)報, 2021, 43(8): 2414-2420. doi: 10.11999/JEIT200756
Kaijun WANG, Yuanpeng ZENG, Zhongjian MIAO. Different-region Balance Method for Exploring Varying Causal Relations Between Time Series[J]. Journal of Electronics & Information Technology, 2021, 43(8): 2414-2420. doi: 10.11999/JEIT200756
Citation: Kaijun WANG, Yuanpeng ZENG, Zhongjian MIAO. Different-region Balance Method for Exploring Varying Causal Relations Between Time Series[J]. Journal of Electronics & Information Technology, 2021, 43(8): 2414-2420. doi: 10.11999/JEIT200756

差異區(qū)域平衡法探索時間序列變化的因果關(guān)系

doi: 10.11999/JEIT200756
基金項目: 國家自然科學(xué)基金(61672157),福建省自然科學(xué)基金 (2018J01778)
詳細(xì)信息
    作者簡介:

    王開軍:男,1965年生,副教授,研究方向為機(jī)器學(xué)習(xí)和數(shù)據(jù)挖掘

    曾元鵬:男,1995年生,碩士生,研究方向為模式識別和數(shù)據(jù)挖掘

    通訊作者:

    王開軍 wkjwang@qq.com

  • 中圖分類號: TP391.4

Different-region Balance Method for Exploring Varying Causal Relations Between Time Series

Funds: The National Natural Science Foundation of China (61672157), The Natural Science Foundation of Fujian Province (2018J01778)
  • 摘要: 針對探索時間序列之間隨時間變化的因果關(guān)系問題,在每個窗口進(jìn)行Granger因果檢測的滑動時間窗口方法是求解該問題的常用方法,但其性能對窗寬敏感,不合適的窗寬很可能導(dǎo)致低性能。該文提出一種差異區(qū)域平衡方法,首先計算當(dāng)前滑動窗口W內(nèi)序列的波動程度Sw并作為波動界,計算窗口W的前向相鄰區(qū)域U內(nèi)序列的波動程度Su。然后,實施前向探索策略:若Su未超過Sw,則實施不同長度區(qū)域的平衡檢測方案,即對窗口W、對窗口W與U的合并區(qū)域、對窗口W與后向相鄰區(qū)域V的合并區(qū)域這3種不同長度的差異區(qū)域,分別進(jìn)行時間序列之間因果關(guān)系的檢測;若Su超過Sw,則實施上述平衡檢測方案時,其中區(qū)域U和V的長度取相同值。最后,將窗口W的多次檢測結(jié)果進(jìn)行綜合后輸出。新方法將不同長度區(qū)域的結(jié)果進(jìn)行綜合,能夠降低方法的性能對窗寬的敏感性,保障最終結(jié)果的準(zhǔn)確性和穩(wěn)定性。在1個模擬數(shù)據(jù)集和4個真實數(shù)據(jù)集上的實驗結(jié)果顯示,該文方法能有效地揭示出時間序列之間隨時間變化的因果關(guān)系,在正確率高且性能穩(wěn)定的綜合性能上優(yōu)于對比方法。
  • 圖  1  兩條序列的有近似線性關(guān)系區(qū)域[t1, t2]和無線性關(guān)系區(qū)域[t2, t7]

    表  1  不同方法在模擬數(shù)據(jù)集上發(fā)掘因果關(guān)系的正確率(%)

    窗口寬度滑動步長噪聲方差0.01噪聲方差0.2噪聲方差0.5
    常規(guī)F界轉(zhuǎn)折平衡常規(guī)F界轉(zhuǎn)折平衡常規(guī)F界轉(zhuǎn)折平衡
    20591.3288.1890.9995.4080.8294.565884.1380.5791.0050.2982.52
    1088.9888.1891.9195.0680.2594.5653.3983.3380.1591.0046.3382.54
    1586.7888.1890.0094.4378.194.5644.8683.2678.5291.0046.2282.03
    2083.6588.1889.1792.7777.0594.5645.482.1577.9891.0045.4881.87
    30595.8588.1890.6195.8785.6994.5660.492.3183.6391.0047.3787.78
    1094.4388.1890.1595.4984.9594.5653.0191.9583.6991.0046.487.41
    1594.0788.1890.8594.9183.2294.5651.6291.6581.9391.0045.9886.84
    2092.9688.1890.9595.5781.6294.5653.2191.3781.1891.0046.3886.96
    40595.5688.1891.8394.8592.4694.5663.5294.6587.6291.0046.4392.17
    1095.3188.1890.0794.8791.0594.5658.8994.2787.0891.0045.3892.22
    1594.9588.1890.6594.7790.6294.5658.7794.5586.8791.0046.3991.76
    2094.5988.1889.994.3189.594.5652.3193.9385.8691.0045.8091.03
    下載: 導(dǎo)出CSV

    表  2  在數(shù)據(jù)集Dropoff-tweet上發(fā)掘因果關(guān)系的正確率(%)

    窗口
    寬度
    滑動
    步長
    常規(guī)滑
    動窗
    F界檢測法轉(zhuǎn)折點法差異平衡法
    12491.9592.6293.5693.42
    890.8792.6293.5693.83
    1289.2692.6294.3690.20
    18494.0992.6294.9095.30
    894.3692.6294.3694.77
    1292.2192.6294.3694.77
    24494.3692.6294.0996.51
    897.0592.6296.2496.78
    1291.9592.6291.4195.70
    下載: 導(dǎo)出CSV

    表  3  在數(shù)據(jù)集Tweet-pickup上發(fā)掘因果關(guān)系的正確率(%)

    窗口
    寬度
    滑動
    步長
    常規(guī)滑
    動窗
    F界檢測法轉(zhuǎn)折點法差異平衡法
    12490.8794.9090.8793.29
    891.9594.9094.0994.09
    1292.4894.9094.0991.01
    18492.4894.9088.1994.90
    892.4894.9093.8394.90
    1293.0294.9094.0993.02
    24492.7594.9091.4195.44
    893.2994.9082.8295.97
    1292.2194.9095.4495.44
    下載: 導(dǎo)出CSV

    表  4  在數(shù)據(jù)集Fish-school上發(fā)掘因果關(guān)系的正確率(%)

    窗口
    寬度
    滑動
    步長
    常規(guī)滑動窗F界檢測法轉(zhuǎn)折點法差異平衡法
    1401089.6054.1969.8090.1
    2086.2454.1969.8093.29
    3091.2854.1969.8095.64
    1501089.6054.1969.8084.90
    2083.2254.1969.8091.28
    3089.9354.1969.8099.66
    1601083.2254.1969.8086.91
    2069.8054.1969.8093.62
    3081.5454.1969.8092.95
    下載: 導(dǎo)出CSV

    表  5  在數(shù)據(jù)集Baboon-troop上發(fā)掘因果關(guān)系的正確率(%)

    窗口
    寬度
    滑動
    步長
    常規(guī)滑動窗F界檢測法轉(zhuǎn)折點法差異平衡法
    1101080.6335.3959.1080.63
    2070.6235.3959.1082.30
    3070.6235.3959.1080.47
    1201080.6335.3959.1081.64
    2062.2735.3959.1083.31
    3063.9435.3959.1083.97
    1301080.8035.3959.1082.30
    2075.7935.3959.1083.97
    3082.3035.3959.1082.97
    下載: 導(dǎo)出CSV
  • [1] XIE Feng, CAI Ruichu, ZENG Yan, et al. An efficient entropy-based causal discovery method for linear structural equation models with IID noise variables[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(5): 1667–1680. doi: 10.1109/TNNLS.2019.2921613
    [2] YANG Jing, GUO Xiaoxue, AN Ning, et al. Streaming feature-based causal structure learning algorithm with symmetrical uncertainty[J]. Information Sciences, 2018, 467: 708–724. doi: 10.1016/j.ins.2018.04.076
    [3] 任偉杰, 韓敏. 多元時間序列因果關(guān)系分析研究綜述[J/OL]. 自動化學(xué)報, https://doi.org/10.16383/j.aas.c180189, 2019.

    REN Weijie and HAN Min. Survey on causality analysis of multivariate time series[J/OL]. Acta Automatica Sinica, https://doi.org/10.16383/j.aas.c180189, 2019.
    [4] HUANG Biwei, ZHANG Kun, GONG Mingming, et al. Causal discovery and forecasting in nonstationary environments with state-space models[C]. The 36th International Conference on Machine Learning, Long Beach, USA, 2019.
    [5] DU Sizhen, SONG Guojie, HAN Lei, et al. Temporal causal inference with time lag[J]. Neural Computation, 2018, 30(1): 271–291. doi: 10.1162/neco_a_01028
    [6] GRANGER C W J. Investigating causal relations by econometric models and cross-spectral methods[J]. Econometrica, 1969, 37(3): 424–438. doi: 10.2307/1912791
    [7] ORJUELA-CA?óN A D, CERQUERA A, FREUND J A, et al. Sleep apnea: Tracking effects of a first session of CPAP therapy by means of Granger causality[J]. Computer Methods and Programs in Biomedicine, 2020, 187: 105235. doi: 10.1016/j.cmpb.2019.105235
    [8] 范立夫, 趙善學(xué), 張永軍. 信貸結(jié)構(gòu)和產(chǎn)業(yè)結(jié)構(gòu)的相互影響研究——基于異質(zhì)面板數(shù)據(jù)的格蘭杰因果檢驗[J]. 宏觀經(jīng)濟(jì)研究, 2019(6): 73–82. doi: 10.16304/j.cnki.11-3952/f.2019.06.007

    FAN Lifu, ZHAO Shanxue, and ZHANG Yongjun. Research on the interaction between credit structure and industrial structure——Granger causality test based on heterogeneous panel data[J]. Scientific Management Research, 2019(6): 73–82. doi: 10.16304/j.cnki.11-3952/f.2019.06.007
    [9] 李永立, 吳沖. 基于多變量的Granger因果檢驗方法[J]. 數(shù)理統(tǒng)計與管理, 2014, 33(1): 50–58. doi: 10.13860/j.cnki.sltj.2014.01.003

    LI Yongli and WU Chong. The Granger causality test method based on the multiple variables[J]. Journal of Applied Statistics and Management, 2014, 33(1): 50–58. doi: 10.13860/j.cnki.sltj.2014.01.003
    [10] REN Weijie, LI Baisong, and HAN Min. A novel Granger causality method based on HSIC-Lasso for revealing nonlinear relationship between multivariate time series[J]. Physica A: Statistical Mechanics and its Applications, 2020, 541: 123245. doi: 10.1016/j.physa.2019.123245
    [11] FINKLE J D, WU J J, and BAGHERI N. Windowed Granger causal inference strategy improves discovery of gene regulatory networks[J]. Proceedings of the National Academy of Sciences of the United States of America, 2018, 115(9): 2252–2257. doi: 10.1073/pnas.1710936115
    [12] CHANG T, TSAI S L, and HAGA K Y A. Uncovering the interrelationship between the U. S. stock and housing markets: A bootstrap rolling window Granger causality approach[J]. Applied Economics, 2017, 49(58): 5841–5848. doi: 10.1080/00036846.2017.1346365
    [13] LI Zhenhui, ZHENG Guanjie, AGARWAL A, et al. Discovery of causal time intervals[C]. 2017 SIAM International Conference on Data Mining, Houston, USA, 2017: 804–812.
    [14] MASNADI-SHIRAZI M, MAURYA M R, PAO G, et al. Time varying causal network reconstruction of a mouse cell cycle[J]. BMC Bioinformatics, 2019, 20: 294. doi: 10.1186/s12859-019-2895-1
    [15] AMORNBUNCHORNVEJ C, ZHELEVA E, and BERGER-WOLF T Y. Variable-lag granger causality for time series analysis[C]. 2019 IEEE International Conference on Data Science and Advanced Analytics, Washington, USA, 2019.
  • 加載中
圖(1) / 表(5)
計量
  • 文章訪問數(shù):  1045
  • HTML全文瀏覽量:  545
  • PDF下載量:  91
  • 被引次數(shù): 0
出版歷程
  • 收稿日期:  2020-08-26
  • 修回日期:  2021-01-01
  • 網(wǎng)絡(luò)出版日期:  2021-01-07
  • 刊出日期:  2021-08-10

目錄

    /

    返回文章
    返回