[1]李海林,梁叶.分段聚合近似和数值导数的动态时间弯曲方法[J].智能系统学报编辑部,2016,11(2):249-256.[doi:10.11992/tis.201507064]
LI Hailin,LIANG Ye.Dynamic time warping based on piecewise aggregate approximation and data derivatives[J].CAAI Transactions on Intelligent Systems,2016,11(2):249-256.[doi:10.11992/tis.201507064]
点击复制
LI Hailin,LIANG Ye.Dynamic time warping based on piecewise aggregate approximation and data derivatives[J].CAAI Transactions on Intelligent Systems,2016,11(2):249-256.[doi:10.11992/tis.201507064]
分段聚合近似和数值导数的动态时间弯曲方法
《智能系统学报》编辑部[ISSN 1673-4785/CN 23-1538/TP] 卷:
11
期数:
2016年第2期
页码:
249-256
栏目:
学术论文—人工智能基础
出版日期:
2016-04-25
- Title:
- Dynamic time warping based on piecewise aggregate approximation and data derivatives
- Keywords:
- dynamic time warping; time series; piecewise aggregate approximation; numerical derivative; similarity measure; classification; dimensionality reduction; feature representation
- 分类号:
- TP301
- 摘要:
- 针对动态弯曲方法对时间序列数据相似性度量的质量和效率的局限性,本文提出一种基于分段聚合近似和数值导数的动态时间弯曲方法。该方法通过分段聚合近似将时间序列数据进行有效地降维,再结合数值导数对降维后的特征序列构建新特征序列,并且设计符合该特征序列相似性度量方法。实验结果分析表明,与传统动态弯曲方法相比,新方法具有较好的度量质量,能在时间序列数据挖掘中得到较好的分类效果,且在低维空间具有较高的分类效率,具有一定的优越性。
- Abstract:
- Dynamic time warping (DTW) is often used to measure the similarity of time series data; however, it has efficiency and quality limitations. In this study, a novel DTW method combining piecewise aggregate approximation (PAA) and derivatives is proposed to measure the similarity of time series. The dimensionality of the time series data was effectively reduced by PAA, and the feature sequence was transformed into new sequences by combining the numerical derivatives after the dimensionality reduction. Furthermore, the DTW design corresponded to the similarity measurement method of the feature sequence. The experimental results demonstrate that the proposed method is superior because it has better measurement quality, obtains a better classification effect in time series data mining, and has high efficiency in lower dimensional spaces.
- 参考文献/References:
-
[1] 韩敏, 许美玲, 王新迎. 多元时间序列的子空间回声状态网络预测模型[J]. 计算机学报, 2014, 37(11): 2268-2275. HAN Min, XU Meiling, WANG Xinying. A multivariate time series prediction model based on subspace echo state network[J]. Chinese journal of computers, 2014, 37(11): 2268-2275.
[2] MARSZA EK A, BURCZY SKI T. Modeling and forecasting financial time series with ordered fuzzy candlesticks[J]. Information sciences, 2014, 273: 144-155.
[3] ZAMORA M, LAMBERT A, MONTERO G. Effect of some meteorological phenomena on the wind potential of Baja California[J]. Energy procedia, 2014, 57: 1327-1336.
[4] GRAVIO G D, MANCINI M, PATRIARCA R, et al. Overall safety performance of air traffic management system: forecasting and monitoring[J]. Safety science, 2015, 72: 351-362.
[5] 李海林, 郭韧 万校基. 基于特征矩阵的多元时间序列最小距离度量方法[J]. 智能系统学报, 2015, 10(3): 442-447. LI Hailin, GUO Ren, WAN Xiaoji. A minimum distance measurement method for multivariate time series based on the feature matrix[J]. CAAI transactions on intelligent systems, 2015, 10(3): 442-447.
[6] SAKOE H, CHIBA S. Dynamic programming algorithm optimization for spoken word recognition[J]. IEEE transactions on acoustics, speech, and signal processing, 1978, 26(1): 43-49.
[7] IZAKIAN H, PEDRYCZ W, JAMAL I. Fuzzy clustering of time series data using dynamic time warping distance[J]. Engineering applications of artificial intelligence, 2015, 39: 235-244.
[8] ZHANG Zheng, TANG Ping, DUAN Rubing. Dynamic time warping under pointwise shape context[J]. Information sciences, 2015, 315: 88-101.
[9] 李正欣, 张凤鸣, 李克武. 基于DTW的多元时间序列模式匹配方法[J]. 模式识别与人工智能, 2011, 24(3): 425-430. LI Zhengxin, ZHANG Fengming, LI Kewu. DTW based pattern matching method for multivariate time series[J]. Pattern recognition and artificial intelligence, 2011, 24(3): 425-430.
[10] LI Hailin. Asynchronism-based principal component analysis for time series data mining[J]. Expert systems with applications, 2014, 41(6): 2842-2850.
[11] KEOGH E, PAZZANI M J. Derivative dynamic time warping[C]//Proceedings of the 1st SIAM International Conference on Data Mining. Chicago, IL, USA, 2001: 1-11.
[12] JEONG Y S, JAYARAMAN R. Support vector-based algorithms with weighted dynamic time warping kernel function for time series classification[J]. Knowledge-based systems, 2015, 75: 184-191.
[13] GóRECKI T, ?UCZAK M. Using derivatives in time series classification[J]. Data mining and knowledge discovery, 2013, 26(2): 310-331.
[14] 李海林, 杨丽彬. 时间序列数据降维和特征表示方法[J]. 控制与决策, 2013, 28(11): 1718-1722. LI Hailin, YANG Libin. Method of dimensionality reduction and feature representation for time series[J]. Control and decision, 2013, 28(11): 1718-1722.
[15] BANKó Z, ABONYI J. Mixed dissimilarity measure for piecewise linear approximation based time series applications[J]. Expert systems with applications, 2015, 42(21): 7664-7675.
[16] AGRAWAL R, FALOUTSOS C, SWAMI A. Efficient similarity search in sequence databases[C]//Proceedings of the 4th International Conference on Foundations of Data Organization and Algorithms. Berlin Heidelberg: Springer, 1993, 730: 69-84.
[17] WANG Hongfa. Clustering of hydrological time series based on discrete wavelet transform[J]. Physics procedia, 2012, 25: 1966-1972.
[18] WENG Xiaoqing, SHEN Junyi. Classification of multivariate time series using two-dimensional singular value decomposition[J]. Knowledge-based systems, 2008, 21(7): 535-539.
[19] LIN J, KEOGH E, WEI Li, et al. Experiencing SAX: a novel symbolic representation of time series[J]. Data mining and knowledge discovery, 2008, 15(2): 107-144.
[20] KEOGH E, XI X, WEI L, et al. The UCR time series classification/clustering homepage[EB/OL]. 2007. http://www.cs.ucr.edu/~eamonn/time_series_data/.
- 相似文献/References:
-
[1]彭昱忠,元昌安,李洁,等.个体最优共享GEP算法及其气象降水数据预测建模[J].智能系统学报编辑部,2016,11(3):401.[doi:10.11992/tis.201603035]
PENG Yuzhong,YUAN Changan,LI Jie,et al.Individual optimal sharing GEP algorithm and its application in forecast modeling of meteorological precipitation[J].CAAI Transactions on Intelligent Systems,2016,11():401.[doi:10.11992/tis.201603035]
[2]李海林,龙芳菊.基于同步频繁树的时间序列关联规则分析[J].智能系统学报编辑部,2021,16(3):502.[doi:10.11992/tis.202008012]
LI Hailin,LONG Fangju.Association rules analysis of time series based on synchronization frequent tree[J].CAAI Transactions on Intelligent Systems,2021,16():502.[doi:10.11992/tis.202008012]
[3]李锵,吴正彪,关欣.结合深度乐谱特征融合的钢琴指法生成方法[J].智能系统学报编辑部,2023,18(6):1287.[doi:10.11992/tis.202303018]
LI Qiang,WU Zhengbiao,GUAN Xin.Piano fingering generation with deep musical score feature fusion[J].CAAI Transactions on Intelligent Systems,2023,18():1287.[doi:10.11992/tis.202303018]
[4]李海林,梁叶.标签传播时间序列聚类的股指期货套期保值策略研究[J].智能系统学报编辑部,2019,14(2):288.[doi:10.11992/tis.201707023]
LI Hailin,LIANG Ye.Research on the stock index futures hedging strategy using label propagation time series clustering[J].CAAI Transactions on Intelligent Systems,2019,14():288.[doi:10.11992/tis.201707023]
备注/Memo
收稿日期:2015-7-24;改回日期:。
基金项目:国家自然科学基金项目(61300139);福建省中青年教育科研基金项目(JAS14024);华侨大学中青年教师科研提升计划项目(ZQN-PY220).
作者简介:李海林,男,1982年生,副教授,博士,主要研究方向为数据挖掘与决策支持,主持国家自然科学基金、省部级基金多项,发表学术论文30余篇,其中被SCI检索11篇,EI检索10余篇;梁叶,女,1992年生,硕士研究生,主要研究方向为数据挖掘与金融数据分析。
通讯作者:李海林.E-mail:hailin@hqu.edu.cn.
更新日期/Last Update:
1900-01-01