基于导数序列的时间序列同构关系发现

doi:10.11772/j.issn.1001-9081.2016.09.2472

计算机应用 ›› 2016, Vol. 36 ›› Issue (9): 2472-2474.DOI: 10.11772/j.issn.1001-9081.2016.09.2472

基于导数序列的时间序列同构关系发现

邹蕾, 高学东

北京科技大学东凌经济管理学院, 北京 100083

收稿日期:2016-01-26 修回日期:2016-04-15 出版日期:2016-09-10 发布日期:2016-09-08
通讯作者: 邹蕾
作者简介:邹蕾(1988-),女,山东烟台人,博士研究生,主要研究方向:数据挖掘、时间序列分析;高学东(1963-),男,河北唐山人,教授,博士,主要研究方向:管理过程优化、数据挖掘。
基金资助:
国家自然科学基金资助项目（71272161）。

Homogeneous pattern discovery of time series based on derivative series

ZOU Lei, GAO Xuedong

Donlinks School of Economics and Management, University of Science and Technology of Beijing, Beijing 100083, China

Received:2016-01-26 Revised:2016-04-15 Online:2016-09-10 Published:2016-09-08
Supported by:
This work is partially supported by the National Natural Science Foundation of China (71272161).

摘要/Abstract

摘要： 时间序列子序列匹配作为时间序列检索、聚类、分类、异常监测等挖掘任务的基础被广泛研究。但传统的时间序列子序列匹配都是对精确相同或近似相同的模式进行匹配，为此定义了一种全新的具有相似发展趋势的序列模式——时间序列同构关系，经过数学推导给出了时间序列同构关系判定的法则，并基于此提出了同构关系时间序列片段发现的算法。该算法首先对原始时间序列进行预处理，然后分段拟合后对各时间序列分段进行同构关系判定。针对现实背景数据难以满足理论约束的问题，通过定义一个同构关系容忍度参数使实际时间序列数据的同构关系挖掘成为可能。实验结果表明，该算法能有效挖掘出满足同构关系的时间序列片段。

关键词: 时间序列, 数据挖掘, 子序列匹配, 分段, 模式发现

Abstract: As the basis of time series data mining tasks, such as indexing, clustering, classification, and anomaly detection, subsequence matching has been researched widely. Since the traditional time series subsequence matching only aims at matching the exactly same or approximately same patterns, a new sequence pattern with similar tendency, called time series homogeneous pattern, was defined. With mathematical derivation, the time series homogeneous pattern judgment rules were given, and an algorithm on time series homogeneous pattern discovery was proposed based on those rules. Firstly, the raw time series were preprocessed. Secondly, the homogeneous patterns were matched with segmentation and fitting subsequences. Since practical data can not satisfy the theoretical constraints, a parameter of homogeneous pattern tolerance was defined to make it possible for the practical data homogeneous patterns mining. The experimental results show that the proposed algorithm can effectively mine the time series homogeneous patterns.

Key words: time series, data mining, subsequence matching, segmentation, pattern discovery

中图分类号:

TP301.6

邹蕾, 高学东. 基于导数序列的时间序列同构关系发现[J]. 计算机应用, 2016, 36(9): 2472-2474.

ZOU Lei, GAO Xuedong. Homogeneous pattern discovery of time series based on derivative series[J]. Journal of Computer Applications, 2016, 36(9): 2472-2474.

参考文献

[1] AGRAWAL R, SRIKANT R. Mining sequential patterns [C]// ICDE '95: Proceedings of the 11th International Conference on Data Engineering. Washington, DC: IEEE Computer Society, 1995: 3-14.
[2] RATANAMAHATANA C A, LIN J, GUNOPULOS D, et al. Data Mining and Knowledge Discovery Handbook [M]. Berlin: Springer, 2005: 1069-1103.
[3] HAN J, DONG G, YIN Y. Efficient mining of partial periodic patterns in time series database [C]// Proceedings of the 1999 15th International Conference on Data Engineering. Washington, DC: IEEE Computer Society, 1999: 106-115.
[4] SIRISHA G N V G, SHASHI M, RAJU G V P. Periodic pattern mining—algorithms and applications [EB/OL]. [2015-12-04]. http://globaljournals.org/GJCST_Volume13/4-Periodic-Pattern-Mining-Algorithms.pdf.
[5] YU X, YU H. An asynchronous periodic sequential patterns mining algorithm with multiple minimum item supports [C]// Proceedings of the 2014 9th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing. Washington, DC: IEEE Computer Society, 2014: 274-281.
[6] 董晓莉.时间序列数据挖掘相似性度量和周期模式挖掘研究[D].天津:天津大学,2007:20-25.(DONG X L. Similarity measure and periodic pattern mining of time series data mining [D]. Tianjin: Tianjin University, 2007: 20-25.)
[7] AMIR A, APOSTOLICO A, EISENBERG E, et al. Detecting approximate periodic patterns [C]// Proceedings of the 1st Mediterranean Conference on Design and Analysis of Algorithms. Berlin: Springer, 2012: 1-12.
[8] YANG J, WANG W, YU P S. Mining surprising periodic patterns [J]. Data Mining and Knowledge Discovery, 2004, 9(2): 189-216.
[9] 肖辉.时间序列的相似性查询与异常检测[D].上海:复旦大学,2005:13.(XIAO H. Similarity search and outlier detection in time series [D]. Shanghai: Fudan University, 2005: 13.)
[10] 刘芬,郭躬德.基于符号化聚合近似的时间序列相似性复合度量方法[J].计算机应用,2013,33(1):192-198.(LIU F, GUO G D. Composite metric method for time series similarity measurement based on symbolic aggregate approximation [J]. Journal of Computer Applications, 2013, 33(1): 192-198.)
[11] 汤全武,史崇升,吴佳.基于DFT变换的彩色图像平滑滤波[J].计算机工程与设计,2014,35(4):1327-1331.(TANG Q W, SHI C S, WU J. Smoothing filter for color image using discrete Fourier transform [J]. Computer Engineering and Design, 2014, 35(4): 1327-1331.)
[12] 邱益鸣,胡华成,郑建彬,等.基于曲线相似的在线签名认证方法[J].系统工程与电子技术,2014,36(5):1016-1020.(QIU Y M, HU H C, ZHENG J B, et al. On-line handwriting signature verification based on curve similarity [J]. Systems Engineering and Electronics, 2014, 36(5): 1016-1020.)
[13] 张巍,郑建彬.基于遗传算法实现签名曲线的匹配[J].武汉理工大学学报(信息与管理工程版),2008,30(1):39-43.(ZHANG W, ZHENG J B. Implementation of the signature curve matching based on genetic algorithm [J]. Journal of Wuhan University of Technology (Information & Management Engineering), 2008, 30(1): 39-43.)
[14] 郑建彬.在线手写签名认证及其演化算法实现[D].武汉:华中科技大学,2006:66-81.(ZHENG J B. On-line handwriting signature verification and its evolutionary algorithm implementation [D]. Wuhan: Huazhong University of Science & Technology, 2006: 66-81.)
[15] 匡韬.基于演化计算的在线手写签名验证方法实现[D].武汉:武汉理工大学,2006:22-42.(KUANG T. Implementation of on-line handwritten signature verification based on evolutionary computation [D]. Wuhan: Wuhan University of Technology, 2006: 22-42.)

基于导数序列的时间序列同构关系发现

Homogeneous pattern discovery of time series based on derivative series

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李洋莹, 陈智军, 张子豪, 游兰. 基于改进Elman神经网络的制糖企业原糖需求预测模型[J]. 计算机应用, 2021, 41(7): 2113-2120.
[2]	刘世泽, 秦艳君, 王晨星, 苏琳, 柯其学, 罗海勇, 孙艺, 王宝会. 基于深度残差长短记忆网络交通流量预测算法[J]. 计算机应用, 2021, 41(6): 1566-1572.
[3]	李国荣, 冶继民, 甄远婷. 基于新的鲁棒相似性度量的时间序列聚类[J]. 计算机应用, 2021, 41(5): 1343-1347.
[4]	李旭娟, 皮建勇, 黄飞翔, 贾海朋. 基于自生成深度神经网络的4D航迹预测[J]. 计算机应用, 2021, 41(5): 1492-1499.
[5]	曹阳, 闫秋艳, 吴鑫. 不平衡时间序列集成分类算法[J]. 计算机应用, 2021, 41(3): 651-656.
[6]	张凌哲, 黄向东, 乔嘉林, 勾王敏浩, 王建民. 面向时序数据的两阶段日志结构合并树文件合并框架[J]. 计算机应用, 2021, 41(3): 618-622.
[7]	钱斌, 郑楷洪, 陈子鹏, 肖勇, 李森, 叶纯壮, 马千里. 基于残差连接长短期记忆网络的时间序列修复模型[J]. 计算机应用, 2021, 41(1): 243-248.
[8]	肖勇, 郑楷洪, 郑镇境, 钱斌, 李森, 马千里. 基于多尺度跳跃深度长短期记忆网络的短期多变量负荷预测[J]. 计算机应用, 2021, 41(1): 231-236.
[9]	高世乐, 王滢, 李海林, 万校基. 基于矩阵画像的金融时序数据预测方法[J]. 计算机应用, 2021, 41(1): 199-207.
[10]	陈凯, 于彦伟, 赵金东, 宋鹏. 基于城市交通监控大数据的工作位置推理方法[J]. 计算机应用, 2021, 41(1): 177-184.
[11]	马停停, 冀天娇, 杨冠羽, 陈阳, 许文波, 刘宏图. 基于长短时记忆神经网络的手足口病发病趋势预测[J]. 计算机应用, 2021, 41(1): 265-269.
[12]	郭秀婷, 朱昶胜, 张生财, 赵奎鹏. 分形插值在风速时间序列中的应用[J]. 计算机应用, 2020, 40(9): 2628-2633.
[13]	胡珉, 白雪, 徐伟, 吴秉键. 多维时间序列异常检测算法综述[J]. 计算机应用, 2020, 40(6): 1553-1564.
[14]	龙洋洋, 陈玉玲, 辛阳, 豆慧. 基于联盟区块链的安全能源交易方案[J]. 计算机应用, 2020, 40(6): 1668-1673.
[15]	徐周波, 杨健, 刘华东, 黄文文. 基于XGBoost与拓扑结构信息的蛋白质复合物识别算法[J]. 计算机应用, 2020, 40(5): 1510-1514.