标题: 基于多域深度类神经网路之多变量时间序列早期分类
Multivariate Time Series Early Classification by Using Multi-Domain Deep Neuron Networks
作者: 黄怀硕
曾新穆
Huang, Huai-Shuo
Tseng, Vincent Shin-Mu
资讯科学与工程研究所
关键字: 时间序列;多变量;早期分类;深度类神经网路;资料探勘;Time Series;Multivariate;Early Classification;Deep Neural Network;Data Mining
公开日期: 2017
摘要: 多变量时间序列早期预测已在资料探勘领域中成为非常重要的研究议题,并已应用在许多领域中。随着物联网(Internet of Things)等技术的快速发展与行动感测设备之日益普及,各种类型的感测资料之快速累积形成了庞大之多变量时间序列资料,如何从中撷取出有意义的特征资讯并进行有效的分析与处理为一重要课题。以往之时间序列早期预测方法多采用形状特征(Shapelet)作为分类器基础,然而这些方法将无法在任意时间点做出预测。本研究利用结合卷积式类神经网路与长短期记忆网路提出一新颖之多域深度类神经网路方法,于多变数时间序列进行探勘分析,以建构有效的早期分类预测架构。本研究的主轴在于探讨如何使用多变量时间序列之前段萃取有用资讯,用于提早预测测试序列之类别,且保证其准确率相当于利用完整资讯的时间序列执行分类之准确率。实验结果有效证实比起现有之代表性方法,本研究方法在准确性与及早性指标上皆获得大幅提升。
Early classification on multivariate time series has become an important topic not only in data mining fields but also in areas such as medical research, motion detection, product manufacture, financial market prediction, nature event forecasting and anomaly detection. Most of the existing works use shapelet-based methods for early classification. However, shapelet extraction process is inefficient and the extracted shapelets may not be applicable to every test case at any time point. We present a novel framework named Multi-Domain Deep Neural Network (MD-DNN) that combines the characteristic of convolutional neural network and long-short term memory. Our framework is the first work addressing convolutional neural network and recurrent neural network for multivariate time series early classification. By using a truncation process, it can make predictions at any time point of a multivariate time series. Experimental results on real datasets show that MD-DNN outperforms existing methods on both earliness and accuracy.
URI: http://etd.lib.nctu.edu.tw/cdrfb3/record/nctu/#GT070456029
http://hdl.handle.net/11536/141800
显示于类别:Thesis