机构:[1]School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China[2]Guangdong Provincial Key Laboratory of New and Renewable Energy Research and Development, Guangzhou 510640, China[3]School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou 510275, China[4]College of Materials Science and Engineering, Shenzhen University, Shenzhen 518060, China[5]Key Laboratory of Fluid and Power Machinery, Ministry of Education, Xihua University, Chengdu 610039, China[6]Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei 10608, Taiwan[7]Department of Systems Engineering and Engineering Management, City University of Hong Kong, Hong Kong[8]Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing 100054, China重点科室诊疗科室神经病学中心首都医科大学附属天坛医院
Deep Neural Networks (DNNs) has been dominating recent data mining related tasks with better performances. This article proposes a hybrid approach that exploits the unique predictive power of DNN and classical time series regression models, including Generalized Linear Model (GLM), Seasonal AutoRegressive Integrated Moving Average model (SARIMA) and AutoRegressive Integrated Moving Average with eXplanatory variable (ARIMAX) method, in forecasting time series in reality. For each selected time series regression model, three different hybrid strategies are designed in order to merge its results with DNNs, namely, Zhang's method, Khashei's method, and moving average filter-based method. The real seasonal time series data of patient arrival volume in a Hong Kong A&ED center was collected for the period July 1, 2009, through June 30, 2011 and is used for comparing the forecast accuracy of proposed hybrid strategies. The mean absolute percentage error (MAPE) is set as the metric and the result indicates that all hybrid models achieved higher accuracy than original single models. Among 3 hybrid strategies, generally, Khashei's method and moving average filter-based method achieve lower MAPE than Zhang's method. Furthermore, the predicted value is an important prerequisite of conducting the rostering and scheduling in A&ED center, either in the simulation-based approach or in the mathematical programming approach.
基金:
Guangdong Provincial Key Laboratory of New and Renewable Research and Development [Y807s61001]; University of Science and Technology Beijing through the National Taipei University of Technology Joint Research Program [TW2018008]; Fundamental Research Funds for the Central UniversitiesFundamental Research Funds for the Central Universities [06500103, 06500078]; Hong Kong RGCHong Kong Research Grants Council [T32-102/14N]; National Nature Science and Foundation of ChinaNational Natural Science Foundation of China [71801031]; City University of Hong Kong SRGCity University of Hong Kong [7004698]; National Key Research and Development Program of China [2018YFC0810601]; Open Research Subject of Key Laboratory of Fluid and Power Machinery, Xihua University, Ministry of Education [szjj2019-011]
语种:
外文
被引次数:
WOS:
中科院(CAS)分区:
出版当年[2018]版:
大类|2 区工程技术
小类|2 区计算机:信息系统3 区工程:电子与电气3 区电信学
最新[2023]版:
大类|3 区计算机科学
小类|3 区工程:电子与电气4 区计算机:信息系统4 区电信学
JCR分区:
出版当年[2017]版:
Q1ENGINEERING, ELECTRICAL & ELECTRONICQ1TELECOMMUNICATIONSQ1COMPUTER SCIENCE, INFORMATION SYSTEMS
最新[2023]版:
Q2COMPUTER SCIENCE, INFORMATION SYSTEMSQ2ENGINEERING, ELECTRICAL & ELECTRONICQ2TELECOMMUNICATIONS
第一作者机构:[1]School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China[2]Guangdong Provincial Key Laboratory of New and Renewable Energy Research and Development, Guangzhou 510640, China[3]School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou 510275, China
共同第一作者:
通讯作者:
通讯机构:[1]School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China[2]Guangdong Provincial Key Laboratory of New and Renewable Energy Research and Development, Guangzhou 510640, China
推荐引用方式(GB/T 7714):
SHANCHENG JIANG,RAN XIAO,LONG WANG,et al.Combining Deep Neural Networks and Classical Time Series Regression Models for Forecasting Patient Flows in Hong Kong[J].IEEE ACCESS.2019,7:118965-118974.doi:10.1109/ACCESS.2019.2936550.
APA:
SHANCHENG JIANG,RAN XIAO,LONG WANG,XIONG LUO,CHAO HUANG...&XIMING NIE.(2019).Combining Deep Neural Networks and Classical Time Series Regression Models for Forecasting Patient Flows in Hong Kong.IEEE ACCESS,7,
MLA:
SHANCHENG JIANG,et al."Combining Deep Neural Networks and Classical Time Series Regression Models for Forecasting Patient Flows in Hong Kong".IEEE ACCESS 7.(2019):118965-118974