A NEURAL NETWORK MODEL FOR TIME-SERIES FORECASTING

被引:0
|
作者
Morariu, Nicolae [1 ]
Iancu, Eugenia [1 ]
Vlad, Sorin [1 ]
机构
[1] Stefan Cel Mare Univ Suceava, Econ Sci & Publ Adm Fac, Suceava, Romania
来源
关键词
time-series; pattern recognition; neural networks; multilayer perceptron; diagnostication; forecasting;
D O I
暂无
中图分类号
F [经济];
学科分类号
02 ;
摘要
The paper presents some aspects regarding the use of pattern recognition techniques and neural networks for the activity evolution diagnostication and prediction by means of a set of indicators. Starting from the indicators set there is defined a measure on the patterns set, measure representing a scalar value that characterizes the activity analyzed at each time moment. A pattern is defined by the values of the indicators set at a given time. Over the classes set obtained by means of the classification and recognition techniques is defined a relation that allows the representation of the evolution from negative evolution towards positive evolution. For the diagnostication and prediction the following tools are used: pattern recognition and multilayer perceptron. The paper also presents the REFORME software written by the authors and the results of the experiment obtained with this software for macroeconomic diagnostication and prediction during the years 2003-2010.
引用
收藏
页码:213 / 223
页数:11
相关论文
共 50 条
  • [41] Time series forecasting model using a hybrid ARIMA and neural network
    Zou, Haofei
    Yang, Fangfing
    Xia, Guoping
    PROCEEDINGS OF THE 2005 CONFERENCE OF SYSTEM DYNAMICS AND MANAGEMENT SCIENCE, VOL 2: SUSTAINABLE DEVELOPMENT OF ASIA PACIFIC, 2005, : 934 - 939
  • [42] An investigation of model selection criteria for neural network time series forecasting
    Qi, M
    Zhang, GP
    EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2001, 132 (03) : 666 - 680
  • [43] Evolving the neural network model for forecasting air pollution time series
    Niska, H
    Hiltunen, T
    Karppinen, A
    Ruuskanen, J
    Kolehmainen, M
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2004, 17 (02) : 159 - 167
  • [44] A dynamic artificial neural network model for forecasting time series events
    Ghiassi, M
    Saidane, H
    Zimbra, DK
    INTERNATIONAL JOURNAL OF FORECASTING, 2005, 21 (02) : 341 - 362
  • [45] Neural Network Model for Efficient portfolio Management and Time Series Forecasting
    Pai, Nikhitha
    Ilango, V
    PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND CONTROL SYSTEMS (ICICCS 2020), 2020, : 150 - 155
  • [46] Time series forecasting using a hybrid ARIMA and neural network model
    Zhang, GP
    NEUROCOMPUTING, 2003, 50 : 159 - 175
  • [47] Deformation Forecasting using a Hybrid Time Series and Neural Network Model
    Wang, Qiang
    Gao, Ning
    Jiao, Wen Zhe
    Wang, Guan Jie
    ADVANCES IN CIVIL ENGINEERING II, PTS 1-4, 2013, 256-259 : 2343 - 2346
  • [48] Evolving the neural network model for forecasting air pollution time series
    Niska, H
    Kolehmainen, M
    Hiltunen, T
    Karppinen, A
    Ruuskanen, J
    INTELLIGENT CONTROL SYSTEMS AND SIGNAL PROCESSING 2003, 2003, : 279 - 284
  • [49] A neural network based time series forecasting
    Jana, PK
    PROCEEDINGS OF INTERNATIONAL CONFERENCE ON INTELLIGENT SENSING AND INFORMATION PROCESSING, 2004, : 329 - 331
  • [50] A Neural Network Approach to Time Series Forecasting
    Gheyas, Iffat A.
    Smith, Leslie S.
    WORLD CONGRESS ON ENGINEERING 2009, VOLS I AND II, 2009, : 1292 - 1296