Hybrid approaches based on SARIMA and artificial neural networks for inspection time series forecasting

被引：75

作者：

Ruiz-Aguilar, J. J. ^{[1
]}

Turias, I. J. ^{[1
]}

Jimenez-Come, M. J. ^{[1
]}

机构：

[1] Univ Cadiz, Polytech Sch Engn Algeciras, Intelligent Modelling Syst Res Grp, Cadiz 11202, Spain

来源：

TRANSPORTATION RESEARCH PART E-LOGISTICS AND TRANSPORTATION REVIEW | 2014年 / 67卷

关键词：

Inspection forecasting; Artificial neural networks; SARIMA; Hybrid models; FEEDFORWARD NETWORKS; ARIMA MODEL; FLOW; PREDICTION; CHOICE;

D O I：

10.1016/j.tre.2014.03.009

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

In this paper, the number of goods subject to inspection at European Border Inspections Post are predicted using a hybrid two-step procedure. A hybridization methodology based on integrating the data obtained from autoregressive integrated moving averages (SARIMA) model in the artificial neural network model (ANN) to predict the number of inspections is proposed. Several hybrid approaches are compared and the results indicate that the hybrid models outperform either of the models used separately. This methodology may become a powerful decision-making tool at other inspection facilities of international seaports or airports. (C) 2014 Elsevier Ltd. All rights reserved.

引用

页码：1 / 13

页数：13

共 38 条

[21] Traffic volume time-series analysis according to the type of road use [J].

Lingras, P ;

Sharma, SC ;

Osborne, P ;

Kalyar, I .

COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2000, 15 (05) :365-373

[22]

Makridakis S.G., 1989, Forecasting methods for management / spyros makridakis, V5th

[23] A comparison of univariate methods for forecasting container throughput volumes [J].

Peng, Wen-Yi ;

Chu, Ching-Wu .

MATHEMATICAL AND COMPUTER MODELLING, 2009, 50 (7-8) :1045-1057

[24] Multiple comparison procedures applied to model selection [J].

Pizarro, J ;

Guerrero, E ;

Galindo, PL .

NEUROCOMPUTING, 2002, 48 :155-173

[25] Evaluation of two modeling methods for generating heavy-truck trips at an intermodal facility by using vessel freight data [J].

Sarvareddy, P ;

Al-Deek, H ;

Klodzinski, J ;

Anagnostopoulos, G .

FREIGHT ANALYSIS, EVALUATION, AND MODELING: 2005 THOMAS B. DEEN DISTINGUISHED LECTURE, 2005, (1906) :113-120

[26] Comparison of neural and conventional approaches to mode choice analysis [J].

Sayed, T ;

Razavi, A .

JOURNAL OF COMPUTING IN CIVIL ENGINEERING, 2000, 14 (01) :23-30

[27] Evaluation of hybrid forecasting approaches for wind speed and power generation time series [J].

Shi, Jing ;

Guo, Jinmei ;

Zheng, Songtao .

RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2012, 16 (05) :3471-3480

[28] Comparison of parametric and nonparametric models for traffic flow forecasting [J].

Smith, BL ;

Williams, BM ;

Oswald, RK .

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2002, 10 (04) :303-321

[29] CROSS-VALIDATORY CHOICE AND ASSESSMENT OF STATISTICAL PREDICTIONS [J].

STONE, M .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 1974, 36 (02) :111-147

[30] A comparative study of autoregressive neural network hybrids [J].

Taskaya-Temizel, T ;

Casey, MC .

NEURAL NETWORKS, 2005, 18 (5-6) :781-789

← 1 2 3 4 →