DocumentCode :
2864275
Title :
Prediction of Amount of Imports Based on Adaptive Neuro-Fuzzy Inference System
Author :
Chang, Zhipeng ; Liu, Liping ; Li, Zhiping
Author_Institution :
Anhui Univ. of Technol., Maanshan
fYear :
2007
fDate :
11-13 Oct. 2007
Firstpage :
437
Lastpage :
440
Abstract :
In this paper, Adaptive network-based fuzzy inference system (ANFIS) was proposed to develop a predictive model for amount of imports. Aggregate import demand function was employed to select input variables. According to aggregate import demand function, the ANFIS model with five input variables and one output variable was built. To show ANFIS model has better ability than some other conventional statistical methods in predicting economics problems, the ANFIS model results were compared with ARIMA model results. The verification of the proposed model was achieved through wave characteristics time series plots and scatter diagrams. The experimental results show that the ANFIS has higher prediction accuracy than some other conventional statistical methods.
Keywords :
economic forecasting; inference mechanisms; ANFIS model; adaptive neuro-fuzzy inference system; aggregate import demand function; economics problem prediction; predictive model; statistical methods; Accuracy; Adaptive systems; Aggregates; Economic forecasting; Fuzzy neural networks; Fuzzy systems; Input variables; Predictive models; Scattering; Statistical analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Pervasive Computing, 2007. IPC. The 2007 International Conference on
Conference_Location :
Jeju City
Print_ISBN :
978-0-7695-3006-2
Type :
conf
DOI :
10.1109/IPC.2007.36
Filename :
4438471
Link To Document :
بازگشت