Title :
Application of ANFIS to Stream-Way Transition
Author :
Ma, Shih-Wei ; Kou, Chang-Huan ; Chen, Li ; Wang, An-Pei ; Sung, Cheng-Yuan
Author_Institution :
Dept. of Civil Eng. & Eng. Inf., Chung Hua Univ., Hsinchu, Taiwan
Abstract :
The main purpose of this paper is to predict stream-way transition with adaptive-network-based fuzzy inference system (ANFIS). Therefore, the downstream stream-way transition according to the upstream conditions is forecasted by ANFIS. Five main factors may affect the stream-way transition include inflow position, inflow angle, slope, flow discharge, and sand content of suspended sediment. We selected some cross sections of Ta-Chia River in Taiwan as a case study. The results show that ANFIS has better performance than the traditional linear regression method (LR).
Keywords :
forecasting theory; fuzzy neural nets; inference mechanisms; regression analysis; rivers; ANFIS; Ta-Chia River; adaptive-network-based fuzzy inference system; flow discharge; inflow angle; inflow position; linear regression method; sand content; slope; stream-way transition; suspended sediment; Arteries; Artificial neural networks; Civil engineering; Floods; Fuzzy systems; Informatics; Knowledge engineering; Linear regression; Rivers; Typhoons; adaptive-network-based fuzzy inference system; linear regression method; stream-way transition;
Conference_Titel :
Fuzzy Systems and Knowledge Discovery, 2009. FSKD '09. Sixth International Conference on
Conference_Location :
Tianjin
Print_ISBN :
978-0-7695-3735-1
DOI :
10.1109/FSKD.2009.637
