Title :
Research on One Intelligent Prediction Method for Water Bloom
Author :
Xiaoyi Wang ; Zaiwen Liu ; Shiping Zhu ; Jun Dai ; Chenling Zhu ; Minghua Yang
Author_Institution :
Sch. of Comput. & Inf. Eng., Beijing Technol. & Bus. Univ., Beijing, China
Abstract :
An intelligent method on short-term prediction on water bloom of BP neural network based on rough set and wavelet analysis is proposed in this paper. This method analyzes factors of effecting the outbreak of water bloom, and these many factors which were processed by reduction method based on rough set were used as input information of the prediction model; after analyzing the main input information by wavelet multi-resolution, it can eliminate the interference factors in the input information, and use BP network to establish the non-linear relationship between input factors and result of water bloom prediction. After experimental simulation, it can validate that this kind of short-term forecast model can predict the short-term change regularity of chlorophyll more precisely, and provides an efficient new method for short-term prediction of water bloom.
Keywords :
backpropagation; environmental science computing; neural nets; rough set theory; water; wavelet transforms; BP neural network; backpropagation neural network; interference factor elimination; reduction method; rough set theory; short term intelligent prediction method; short-term forecast model; water bloom prediction; wavelet analysis; wavelet multiresolution method; Algae; Chemicals; Interference elimination; Neural networks; Prediction methods; Predictive models; Set theory; Water pollution; Water resources; Wavelet analysis; Neural network; Rough set; Short-term prediction; Water bloom; Wavelet analysis;
Conference_Titel :
Dependable, Autonomic and Secure Computing, 2009. DASC '09. Eighth IEEE International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-0-7695-3929-4
Electronic_ISBN :
978-1-4244-5421-1
DOI :
10.1109/DASC.2009.35