Title :
Neuron Classification Algorithm and Megathermal Weather Forecast
Author :
Zhang Hongwei ; Zhao Xiao ; Zou Shurong
Author_Institution :
Coll. of Comput., Chengdu Univ. of Inf. Technol., Chengdu, China
Abstract :
A new neuron classification algorithm called NCA is proposed in the paper.The neurons of NCA divided the sample space non-linearly and adjusted themselves to cover the sample space optimally.After the noise data processed,the generalization of NCA has been enhanced.In the forecast,the introduction of law of attraction not only overcome the lack of Euclidean distance but also increases the accuracy of the forecast. NCA is used to abnormal megathermal weather forecast in north of Zhejiang province,the results demonstrate that NCA has good practicability and intelligence.
Keywords :
environmental science computing; neural nets; pattern classification; weather forecasting; Euclidean distance; Zhejiang province; megathermal weather forecast; neuron classification algorithm; sample space optimally; Classification algorithms; Correlation; Neurons; Temperature; Training; Weather forecasting;
Conference_Titel :
Intelligent Systems and Applications (ISA), 2011 3rd International Workshop on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-9855-0
Electronic_ISBN :
978-1-4244-9857-4
DOI :
10.1109/ISA.2011.5873446