Abstract | ||
---|---|---|
In this paper a neural network based method of local rainfall prediction is proposed. This method is developed based on past observations on various atmospheric parameters such as temperature, relative humidity, vapor presser, etc. We propose a neural network model whose architecture combines several multilayer perceptron networks (MLPs) to realize better performance after capturing the seasonality effect in the atmospheric data. We also demonstrate that the use of appropriate features can further improve the performance in prediction accuracy. These observations inspired us to use a feature selection MLP, FSMLP, (instead of MLP) which can select good features on-line while learning the prediction task. The FSMLP is used as a preprocessor to select good features. The combined use of FSMLP and SOFM-MLP results in a network system that uses only very few inputs but can produce good prediction. |
Year | Venue | Keywords |
---|---|---|
2009 | Neural Parallel & Scientific Comp. | multilayer perceptron network,good feature,prediction task,network system,neural network,prediction accuracy,local rainfall prediction,neural network model,combined use,good prediction,connectionist model,feature selection,multi layer perceptron,neural networks,rainfall,atmospheric science,backpropagation |
Field | DocType | Volume |
Data mining,Feature selection,Computer science,Multilayer perceptron,Preprocessor,Artificial intelligence,Backpropagation,Artificial neural network,Machine learning,Connectionism,Precipitation | Journal | 17 |
Issue | Citations | PageRank |
1 | 3 | 0.67 |
References | Authors | |
6 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bimal Dutta | 1 | 3 | 0.67 |
Angshuman Ray | 2 | 3 | 0.67 |
Srimanta Pal | 3 | 242 | 32.13 |
Dipak Chandra Patranabis | 4 | 3 | 0.67 |