How to normalize a data serie which have negative and positive values for Prediction through ANN?

2 次查看（过去 30 天）
Numan
Numan 2014-1-22
编辑： Greg Heath 2014-1-22
Hey,
I want normalize a data serie for prediction. The serie has negative and positive data.
First question, can I normalize data between 0 and 1 or should I normalize it between -1 and 1?
Second question, how do I normalize between -1 and 1?
Thank you

请先登录，再回答此问题。

采纳的回答

Amit
Amit 2014-1-22
I dont know what is ANN.
But for normal scenarios, lets say your data is variable A.
factor = max([max(A) abs(min(A))]);
normalized_data = A/factor;

更多回答（1 个）

Greg Heath
Greg Heath 2014-1-22
编辑：Greg Heath 2014-1-22
Normalization to [ -1, 1] is a default for most of the ANN functions. This includes the most important timeseries functions timedelaynet, narnet and narxnet.
Details are available in the help and doc documentation. For example,
help narxnet
doc narxnet
Hope this helps.
Thank you for formally accepting my answer
Greg

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by