I am working on my thesis for my undergraduate degree and I am meant to carry out a load forecast on my school's data. While collating the data for my forecast, I noticed that some values were missing. What method can I use to fill in these values to increase the accuracy of my forecast? I am using the regression analysis method and also working with Artificial Neural Networks. I am working with MicroSoft Excel.
I guess the section on data normalization in your EIE520 lecture note should sort you out on this. Checkout the note on Moodle.
Just a note of care: Filling in values (what must somehow be dependent on the actual data) will increase the precision but it surely will also increase the bias! Is this really worth it?
Hello,
If you have some missing data in a data set you can use artificial intelligence like ANN or ANFIS to predict missing values. To do that sometimes you need to normalize data or you need pre-processing before training your network.
hello
you can used the artificial neural network ANN tools. it is very good for normalize and regression.
also you can transform this black box tools to an open tools by used the wight from ANN with Excel sheet. every think in this way it is clear .
http://pure.ltu.se/portal/da/publications/simplified-methods-for-crack-risk-analyses-of-early-age-concrete(db28abfa-df20-4a4c-aca7-4db5a25739c7).html
- Badges
- Science topic