neural network - How can I train my ANFIS dataset in MATLAB? -
i have following dataset of 9 years represents people per infected of dengue 2007 2015 divide in 4 quadrant in each year. how can prepare dataset anfis. , train them predict previous year record ?
for fis n inputs, training data has n+1 columns, first n columns contain input data , final column contains output data. here can choose have 2 inputs (the year , quadrant) , 1 output (the value). in way 9 years, number of rows becomes 36. number of columns equal number of inputs + output (2+1).
a = 1:4; b = (2007:2015)'; [a,b] = meshgrid(a,b); = a(:); b = b(:); c = ones(36,1); % should insert numbers here table traindata = [b c]
now try use genfis
generate fis:
nummfs = 5; % number of membership function mftype = 'gbellmf'; % type of mf fis = genfis1(traindata,nummfs,mftype);
the more compact way becomes:
[a,b] = meshgrid(a,b); traindata = [a(:) b(:) c];
Comments
Post a Comment