SaDE_ELM Input data format should be features?or labels? and how to normalize the data inside

hi there. Basically question is how elm will input data. In the form of features or labels or both? SaDE_ELM(Traingngfile, testing file, Elm_Type, numberofHiddenNeurons, Max_FES, Lbound, Ubound, NP, Max_Gen, F_par, CR, strategy, numst). i have used CNN to get features so now i have training features(1000*910) and test feature(1000*2114). Traininglabels(910*1) and Traininglabels(2114*1). currently i am passing training and testing feature .mat file but it is not working. and how can we normalize the data inside of mat file? Can anoyone please help? thankyou in advance,

[BERGHOUT Tarek]

hi, for the first question :

your training and testing files should be orgnized as follow: [targets, features].

and you should normalize only the features between 0 and 1 but inside the ELM function :

you can download the normalization function from here https://www.mathworks.com/matlabcentral/fileexchange/70175-extreme-learning-machine-with-sub-nets-classify-or-predict?s_tid=prof_contriblnk as "scaledata.m".

then search inside the code were you can found inputs (features) then write (inputs =scale data(inputs,0,1)).

do the same thing for trainig inputs and testing inputs only (do not normalize the targets)