Black-box Modelling with suppurt vector machine. LibSvm / LS-SVM Matlab toolbox

I'm trying to use support vector machine (on Matlab) for a data driven blackbox-system identification. The problem is the format of the data. Then, for evey sample of the data, the input is a vector (time Serie) and the Output as well. Both have the same length. I'm not trying to predict any value in the future (so dont mix it up with one-step ahead prediction). Let's say that I have 10 samples that I created from the 10 expremients I done. Those experiments consists in heating then cooling down a tire with some variable Temperature over time. My Input is then a vector that contains those Temperature for each time step : [0 3 15 25 40 100 ... 0]. I installed a Sensor inside the tire that gives me the output temperature inside the tire : [0 24.2 33 44 ... 0]. Now that I've done this 10 times (so I have 10 samples for the same system --> a tire) I would like to know how can I use my data for training a SVM (Regression). Since for every Sample my output is not only a value but a hole Vector. I'm using Matlab so I downloaded both toolboxes : LibSVM and also LS-SVM. I successfully implemented this experiment in a dynamic neural network I used the so called "catsamples" for formatting my In/Output (see this Link : https://de.mathworks.com/help/nnet/ug/multiple-sequences-with-dynamic-neural-networks.html) and now I'm trying to do this through implementig a SVM. Thank you for your Help