A Multiple Kernel Learning Approach for Air Quality Prediction

Algorithm 1

: MKSVC.

Input: dataset: , n samples

Output: decision function of MKSVC

Start First, get the kernel coefficients by optimizing the single kernel-base learners ()

Second, get the weight of each kernel by the centered kernel alignment algorithm ()

Third, get the number of kernels by boosting approach (P)

Fourth, get the combined optimized kernel

Then, use SVC as the base learner and optimize it with a general optimizing algorithm

Return

Stop