A Multiple Kernel Learning Approach for Air Quality Prediction

Table 7

Performance comparison for predicting the next hour’s AQHI in HK.

	Accuracy	mse	wr	wf	wp
ARIMA	0.608	0.795	0.608	0.605	0.605
RF	0.782	0.279	0.782	0.779	0.782
MLP	0.908	0.101	0.908	0.908	0.909
SVC_linear	0.960	0.041	0.96	0.961	0.963
SVC_rbf	0.937	0.065	0.937	0.937	0.938
SVC_poly	0.959	0.042	0.959	0.959	0.961
SVC_sigmoid	0.267	4.996	0.267	0.113	0.071
LSTM	0.763	0.265	0.763	0.763	0.773
MKSVC	0.972	0.030	0.972	0.971	0.972