A Novel Reformed Reduced Kernel Extreme Learning Machine with RELIEF-F for Classification

Table 1

The advantages and drawbacks of ELM and variant ELM models.

Model	Advantages	Drawbacks
ELM	Fast training speed; same or better performance than the conventional models	Unstable forecasting performance; parameter dependency (2 parameters)
KELM	Stable performance	Heavy computation; parameter dependency (1 parameter)
Reduced-KELM	Less computation than KELM	Unstable forecasting performance; parameter dependency (1 parameter)