Forecast of small faults extending length based on support vector machine with particle swarm optimization : Long Qing Shi, Mei Qiu, Jin Han & Chao Teng

Chapter

ABSTRACT

In order to obtain weight vector ωT and bias term b, we must minimize the sum of the ε-insensitive loss function:

1 2

1 ω ε+

∑C L x y fi i i

N ( , , ) (2)

where, parameter C can measure the trade-off between complexity and losses.