A Genetic Programming-Driven Data Fitting Method

杨利霞

A Genetic Programming-Driven

Data Fitting Method

' J6 }% L7 L& ^+ s2 I
3 o6 i$ q& K! [% R, Z

/ s2 `0 [& M" U6 mData fifitting is the process of constructing a curve, or a set of mathematical functions, that has
the best fifit to a series of data points. Different with constructing a fifitting model from same type of function,
such as the polynomial model, we notice that a hybrid fifitting model with multiple types of function may have
a better fifitting result. Moreover, this also shows better interpretability. However, a perfect smooth hybrid
* d! b$ h  x- V, lfifitting model depends on a reasonable combination of multiple functions and a set of effective parameters.
That is a high-dimensional multi-objective optimization problem. This paper proposes a novel data fifitting
model construction approach. In this approach, the model is expressed by an improved tree coding expression
and constructed through an evolution search process driven by the genetic programming. In order to verify
the validity of generated hybrid fifitting model, 6 prediction problems are chosen for experiment studies. The
experimental results show that the proposed method is superior to 7 typical methods in terms of the prediction
accuracy and interpretability
* k$ \8 u( O+ E% F" t, k2 ?



9 C" v  p* \1 L8 j/ m5 ]% Y) x
& I, h/ }0 b+ o0 j* [