- author = "Maryam Amir Haeri and Mohammad Mehdi Ebadzadeh and Gianluigi Folino",
- title = "Statistical genetic programming for symbolic regression",
- journal = "Applied Soft Computing",
- year = "2017",
- volume = "60",
- pages = "447--469",
- month = nov,
- keywords = "genetic algorithms, genetic programming, Symbolic regression, Well-structured subtree, Semi-well-structured tree, Well-structuredness measure, Correlation coefficient",
- bibdate = "2017-11-22",
- bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/asc/asc60.html#HaeriEF17",
-
DOI = "
doi:10.1016/j.asoc.2017.06.050",
-
abstract = "In this paper, a new genetic programming (GP)
algorithm for symbolic regression problems is proposed.
The algorithm, named statistical genetic programming
(SGP), uses statistical information (such as variance,
mean and correlation coefficient) to improve GP. To
this end, we define well-structured trees as a tree
with the following property: nodes which are closer to
the root have a higher correlation with the target. It
is shown experimentally that on average, the trees with
structures closer to well-structured trees are smaller
than other trees. SGP biases the search process to find
solutions whose structures are closer to a
well-structured tree. For this purpose, it extends the
terminal set by some small well-structured subtrees,
and starts the search process in a search space that is
limited to semi-well-structured trees (i.e., trees with
at least one well-structured subtree). Moreover, SGP
incorporates new genetic operators, i.e.,
correlation-based mutation and correlation-based
crossover, which use the correlation between outputs of
each subtree and the targets, to improve the
functionality. Furthermore, we suggest a variance-based
editing operator which reduces the size of the trees.
SGP uses the new operators to explore the search space
in a way that it obtains more accurate and smaller
solutions in less time.
SGP is tested on several symbolic regression benchmarks. The results show that it increases the evolution rate, the accuracy of the solutions, and the generalization ability, and decreases the rate of code growth.",
- notes = "Department of Computer Engineering and Information Technology, Amirkabir University of Technology, Tehran, Iran",
