Using Multiobjective Genetic Programming to Infer Logistic Polynomial Regression Models – Experimental Supplement
نویسنده
چکیده
This document presents supplementary results to paper [2], excluded from that paper for reasons of brevity. Results are presented on three data sets: Ionosphere, Credit and Sonar. All are originally sourced from the UCI Machine Learning Repository [1] – the versions used for these experiments are available from http://www.andrew1.hunter/durham.ac.uk/LogPoly/. Results summarize algorithm performance and consistency.
منابع مشابه
Using Multiobjective Genetic Programming to Infer Logistic Polynomial Regression Models
In designing non-linear classifiers, there are important trade-offs to be made between predictive accuracy and model comprehensibility or complexity. We introduce the use of Genetic Programming to generate logistic polynomial models, a relatively comprehensible non-linear parametric model; describe an efficient twostage algorithm consisting of GP structure design and Quasi-Newton coefficient se...
متن کاملInference of computational models of tendon networks via sparse experimentation
This dissertation presents novel computational methods to infer accurate functional models of musculoskeletal systems from minimal experimental data focussing on the tendon networks of the human fingers as an example. State of the art biomechanical modeling consists of assuming a fixed structure to the system being modeled and measurement or regression of specific parameter values. However, the...
متن کاملExploring the Use of Random Regression Models withLegendre Polynomials to Analyze Clutch Sizein Iranian Native Fowl
Random regression models (RRM) have become common for the analysis of longitudinal data or repeated records on individual over time. The goal of this paper was to explore the use of random regression models with orthogonal / Legendre polynomials (RRL) to analyze new repeated measures called clutch size (CS) as a meristic trait for Iranian native fowl. Legendre polynomial functions of increasing...
متن کاملMultiobjective Genetic Programming: a Nonlinear System Identification Application
Genetic programming (GP) is applied to a multobjective optimisation problem and the advantages of its hierarchical tree encoding scheme are compared with an earlier use of a subset representation approach which used string-encoded genetic algorithms. The GP approach is applied to the identification of non-linear system polynomial models and provides a trade-off between the complexity and the pe...
متن کاملThe Position of Multiobjective Programming Methods in Fuzzy Data Envelopment Analysis
Traditional Data Envelopment Analysis (DEA) models evaluate the efficiency of decision making units (DMUs) with common crisp input and output data. However, the data in real applications are often imprecise or ambiguous. This paper transforms fuzzy fractional DEA model constructed using fuzzy arithmetic, into the conventional crisp model. This transformation is performed considering the goal pr...
متن کامل