Genetic programming: on the programming of computers by means of natural selection
Genetic programming: on the programming of computers by means of natural selection
Genetic algorithms + data structures = evolution programs (3rd ed.)
Genetic algorithms + data structures = evolution programs (3rd ed.)
Damage detection of truss bridge joints using Artificial Neural Networks
Expert Systems with Applications: An International Journal
Knowledge discovery of concrete material using Genetic Operation Trees
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
Generalization performance of support vector machines and neural networks in runoff modeling
Expert Systems with Applications: An International Journal
Hybrid high order neural networks
Applied Soft Computing
Engineering Applications of Artificial Intelligence
Engineering Applications of Artificial Intelligence
Hi-index | 12.08 |
This study introduces weighted operation structures (WOS) to program engineering problems, in which each WOS adopts a fixed binary tree topology. The first WOS layer serves as the parameter input entrance. The target is produced at the eventual layer using both values and a mathematical formula. Each WOS element is operated by two front nodal inputs, an undetermined function, and two undetermined weights to produce one nodal output. This study proposes the novel concept of introducing weights into a WOS. Doing so provides two unique advantages: (1) achieving a balance between the influences of two front inputs and (2) incorporating weights throughout the generated formulas. Such a formula is composed of a certain quantity of optimized functions and weights. To determine function selections and proper weights, genetic algorithm is employed for optimization. Case studies herein focused on three kinds of concrete-typed specimen strengths: (1) concrete compressive strength, (2) deep beam shear strength, and (3) squat wall shear strength. Results showed that the proposed WOS can provide accurate results that nearly equal the results obtainable using the familiar neural network. The weighted formula, however, offers a distinct advantage in that it can be programmed for practical cases.