Genetic Algorithms in Mechanical Systems Identification: State-of-the-Art Review

This review focuses on self-cleaning surfaces, from passive bio-inspired surface modification including superhydrophobic, superomniphobic, and superhydrophilic surfaces, to active micro-electro-mechanical systems (MEMS) and digital microfluidic systems. We describe models and designs for nature-inspired self-cleaning schemes as well as novel engineering approaches, and we discuss examples of how MEMS/microfluidic systems integrate with functional surfaces to dislodge dust or undesired liquid residues. Meanwhile, we also examine “waterless” surface cleaning systems including electrodynamic screens and gecko seta-inspired tapes. The paper summarizes the state of the art in self-cleaning surfaces, introduces available cleaning mechanisms, describes established fabrication processes and provides practical application examples.

Download Full-text

Multi-Operator Genetic Algorithm for Dynamic Optimization Problems

IAES International Journal of Artificial Intelligence (IJ-AI) ◽

10.11591/ijai.v6.i3.pp139-142 ◽

2017 ◽

Vol 6 (3) ◽

pp. 139

Author(s):

Al-khafaji Amen

Keyword(s):

Genetic Algorithm ◽

Genetic Algorithms ◽

Dynamic Optimization ◽

Optimization Problems ◽

State Of The Art ◽

Population Diversity ◽

Dynamic Optimization Problems ◽

Uncertain Environments ◽

Convergence Problem ◽

Royal Road

<span lang="EN-US">Maintaining population diversity is the most notable challenge in solving dynamic optimization problems (DOPs). Therefore, the objective of an efficient dynamic optimization algorithm is to track the optimum in these uncertain environments, and to locate the best solution. In this work, we propose a framework that is based on multi operators embedded in genetic algorithms (GA) and these operators are heuristic and arithmetic crossovers operators. The rationale behind this is to address the convergence problem and to maintain the diversity. The performance of the proposed framework is tested on the well-known dynamic optimization functions i.e., OneMax, Plateau, Royal Road and Deceptive. Empirical results show the superiority of the proposed algorithm when compared to state-of-the-art algorithms from the literature.</span>

Download Full-text

An Experiment on the Use of Genetic Algorithms for Topology Selection in Deep Learning

Journal of Electrical and Computer Engineering ◽

10.1155/2019/3217542 ◽

2019 ◽

Vol 2019 ◽

pp. 1-12 ◽

Cited By ~ 1

Author(s):

Fernando Mattioli ◽

Daniel Caetano ◽

Alexandre Cardoso ◽

Eduardo Naves ◽

Edgard Lamounier

Keyword(s):

Genetic Algorithms ◽

Deep Learning ◽

Deep Neural Networks ◽

State Of The Art ◽

Complex Task ◽

Trial And Error ◽

Complex Solution ◽

Computation Algorithms ◽

Computational Resources ◽

Topology Selection

The choice of a good topology for a deep neural network is a complex task, essential for any deep learning project. This task normally demands knowledge from previous experience, as the higher amount of required computational resources makes trial and error approaches prohibitive. Evolutionary computation algorithms have shown success in many domains, by guiding the exploration of complex solution spaces in the direction of the best solutions, with minimal human intervention. In this sense, this work presents the use of genetic algorithms in deep neural networks topology selection. The evaluated algorithms were able to find competitive topologies while spending less computational resources when compared to state-of-the-art methods.

Download Full-text