Computational method for unsupervised segmentation of lymphoma histological images based on fuzzy 3-partition entropy and genetic algorithm

Designing novel robots that can cope with a specific task is a challenging problem because of the enormous design space that involves both morphological structures and control mechanisms. To this end, we present a computational method for automating the design of modular robots. Our method employs a genetic algorithm to evolve robotic structures as an outer optimization, and it applies a reinforcement learning algorithm to each candidate structure to train its behavior and evaluate its potential learning ability as an inner optimization. The size of the design space is reduced significantly by evolving only the robotic structure and by performing behavioral optimization using a separate training algorithm compared to that when both the structure and behavior are evolved simultaneously. Mutual dependence between evolution and learning is achieved by regarding the mean cumulative rewards of a candidate structure in the reinforcement learning as its fitness in the genetic algorithm. Therefore, our method searches for prospective robotic structures that can potentially lead to near-optimal behaviors if trained sufficiently. We demonstrate the usefulness of our method through several effective design results that were automatically generated in the process of experimenting with actual modular robotics kit.

Download Full-text

Unsupervised Segmentation of Satellite Images Based on Neural Network and Genetic Algorithm

Advances in Intelligent Systems and Computing - Intelligent Computing, Communication and Devices ◽

10.1007/978-81-322-2009-1_37 ◽

2014 ◽

pp. 319-326 ◽

Cited By ~ 1

Author(s):

P. Ganesan ◽

V. Rajini ◽

B.S. Sathish ◽

V. Kalist

Keyword(s):

Neural Network ◽

Genetic Algorithm ◽

Satellite Images ◽

Unsupervised Segmentation

Download Full-text

Fast Computational Method for a Class of Nonlinear Bilevel Programming Problems Using the Hybrid Genetic Algorithm

2006 International Conference on Computational Intelligence and Security ◽

10.1109/iccias.2006.294125 ◽

2006 ◽

Author(s):

Hong Li ◽

Yong-chang Jiao ◽

Li Zhang ◽

Yuping Wang

Keyword(s):

Genetic Algorithm ◽

Bilevel Programming ◽

Hybrid Genetic Algorithm ◽

Computational Method ◽

Bilevel Programming Problems

Download Full-text

Prism-Based Sunlight Concentrator Layout: A Genetic Algorithm Solution

Journal of Solar Energy Engineering ◽

10.1115/1.4025845 ◽

2013 ◽

Vol 136 (2) ◽

Cited By ~ 5

Author(s):

Kung-Jeng Wang ◽

Nguyen Dang Tien Dung ◽

Allen Jong-Woei Whang

Keyword(s):

Genetic Algorithm ◽

Solar Energy ◽

Light Intensity ◽

Light Transmission ◽

Layout Design ◽

Computational Method ◽

Transmission Rates ◽

Critical Issues ◽

Promising Source

Solar energy is a promising source of energy because it is abundant and harmless to the environment. One of the critical issues involving solar energy is the layout design of sunlight concentrators. This study presents a computational method for reforming the layout of a special sunlight concentrator that consists of a set of prisms to significantly enhance its light intensity. Sunlight movement toward the prisms is modeled, and a genetic algorithm is applied to find a good concentrator layout. Experiments under various light transmission rates validate the performance of our proposed method. The proposed optimal sunlight concentrator layout improves the intensity of light by 55%.

Download Full-text

Model-based view planning for building inspection and surveillance using voxel dilation, Medial Objects, and Random-Key Genetic Algorithm

Journal of Computational Design and Engineering ◽

10.1016/j.jcde.2017.11.013 ◽

2017 ◽

Vol 5 (3) ◽

pp. 337-347 ◽

Cited By ~ 1

Author(s):

Wei Jing ◽

Kenji Shimada

Keyword(s):

Genetic Algorithm ◽

Computational Method ◽

Set Covering ◽

Covering Problem ◽

Set Covering Problem ◽

Greedy Search ◽

View Planning ◽

3D Environment ◽

Optimal Set ◽

Gaussian Sampling

Abstract Model-based view planning is to find a near-optimal set of viewpoints that cover the surface of a target geometric model. It has been applied to many building inspection and surveillance applications with Unmanned Aerial Vehicle (UAV). Previous approaches proposed in the past few decades suffer from several limitations: many of them work exclusively for 2D problems, generate only a sub-optimal set of views for target surfaces in 3D environment, and/or generate a set of views that cover only part of the target surfaces in 3D environment. This paper presents a novel two-step computational method for finding near-optimal views to cover the surface of a target set of buildings using voxel dilation, Medial Objects (MO), and Random-Key Genetic Algorithm (RKGA). In the first step, the proposed method inflates the building surfaces by voxel dilation to define a sub-volume around the buildings. The MO of this sub-volume is then calculated, and candidate viewpoints are sampled using Gaussian sampling around the MO surface. In the second step, an optimization problem is formulated as (partial) Set Covering Problem and solved by searching through the candidate viewpoints using RKGA and greedy search. The performance of the proposed two-step computational method was measured with several computational cases, and the performance was compared with two previously proposed methods: the optimal-scan-zone method and the randomized sampling-based method. The results demonstrate that the proposed method outperforms the previous methods by finding a better solution with fewer viewpoints and higher coverage ratio compared to the previous methods. Highlights A two-step “generate-test” view planning method is proposed. Voxel dilation, Medial Objects and Gaussian sampling are used to generate viewpoints. Random-Key GA and Greedy search are combined to solve the Set Covering Problem. The proposed method is benchmarked and outperforms two existing methods.

Download Full-text

Fitness Functions Evaluation for Segmentation of Lymphoma Histological Images Using Genetic Algorithm

Applications of Evolutionary Computation - Lecture Notes in Computer Science ◽

10.1007/978-3-319-77538-8_4 ◽

2018 ◽

pp. 47-62 ◽

Cited By ~ 1

Author(s):

Thaína A. A. Tosta ◽

Paulo Rogério de Faria ◽

Leandro Alves Neves ◽

Marcelo Zanchetta do Nascimento

Keyword(s):

Genetic Algorithm ◽

Fitness Functions ◽

Histological Images

Download Full-text

Lamination Optimization of Composite Curved Wing for Maximum Flutter Stability Using Micro Genetic Algorithm

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.324-325.743 ◽

2006 ◽

Vol 324-325 ◽

pp. 743-746

Author(s):

Dong Hyun Kim ◽

Il Kwon Oh

Keyword(s):

Genetic Algorithm ◽

Genetic Algorithms ◽

Composite Materials ◽

Computational Method ◽

Computational System ◽

Wing Model ◽

Weight Condition ◽

Micro Genetic Algorithm

Flutter characteristics of composite curved wing are investigated in this study. The efficient and robust computational system for the flutter optimization has been developed using the coupled computational method based on the micro genetic algorithms. The present results show that the micro genetic algorithm is very efficient in order to find optimized lay-ups for a composite curved wing model. It is found that the flutter stability of curved wing model can be significantly increased using composite materials with proper optimum lamination design when compared to the case of isotropic wing model under the same weight condition.

Download Full-text

COMPUTER-AIDED OPTIMISATION OF ELECTRONIC CIRCUIT LAYOUT

T-Comm ◽

10.36724/2072-8735-2021-15-9-64-71 ◽

2021 ◽

Vol 15 (9) ◽

pp. 64-71

Author(s):

Abas Wisam Mahdi Abas ◽

Keyword(s):

Genetic Algorithm ◽

Assignment Problem ◽

Hybrid Methods ◽

Quadratic Assignment Problem ◽

Distance Matrix ◽

Computational Method ◽

Optimal Placement ◽

Quadratic Assignment ◽

Genetic Method ◽

The Monte Carlo Method

The problem of optimal placement of elements of electrical and electronic circuits is considered. The minimum weighted length of the connections is selected as the criterion. The scheme is defined by a matrix of connections. We consider a fixed set of element positions and a distance matrix based on an orthogonal metric. This problem is a variant of the general mathematical model, called the quadratic assignment problem. The geometric limitation of the problem is that no more than one element is placed in one cell. Combinatorial analogs of the Gauss-Seidel method, the genetic algorithm, and the corresponding hybrid methods for solving the quadratic assignment problem with optimal placement of electronic equipment elements are developed and implemented on a computer. A series of computational experiments was conducted, which showed satisfactory computational qualities of the proposed methods. The proposed computational method, which is a combinatorial analog of the method of coordinate descent and one of the variants of the general approach based on paired permutations, is characterized by the best computational qualities among the methods studied in the article. According to well-known studies, the genetic algorithm is obviously no worse than the Monte Carlo method. The research conducted in the article shows that the method of penalty functions in the problem of placement and for the case of a genetic algorithm is ineffective. Therefore, it is of interest to consider permutations without repetitions as individuals of the population. This circumstance is taken into account at the stages of selection and mutation: at these stages, the standard calculations according to the genetic algorithm are supplemented by the procedure of paired rearrangements of genes in the chromosome. The article provides a detailed description of the program for the implementation of the genetic method on a computer.

Download Full-text