Article | 27-August-2018
This paper presents a genetic algorithm method for the optimization of the weight of steel truss structures. In the method of genetic algorithm integer encoding of a discrete set of design variables and novel self-adaptive method based on fuzzy logic mechanism are applied for improving the quality and speed of optimization. Self-adaptive method is applied simultaneously in the selection of chromosomes and to control basic parameters of genetic algorithm. The algorithm proposed in the work was
Krzysztof GRYGIEREK
Architecture, Civil Engineering, Environment, Volume 9 , ISSUE 4, 67–78
research-article | 31-August-2021
-parameters that are chosen by researchers using new theoretical insights or intuition gained from experimentation. In this paper, we achieved the following objectives:
Automate the process of CNN architecture selection.
Achieve the architecture by evolving the hyper parameters of CNN using Genetic Algorithm (GA)
Discover CNN architectures without any human intervention that perform well on a given machine-learning task.
GA is inspired by biological evolution, used to find globally optimal solutions and
Ashray Bhandare,
Devinder Kaur
International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 3, 26–35
Research Article | 13-December-2017
Advanced methods of data processing in magnetic anomaly detection (MAD) systems are investigated. Raw signals of MAD based on component magnetic sensors are transformed into energy signals in the space of specially constructed orthonormalized functions. This procedure provides a considerable improvement of the SNR thus enabling reliable target detection. Estimation of the target parameters is implemented with the help of Genetic Algorithm. Numerous computer simulations show good algorithm
B. Ginzburg,
L. Frumkis,
B.Z. Kaplan,
A. Sheinker,
N. Salomonski
International Journal on Smart Sensing and Intelligent Systems, Volume 1 , ISSUE 1, 110–122
Research Article | 13-December-2017
(2) adjustment precision due to observational noise. In order to solve these problems, we propose a robust and efficient automatic adjustment method for the optical axes of laser systems using a binary search algorithm. Adjustment experiments for optical axes with 4-DOF demonstrate that the adjustment time could be reduced to half the conventional adjustment time with the genetic algorithm. Adjustment precision was enhanced by 60%.
Hirokazu Nosato,
Nobuharu Murata,
Tatsumi Furuya,
Masahiro Murakawa
International Journal on Smart Sensing and Intelligent Systems, Volume 1 , ISSUE 2, 512–533
Article | 28-August-2018
building orientation has been analysed. Optimal selection of these parameters for reduction of the energy consumption has been carried out. Genetic algorithms were used for the optimization, while TRNSYS program was used for energy analysis. The analyses were performed on an exemplary single family detached house. Self-adaptive genetic algorithm connected with energy building simulation successfully identifies the lowest energy costs. Optimal window type and size design and window orientation reduce
Joanna FERDYN-GRYGIEREK,
Krzysztof GRYGIEREK
Architecture, Civil Engineering, Environment, Volume 10 , ISSUE 4, 133–140
Research paper | 10-April-2013
In this paper, we present a novel method for the labeling of human motion which uses Constraint-Based Genetic Algorithm (CBGA) to optimize the probabilistic model of body features and construct the set of conditional independence relations among the body features by a fitness function. The approach also allows the user to add custom rules to produce valid candidate solutions to achieve more accurate results with constraint-based genetic operators. Specifically, we design the fitness function
Fuyuan Hu,
Hau San Wong
International Journal on Smart Sensing and Intelligent Systems, Volume 6 , ISSUE 2, 583–609
Article | 06-November-2017
The ball and beam system is a laboratory equipment with high nonlinearity in its dynamics. The aims of this research are to model the ball and beam system considering nonlinear factors and coupling effect and to design controllers to control the ball position. The LQR is designed considering two Degrees-of-Freedom and coupling dynamics. The parameters of the LQR are tuned using Genetic Algorithm (GA). Jacobian linearization method is used to linearize the system around operating-point. Due to
Mohammad Keshmiri,
Ali Fellah Jahromi,
Abolfazl Mohebbi,
Mohammad Hadi Amoozgar,
Wen-Fang Xie
International Journal on Smart Sensing and Intelligent Systems, Volume 5 , ISSUE 1, 14–35
Research Article | 01-December-2011
While the top-down approach of artificial intelligence encounters the frame problem, the bottom-up approach based on a creature’s evolution and behavior is effective for robotic design of intellectual behavior in a specific field. We propose the Evolutionary Behavior Table System (EBTS) using a simple genetic algorithm (SGA) to acquire the autonomous cooperative behavior of multi-agents as the bottom-up approach. In EBTS, a set of rules is expressed as a table composed of sensor input columns
Naoto Hoshikawa,
Masahiro Ohka,
Hanafiah Bin Yussof
International Journal on Smart Sensing and Intelligent Systems, Volume 4 , ISSUE 4, 583–606
Research Article | 13-December-2017
, we treat a long string composed of rule strings as a gene to obtain an optimum gene that adapts to its environment using a genetic algorithm (GA). For methodology 1, we established an ATAS composed of 3 to 5 modules to accomplish such tasks as object grasping, pick and place, cap screwing, and assembling. Using methodology 1, a two-hand-arm robot equipped with an optical threeaxis tactile sensor performed the above tasks. For methodology 2, we propose the Evolutionary Behavior Table System (EBTS
M. Ohka,
N. Hoshikawa,
J. Wada,
H. B. Yussof
International Journal on Smart Sensing and Intelligent Systems, Volume 3 , ISSUE 3, 466–487
Research Article | 20-November-2017
Tomasz Górecki,
Maciej Łuczak
Statistics in Transition New Series, Volume 18 , ISSUE 3, 443–458
Research Article | 27-December-2017
Wei Guo,
Kaibo Luo,
Xinjun Wang,
Lizhen Cui
International Journal on Smart Sensing and Intelligent Systems, Volume 7 , ISSUE 1, 13–30
Research Article | 12-December-2017
problem formulation. Then a genetic algorithm is formulated for obtaining maximum efficiency and minimizing machine size. In the second genetic problem formulation, we attempt to obtain minimum mass, the machine sizing that is constrained by the non-linear constraint function of machine losses. Finally, an optimum torque per ampere genetic sizing is predicted. All results are simulated with MATLAB, Optimization Toolbox and its Genetic Algorithm. Finally, six design examples comparisons are introduced
Adel El Shahat,
Ali Keyhani,
Hamed El Shewy
International Journal on Smart Sensing and Intelligent Systems, Volume 3 , ISSUE 2, 176–216
Research Article | 27-December-2017
The problem of multi-objective robust feedback linearization controller design of nonlinear system with parametric uncertainties is solved in this paper. The main objective of this paper is to propose an optimal technique to design a robust feedback linearization controller with multi-objective genetic algorithm. A nonlinear system is considered as a benchmark and feedback linearization controller is designed for deterministic and probabilistic model of the benchmark. Three and four conflicting
A. Hajiloo,
M. samadi,
N. Nariman-Zadeh
International Journal on Smart Sensing and Intelligent Systems, Volume 7 , ISSUE 1, 214–237
Review | 06-August-2019
genetic algorithm method to select the best combination of several components of the building envelope (orientation, wall, roof and foundation insulation, window area, glazing type, air leakage level and thermal mass). In turn Bichiou and Krarti [28] compared the performance of three optimization techniques (genetic algorithm, particle swarm optimization, and sequential search methodology) to select HVAC system design features and its operation settings.
To perform the optimization analysis the
Krzysztof GRYGIEREK,
Joanna FERDYN-GRYGIEREK
Architecture, Civil Engineering, Environment, Volume 12 , ISSUE 2, 81–90
Article | 11-April-2018
This paper focuses on the effective analysis of the mine gas emission monitoring data, so as to realize the accurate and reliable mine gas emission prediction. Firstly, a weighted multiple computing models based on parametric t– norm is constructed. And a new mine gas emission combination forecasting method is proposed. The BP neural network model and the support vector machine were used as the single prediction models. Finally, genetic algorithm and least square method were used to
Liang Rong,
Chang Xintan,
Jia Pengtao,
Dong Dingwen
International Journal of Advanced Network, Monitoring and Controls, Volume 2 , ISSUE 3, 194–198
Article | 01-December-2014
This paper studies some key technology of multifunctional sensor signal reconstruction. The multifunctional sensor signal reconstruction problem, presented a multifunctional sensor signal reconstruction method based on B spline and the extended Calman filter. The method of inverse model of the process was studied, gives a method to estimate signal reconstruction accuracy and computation. Genetic algorithm is proposed to balance the multifunctional sensor signal reconstruction accuracy and
Junjie Yang,
Wenxiang Chen,
Zhihe Fu,
Wei Wu,
Zhiping Xie
International Journal on Smart Sensing and Intelligent Systems, Volume 7 , ISSUE 4, 1701–1716
Article | 10-April-2018
To come over the limitations of Apriori algorithm and association rule mining algorithm based on Genetic Algorithm (GA), this paper proposed a new association rule mining algorithm based on the population-based incremental algorithm (PBIL), which is a kind of distribution estimation algorithms. The proposed association rule-mining algorithm keeps the advantages of GA mining association rules in coding and the fitness function. Through using probability vector possessing learning properties to
Xinyu Zhang,
Botu Xue,
Guanghu Sui,
Jianjiang Cui
International Journal of Advanced Network, Monitoring and Controls, Volume 2 , ISSUE 3, 20–26
Article | 11-June-2016
. Therefore, this paper puts forward a different multi-objective framework, and correspondingly, an improved optimization algorithm is applied to intermittent sugar cane crystallization. This method combines the elitist non-dominated sorting genetic algorithm (NSGA-II) with technique for order preference which is similar to an ideal solution (TOPSIS), and it provides a quantitative way to analyze the effect of both seed characteristics and process variables on the trade-off between MA and CV. Furthermore
Yanmei Meng,
Wenxing Li,
Qingwei Chen,
Xian Yu,
Kangyuan Zheng,
Guancheng Lu
International Journal on Smart Sensing and Intelligent Systems, Volume 9 , ISSUE 2, 953–978
Article | 09-April-2018
experiments are carried out and the conclusions are made for it. The algorithm can obtain the optimal solution through the continuous updating of pheromone. The main consideration is the Service level contract violation rate(S), Resource loss(W),Power consumption (P). Experimental results show that ,compared with the traditional heuristic method and genetic algorithm, the algorithm is advantageous to the parallel computation, and it’s able to achieve the optimal tradeoff and compromise between
Sun Hong,
Tang Qing,
Xu Liping,
Chen Shiping
International Journal of Advanced Network, Monitoring and Controls, Volume 2 , ISSUE 2, 120–129
Research Article | 01-September-2017
concerns for effective testing as well as cost of the testing process. During the Regression testing, executing all the test cases from existing test suite is not possible because that takes more time to test the modified software. This paper proposes new Hybrid approach that consists of modified Greedy approach for handling the test case selection and Genetic Algorithm uses effective parameter like Initial Population, Fitness Value, Test Case Combination, Test Case Crossover and Test Case Mutation for
M. Mohan,
Tarun Shrimali
International Journal on Smart Sensing and Intelligent Systems, Volume 10 , ISSUE 5, 1–24