Self-Tune Linear Adaptive-Genetic Algorithm for Feature Selection

Ooi, Ching Sheng; Lim, Meng Hee; Leong, M. Salman

doi:10.1109/access.2019.2942962

Cited by 9 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, the GA parameters should be optimized to find the ideal simulation parameters using tuning algorithms (Eiben and Smit, 2012; Montero et al , 2018). For example, Ooi et al (2019) proposed a self-tune linear adaptive GA which modifies the mutation probability rate and the population size based on the diversity of the population. Moreover, the product specifications should undergo a sensitivity analysis to evaluate the robustness of the design.…”

Section: Resultsmentioning

confidence: 99%

Evolutionary layout design synthesis of an autonomous greenhouse using product-related dependencies

Cio

Vadean

et al. 2020

AIEDAM

View full text Add to dashboard Cite

The development of autonomous greenhouses has caught the interest of many researchers and industrial considering their potential of offering an optimal environment for the growth of high-quality crops with minimum resources. Since an autonomous greenhouse is a mechatronic system, the consideration of its subsystem (e.g. heating systems) and component (e.g. actuators and sensors) interactions early in the design phase can ease the product development process. Indeed, this consideration could shorten the design process, reduce the number of redesign loops, and improve the performance of the overall mechatronic system. In the case of a greenhouse, it would lead to a higher quality of the crops and a better management of resources. In this work, the layout design of a general autonomous greenhouse is translated into an optimization problem statement while considering product-related dependencies. Then, a genetic algorithm is used to carry out the optimization of the layout design. The methodology is applied to the design of a fully autonomous greenhouse (45 cm × 30 cm × 30 cm) for the growth of plants in space. Although some objectives are conflictual, the developed algorithm proposes a compromise to obtain a near-optimal feasible layout design. The algorithm was also able to optimize the volume of components (occupied space) while considering the energy consumption and the overall mass. Their respective summed values are 2844.32 cm3, which represents 7% of the total volume, 5.86 W, and 655.8 g.

show abstract

Section: Resultsmentioning

confidence: 99%

Evolutionary layout design synthesis of an autonomous greenhouse using product-related dependencies

Cio

Vadean

et al. 2020

AIEDAM

View full text Add to dashboard Cite

show abstract

“…Recombination ‐ also known as crossover ‐ is the process of creating offspring, or children, by combining two different solutions, or parents. Our study utilised crossover scattered [29], a specific implementation of crossover. This method works by creating a random binary vector R , where ‘1’ indicates selecting bits from the first parent and ‘0’ indicates selecting bits from the second parent.…”

Section: Methods and Definitionsmentioning

confidence: 99%

Performance analysis of pixelated antennas employing shifted cross‐shaped elements

Mair

Renzler

Unterladstaetter

et al. 2023

IET Microwaves Antenna & Prop

View full text Add to dashboard Cite

This article presents a detailed analysis of pixelated antennas employing shifted cross‐shaped elements optimised by evolutionary algorithms. Although, the size and number of the involved pixels, as well as the overall antenna size strongly influence performance of such antennas, detailed investigations on the interplay of geometrical considerations and their influence on parameters such as gain are missing from literature. Thus, the influence of various geometrical parameters on the performance of pixelated antennas for the first time, resulting in valuable design considerations is presented in this study. A maximum cross size could be found, for which an optimisation is viable. Based on this, a dataset consisting of 400 pixelated antennas was created, for different pixel‐ and antenna sizes and investigated certain parameters such as bandwidth and antenna gain. Most notably, a directly proportional dependence from the pixel‐on the antenna size for the optimisation of electrically large antennas was found. For small antennas, this dependency begins to deviate, leading to the fact that smaller pixels are needed to successfully optimise an antenna. Furthermore, the authors find that multi‐objective optimisation is a necessity to optimise matched antennas with a defined bandwidth and gain. The antenna gain shows a dependency on the cross size for electrically small antennas. From these results, design considerations for pixelated antennas can be derived. In addition to the extensive simulations, the dataset was verified in laboratory measurements.

show abstract

“…Leong et al, Ooi et al, and Lim et al proposed an adaptive Genetic Algorithm to overcome problems faced in standard feature selection processes such as convergence towards local optima, manual parameter tuning, premature convergence, lower feature subset reduction rates, and the excessive cost of computation. The proposed STLA-GA was able to outperform classic feature-selection methods due to its adaptive nature [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

Fault Classification for Cooling System of Hydraulic Machinery Using AI

Khan

Bhatti

Kamal

et al. 2023

Sensors

View full text Add to dashboard Cite

Hydraulic systems are used in all kinds of industries. Mills, manufacturing, robotics, and Ports require the use of Hydraulic Equipment. Many industries prefer to use hydraulic systems due to their numerous advantages over electrical and mechanical systems. Hence, the growth in demand for hydraulic systems has been increasing over time. Due to its vast variety of applications, the faults in hydraulic systems can cause a breakdown. Using Artificial-Intelligence (AI)-based approaches, faults can be classified and predicted to avoid downtime and ensure sustainable operations. This research work proposes a novel approach for the classification of the cooling behavior of a hydraulic test rig. Three fault conditions for the cooling system of the hydraulic test rig were used. The spectrograms were generated using the time series data for three fault conditions. The CNN variant, the Residual Network, was used for the classification of the fault conditions. Various features were extracted from the data including the F-score, precision, accuracy, and recall using a Confusion Matrix. The data contained 43,680 attributes and 2205 instances. After testing, validating, and training, the model accuracy of the ResNet-18 architecture was found to be close to 95%.

show abstract

Self-Tune Linear Adaptive-Genetic Algorithm for Feature Selection

Cited by 9 publications

References 32 publications

Evolutionary layout design synthesis of an autonomous greenhouse using product-related dependencies

Evolutionary layout design synthesis of an autonomous greenhouse using product-related dependencies

Performance analysis of pixelated antennas employing shifted cross‐shaped elements

Fault Classification for Cooling System of Hydraulic Machinery Using AI

Contact Info

Product

Resources

About