Article
Forestry
Zirui Liu, Chengjie Gao, Jin Li, Yingchun Miao, Kai Cui
Summary: This study assessed the phenotypic diversity of Pinus yunnanensis natural populations, revealing abundant variations within and among populations. Temperature was found to be the most important factor affecting the diameter of breast height. Cluster analysis showed that populations were not strictly clustered according to geographic distance. The Lufeng population had noticeable advantages in multiple traits, while the Yongren population showed the worst performance. Eleven superior families were successfully selected using a comprehensive scoring method and principal component analysis.
Article
Robotics
Luis Cruz-Teran, Leopoldo Ruiz-Huerta, Alex Elias-Zuniga, Oscar Martinez-Romero, Alberto Caballero-Ruiz
Summary: In this study, a novel approach using a genetic algorithm (GA) is presented to optimize the parameters of constitutive models for soft materials. The GA is applied to obtain a set of solutions from uniaxial tensile test data, which are then used to simulate mechanical tests using finite element analysis (FEA), resulting in an optimal solution that satisfies Drucker's stability criterion. The proposed GA not only accurately predicts experimental data but also demonstrates high reproducibility.
Article
Computer Science, Artificial Intelligence
K. Aditya Shastry, H. A. Sanjay
Summary: Data pre-processing is a technique that transforms raw data into a useful format for machine learning, with feature selection and feature extraction being significant components. This study proposes a hybrid strategy using modified Genetic Algorithm and weighted Principal Component Analysis for selecting and extracting features from agricultural datasets, resulting in significant improvements in benchmark and real-world farming datasets.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Mechanics
Luigi Solazzi, Andrea Buffoli
Summary: The study demonstrates that hydraulic cylinders made of composite materials perform similarly to those made of structural steel in terms of safety factor, with a weight reduction of about 87%.
COMPOSITE STRUCTURES
(2021)
Article
Chemistry, Physical
Luigi Solazzi, Andrea Buffoli, Federico Ceresoli
Summary: This research evaluates the fatigue phenomenon of the arms of a medium-large excavator made of composite material, compared to the traditional steel construction. The results show that the arms made of composite material are significantly lighter while maintaining the same performance. The evaluation includes the analysis of fatigue behavior under various load conditions, and the implementation of a loading cycle plan is crucial to accurately assess the fatigue behavior.
Article
Computer Science, Artificial Intelligence
Wenbin Pei, Bing Xue, Lin Shang, Mengjie Zhang
Summary: Cost-sensitive learning is a popular approach for addressing class imbalance in machine learning, but the proposed genetic programming-based approach in this paper shows promising results in developing cost-sensitive classifiers independent of manually designed cost matrices. Experiment results on high-dimensional unbalanced datasets demonstrate the effectiveness of this approach.
IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE
(2021)
Article
Energy & Fuels
Zhou Dai, Gang Wang, Ruien Bian, Chaozhi Deng
Summary: This study proposes a power grid material demand forecasting model based on feature selection and multi-model fusion, which can effectively support the management of power grid materials with higher accuracy and generalization ability.
FRONTIERS IN ENERGY RESEARCH
(2022)
Article
Forestry
Kyungmi Lee, In-Sik Kim, Wan-Yong Choi
Summary: This study presents a comprehensive approach to plus-tree selection, improving traditional methods by emphasizing growth differentiation. A total of 62 superior individuals were selected from 176 candidates across 20 populations, expanding the geographical boundaries. This method provides practical insights for selective breeding and genetic conservation.
Article
Dentistry, Oral Surgery & Medicine
Maria Tejada-Casado, Razvan Ghinea, Maria M. Perez, Henning Lubbe, Ioana S. Pop-Ciutrila, Javier Ruiz-Lopez, Luis Javier Herrera
Summary: By utilizing Principal Component Analysis (PCA), the accuracy of reflectance reconstruction and color estimation for different dental materials with varying thicknesses can be effectively assessed. The proposed PCA-based algorithm demonstrates its ability to predict the reflectance spectrum and color of monolithic dental samples, offering potential benefits for optimizing dental material manufacturing processes and enhancing chromatic accuracy in clinical dental restorations.
Article
Energy & Fuels
Melodie Chen-Glasser, Amy E. Landis, Steven C. DeCaluwe
Summary: High energy density lithium-O2 batteries have the potential to increase electric vehicle driving range, but technical challenges prevent commercialization. Researchers propose electrolytes, catalysts, and binders to improve battery capacity and reduce capacity fade. However, novel battery design is not always consistent with reducing greenhouse gas emissions.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Computer Science, Artificial Intelligence
Motahare Akhavan, Seyed Mohammad Hossein Hasheminejad
Summary: A new two-phase gene selection method for microarray data is proposed in this study. This method reduces the number of genes significantly and improves the classification accuracy through anomaly detection and guided genetic algorithm.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Metallurgy & Metallurgical Engineering
Xu Zhe, Ni Wei-chen, Ji Yue-hui
Summary: Randomness is crucial in ensemble learning, and a common practice is to rotate feature space randomly. However, this requires a large number of trees and computing resources. The MGARF algorithm proposed in this paper utilizes multimodal genetic algorithm to select diverse and accurate base learners, outperforming random forest and random rotation methods on classification datasets.
JOURNAL OF CENTRAL SOUTH UNIVERSITY
(2021)
Article
Automation & Control Systems
Abhinav Pandey, Litton Bhandari, Vidit Gaur
Summary: This research proposes a novel model-agnostic framework based on genetic algorithms to identify and optimize the set of coefficients of the constitutive equations of engineering materials. The framework demonstrates solution convergence, scalability, and high explainability for a wide range of engineering materials. The experimental validation shows that the proposed framework outperforms commercially available software in terms of optimization efficiency.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2024)
Article
Computer Science, Artificial Intelligence
Demeke Endalie, Getamesay Haile, Wondmagegn Taye Abebe
Summary: Text classification categorizes documents based on their content into predefined categories. Selecting appropriate features is crucial when dealing with a large number of features. This paper presents a hybrid feature selection method combining document frequency and genetic algorithm for Amharic text classification, which outperforms other methods and improves classification accuracy when combined with Extra Tree Classifier.
PEERJ COMPUTER SCIENCE
(2022)
Article
Optics
Ali Payami Golhin, Are Strandlie
Summary: This study investigates the relationship between appearance attributes and texture variation in material jetting technology, and examines the impact of different build orientations on surface quality. The results demonstrate that build orientation significantly affects surface texture and layer orientation, resulting in variation in all studied appearance attributes.
OPTICS AND LASER TECHNOLOGY
(2024)