A parallel genetic algorithm for optimization is outlined, and its performance on both mathematical and biomechanical optimization problems is compared to a sequential quadratic programming algorithm, a downhill simplex algorithm and a simulated annealing algorithm. When high-dimensional non-smooth or discontinuous problems with numerous local optima are considered, only the simulated annealing and the genetic algorithm, which are both characterized by a weak search heuristic, are successful in finding the optimal region in parameter space. The key advantage of the genetic algorithm is that it can easily be parallelized at negligible overhead.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1115/1.1537735 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Integrative bioinformatics and machine learning approach unveils potential biomarkers linking coronary atherosclerosis and fatty acid metabolism-associated gene.
J Cardiothorac Surg
January 2025
Dongying People's Hospital (Dongying Hospital of Shandong Provincial Hospital Group), Dongying, 257091, Shandong, People's Republic of China.
Background: Atherosclerosis (AS) is increasingly recognized as a chronic inflammatory disease that significantly compromises vascular health and acts as a major contributor to cardiovascular diseases. Advancements in lipidomics and metabolomics have unveiled the complex role of fatty acid metabolism (FAM) in both healthy and pathological states. However, the specific roles of fatty acid metabolism-related genes (FAMGs) in shaping therapeutic approaches, especially in AS, remain largely unexplored and are a subject of ongoing research.
View Article and Find Full Text PDFMGATAF: multi-channel graph attention network with adaptive fusion for cancer-drug response prediction.
BMC Bioinformatics
January 2025
School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, 611756, Sichuan, China.
Background: Drug response prediction is critical in precision medicine to determine the most effective and safe treatments for individual patients. Traditional prediction methods relying on demographic and genetic data often fall short in accuracy and robustness. Recent graph-based models, while promising, frequently neglect the critical role of atomic interactions and fail to integrate drug fingerprints with SMILES for comprehensive molecular graph construction.
View Article and Find Full Text PDFExploration of the shared diagnostic genes and molecular mechanism between obesity and atherosclerosis via bioinformatic analysis.
Sci Rep
January 2025
Department of Endocrinology, Second Affiliated Hospital of Shandong University of Traditional Chinese Medicine, Jinan, 250001, Shandong, China.
Obesity (OB) and atherosclerosis (AS) represent two highly prevalent and detrimental chronic diseases that are intricately linked. However, the shared genetic signatures and molecular pathways underlying these two conditions remain elusive. This study aimed to identify the shared diagnostic genes and the associated molecular mechanism between OB and AS.
View Article and Find Full Text PDFHybrid multi-objective optimization of µ-synthesis robust controller for frequency regulation in isolated microgrids.
Sci Rep
January 2025
Faculty of Engineering, Helwan University, Cairo, Egypt.
Frequency regulation in isolated microgrids is challenging due to system uncertainties and varying load demands. This study presents an optimal µ-synthesis robust control strategy that regulates microgrid frequency while enhancing system performance and stability-a proposed fixed-structure approach for selecting performance and robustness weights, informed by subsystem frequency analysis. The controller is optimized using multi-objective particle swarm optimization (MOPSO) and multi-objective genetic algorithm (MOGA) under inequality constraints, employing a Pareto front to identify optimal solutions.
View Article and Find Full Text PDFInterpretable and integrative deep learning for discovering brain-behaviour associations.
Sci Rep
January 2025
University Paris-Saclay, CEA, CNRS, Neurospin, Baobab UMR 9027, Gif-sur-Yvette, 91191, France.
Recent advances highlight the limitations of classification strategies in machine learning that rely on a single data source for understanding, diagnosing and predicting psychiatric syndromes. Moreover, approaches based solely on clinician labels often fail to capture the complexity and variability of these conditions. Recent research underlines the importance of considering multiple dimensions that span across different psychiatric syndromes.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!