检索结果-内蒙古大学图书馆

Competition of tribes and cooperation of membersa* algorithm: An evolutionary computation approach for model free optimization

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 265卷

作者： Chen, Zuyan Li, Shuai Khan, Ameer Tamoor Mirjalili, Seyedali Univ Oulu Fac Informat Technol & Elect Engn Oulu 90570 Finland VTT Tech Res Ctr Finland Oulu 90590 Finland Univ Copenhagen Dept Plant & Environm Sci DK-1172 Copenhagen Denmark Torrens Univ Australia Ctr Artificial Intelligence Res & Optimizat Brisbane Qld 4006 Australia Obuda Univ Univ Res & Innovat Ctr H-1034 Budapest Hungary

Metaheuristica* algorithms solve optimization problems mostly by imitating behaviors observed in nature. Over time, thesea* algorithms have proven to be very effective in solving complex optimization problems. Due to the rising complexity and scale of practical engineering problems, numerous metaheuristica* algorithms have been developed recently and applied in various fields. In response to this need, researchers continue to explore novel approaches inspired by natural and social phenomena. Inspired by the competition among ancient tribes and their cooperative behavior, this paper proposes a meta-heuristic called the Competition of Tribes and Cooperation of Membersa* algorithm (CTCM). Experiments are conducted on 23 benchmark test functions and comprehensively compared with other state-of-the-arta* algorithms, including particle swarm optimization (PSO), grey wolf optimizer (GWO), sparrow searcha* algorithm (SSA), egret swarm optimization (ESOA), beetle antennae search (BAS) and whale optimization (WOA). The standard deviation and average, as well as statistical tests are utilized to compare the performance of eacha* algorithm, which demonstrates that CTCM is superior in the majority of problems. In addition, the results of Wilcoxon and Friedman rank tests show that the CTCM achieves the first place in all categories of problems. The results indicate that CTCM possesses strong global optimization search capability and stability, and has faster convergence speed. The paper also considers solving practical engineering optimization problems as proof-of-concept case studies, in which CTCM achieves all the optimal solutions for each engineering problem.

关键词： Evolutionary computation Competition of tribes and cooperation of membersa* algorithm Meta-heuristics Swarm intelligence Engineering optimization Optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A time series forecasting method for oil production based on Informer optimized by Bayesian optimization and the hyperbanda* algorithm (BOHB)

引用

COMPUTERS & CHEMICAL ENGINEERING 2025年 197卷

作者： Deng, Wu Xin, Xiankang Song, Ruixuan Yang, Xinzhou Wang, Weifeng Yu, Gaoming Yangtze Univ Sch Petr Engn Wuhan 430100 Peoples R China Yangtze Univ Hubei Key Lab Oil & Gas Drilling & Prod Engn Wuhan 430100 Peoples R China Yangtze Univ Natl Engn Res Ctr Oil & Gas Drilling & Complet Tec Sch Petr Engn Wuhan 430100 Peoples R China Univ Calif Santa Cruz Dept Earth & Planetary Sci Santa Cruz CA 95064 USA Shenzhen Branch CNOOC Ltd Shenzhen 518000 Peoples R China

Oil production forecasting is essential in the petroleum and natural gas sector, providing a fundamental basis for the adjustment of development plans and improving resource utilization efficiency for engineers and decisionmakers. However, current deep learning models often struggle with long-term dependencies in long time series and high computational costs, limiting their effectiveness in complex time series forecasting tasks. This paper introduced the Informer model, an enhancement over the Transformer framework, to address these limitations. For evaluation and verification, the Informer model and reference models such as CNN, LSTM, GRU, CNN-GRU, and GRU-LSTM were applied to publicly available time-series datasets, and the optimal hyperparameters of the model were identified using Bayesian optimization and the hyperbanda* algorithm (BOHB). The experimental results demonstrated that the Informer model outperformed others in computational speed, resource efficiency, and handling large-scale data, showing potential for practical applications in the future.

关键词： Oil production forecasting Deep learning Time series forecasting Informer Bayesian optimization and hyperband algorithm

来源：评论

学校读者我要写书评

暂无评论

ARC-LIGHT:a* algorithm for Robust Characterization of Lunar Surface Imaging for Ground Hazards and Trajectory

引用

AEROSPACE 2025年第3期12卷 177-177页

作者： Cushen, Alexander Bueno, Ariana Carrico, Samuel Wettstein, Corrydon Adalja, Jaykumar Ishvarbhai Shi, Mengxiang Garcia, Naila Garcia, Yuliana Gamba, Mirko Ruf, Christopher Univ Michigan Climate & Space Sci & Engn Dept Ann Arbor MI 48109 USA Univ Michigan Dept Aerosp Engn Ann Arbor MI 48109 USA Univ Michigan Elect Engn & Comp Sci Dept Ann Arbor MI 48109 USA Univ Michigan Dept Mech Engn Ann Arbor MI 48109 USA

Safe and reliable lunar landings are crucial for future exploration of the Moon. The regolith ejected by a lander's rocket exhaust plume represents a significant obstacle in achieving this goal. It prevents spacecraft from reliably utilizing their navigation sensors to monitor their trajectory and spot emerging surface hazards as they near the surface. As part of NASA's 2024 Human Lander Challenge (HuLC), the team at the University of Michigan developed an innovative concept to help mitigate this issue. We developed and implemented a machine learning (ML)-based sensor fusion system, ARC-LIGHT, that integrates sensor data from the cameras, lidars, or radars that landers already carry but disable during the final landing phase. Using these data streams, ARC-LIGHT will remove erroneous signals and recover a useful detection of the surface features to then be used by the spacecraft to correct its descent profile. It also offers a layer of redundancy for other key sensors, like inertial measurement units. The feasibility of this technology was validated through development of a prototypea* algorithm, which was trained on data from a purpose-built testbed that simulates imaging through a dusty environment. Based on these findings, a development timeline, risk analysis, and budget for ARC-LIGHT to be deployed on a lunar landing was created.

关键词： Plume Surface Interaction (PSI) lunar landing navigation machine learning Artemis dust imaging algorithm surface hazards

来源：评论

学校读者我要写书评

暂无评论

A stochastic recursive gradienta* algorithm with inertial extrapolation for non-convex problems and machine learning

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2025年 1-15页

作者： Mo, Zhongyu Ouyang, Chen Pham, Hongtruong Yuan, Gonglin Guangxi Univ Ctr Appl Math Guangxi Sch Math & Informat Sci Nanning 530004 Guangxi Peoples R China Thai Nguyen Univ Econ & Business Adm Thai Nguyen Vietnam

In recent years, the inertial extrapolation step has gained significant attention due to its capacity to expeditea* algorithm convergence. This technology has found widespread application across variousa* algorithms. However, within the domain of machine learning, the utilization of extrapolation technology has yielded limited results. Therefore, we apply it to stochastic optimizationa* algorithms to address non-convex and machine learning problems. By integrating the inertial extrapolation step and the modified Barzilai-Borwein (BB) technique into the SARAH framework, we propose an inertial stochastic recurrence gradient method. This method incorporates both the inertial extrapolation step and the improved BB technique. Through theoretical analysis presented in this paper, we demonstrate that thea* algorithm converges to a global optimum and analyze the linear convergence rate of the non-convex ((lambda) over tilde -gradient-dominated) objective functions. The numerical results obtained from evaluating three widely utilized machine learning problems clearly illustrate the superior performance and practical feasibility of the proposeda* algorithm.

关键词： Extrapolation algorithm Non-convex Global optimum Convergence Numerical results

来源：评论

学校读者我要写书评

暂无评论

Peridynamic modeling of transient heat conduction in solids using a highly efficienta* algorithm

引用

NUMERICAL HEAT TRANSFER PART B-FUNDAMENTALS 2025年第5期86卷 1255-1270页

作者： Abdoh, D. A. Hong Kong Polytech Univ Dept Bldg Environm & Energy Engn Kowloon Hong Kong Peoples R China

This article presents a novel peridynamica* algorithm to model the transient heat conduction in two-dimensional (2-D) problems. The peridynamic method is used to solve the heat transfer equation, and a newa* algorithm is developed to simulate heat conduction efficiently. The new peridynamica* algorithm can simulate the heat conduction for the whole geometry within only 2 s when using up to 5,000 particles and 5,000 simulation steps, where the mesh-free nature of peridynamics is well utilized. Moreover, the thermal results obtained from the new peridynamica* algorithm demonstrate high accuracy by solving several heat conduction problems under different boundary conditions. The results are validated against exact and analytical solutions and compared with other numerical models. The developeda* algorithm can be easily implemented in software packages and industrial applications.

关键词： algorithm Computational cost Heat conduction Peridynamics Transient

来源：评论

学校读者我要写书评

暂无评论

Research on Simulationa* algorithm of Bounded Wave Simulator Based on Nonuniform Multiconductor Transmission Lines and Electric Dipole Theory

引用

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION 2025年第1期73卷 351-361页

作者： Gu, Yixing Zhou, Zhongyuan Li, Chengjie Jing, Shenhui Sheng, Mingjie Zhao, Wei Southeast Univ Res Ctr Electromagnet Environm Effects Sch Mech Engn Nanjing 211189 Peoples R China

This article analyzes the E-field response in the test volume of bounded wave simulator (BWS) in time domain (TD) based on nonuniform multiconductor transmission lines (NMTLs) and electric dipole theory. First, the transmission lines (TLs) in BWS are modeled as a NMTL system and divided into a certain number of cascaded uniform multiconductor TLs (MTLs). Second, the current distribution in frequency domain (FD) along the TLs of BWS is determined based on the theory of MTL and the chain parameter matrix (CPM) when sinusoidal continuous wave signals of different frequencies are fed into BWS. Third, the E-field at field point of the test area of BWS is calculated by summing the E-field radiated by all the currents on the TLs in BWS via the electric dipole theory. Finally, the E-field response in TD is solved via discrete Fourier transform (DFT) and inverse DFT (IDFT). The validity of the proposeda* algorithm is investigated by analyzing an example of BWS, which is measured experimentally. It has been shown from the established results that the proposed method leads to an effective technique for analyzing the E-field response in the test volume of BWS. Related research in this article can provide some guidance in the analysis of BWS and transient electromagnetic field radiation sensitivity test (RS 105).

关键词： algorithm bounded wave simulator (BWS) current distribution current distribution electric dipole electric dipole Fourier transform (FT) Fourier transform (FT) nonuniform multiconductor transmission lines (NMTLs) nonuniform multiconductor transmission lines (NMTLs) nonuniform multiconductor transmission lines (NMTLs)

来源：评论

学校读者我要写书评

暂无评论

Prediction of total heat exchange factor using an improved particle swarm optimizationa* algorithm for the reheating furnace

引用

INTERNATIONAL JOURNAL OF THERMAL SCIENCES 2025年 210卷

作者： Yang, Zhi Luo, Xiaochuan Qiao, Jinwei Chen, Jun Liu, Pengbo Qilu Univ Technol Shandong Acad Sci Sch Mech Engn Jinan 250353 Peoples R China Shandong Inst Mech Design & Res Jinan 250353 Peoples R China Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China Northeastern Univ State Key Lab Synthet Automat Proc Ind Shenyang 110819 Peoples R China

For the reheating furnace, it is very difficult to determine the total heat exchange factor because of the complex environment and lack of efficienta* algorithms. To determine the unknown total heat exchange factors, an improved particle swarm optimization (named NDWPSO)a* algorithm is proposed by solving the inverse heat conduction problem (IHCP). Firstly, a nonlinear IHCP inversion model is built based on the one-dimensional heat transfer model with the Galerkin weighted residual method for the reheating furnace. Secondly, this study incorporates differential evolution(DE) and whale optimization (WO) into the NDWPSOa* algorithm to improve the effectiveness and enhance the adaptability. Thirdly, the global convergence and stability analysis are performed for the NDWPSOa* algorithm. Implemented in MATLAB, 2 different simulation experiments (3 typical benchmark functions experiment, the total heat exchange factor with the functional form) were given to compare thea* algorithm performance. The results demonstrate that the NDWPSOa* algorithm performs more quickly and accurately than the other 8 heuristica* algorithms. Finally, the application of the NDWPSOa* algorithm with real furnace temperature data can obtain the minimum mean error of 0.4890 o C, indicating the reliability of the NDWPSOa* algorithm.

关键词： Total heat exchange factor Inverse heat conduction problem Improved particle swarm optimization algorithm Convergence analysis Benchmark function tests

来源：评论

学校读者我要写书评

暂无评论

Data-driven study on the mechanical properties of strain-hardening cementitious composites usinga* algorithm-enhanced interpretable machine learning models and interactive interface development

引用

MATERIALS TODAY COMMUNICATIONS 2025年 46卷

作者： Huang, Xiaoyu Ma, Hongrui Ren, Xuanze Shen, Yinong Ba, Mingfang Ningbo Univ Sch Civil & Environm Engn & GeographySci Ningbo 315211 Peoples R China

Accurate prediction of the mechanical properties of strain-hardening cementitious composites (SHCC) is crucial for engineering application. While machine learning (ML) techniques excel in capturing nonlinear relationships compared to traditional regression models, the acquisition of experimental data for SHCC remains challenging, resulting in small datasets that are unfavorable for ML model development. Improved intelligenta* algorithms have been employed to enhance ML model performance through automatic hyperparameter tuning, offering improved probability of escaping local optima and consequently achieving higher accuracy compared to conventional intelligenta* algorithms. However, research on optimizing ML model parameters for SHCC using improved intelligenta* algorithms remains limited, and the interpretability analysis of existing model to SHCC is still limited, especially in the perspective of the combination of three dimension (3D) and two dimension (2D). Moreover, the prediction accuracy for ductility in most studies remains relatively low and the interactive graphical user interface (GUI) design in currently study is not comprehensive. In this study, 434 experimental data from published literature is collected, and an improved sparrow searcha* algorithm (MSSA) is established. The MSSA is based on the sparrow searcha* algorithm and incorporates five improvement strategies, including Levy flights, to optimize decision tree and random forest (RF) models for predicting the compressive strength (CS), tensile strength (TS), and ductility of SHCC. An isolated foresta* algorithm is used for outlier removal, while shapley additive explanations (SHAP) and partial dependence plots (PDP) are employed to enhance interpretability. Furthermore, a comprehensive GUI, which improves research diversity and system scalability, is developed to facilitate practical application. The results show that the MSSA successfully improves the prediction accuracy in small datasets, with t

关键词： Machine learning Strain hardening cementitious composites algorithm Prediction

来源：评论

学校读者我要写书评

暂无评论

A modified memetica* algorithm for the home health care scheduling and routing problem considering caregiver skill deviation and synchronous service

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2025年 203卷

作者： Li, Yan Wang, Qiangqiang Wang, Heping Wang, Fuyu Zhao, Dan Anhui Univ Technol Sch Management Sci & Engn Maanshan 243000 Peoples R China Multiple Sci Management & Control Complex Syst Key Maanshan 243000 Peoples R China

Based on the real scenario that two caregivers are needed to serve an elderly patient simultaneously, the paper studies the home health care synchronous scheduling and routing problem. The value function of prospect theory is used to describe their perceived satisfaction from the perspective of caregivers' bounded rationality towards skill deviations. A mixed-integer programming model is proposed to maximize the caregivers' satisfaction and minimize the total operating cost. An improved multi-objective memetica* algorithm (IMOMA) is designed to solve the problem. In the IMOMA, an improved push-forward insertion heuristic (IPFIH)a* algorithm is proposed to generate initial solutions. Two types of crossover operators, three types of mutation operators and four types of neighborhood search operators with the properties of the problem are designed to improve the performance of the IMOMA. Taguchi experiment is constructed to set the optimal parameters of thea* algorithm. Simulation experiments are conducted in cases of various scales. The results indicate that the IMOMA can efficiently solve the scheduling problem by comparing with the threea* algorithms. Finally, the sensitivity analysis is conducted on the key parameters of the scheduling model to explore their impact on the optimization objectives of the scheduling scheme.

关键词： Home health care Scheduling and routing Skill deviation Synchronous service An improved multi-objective memetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Quantification of Spatial Ventilation Defect Sparsity in Hyperpolarized Gas Magnetic Resonance Imaging of Lungs Utilizing a Three-Dimensional Clusteringa* algorithm

引用

NMR IN BIOMEDICINE 2025年第3期38卷 e70005页

作者： Delgado, Gabriela Maria Garcia Shammi, Ummul Afia Ruppel, Mia R. Altes, Talissa A. Mugler III, John P. Meyer, Craig H. Qing, Kun de Lange, Eduard E. Mata, Jaime Ruset, Iulian C. Hersman, F. W. Thomen, Robert P. Univ Missouri Chem & Biomed Engn Columbia MO 65211 USA Univ Illinois Sch Engn Biomed Engn Chicago IL USA Univ Missouri Sch Med Radiol Columbia MO 65211 USA Univ Virginia Sch Med Radiol & Med Imaging Charlottesville VA USA Univ Virginia Biomed Engn Charlottesville VA USA City Hope Natl Med Ctr Radiat Oncol Duarte CA USA Xemed LLC Durham NH USA

Hyperpolarized gas (HPG) magnetic resonance (MR) imaging allows for the quantification of pulmonary defects with the ventilation defect percentage (VDP). Although informative, VDPs lack information regarding the spatial distribution of defects. We developed a method of quantifying the focality/sparseness of ventilation defects in hyperpolarized-gas lung MR images. The study involved a total of 56 subjects: 14 asthmatics (age mean +/- sd = 45.1 +/- 18.9), 25 COPD subjects (age = 60.6 +/- 10.4), and 17 CF subjects (age = 21.8 +/- 8.4). The analyzed data are from four different studies: Study 1 used a 3-T gradient echo (GRE) sequence, Study 2 used a 1.5-T GRE sequence, Study 3 used a 1.5-T two-dimensional spiral sequence, and Study 4 used a 1.5-T three-dimensional balanced steady-state free precession (bSSFP) sequence. We developed ana* algorithm that quantifies the focality/sparseness of ventilation defects as a subject's cluster index (CI). Thea* algorithm was assessed on synthesized spherical defect clusters and 3D lung volume defects of varying sizes/distributions. CI and whole-lung VDP were calculated for asthmatic, COPD, and CF subjects. Pearson correlation coefficients and linear regression models between CI and FEV1pp, as well as CI and VDP, were performed to evaluate CI among asthma, COPD, and CF. T tests were performed to evaluate CI/VDP ratios among previously mentioned lung diseases. p values less than 0.05 were statistically significant. Subject CI well represents defect focality by visual inspection. Pearson correlation coefficients between CI and VDP were r = 0.60 (p = 2.21 x 10-2) for asthma, r = 0.79 (p = 3.15 x 10-6) for COPD, and r = 0.84 (p = 2.80 x 10-5) for CF. Pearson correlation coefficients between CI and FEV1pp was r = -0.47 (p = 0.0002). Analysis of variance (ANOVA) and a Tukey's honestly significant difference (HSD) test revealed that the ratio of whole-lung CI/VDP was significantly different between asthma/CF (p = 0.04) and CF/COPD (p = 0.008),

关键词： algorithm clustering defects gas hyperpolarized lungs MRI ventilation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：