检索结果-内蒙古大学图书馆

Detecting self-organising patterns in crowd motion: effect of optimisation algorithms

JOURNAL OF MATHEMATICS IN INDUSTRY 2024年第1期14卷 6页

作者： Worku, Samson Mullick, Pratik Wroclaw Univ Sci & Technol Dept Operat Res & Business Intelligence Wroclaw Poland

The escalating process of urbanization has raised concerns about incidents arising from overcrowding, necessitating a deep understanding of large human crowd behavior and the development of effective crowd management strategies. This study employs computational methods to analyze real-world crowd behaviors, emphasizing self-organizing patterns. Notably, the intersection of two streams of individuals triggers the spontaneous emergence of striped patterns, validated through both simulations and live human experiments. Addressing a gap in computational methods for studying these patterns, previous research utilized the pattern-matching technique, employing the Nelder-Mead Simplex algorithm for fitting a two-dimensional sinusoidal function to pedestrian coordinates. This paper advances the pattern-matching procedure by introducing Simulated Annealing as the optimization algorithm and employing a two-dimensional square wave for data fitting. The amalgamation of Simulated Annealing and the square wave significantly enhances pattern fitting quality, validated through statistical hypothesis tests. The study concludes by outlining potential applications of this method across diverse scenarios.

关键词： Pedestrian dynamics Human-crowd motion Geometric patterns Stripe detection optimisation algorithms

来源：评论

学校读者我要写书评

暂无评论

optimisation algorithms for OSNR measurement based on polarisation nulling

引用

ELECTRONICS LETTERS 2015年第13期51卷 1007-1009页

作者： Feres, M. M. Floridia, C. Romero, M. A. Univ Sao Paulo EESC USP Sao Carlos SP Brazil CPqD Fdn Campinas SP Brazil

optimisation algorithms are demonstrated as a nulling finder for an in-band optical signal-to-noise ratio (OSNR) monitoring method based on polarisation extinction. The method was tested and validated in the Brazilian GIGA optical fibre testbed. When three optimisation techniques (genetic algorithm, particle swarm optimisation (PSO) and downhill simplex) were compared, PSO provided the best results regarding convergence time and nulling efficiency.

关键词： particle swarm optimisation genetic algorithms optical fibre communication light polarisation optimisation algorithms OSNR measurement polarisation nulling nulling finder in-band optical signal-to-noise ratio monitoring method Brazilian GIGA optical fibre testbed genetic algorithm particle swarm optimisation PSO downhill simplex DS convergence time nulling efficiency

来源：评论

学校读者我要写书评

暂无评论

Probabilistic online learning framework for short-term wind power forecasting using ensemble bagging regression model

引用

ENERGY CONVERSION AND MANAGEMENT 2025年 323卷

作者： Nayak, Arun Kumar Sharma, Kailash Chand Bhakar, Rohit Tiwari, Harpal Malaviya Natl Inst Technol Dept Elect Engn Jaipur Rajasthan India Dr BR Ambedkar Natl Inst Technol Dept Elect Engn Jalandhar Punjab India

The increasing penetration of renewable energy sources, with a notable focus on wind power, within modern electricity grids requires computationally efficient and burden-free short-term wind power forecasting models. Traditional models generating prediction intervals are trained offline and thus deployed for prediction purposes. However, this approach cannot obtain interval forecasts from the most recent wind power observations. In contrast, combining multiple regression models through ensemble learning is recognised as a successful method for improving forecasting performance. By utilising the most recent observations and exploiting the strengths of multiple regression models, this article investigates an Online Ensemble Bagging Regression (OEBR) model for generating prediction intervals. Online gradient descent based optimisation algorithms capable of adaptive-depth calculation from a stream of observations are used hereto address the problems with traditional batch learning frameworks. The proposed online learning framework is evaluated against other online learning frameworks using publicly accessible datasets. The results show the proposed model competes with the compared models regarding probabilistic metrics and energy estimations and outperforms computational time requirements for the same number of observations.

关键词： Batch learning framework Computationally efficient Ensemble bagging Online learning optimisation algorithms Prediction intervals Short-term wind power forecasting

来源：评论

学校读者我要写书评

暂无评论

Analysis of different neural network models based on variational mode decomposition and dung beetle optimizer algorithm for the prediction of air-conditioning energy consumption in multifunctional complex large public buildings

引用

ENERGY AND BUILDINGS 2025年 334卷

作者： Liu, Jingtao Zhang, Yuxiang Wen, Kunbo Ding, Yunfei Guangzhou Univ Sch Civil Engn & Transportat Guangzhou 510006 Peoples R China Guangzhou Yuexiu Commercial Real Estate Management Guangzhou 510000 Peoples R China China Construct Third Engn Bur Grp Co Ltd Guangzhou 510600 Peoples R China

Forecasting daily air-conditioning energy consumption helps managers to plan system operations proactively, enhance the operational efficiency of units and equipment, and reduce overall energy consumption. Artificial neural network models have achieved remarkable results in the field of energy consumption prediction. However, some comprehensive large-scale public buildings, due to their complex functions, exhibit highly irregular daily variations in air-conditioning energy consumption, posing significant challenges for accurate prediction. In order to enhance the accuracy of predicting air-conditioning energy consumption in such buildings, and mitigate the issue of significant prediction errors in neural network models caused by abrupt changes in energy consumption over certain periods, the actual operational data from the central air-conditioning system of a largescale comprehensive public building in Guangzhou over the past two years has been collected. Based on this data, a novel prediction method for air-conditioning energy consumption is proposed. Based on Long short-term memory (LSTM), Back propagation algorithm (BP) and Gate recurrent unit (GRU) neural networks, combined with Variational Mode Decomposition (VMD) and Dung Beetle Optimizer (DBO), nine machine learning energy consumption prediction models were established, and the prediction effects before and after the optimisation of different models, as well as the consumption of computational resources by the models, were tested and compared. The results show that without optimization, LSTM, BP and GRU neural network models are easy to produce large errors, especially in the part of air conditioning energy consumption mutation, making it difficult for them to identify the change law of data. The optimised models significantly improve this situation and also improve the overall prediction accuracy. Compared with the pre-optimization models, the mean absolute percentage error (MAPE) of the optimized VMD-DBO-LS

关键词： Comprehensive large-scale public buildings Air-conditioning energy consumption prediction Local mutations optimisation algorithms Machine learning

来源：评论

学校读者我要写书评

暂无评论

Stochastic optimisation-based methods for the identification of the physical parameters of a metal hydride tank

引用

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY 2024年 50卷 178-189页

作者： Suarez, S. H. Chabane, D. N'Diaye, A. Ait-Amirat, Y. Djerdir, A. UTBM CNRS Inst FEMTO ST FCLAB F-90000 Belfort France Univ Franche Comte Inst FEMTO ST UTBM CNRSFCLAB F-90000 Belfort France

In this paper, three optimisation methods are used to determine the parameters of a commercial metal hydride hydrogen tank, considered as a grey box in which the thermophysical parameters are unknown. These parameters are essential for the development of energy management strategies and the study of tank ageing. A model of the hydride tank containing an AB5 intermetallic was developed and experimentally validated. An absorption test campaign of the studied tank was carried out to collect data necessary for the optimisation algorithms. A comparative study was carried out in accordance with the speed of convergence and precision between the three stochastic optimisation methods: Particle Swarm optimisation (PSO), Genetic Algorithm (GA) and Differential Evolution (DE). The results of the simulation of the storage system using the parameters determined by the algorithms show a remarkably close agreement with the experimental data, with a maximum error of 2.1%.(c) 2023 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.

关键词： Parameter estimation optimisation algorithms Hydrogen storage Metal hydride Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Improving CNTs properties using computational intelligence algorithms

引用

INTERNATIONAL JOURNAL OF MATERIALS & PRODUCT TECHNOLOGY 2024年第1-2期68卷 169-198页

作者： Jarrah, Muath Alqattan, Zakaria N. M. Jaya, Abdul Syukor Mohamad Makhadmeh, Sharif Naser Abu-Khadrah, Ahmed Ismail Aljarrah, Ibrahim Alomari, Osama Ahmad Univ Sharjah Coll Comp & Informat Sharjah 27272 U Arab Emirates Univ Malaysia Comp Sci & Engn UNIMY Dept Comp Sci Cyberjaya Selangor Malaysia Northern Tech Univ Dept Cyber Secur & Cloud Comp Tech Engn Mosul Iraq Int Islamic Univ Malaysia IIUM Dept Comp Sci Kulliyyah Informat & Commun Technol Kuala Lumpur Malaysia Univ Teknikal Malaysia Melaka Dept Intelligent Comp & Analyt Hang Tuah Jaya 76100 Melaka Malaysia Univ Petra Dept Data Sci & Artificial Intelligence Amman 11196 Jordan Saudi Elect Univ Coll Comp & Informat Riyadh Saudi Arabia Jordan Univ Sci & Technol Dept Comp Informat Syst CIS Irbid Jordan Abu Dhabi Univ Coll Engn Dept Comp Sci & Informat Technol Abu Dhabi U Arab Emirates

Carbon nanotubes (CNTs) have emerged in various applications due to their outstanding characteristics. The most common technique for producing CNTs with high yield and quality is known as chemical vapour deposition (CVD). However, manufacturers rely on conventional experimental studies to produce CNTs, which raise issues such as time, cost, and dealing with toxic materials. Alternatively, modelling and optimisation using metaheuristic algorithms are suggested to address these issues. This paper uses response surface methodology (RSM) for modelling work, while four metaheuristic algorithms are employed for optimisation. The regression and mathematical models, correlations, and significant CNTs process parameters are identified, analysed, and validated using RSM. The optimisation process and result are validated using different performance measure metrics and supported by other researchers. The CNTs yield and quality values improvement percentages in this paper are up to 36.45% compared to the referred original work.

关键词： carbon nanotubes CNTs chemical vapour deposition CVD optimisation algorithms response surface methodology RSM

来源：评论

学校读者我要写书评

暂无评论

Joint scheduling of spare parts production and service engineers based on progressive Pareto algorithm

引用

INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH 2024年第6期62卷 2124-2141页

作者： Miao, Bingxin Deng, Qianwang Zhang, Like Huo, Zhangwen Han, Weifeng Hunan Univ State Key Lab Adv Design & Mfg Vehicle Body Changsha Peoples R China Zhengzhou Univ Light Ind Henan Prov Key Lab Intelligent Mfg Mech Equipment Zhengzhou Peoples R China China Railway Tunnel Grp Co Ltd Guangzhou Peoples R China Hunan Univ State Key Lab Adv Design & Mfg Vehicle Body 2 South Lushan Rd Changsha 410082 Peoples R China

We analyse the joint scheduling of spare parts production and service engineers in a multi-site maintenance system. In the system, for each failure, a service engineer with the required spare part needs to be allocated for on-site maintenance. If one of the required resources is not readily available, the maintenance task can be satisfied via an external channel with quick responsiveness but high involved costs. Service providers need to make an efficient plan, including production scheduling of spare parts, allocation of service engineers and outsourcing strategy. First, a mathematical model with the objectives of minimum total outsourcing costs and minimum weighted tardiness is formulated. Then, a novel and knowledge-based heuristic algorithm is developed, namely progressive Pareto algorithm based on step-size (PPAS). To verify the performance of PPAS, it is compared against other well-known algorithms, including NSGA-II, MOEA/D, NNIA, RIPG, MMOIG and MNNIA. Finally, the effectiveness of the joint scheduling mode is demonstrated by comparing it with the separate optimisation mode of spare parts production and workforce allocation.

关键词： Maintenance spare parts service engineers joint scheduling optimisation algorithms

来源：评论

学校读者我要写书评

暂无评论

Intelligent techniques and optimization algorithms in textile colour management: a systematic review of applications and prediction accuracy

引用

FASHION AND TEXTILES 2024年第1期11卷 13页

作者： Liu, Senbiao Liu, Yaohui Keane Lo, Kwan-yu Chris Kan, Chi-wai Hong Kong Polytech Univ Sch Fash & Text Hung Hom Kowloon Hong Kong Peoples R China Technol & Higher Educ Inst Hong Kong Dept Construct Technol & Engn 20A Tsing Yi Rd Hong Kong Peoples R China Hong Kong Polytech Univ Fac Business Dept Logist & Maritime Studies Hung HomKowloon Hong Kong Peoples R China

Based on a selection of 101 articles published from 2013 to 2022, this study systematically reviews the application of intelligent techniques and optimization algorithms in textile colour management. Specifically, the study explores how these techniques have been applied to four subfields within textile colour management: colour matching and prediction, colour difference detection and assessment, colour recognition and segmentation, and dye solution concentration and decolourization. Following an introduction to intelligent techniques and optimization algorithms in textile colour management, the study describes the specific applications of these techniques in the field over the past decade. Descriptive statistics are used to analyse trends in the use of these techniques and optimization algorithms, and comparative performances indicate the effectiveness of the techniques and algorithms. The study finds that the primary intelligent techniques used in the field of textile colour management include artificial neural networks (ANN), support vector machines (SVM) such as SVM, LSSVM, LSSVR, SLSSVR, FWSVR, fuzzy logic (FL) and adaptive neuro-fuzzy inference systems (ANFIS), clustering algorithms (e.g., K-means, FCM, X-means algorithms), and extreme learning machines (ELM) such as ELM, OSLEM, KELM, RELM. The main optimization algorithms used include response surface methodology (RSM), genetic algorithms (GA), particle swarm optimization (PSO), and differential evolution (DE). Finally, the study proposes a comparison of the performance of intelligent techniques and optimization algorithms, summarizes the relevant research trends, and suggests future research opportunities and directions, besides stating the limitations of this paper.

关键词： Intelligent techniques optimisation algorithms Textile colour management Performance comparison reference Review

来源：评论

学校读者我要写书评

暂无评论

Multi-layers deep learning model with feature selection for automated detection and classification of highway pavement cracks

引用

SMART AND SUSTAINABLE BUILT ENVIRONMENT 2025年第2期14卷 511-535页

作者： Elghaish, Faris Matarneh, Sandra Abdellatef, Essam Rahimian, Farzad Hosseini, M. Reza Kineber, Ahmed Farouk Queens Univ Belfast Fac Engn & Phys Sci Belfast Antrim North Ireland Al Ahliyya Amman Univ Dept Civil Engn Amman Jordan Delta Higher Inst Engn & Technol Mansoura Egypt Teesside Univ Middlesbrough Cleveland England Teesside Univ Dept Engn Middlesbrough Cleveland England Deakin Univ Fac Sci Engn & Built Environm Dept Architecture & Built Environm Geelong Vic Australia Prince Sattam Bin Abdulaziz Univ Al Kharj Saudi Arabia

PurposeCracks are prevalent signs of pavement distress found on highways globally. The use of artificial intelligence (AI) and deep learning (DL) for crack detection is increasingly considered as an optimal solution. Consequently, this paper introduces a novel, fully connected, optimised convolutional neural network (CNN) model using feature selection algorithms for the purpose of detecting cracks in highway ***/methodology/approachTo enhance the accuracy of the CNN model for crack detection, the authors employed a fully connected deep learning layers CNN model along with several optimisation techniques. Specifically, three optimisation algorithms, namely adaptive moment estimation (ADAM), stochastic gradient descent with momentum (SGDM), and RMSProp, were utilised to fine-tune the CNN model and enhance its overall performance. Subsequently, the authors implemented eight feature selection algorithms to further improve the accuracy of the optimised CNN model. These feature selection techniques were thoughtfully selected and systematically applied to identify the most relevant features contributing to crack detection in the given dataset. Finally, the authors subjected the proposed model to testing against seven pre-trained *** study's results show that the accuracy of the three optimisers (ADAM, SGDM, and RMSProp) with the five deep learning layers model is 97.4%, 98.2%, and 96.09%, respectively. Following this, eight feature selection algorithms were applied to the five deep learning layers to enhance accuracy, with particle swarm optimisation (PSO) achieving the highest F-score at 98.72. The model was then compared with other pre-trained models and exhibited the highest *** implicationsWith an achieved precision of 98.19% and F-score of 98.72% using PSO, the developed model is highly accurate and effective in detecting and evaluating the condition of cracks in pavements. As a result, the model has the potential to signi

关键词： CNN Highway surface cracks Feature selection optimisation algorithms Particle swarm optimisation (PSO)

来源：评论

学校读者我要写书评

暂无评论

Evaluation of optimization algorithms for power and voltage in solar power generation system: FOPID controller and MPPT-based P&O algorithm

引用

International Journal of Information Technology (Singapore) 2025年 1-13页

作者： Dawood, Zahraa Ali Tackie, Samuel Nii Dimililer, Kamil Department of Electrical and Electronic Engineering Faculty of Engineering Near East University Nicosia Cyprus Ministry of Higher Education and Scientific Research Baghdad Iraq

In this work, the study gives attention for improvement of the Maximum Power Point Tracking (MPPT) using the Perturb and Observe (P&O) algorithm based MPPT applied to solar power generation system (SPGS). The algorithm components are refined, outcomes of the resultant optimized values are compared to address challenges in optimizing power, voltage and efficiency with the research. Further to improve this performance, Fractional Order Proportional Integral Derivative (FOPID) criteria are tuned using optimization techniques such as Black Hole (BH) Optimization, Jaya Optimization Algorithm (JOA), and Sunflower Optimization (SFO). Selection of optimal power and voltage values was aided by these methods. Limitations of the study include the exclusion of dynamic environmental changes in the analysis, and the potential non specificity of optimization algorithms for all SPGS scenarios considered. SPGS offers an opportunity to explore more dynamic models, as well as alternative algorithms, to improve the power and voltage management done in SPGS. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2025.

关键词： FOPID controller MPPT optimisation algorithms P&O algorithm SPGS

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：