检索结果-内蒙古大学图书馆

Sparse signal reconstruction by swarm intelligence algorithms

ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH 2021年第2期24卷 319-330页

作者： Erkoc, Murat Emre Karaboga, Nurhan Erciyes Univ Elect & Elect Eng Dep TR-38039 Kayseri Turkey

This study introduces a new technique for sparse signal reconstruction. In general, there are two classes of algorithms in the recovery of sparse signals: greedy approaches and l(1)-minimization methods. The proposed method employs swarm intelligence based techniques for sparse signal reconstruction. With this technique, the proposed method tries to find nonzero entries of a sparse signal. In addition, it uses least square method to obtain the magnitude of the reconstructed signal. In this study, artificial bee colony and particle swarm optimization algorithms are employed for the reconstruction of sparse signals. The algorithms are tested on some benchmark problems and empirical results for a number of test cases are obtained. In addition, the reconstruction performances of these two algorithms are compared with l(1) minimization, greedy algorithms and several lately announced methods. According to the results of the tests and comparisons, the proposed method for artificial bee colony and particle swarm optimization algorithms have better performance than the classical methods for some test cases and it can be used to recover sparse signals in general. Additionally, this method can be used to recover a sparse signal when classical methods fail to reconstruct the signal for some cases. (C) 2020 Karabuk University. Publishing services by Elsevier B.V.

关键词： Compressive sensing Sparse signal reconstruction swarm intelligence algorithms Artificial bee colony algorithm Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Intelligent Management of Preparations for Programming Olympiads on the Basis of swarm intelligence algorithms

引用

SCIENTIFIC AND TECHNICAL INFORMATION PROCESSING 2022年第5期49卷 301-309页

作者： Borisov, V. V. Yanukovich, S. P. Mrochek, T. V. Vorob'ev, M. V. Mirankov, A. Yu. Natl Res Univ Moscow Power Engn Inst Moscow 111250 Russia OAO Mogilev Reg Dev Agcy Mogilev 212030 BELARUS Belarusian Russian Univ Mogilev 212000 BELARUS IOOO Epam Syst Mogilev 212030 BELARUS

As a rule, approaches to managing the preparation of learners for programming Olympiads are not intended for intelligent interactive support from learning management and the software tools based on these approaches do not allow efficient processing of information for shaping individual and team preparation trajectories and providing this information to learners. This study proposes a method of organizing the intelligent management of preparation for programming Olympiads, based on the system-level approach, organizational systems control theory, and implementation of the entire IT specialist training cycle, including the phases of planning, organization, control, and motivation. It is proposed to adaptively shape learning trajectories and adjust them on the basis of swarm intelligence algorithms modified to include features for managing the training of learners for programming Olympiads. It is proposed to shape individual learning trajectories for participants in individual Olympiads on the basis of a modified firefly algorithm and team learning trajectories for participants in team Olympiads on the basis of a modified fish school search algorithm. It is also proposed to supplement the training process with recommendations and exercises selected by the results of psychological testing and intended to develop the personal and psychological qualities of the learners. The recommendations are followed throughout the preparation process until the threshold values of personal and psychological qualities necessary for participation in an Olympiad are reached.

关键词： Olympiads programming contest swarm intelligence algorithms modified firefly and fish school search algorithms online judge systems individual and team learning trajectories

来源：评论

学校读者我要写书评

暂无评论

A Voting Approach for Comparing Several swarm intelligence algorithms 20

A Voting Approach for Comparing Several Swarm Intelligence A...

引用

20th International Conference on System Controls and Computer Science 2015

作者： Mogos, Andrei-Horia Mogos, Bianca Florea, Adina Magda Univ Politehn Bucuresti Fac Automat Control & Comp Bucharest Romania Univ Bucharest Fac Math & Comp Sci Bucharest Romania

ISBN: (纸本)9781479917808

In the last decades, social choice theory has gained a significant popularity. Its main application areas are social sciences, political sciences, economic sciences and computer science. Computational social choice is a new research area situated at the intersection of social choice theory and computer science. Another popular and relatively new research area is swarm intelligence that aims to propose and use bio-inspired algorithms for solving optimization problems. In this paper we propose a methodology of comparing various swarm intelligence algorithms using voting methods (an important topic in social choice theory). Also, as a case study, we use our methodology to compare three swarm intelligence algorithms (Particle swarm Optimization, Cat swarm Optimization, and Artificial Bee Colony) on several minimization functions. For the interpretation of our comparison results, we use two important theorems: No Free Lunch Theorem (from optimization theory) and Arrow's Impossibility Theorem (from voting theory).

关键词： swarm intelligence algorithms Voting Methods No Free Lunch Theorem Arrow's Impossibility Theorem

来源：评论

学校读者我要写书评

暂无评论

swarm intelligence algorithms for Circles Packing Problem with equilibrium Constraints

Swarm intelligence algorithms for Circles Packing Problem wi...

引用

第12届分布式计算及其应用国际学术研讨会

作者： Peng Wang Shuai Huang ZhouQuan Zhu College of Marine Northwestern Polytechnical University College of Marine Northwestern Polytechnical University

Circles packing problem with equilibrium constraints is difficult to solve due to its NP-hard nature. Aiming at this NP-hard problem, three swarm intelligence algorithms are employed to solve this problem. Particle swarm Optimization and Ant Colony Optimization has been used for the circular packing problem with equilibrium constraints. In this paper, Artificial Bee Colony Algorithm(ABC) for equilibrium constraints circular packing problem is presented. Then we compare the performances of well-known swarm intelligence algorithms(PSO, ACO, ABC) for this problem. The results of experiment show that ABC is comparatively satisfying because of its stability and applicability.

关键词： Circles Packing swarm intelligence algorithms Equilibrium Constraints

来源：评论

学校读者我要写书评

暂无评论

Optimal energy management system for residential buildings considering the time of use price with swarm intelligence algorithms

引用

JOURNAL OF BUILDING ENGINEERING 2022年 59卷

作者： Yelisetti, Srinivas Saini, Vikash Kumar Kumar, Rajesh Lamba, Ravita Saxena, Akash MNIT Dept Elect Engn Jaipur 302017 India MNIT Ctr Energy & Environm Jaipur 302017 India Swami Keshvanand Inst Technol Management & Gramoth Dept Elect Engn Jaipur 302017 India

Revolutions in human activities and lifestyles result in a transition from conventional to intelligent residential building infrastructure. Conventional heating, ventilation, and air con-ditioning (HVAC), refrigerator and lighting system challenges are addressed without taking into account building heat gains, outdoor illuminance, and temperature. Based on these param-eters, a mathematical model for cost estimation of residential building energy consumption, considering indoor heat gains, outdoor temperature, outdoor illuminance, and TOU price has been developed. A total of 46 swarm intelligence based optimization algorithms are used to optimize different building parameters. These swarm intelligence algorithms (SIA) are compared using the convergence curves, statistical and box-plot analysis and the Bald Eagle search (BES) algorithm is found to be the best algorithm among all 46 SIAs. The mean energy consumption costs of the best algorithm, BES, and the worst algorithm, fireworks algorithm (FA) are found to be Rs. 8.85 and Rs. 12.98, respectively. In addition, economic analysis has been conducted for the proposed study and it is compared with the existing models with building energy management systems (BEMS) and conventional model (without BEMS). It is observed that, based on this analysis, the cost savings achieved by the proposed study are nearer to 34% and 57% as compared to existing and conventional models.

关键词： Building energy management system Heating ventilation and air conditioning system Lighting system swarm intelligence algorithms

来源：评论

学校读者我要写书评

暂无评论

Modified swarm intelligence algorithms for the pharmacy duty scheduling problem

引用

EXPERT SYSTEMS WITH APPLICATIONS 2022年 202卷 1页

作者： Kilic, Fatih Uncu, Nusin Adana Alparslan Turkes Sci & Technol Univ Dept Comp Engn Adana Turkey Adana Alparslan Turkes Sci & Technol Univ Dept Ind Engn Adana Turkey

Assigning duties to pharmacies to serve the public on weekends, nights, and public holidays is known as the pharmacy duty scheduling problem (PDSP). In this study, a..-median model is proposed with a casespecific constraint that provides the distance restriction between on-duty pharmacies. We adapted Binary and Random-Key versions of the most recent and popular swarm intelligence (SI) algorithms, which are Grey Wolf Optimizer (GWO), Particle swarm Optimization (PSO), Dragonfly Algorithm (DA), and Harris Hawks Optimization (HHO) to solve it in a reasonable amount of time since the PDSP is known to be an NP-Hard problem. We also proposed several enhancements to the algorithms and conducted computational tests on real cases generated instances using Geographic Information System (GIS) tools to compare the performances of the proposed algorithms with the state-of-the-art general-purpose solver. Two real-world datasets, called DS1 and DS2, are built considering the demand points. To validate the proposed algorithms, the CPLEX results, obtained with the exact solution for the DS1 dataset, are used. Compared to the MIP results for 800 meters distance constraint as an instance, maximum relative errors for Binary and Random-Key GWO, PSO, DA, and HHO are 0.07, 0.08, 0.08, and 0.08, respectively. The success of the algorithms is similar to the other distance criteria as well. Moreover, the results for the large DS2 dataset show that the proposed Binary GWO is more effective and offers efficient solutions compared to the other swarm intelligence algorithms and CPLEX solvers in terms of convergence to optimization and solution time.

关键词： Pharmacy duty scheduling swarm intelligence algorithms p-median problem Location covering Distance restriction

来源：评论

学校读者我要写书评

暂无评论

Prediction of carbonation depth for recycled aggregate concrete using ANN hybridized with swarm intelligence algorithms

引用

CONSTRUCTION AND BUILDING MATERIALS 2021年 301卷 124382-124382页

作者： Liu, Kaihua Alam, M. Shahria Zhu, Jiang Zheng, Jiakai Chi, Lin Guangdong Univ Technol Sch Civil & Transportat Engn Guangzhou 510006 Peoples R China Univ British Columbia Sch Engn Kelowna BC V1V 1V7 Canada Univ Shanghai Sci & Technol Sch Environm & Architecture Shanghai 200093 Peoples R China

This paper investigates the prediction of carbonation depth for recycled aggregate concrete (RAC) with machine learning models. Nine parameters including RAC intrinsic properties and environmental conditions were considered as input variables. A dataset comprising 593 test data was used to train, validate, and test machine learning models. Results show that the Random forest model shows superior performance than the Gaussian progress regression model and standalone artificial neural network (ANN) model. All ANN models hybridized with swarm intelligence algorithms outperform the standalone ANN model, especially for the ANN model hybridized with the whale optimization algorithm. All machine learning models show higher accuracy than the existing code models and statistical models. The variable importance analysis shows that the carbonation resistance for RAC was determined by both internal and external factors. Based on the parametric analysis, the robustness of the proposed machine learning models was further confirmed.

关键词： Recycled aggregate concrete Carbonation depth Machine learning Hybrid model Artificial neural network swarm intelligence algorithms

来源：评论

学校读者我要写书评

暂无评论

A comparative energy and exergy optimization of a supercritical-CO2 Brayton cycle and Organic Rankine Cycle combined system using swarm intelligence algorithms

引用

HELIYON 2020年第6期6卷 e04136页

作者： Ochoa, Guillermo Valencia Forero, Jorge Duarte Rojas, Jhan Piero Univ Atlantico Programa Ingn Mecan Carrera 30 Numero 8-49 Barranquilla 080007 Colombia Univ Francisco Paula Santander Engn Fac Ave Gran Colombia 12E-96 Cucuta 540003 Colombia

This article presents a multivariable optimization of the energy and exergetic performance of a power generation system, which is integrated by a supercritical Brayton Cycle using carbon dioxide, and a Simple Organic Rankine Cycle (SORC) using toluene with reheater (S - CO2RH - SORC), and without reheater (S - CO2NRH - SORC) using the PSO algorithm. A thermodynamic model of the integrated system was developed from the application of mass, energy and exergy balances to each component, which allowed the calculation exergy destroyed a fraction of each equipment, the power generated, the thermal and exergetic efficiency of the system. In addition, through a sensitivity analysis, the effect of the main operational and design variables on thermal efficiency and total exergy destroyed was studied, which were the objective functions selected in the proposed optimization. The results show that the greatest exergy destruction occurs at the thermal source, with a value of 97 kW for the system without Reheater (NRH), but this is reduced by 92.28% for the system with Reheater (RH). In addition, by optimizing the integrated cycle for a particle number of 25, the maximum thermal efficiency of 55.53% (NRH) was achieved, and 56.95% in the RH system. Likewise for a particle number of 15 and 20 in the PSO algorithm, exergy destruction was minimized to 60.72 kW (NRH) and 112.06 kW (RH), respectively. Comparative analyses of some swarm intelligence optimization algorithms were conducted for the integrated S - CO2 - SORC system, evaluating performance indicators, where the PSO optimization algorithm was favorable in the analyses, guar-anteeing that it is the ideal algorithm to solve this case study.

关键词： Energy Mechanical engineering Thermodynamics Mathematical optimization Energy conservation swarm intelligence algorithms Brayton supercritical CO2 cycle Organic Rankine cycle Exergetic analysis Energy analysis

来源：评论

学校读者我要写书评

暂无评论

A systematic review on software reliability prediction via swarm intelligence algorithms

引用

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2024年第7期36卷

作者： Kong, Li Sheng Jasser, Muhammed Basheer Ajibade, Samuel-Soma M. Mohamed, Ali Wagdy Sunway Univ Sch Engn & Technol Dept Comp & Informat Syst 5Jalan Univ Bandar Sunway 47500 Selangor Darul Malaysia Sunway Univ Res Ctr Human Machine Collaborat HUMAC Sch Engn & Technol 5 Jalan Univ Bandar Sunway 47500 Selangor Darul Malaysia Istanbul Ticaret Univ Dept Comp Engn Istanbul Turkiye Cairo Univ Fac Grad Studies Stat Res Operat Res Dept Giza 12613 Egypt Appl Sci Private Univ Appl Sci Res Ctr Amman 11931 Jordan

The widespread integration of software into all parts of our lives has led to the need for software of higher reliability. Ensuring reliable software usually necessitates some form of formal methods in the early stages of the development process which requires strenuous effort. Hence, researchers in the field of software reliability introduced Software Reliability Growth Models (SRGMs) as a relatively inexpensive approach to software reliability prediction. Conventional parameter estimation methods of SRGMs were ineffective and left more to be desired. Consequently, researchers sought out swarm intelligence to combat its flaws, resulting in significant improvements. While similar surveys exist within the domain, the surveys are broader in scope and do not cover many swarm intelligence algorithms. Moreover, the broader scope has resulted in the occasional omission of information regarding the design for reliability predictions. A more comprehensive survey containing 38 studies and 18 different swarm intelligence algorithms in the domain is presented. Each design proposed by the studies was systematically analyzed where relevant information including the measures used, datasets used, SRGMs used, and the effectiveness of each proposed design, were extracted and organized into tables and taxonomies to be able to identify the current trends within the domain. Some notable findings include the distance-based approach providing a high prediction accuracy and an increasing trend in hybridized variants of swarm intelligence algorithms designs to predict software reliability. Future researchers are encouraged to include Mean Square Error (MSE) or Root MSE as the measures offer the largest sample size for comparison.

关键词： swarm intelligence algorithms Software Reliability Prediction Software Reliability Growth Models Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimal band selection and transfer in drone-based hyperspectral images for plant-level vegetable crops identification using statistical-swarm intelligence (SSI) hybrid algorithms

引用

ECOLOGICAL INFORMATICS 2025年 86卷

作者： Sarma, Anagha S. Nidamanuri, Rama Rao Indian Inst Space Sci & Technol Dept Earth & Space Sci Thiruvananthapuram 695547 Kerala India

Hyperspectral imagery from drones are excellent sources of high-resolution plant-level data that helps in efficient crop identification for smart agriculture practices. However, the plant-level crop identification is still challenging, owing to only minute differences among the vegetation spectra and enhanced background diversity. Though the inherent spectral redundancy in hyperspectral data is dealt with various band reduction techniques for distinguishing different land use land cover (LULC) structures at broader level, band reduction at finer level has not been explored, especially for drone-based hyperspectral imagery. In this work, we propose a statisticalswarm intelligence (SSI) hybrid approach for optimal band selection in hyperspectral images for identification of three crops, cabbage, eggplant and tomato, using drone-based imagery acquired over experimental plots of University of Agricultural Sciences, Bengaluru, India. We ranked the spectral bands based on their separability among the ground truth classes that follows a Weibull distribution and applied swarm-intelligence algorithms for the optimal band set. The optimal band set is further tested for its capability to distinguish crops from images acquired at different flight heights of drone, and at different points of time. The results suggest that only 15 bands (462 nm, 470 nm, 498 nm, 502 nm, 514 nm, 534 nm, 542 nm, 550 nm, 582 nm, 590 nm, 614 nm, 762 nm, 902 nm, 914 nm, and 930 nm), spread at specific wavelengths in 450-650 nm and 850-950 nm range are sufficient to distinguish crops at finer spatial resolution and offer classification accuracy of over 93 %, supported by equivalent levels of F1 (0.93) and kappa coefficients (0.9). The specific wavelengths corresponding to optimal bands are capable of detecting crops in images captured at different heights and taken at a different time period, showing the space-time transfer potential of the selected bands for crop detection. The specific wavelengths are

关键词： Precision agriculture Weibull distribution Band selection swarm intelligence algorithms Hyperspectral imagery Drones

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：