检索结果-内蒙古大学图书馆

Improved coyote optimization algorithm and Deep Learning Driven Activity Recognition in Healthcare

IEEE ACCESS 2024年 12卷 22158-22166页

作者： Alazwari, Sana Eltahir, Majdy M. Almalki, Nabil Sharaf Alzahrani, Abdulrahman Alnfiai, Mrim M. Salama, Ahmed S. Taif Univ Coll Comp & Informat Technol Dept Informat Technol Taif 21944 Saudi Arabia King Khalid Univ Coll Sci & Art Mahayil Dept Informat Syst Abha 61421 Saudi Arabia King Saud Univ Coll Educ Dept Special Educ Riyadh 12372 Saudi Arabia Univ Hafr Al Batin Coll Comp Sci & Engn Dept Comp Sci & Engn Hafar al Batin 39524 Saudi Arabia Future Univ Egypt Fac Engn & Technol Dept Elect Engn New Cairo 11845 Egypt

Healthcare is an area of concern where the application of human-centred design practices and principles can enormously affect well-being and patient care. The provision of high-quality healthcare services requires a deep understanding of patients' needs, experiences, and preferences. Human activity recognition (HAR) is paramount in healthcare monitoring by using machine learning (ML), sensor data, and artificial intelligence (AI) to track and discern individuals' behaviours and physical movements. This technology allows healthcare professionals to remotely monitor patients, thereby ensuring they adhere to prescribed rehabilitation or exercise routines, and identify falls or anomalies, improving overall care and safety of the patient. HAR for healthcare monitoring, driven by deep learning (DL) algorithms, leverages neural networks and large quantities of sensor information to autonomously and accurately detect and track patients' behaviors and physical activities. DL-based HAR provides a cutting-edge solution for healthcare professionals to provide precise and more proactive interventions, reducing the burden on healthcare systems and improving patient well-being while increasing the overall quality of care. Therefore, the study presents an improved coyote optimization algorithm with a deep learning-assisted HAR (ICOADL-HAR) approach for healthcare monitoring. The purpose of the ICOADL-HAR technique is to analyze the sensor information of the patients to determine the different kinds of activities. In the primary stage, the ICOADL-HAR model allows a data normalization process using the Z-score approach. For activity recognition, the ICOADL-HAR technique employs an attention-based long short-term memory (ALSTM) model. Finally, the hyperparameter tuning of the ALSTM model can be performed by using ICOA. The stimulation validation of the ICOADL-HAR model takes place using benchmark HAR datasets. The wide-ranging comparison analysis highlighted the improved recognition r

关键词： Human activity recognition hyperparameter tuning coyote optimization algorithm wearable sensor deep learning

来源：评论

学校读者我要写书评

暂无评论

coyote optimization algorithm with Linear Convergence for Global Numerical optimization 9th

Coyote Optimization Algorithm with Linear Convergence for Gl...

引用

9th International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making (IUKM)

作者： Lin, Hsin-Jui Hsieh, Sheng-Ta Asia Eastern Univ Sci & Technol New Taipei Taiwan

ISBN: (纸本)9783030980184;9783030980177

In particular, the popularity of computational intelligence has accelerated the study of optimization. coyote optimization algorithm (COA) is a new meta heuristic optimization. It is pays attention to the social structure and experience exchange of coyotes. In this paper, the coyote optimization algorithm with linear convergence (COALC) is proposed. In order to explore a huge search space in the pre-optimization stage and to avoid premature convergence, the convergence factor is also involved. Thus, the COALC will explore a huge search space in the early optimization stage to avoid premature convergence. Also, the small area is adopted in the later optimization stage to effectively refine the final solution, while simulating a coyote killed by a hunter in the environment. It can avoid the influence of bad solutions. In experiments, ten IEEE CEC2019 test functions is adopted. The results show that the proposed method has rapid convergence, and a better solution can be obtained in a limited time, so it has advantages compared with other related methods.

关键词： Functional optimization Swarm intelligence Global optimization problems coyote optimization algorithm coyote optimization algorithm with linear convergence

来源：评论

学校读者我要写书评

暂无评论

The novel multi-swarm coyote optimization algorithm for automatic skin lesion segmentation

引用

EVOLUTIONARY INTELLIGENCE 2024年第2期17卷 679-711页

作者： Sayed, Gehad Ismail Khoriba, Ghada Haggag, Mohamed H. Cairo Univ Fac Comp & Informat Giza Egypt Helwan Univ Fac Comp & Informat Helwan Egypt

coyote optimization algorithm (COA) is one of population-based swarm intelligence algorithms inspired by the swarming behavior of coyotes. However, COA showed its effectiveness in solving the global optimization problem, it suffers from premature convergence and stagnation in local optima, espicially in a complex space. In this paper, the multi-swarm topology is employed, where the population is divided into several sub-swarms. The performance of multi-swarm coyote optimization algorithm (MCOA) is evaluated on a set of benchmark functions provided in the IEEE CEC 2005 and IEEE CEC 2017 special sessions. Also, it is evaluated for solving multi-level thresholding problem, where 44 skin dermoscopic images obatined from PH2 benchmark dataset are used. The experimental results showed that employing mutli-swarm topology can significantly improve the population diversity and thus the exploration ability. Also, the results reveal that proposed MCOA has the advantages of remarkable stability and high accuracy compared with its classical version and other state-of-art meta-heuristic optimization algorithms. Additionally, a new skin lesion segmentation model based on MCOA is proposed as well. The results illustrate the effectiveness and efficiency of the proposed model and it can be further used for skin disease diagnosis and treatment planning.

关键词： coyote optimization algorithm Multilevel thresholding Global optimization PH2 dataset

来源：评论

学校读者我要写书评

暂无评论

Improved coyote optimization algorithm for parameter estimation of lithium-ion batteries

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART A-JOURNAL OF POWER AND ENERGY 2023年第4期237卷 787-796页

作者： Hao, Yuefei Ding, Jie Huang, Shimeng Xiao, Min Nanjing Univ Posts & Telecommun Sch Automat & Artificial Intelligence Nanjing Peoples R China Nanjing Univ Posts & Telecommun Sch Automat & Artificial Intelligence 9 Wenyuan Rd Nanjing 210023 Peoples R China

This paper studies the parameter estimation of fractional order equivalent circuit model of lithium-ion batteries. Since intelligent optimization algorithms can achieve parameters with high accuracy by transforming the parameter estimation into optimization problem, coyote optimization algorithm is taken in this paper by modifying two key steps so as to improve the accuracy and convergence speed. Firstly, tent chaotic map is introduced to avoid falling into local optimum and enhance population diversity. Secondly, dual strategy learning is employed to improve the searching ability, accuracy and convergence speed. Non-parametric statistical significance is tested by 6 benchmark functions with the comparison of other 5 optimization algorithms. Furthermore, the proposed algorithm is applied to identify the fractional order model of the Samsung ICR18650 (2600 mAh) and compared with conventional coyote optimization algorithm and particle swarm algorithm, which declared the excellence in identification accuracy.

关键词： Fractional order model lithium-ion battery coyote optimization algorithm parameter identification

来源：评论

学校读者我要写书评

暂无评论

Solving the Mesh Router Nodes Placement in Wireless Mesh Networks Using coyote optimization algorithm

引用

IEEE ACCESS 2022年 10卷 52744-52759页

作者： Taleb, Sylia Mekhmoukh Meraihi, Yassine Gabis, Asma Benmessaoud Mirjalili, Seyedali Zaguia, Atef Ramdane-Cherif, Amar Univ MHamed Bougara Boumerdes LIST Lab Boumerdes 35000 Algeria Lab Methodes Concept Syst Algiers 16309 Algeria Torrens Univ Australia Ctr Artificial Intelligence Res & Optimisat Brisbane Qld 4006 Australia Yonsei Univ Yonsei Frontier Lab YFL Seoul 03722 South Korea Taif Univ Coll Comp & Informat Technol Dept Comp Sci At Taif 21944 Saudi Arabia Univ Versailles St Quentin En Yvelines LISV Lab F-78140 Velizy Villacoublay France

Wireless Mesh Networks (WMNs) have rapid real developments during the last decade due to their simple implementation at low cost, easy network maintenance, and reliable service coverage. Despite these properties, the nodes placement of such networks imposes an important research issue for network operators and influences strongly the WMNs performance. This challenging issue is known to be an NP-hard problem, and solving it using approximate optimization algorithms (i.e. heuristic and meta-heuristic) is essential. This motivates our attempts to present an application of the coyote optimization algorithm (COA) to solve the mesh routers placement problem in WMNs in this work. Experiments are conducted on several scenarios under different settings, taking into account two important metrics such as network connectivity and user coverage. Simulation results demonstrate the effectiveness and merits of COA in finding optimal mesh routers locations when compared to other optimization algorithms such as Firefly algorithm (FA), Particle Swarm optimization (PSO), Whale optimization algorithm (WOA), Genetic algorithm (GA), Bat algorithm (BA), African Vulture optimization algorithm (AVOA), Aquila Optimizer (AO), Bald Eagle Search optimization (BES), Coronavirus herd immunity optimizer (CHIO), and Salp Swarm algorithm (SSA).

关键词： optimization Genetic algorithms Measurement Wireless mesh networks Heuristic algorithms Costs Topology coyote optimization algorithm mesh router nodes placement meta-heuristics network design wireless mesh networks

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Hybrid coyote optimization algorithm for Image Thresholding

引用

Computers, Materials & Continua 2022年第8期72卷 3073-3090页

作者： Linguo Li Xuwen Huang Shunqiang Qian Zhangfei Li Shujing Li Romany F.Mansour School of Computer Nanjing University of Posts and TelecommunicationsNanjing210003China School of Computer and Information Engineering Fuyang Normal UniversityFuyang236041China Department of Mathematics Faculty of ScienceNew Valley UniversityEl-Kharga72511Egypt

In order to address the problems of coyote optimization algorithm in image thresholding,such as easily falling into local optimum,and slow convergence speed,a Fuzzy Hybrid coyote optimization algorithm(here-inafter referred to as FHCOA)based on chaotic initialization and reverse learning strategy is proposed,and its effect on image thresholding is *** chaotic initialization,the random number initialization mode in the standard coyote optimization algorithm(COA)is replaced by chaotic *** sequence is nonlinear and long-term unpredictable,these characteristics can effectively improve the diversity of the population in the optimization ***,in this paper we first perform chaotic initialization,using chaotic sequence to replace random number initialization in standard *** combining the lens imaging reverse learning strategy and the optimal worst reverse learning strategy,a hybrid reverse learning strategy is then *** the process of algorithm traversal,the best coyote and the worst coyote in the pack are selected for reverse learning operation respectively,which prevents the algorithm falling into local optimum to a certain extent and also solves the problem of premature *** on the above improvements,the coyote optimization algorithm has better global convergence and computational *** simulation results show that the algorithmhas better thresholding effect than the five commonly used optimization algorithms in image thresholding when multiple images are selected and different threshold numbers are set.

关键词： coyote optimization algorithm image segmentation multilevel thresholding logistic chaotic map hybrid inverse learning strategy

来源：评论

学校读者我要写书评

暂无评论

A modified variant of coyote optimization algorithm for solving ordinary differential equations and oscillatory mechanical problems

引用

SIMULATION-TRANSACTIONS OF THE SOCIETY FOR MODELING AND SIMULATION INTERNATIONAL 2022年第12期98卷 1161-1178页

作者： Eid, Heba F. Mansour, Romany F. Cuevas, Erik Al Azhar Univ Fac Sci Math & Comp Dept Cairo 11651 Egypt New Valley Univ Fac Sci Dept Math Kharga New Valley Gove Egypt Univ Guadalajara Dept Elect Guadalajara Jalisco Mexico

A vital subject of engineering structures is mechanical oscillations. If the mechanical oscillation is uncontrolled, it can lead to structural failure due to large dynamic stresses developed, as the collapse occurred on the Broughton Suspension bridge due to soldiers walking in step. This paper addresses mechanical oscillation problems employing a proposed modified variant of coyote optimizer. coyote optimization algorithm (COA) is a new meta-heuristic which mimics the social behavior of coyotes. COA suffers with stagnation problems and immature convergence while solving optimization problems. In this paper, the COA is hybridized with Laplace Crossover operator and new culture tendency strategies are adapted, modified variants of coyote optimization algorithm (MvCOA). The proposed MvCOA is presented to approximately solve mechanical oscillation problems independently of their order, form, and stated conditions. With the fundamental concepts of ordinary differential equations and Fourier series expansion, mechanical oscillation problems can be modeled as a problem of optimization whereby the optimization task is achieved using the proposed MvCOA. Five different ordinary differential equations and four mechanical oscillation problems are solved approximately and then compared with their corresponding exact solutions. The statistical analysis validates that the presented MvCOA is an effective algorithm for different optimization problems. However, from the empirical results, it is visible that the suggested MvCOA approximate approach was able to reach a successful performance solving different mechanical oscillation problems.

关键词： Bio-inspired computing coyote optimization algorithm mechanical oscillations ordinary differential equations approximate solution

来源：评论

学校读者我要写书评

暂无评论

New optimized configuration for a hybrid PV/diesel/battery system based on coyote optimization algorithm: A case study for Hotan county

引用

ENERGY REPORTS 2022年 8卷 15480-15492页

作者： Sari, Arif Majdi, Ali Opulencia, Maria Jade Catalan Timoshin, Anton Dinh Tran Ngoc Huy Nguyen Dinh Trung Alsaikhan, Fahad Hammid, Ali Thaeer Akhmedov, Abdulaziz Girne Amer Univ Dept Management Informat Syst Via Mersin 10 Kyrenia North Cyprus Turkey Al Mustaqbal Univ Coll Dept Bldg & Construct Tech Hilla Iraq Ajman Univ Coll Business Adm Ajman U Arab Emirates Sechenov Univ IM Sechenov First Moscow State Med Univ Dept Propaedeut Dent Dis Moscow Russia Banking Univ HCMC Ho Chi Minh City Ho Chi Minh City Vietnam Int Univ Japan Niigata Japan NEU Hanoi Vietnam Prince Sattam Bin Abdulaziz Univ Clin Pharm Dept Clin Pharm Coll Pharm Alkharj Saudi Arabia Imam Jaafar Al Sadiq Univ Dept Comp Engn Baghdad Iraq Dept Informat & Teaching Methods Bunyodkor St 27 Tashkent Uzbekistan

The main objective of this study is to present a multi-objective and optimal hybrid PV/diesel generator/battery Renewable Energy System (HRES) to provide this reliability in the Hotan county, placed in Taklamakan Desert. This study uses the epsilon-constraint method along with a developed version of the coyote optimization algorithm to achieve the best values of the component sized to decrease the loss of load probability, CO2 emission value, and the annualized cost of the system. Sensitivity analysis also is performed to show each component's impact on the system. The results demonstrate that the DG backup system improves the yearly cost of the system from 8347.2 $ to 9318.4 $, which shows about 10.42% increasing by increasing the fuel consumption. Here, the LLP increases from 0% to 9.19% and the CO2 emissions improve from 2531.2 kg/yr to 13257 kg/yr. Accordingly, the COE value is reduced from 0.39 $/kWh to 0.24 $/kWh over the PV penetration, reducing from 92.27% to 59.42%. This decreasing indicates that the system fuel cost has more impact than the cost of PV on the COE, which is due to the low cost required of conventional power production than the PV system. The results also indicate a noteworthy upshot on the battery storage unit size such that the size of epsilon(CO2) has been enhanced from 27.4 kWh to 50 kWh in the range from 7000 kg/year to 25 kg/year. The results also are compared with the PSO-based optimal system and HOMER software results to show its excellence toward them. (c) 2022 The Author(s). Published by Elsevier Ltd.

关键词： Hybrid renewable energy system Multi-objective optimization Taklamakan desert epsilon-constraint method Sensitivity analysis HOMER coyote optimization algorithm Improved

来源：评论

学校读者我要写书评

暂无评论

coyote optimization algorithm for Parameters Estimation of Various Models of Solar Cells and PV Modules

引用

IEEE ACCESS 2020年 8卷 111102-111140页

作者： Diab, Ahmed A. Zaki Sultan, Hamdy M. Ton Duc Do Kamel, Omar Makram Mossa, Mahmoud A. Minia Univ Fac Engn Elect Engn Dept Al Minya 61111 Egypt Kyushu Univ Dept Elect & Elect Engn Fukuoka 8190395 Japan Nazarbayev Univ Sch Engn & Digital Sci SEDS Dept Robot & Mechatron Z05H0P9 Nur Sultan Kazakhstan El Minia High Inst Engn & Technol Elect & Comp Dept Al Minya 61125 Egypt Moscow Power Engn Inst MPEI Elect Power Syst Dept Moscow 111250 Russia

Recently, building an accurate mathematical model with the help of the experimentally measured data of solar cells and Photovoltaic (PV) modules, as a tool for simulation and performance evaluation of the PV systems, has attracted the attention of many researchers. In this work, coyote optimization algorithm (COA) has been applied for extracting the unknown parameters involved in various models for the solar cell and PV modules, namely single diode model, double diode model, and three diode model. The choice of COA algorithm for such an application is made because of its good tracking characteristics and the balance creation between the exploration and exploitation phases. Additionally, it has only two control parameters and such a feature makes it very simple in application. The Root Mean Square Error (RMSE) value between the data based on the optimized parameters for each model and those based on the measured data of the solar cell and PV modules is adopted as the objective function. Parameters' estimation for various types of PV modules (mono-crystalline, thin-film, and multi-crystalline) under different operating scenarios such as a change in intensity of solar radiation and cell temperature is studied. Furthermore, a comprehensive statistical study has been performed to validate the accurateness and stability of the applied COA as a competitor to other optimization algorithms in the optimal design of PV module parameters. Simulation results, as well as the statistical measurement, validate the superiority and the reliability of theCOAalgorithm not only for parameter extraction of different PV modules but also under different operating scenarios. With the COA, precise PV models have been established with acceptable RMSE of 7.7547 x 10(-4), 7.64801 x 10(-4), and 7.59756 x 10(-4) for SDM, DDM, and TDM respectively considering R.T.C. France solar cell.

关键词： Mathematical model Integrated circuit modeling optimization Photovoltaic cells Analytical models Parameter estimation Estimation Solar cells PV modules parameter extraction optimization coyote optimization algorithm single diode model double diode model three diode model

来源：评论

学校读者我要写书评

暂无评论

Multi-objective coyote optimization algorithm based on hybrid elite framework and Meta-Lamarckian learning strategy for optimal power flow problem

引用

ARTIFICIAL INTELLIGENCE REVIEW 2024年第5期57卷 117-117页

作者： Zhu, Jun-Hua Wang, Jie-Sheng Zhang, Xing-Yue Wang, Yu-Cai Song, Hao-Ming Zheng, Yue Liu, Xun Univ Sci & Technol Liaoning Sch Elect & Informat Engn Anshan Liaoning Peoples R China

A multi-objective coyote optimization algorithm based on hybrid elite framework and Meta-Lamarckian learning strategy (MOCOA-ML) was proposed to solve the optimal power flow (OPF) problem. MOCOA-ML adds external archives with grid mechanism on the basis of elite non-dominated sorting. It can guarantee the diversity of the population while obtaining the Pareto solution set. When selecting elite coyotes, there is a greater probability to select the elite in sparse areas, which is conducive to the development of sparse areas. In addition, combined with Meta-Lamarckian learning strategy, based on four crossover operators (horizontal crossover operator, longitudinal crossover operator, elite crossover operator and direct crossover operator), the local search method is adaptively selected for optimization, and its convergence performance is improved. First, the simulation is carried out in 20 test functions, and compared with MODA, MOPSO, MOJAYA, NSGA-II, MOEA/D, MOAOS and MOTEO. The experimental results showed that MOCOA-ML achieved the best inverted generational distance value and the best hypervolume value in 11 and 13 test functions, respectively. Then, MOCOA-ML is used to solve the optimal power flow problem. Taking the fuel cost, power loss and total emissions as objective functions, the tests of two-objective and three-objective bechmark problems are carried out on IEEE 30-bus system and IEEE 57-bus system. The results are compared with MOPSO, MOGWO and MSSA algorithms. The experimental results of OPF demonstrate that MOCOA-ML can find competitive solutions and ranks first in six cases. It also shows that the proposed method has obtained a satisfactory uniform Pareto front.

关键词： Optimal power flow coyote optimization algorithm Multi-objective optimization Non-dominated ranking Grid mechanism Meta-Lamarckian learning strategy

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

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

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：