检索结果-内蒙古大学图书馆

Use Of RBF Model In GOA And MPA Optimizers To Estimate The Compressive Strength Of Concrete In The HPC Model

淡江理工学刊 2023年第10期26卷 1427-1439页

作者： Mengyao Pang Gongxing Yan Jie Li Minggui Zhou

High-performance concrete (HPC) is a concrete model with high compressive strength (CS). The problem of compressive strength in concrete is of great importance to civil engineers, and HPC has been able to meet this demand. The employed of this type of concrete model has significant efficiency and durability. In concrete, other components are added to components containing water, cement, and aggregates. Pneumatic ash and Micro-silica are components added to this concrete to reduce the water to cement ratio and increase the compressive strength of concrete. The HPC concrete modeling in this study is done with the Radial Basis Function Neural Network (RBFNN) model of Artificial Intelligence models (AI), and this model uses a combination of two optimizers, grasshopper optimization algorithm (GOA) and Marine Predators algorithm (MPA), both algorithms are used and belong to a new initiative. The combination of the above model and the algorithms in the context of RBF-MPA and RBF-GOA gave the desired results. The maximum values of the RF parameter combination models RBFMPA and RBF-GOA are 97.4% and 97%, and the difference is 0.4%, which is significantly different and close to each other. The OBJs calculated by the RBF-MPA model and the RBF-GOA model are 2.4 and 2.61, respectively. The maximum mathematical SI parameters for each model are 0.0402 and 0.0424, which are provided as output for the training section of each section. The calculated errors in both hybrid models are acceptable and do not differ significantly from each other.

关键词： High-Performance Concrete Radial Basis Function grasshopper optimization algorithm Marine Predators algorithm Compressive Strength

来源：评论

学校读者我要写书评

暂无评论

Use Of RBF Model In GOA And MPA Optimizers To Estimate The Compressive Strength Of Concrete In The HPC Model

JOURNAL OF APPLIED SCIENCE AND ENGINEERING

引用

JOURNAL OF APPLIED SCIENCE AND ENGINEERING 2023年第10期26卷 1427-1439页

作者： Pang, Mengyao Yan, Gongxing Li, Jie Zhou, Minggui Chongqing Creat Vocat Coll Sch Architectural Engn Chongqing 402160 Peoples R China Luzhou Vocat & Tech Coll Sch Intelligent Construct Luzhou 646000 Sichuan Peoples R China

High-performance concrete (HPC) is a concrete model with high compressive strength (CS). The problem of compressive strength in concrete is of great importance to civil engineers, and HPC has been able to meet this demand. The employed of this type of concrete model has significant efficiency and *** concrete, other components are added to components containing water, cement, and aggregates. Pneumatic ash and Micro-silica are components added to this concrete to reduce the water to cement ratio and increase the compressive strength of concrete. The HPC concrete modeling in this study is done with the Radial Basis Function Neural Network (RBFNN) model of Artificial Intelligence models (AI), and this model uses a combination of two optimizers, grasshopper optimization algorithm (GOA) and Marine Predators algorithm (MPA), both algorithms are used and belong to a new initiative. The combination of the above model and the algorithms in the context of RBF-MPA and RBF-GOA gave the desired results. The maximum values of the RF parameter combination models RBFMPA and RBF-GOA are 97.4% and 97%, and the difference is 0.4%, which is significantly different and close to each other. The OBJs calculated by the RBF-MPA model and the RBF-GOA model are 2.4 and 2.61, respectively. The maximum mathematical SI parameters for each model are 0.0402 and 0.0424, which are provided as output for the training section of each section. The calculated errors in both hybrid models are acceptable and do not differ significantly from each other.

关键词： High -Performance Concrete Radial Basis Function grasshopper optimization algorithm Marine Predators

来源：评论

学校读者我要写书评

暂无评论

Flood spatial prediction modeling using a hybrid of meta-optimization and support vector regression modeling

引用

CATENA 2021年 199卷 105114-105114页

作者： Panahi, Mahdi Dodangeh, Esmaeel Rezaie, Fatemeh Khosravi, Khabat Hiep Van Le Lee, Moung-Jin Lee, Saro Binh Thai Pham Korea Inst Geosci & Mineral Resources KIGAM Geosci Platform Div 124 Gwahak Ro Daejeon 34132 South Korea Kangwon Natl Univ Div Sci Educ Chuncheon Si 24341 Gangwon Do South Korea Sari Agr Sci & Nat Resources Univ Dept Watershed Management POB 737 Sari Iran Korea Univ Sci & Technol Dept Geophys Explorat 217 Gajeong Ro Daejeon 305350 South Korea Sari Agr Sci & Nat Resources Univ Dept Watershed Management Engn Sari Iran Duy Tan Univ Inst Res & Dev Da Nang 550000 Vietnam Korea Environm Inst KEI Sejong Ctr Environm Data Strategy Sejong South Korea Univ Transport Technol Hanoi 100000 Vietnam

Flood spatial susceptibility prediction is the first essential step in developing flood mitigation strategies and reducing flood damage. Flood occurrence is a complex process that is not easily predicted through simple methods. This study describes optimization of support vector regression (SVR) using meta-optimization algorithms including the grasshopper optimization algorithm (GOA) and particle swarm optimization (PSO) for flood modeling at Qazvin Plain, Iran. Geospatial data including nine readily available geo-environmental flood conditioning factors (i.e., ground slope, aspect, elevation, planform curvature, profile curvature, proximity to a river, land use, lithology and rainfall) were derived. The information gain ratio (IGR) method was used to determine the relative importance of input variables. A historical flood inventory map for 43 locations was created from existing reports. The geospatial data and historical flood levels were used to construct the training and testing datasets. Then, the training dataset was used to generate flood-susceptibility maps using the optimized SVR model with the GOA and PSO algorithms. Finally, the predictive accuracy of the models was quantified using the statistical measures of root mean square error (RMSE), mean absolute error (MAE), and area under the receiver operating characteristic (ROC) curve (AUC). Although both the GOA and PSO algorithms improved SVR performance, the SVR-GOA model performed best (AUC = 0.959, RMSE = 0.31 and MSE = 0.098), followed by the SVR-PSO model (AUC = 0.959, RMSE = 0.33 and MSE = 0.11) and standalone SVR model (AUC = 0.87, RMSE = 0.35 and MSE = 0.12). Elevation, lithology and aspect had the highest IGR values and were identified as the most effective predictors of flood susceptibility.

关键词： Flood-susceptibility map Support vector regression grasshopper optimization algorithm Particle swarm optimization Qazvin Plain

来源：评论

学校读者我要写书评

暂无评论

A novel committee-based framework for modeling groundwater level fluctuations: A combination of mathematical and machine learning models using the weighted multi-model ensemble mean algorithm

引用

GROUNDWATER FOR SUSTAINABLE DEVELOPMENT 2024年 24卷

作者： Mazraeh, Adnan Bagherifar, Meysam Shabanlou, Saeid Ekhlasmand, Reza Shahid Chamran Univ Fac Earth Sci Dept Geol Ahvaz Iran Islamic Azad Univ Dept Civil Engn Shushtar Branch Shushtar Iran Islamic Azad Univ Dept Water Engn Kermanshah Branch Kermanshah Iran Guilan Univ Civil Engn Gilan Iran

water level (GWL) fluctuations simulation can be divided into three general categories: Analytical solution, conceptual or physical-based models, and data-based or data-driven models. The goal of this research is to develop the MODFLOW conceptual model and the GMDH data-driven model as single models (SMs) for GWL modeling, and then to combine these models to develop a novel mathematical-machine learning model based on a weighted multi-model ensemble mean approach (MMWEM) for a more accurate GWL simulation. For this purpose, the Miqan aquifer, located in northeastern Iran, was selected as a case study. Hydrological and hydrogeological data of the Miqan wetland for ten years (September 2013 to August 2023) with a monthly time step were used to compile models. First, the MODFLOW model was developed for one month (steady-state), then calibrated for nine years (unsteady-state), and finally tested for one year. In the second step, the GMDH model was developed. The grasshopper optimization algorithm (GOA) an d the singular value decomposition (SVD) algorithms were used to determine the Ivakhnenko polynomial coefficients of the GMDH (SVD-GMDH and GOAGMDH). 80% of the data was used to develop SVD-GMDH and GOA-GMDH, and other data was used to test models. Consequently, the sequential forward floating selection (SFFS) method was used to select the best input variables for the SVD-GMDH and GOA-GMDH. The coefficient of determination (R2), root mean squared error (RMSE), and Nash-Sutcliffe Efficiency coefficient (NSE) were used to evaluate the performance of the models. Based on the results of this study, using each of the SMs, GWL can be simulated with acceptable accuracy. However, a closer examination of the results of SMs showed that the MODFLOW has the worst performance among SMs, while the GOA-GMDH has the best function for simulating GWL. In the third step, SMs was used to develop the MMWEM. The GWL of 13 of the 34 piezometers studied in this study was better simulated with

关键词： Groundwater level MODFLOW Group method of data handling Singular value decomposition Metaheuristic grasshopper optimization algorithm Machine learning Weighted multi-model ensemble mean approach Data-driven model Process-based model

来源：评论

学校读者我要写书评

暂无评论

Intelligent optimization of process parameters to corn straw pretreatment

Intelligent optimization of process parameters to corn straw...

引用

第34届中国控制与决策会议

作者： Yalin Guan Juan Chen College of Information Science and Technology Beijing University of Chemical Technology

For the optimization of pretreatment process parameters of corn straw,an intelligent optimization method is used,which combines the prediction model and the optimization *** support vector machine(SVM)prediction model for biogas production is *** the optimal process parameters are obtained by grasshopper optimization algorithm(GOA) on the prediction *** to the difficulty of obtaining experimental data,the problem of small samples during the model training ***,the virtual samples are generated by uniform interpolation combined with GOA to improve the model prediction *** the experiment of dual-frequency ultrasound combined with alkali pretreatment of corn stover fermentation,the effectiveness of virtual sample generation and the feasibility of intelligent process parameter search are verified.

关键词： Corn Straw optimization of Process Parameters Virtual Sample grasshopper optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

ECOPICA: empirical copula-based independent component analysis

引用

Statistics and Computing 2024年第1期34卷 52-52页

作者： Pi, Hung-Kai Guo, Mei-Hui Chen, Ray-Bing Huang, Shih-Feng Department of Applied Mathematics National Sun Yat-sen University Kaohsiung 804 Taiwan Department of Statistics National Cheng Kung University Tainan 701 Taiwan Graduate Institute of Statistics National Central University Taoyuan 320 Taiwan

This study proposes a non-parametric ICA method, called ECOPICA, which describes the joint distribution of data by empirical copulas and measures the dependence between recovery signals by an independent test statistic. We employ the grasshopper algorithm to optimize the proposed objective function. Several acceleration tricks are further designed to enhance the computational efficiency of the proposed algorithm under the parallel computing framework. Our simulation and empirical analysis show that ECOPICA produces better and more robust recovery performances than other well-known ICA approaches for various source distribution shapes, especially when the source distribution is skewed or near-Gaussian. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

关键词： Blind image separation Cocktail-party problem Copula grasshopper optimization algorithm Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

Optimizing pumped-storage power station operation for boosting power grid absorbability to renewable energy

引用

Energy Conversion and Management 2024年 299卷

作者： Yanlai Zhou Yuxin Zhu Qi Luo Yilong Wei Yadong Mei Fi-John Chang State Key Laboratory of Water Resources Engineering and Management Wuhan University Wuhan 430072 China Department of Bioenvironmental Systems Engineering National Taiwan University Taipei 10617 Taiwan

Optimizing peak-shaving and valley-filling (PS-VF) operation of a pumped-storage power (PSP) station has far-reaching influences on the synergies of hydropower output, power benefit, and carbon dioxide (CO 2 ) emission reduction. However, it is a great challenge, especially considering hydro-wind-photovoltaic-biomass power inputs. This study proposed a novel optimization operation framework for a PSP station driven by the PS-VF operation for boosting power grid absorbability to renewable energy inputs. An optimization operation model based on a grasshopper optimization algorithm was developed to minimize the residual load volatility. A PSP station in the Hunan Province of China constituted the case study, and the practical operation scheme formed the benchmark. The findings underscore the effectiveness of the proposed approach in fostering remarkable synergy, evident in substantial improvement rates of 61% for power output, 58% for power benefit, and 62% for CO 2 emission reduction compared to the practical operational scheme. This study not only furnishes valuable scientific and technical backing for the PS-VF operation of the PSP station, enhancing the interplay between hydropower generation, financial benefits, and CO 2 reduction, but also provides policymakers with well-informed strategies that consider potential load volatilities and advantages. These strategies are geared towards enhancing the power grid's capacity to assimilate hydro-wind-photovoltaic-biomass power inputs, aligning with the goals of sustainable renewable energy development.

关键词： Pumped-storage operation Energy management Intelligent optimization grasshopper optimization algorithm China

来源：评论

学校读者我要写书评

暂无评论

Application of deep learning to predict the low serum albumin in new hemodialysis patients

引用

Nutrition & metabolism 2023年第1期20卷 24页

作者： Cheng-Hong Yang Yin-Syuan Chen Jin-Bor Chen Hsiu-Chen Huang Li-Yeh Chuang Department of Information Management Tainan University of Technology Tainan Taiwan. Department of Electronic Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan. Program in Biomedical Engineering Kaohsiung Medical University Kaohsiung Taiwan. School of Dentistry Kaohsiung Medical University Kaohsiung Taiwan. Drug Development and Value Creation Research Center Kaohsiung Medical University Kaohsiung Taiwan. Department of Internal Medicine Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine Kaohsiung Taiwan. chenjb1019@***. Department of Community Health Chia-Yi Christian Hospital Chia-Yi City Taiwan. 03281@cych.org.tw. Department of Chemical Engineering and Institute of Biotechnology and Chemical Engineering I-Shou University Kaohsiung Taiwan. chuang@isu.edu.tw.

BACKGROUND:Serum albumin level is a crucial nutritional indicator for patients on dialysis. Approximately one-third of patients on hemodialysis (HD) have protein malnutrition. Therefore, the serum albumin level of patients on HD is strongly correlated with mortality. METHODS:In study, the data sets were obtained from the longitudinal electronic health records of the largest HD center in Taiwan from July 2011 to December 2015, included 1,567 new patients on HD who met the inclusion criteria. Multivariate logistic regression was performed to evaluate the association of clinical factors with low serum albumin, and the grasshopper optimization algorithm (GOA) was used for feature selection. The quantile g-computation method was used to calculate the weight ratio of each factor. Machine learning and deep learning (DL) methods were used to predict the low serum albumin. The area under the curve (AUC) and accuracy were calculated to determine the model performance. RESULTS:Age, gender, hypertension, hemoglobin, iron, ferritin, sodium, potassium, calcium, creatinine, alkaline phosphatase, and triglyceride levels were significantly associated with low serum albumin. The AUC and accuracy of the GOA quantile g-computation weight model combined with the Bi-LSTM method were 98% and 95%, respectively. CONCLUSION:The GOA method was able to rapidly identify the optimal combination of factors associated with serum albumin in patients on HD, and the quantile g-computation with DL methods could determine the most effective GOA quantile g-computation weight prediction model. The serum albumin status of patients on HD can be predicted by the proposed model and accordingly provide patients with better a prognostic care and treatment.

关键词： Deep learning grasshopper optimization algorithm Hemodialysis Quantile g-computation Serum albumin

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：