检索结果-内蒙古大学图书馆

Forecasting Monthly Water Deficit Based on multi-variable linear regression and Random Forest Models

WATER 2023年第6期15卷 1075页

作者： Li, Yi Wei, Kangkang Chen, Ke He, Jianqiang Zhao, Yong Yang, Guang Yao, Ning Niu, Ben Wang, Bin Wang, Lei Feng, Puyu Yang, Zhe Northwest A&F Univ Coll Water Resources & Architecture Engn Key Lab Agr Soil & Water Engn Arid & Semiarid Area Minist Educ Xianyang 712100 Peoples R China China Inst Water Resources & Hydropower Res State Key Lab Simulat & Regulat Water Cycle River Beijing 100038 Peoples R China Univ Shihezi Coll Water Conservancy & Architectural Engn Shihezi 832003 Peoples R China Wagga Wagga Agr Inst NSW Dept Primary Ind Wagga Wagga NSW 2650 Australia China Agr Univ Coll Land Sci & Technol Beijing 100193 Peoples R China

Forecasting water deficit is challenging because it is modulated by uncertain climate, different environmental and anthropic factors, especially in arid and semi-arid northwestern China. The monthly water deficit index D at 44 sites in northwestern China over 1961-2020 were calculated. The key large-scale circulation indices related to D were screened using Pearson's correlation (r). Subsequently, we predicted monthly D with the multi-variable linear regression (MLR) and random forest (RF) models at certain lagged times after being strictly calibrated and validated. The results showed the following: (1) The r between the monthly D and the screened key circulation indices varied from 0.71 to 0.85 and the lagged time ranged from 1 to 12 months. (2) The calibrated and validated performance of the established MLR and RF models were all good at the 44 sites. Overall, the RF model outperformed the MLR model with a higher coefficient of determination (R-2 > 0.8 at 38 sites) and mean absolute percentage error (MAPE < 50% at 30 sites). (3) The Pacific Polar Vortex Intensity (PPVI) had the greatest impact on D in northwestern China, followed by SSRP, WPWPA, NANRP, and PPVA. (4) The forecasted monthly D values based on RF models indicated that the water deficit in northwestern China would be most severe (-239.7 to -62.3 mm) in August 2022. In conclusion, using multiple large-scale climate signals to drive a machine learning model is a promising method for predicting water deficit conditions in northwestern China.

关键词： monthly water deficit circulation indices random forest multi-variable linear regression northwestern China

来源：评论

学校读者我要写书评

暂无评论

Integrated metaheuristic approaches for estimation of fracture porosity derived from fullbore formation micro-imager logs: Reaping the benefits of stand-alone and ensemble machine learning models

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 139卷

作者： Vijouyeh, Ali Gholami Hamoudi, Maha Raoof Bayz, Dyana Aziz Kadkhodaie, Ali Univ Tabriz Fac Nat Sci Dept Earth Sci Tabriz East Azerbaijan Iran Univ Kurdistan Hewler Dept Nat Resources Engn & Management Erbil Iraq Knowledge Univ Coll Engn Dept Petr Engn Erbil Iraq

Fracture porosity is one of the most effective parameters for reservoir productivity and recovery efficiency. This study aims to predict and improve the accuracy of fracture porosity estimation through the application of advanced machine learning (ML) algorithms. A novel approach was introduced for the first time to estimate fracture porosity by reaping the benefits of petrophysical and fullbore formation micro-imager (FMI) data based on employing various stand-alone, ensemble, optimisation and multi-variable linear regression (MVLR) algorithms. This study proposes a ground-breaking two-step committee machine (CM) model. Petrophysical data containing compressional sonic-log travel time, deep resistivity, neutron porosity and bulk density (inputs), along with FMI-derived fracture porosity values (outputs), were employed. Nine stand-alone ML algorithms, including back-propagation neural network, Takagi and Sugeno fuzzy system, adaptive neuro-fuzzy inference system, decision tree, radial basis function, extreme gradient boosting, least-squares boosting, least squares support vector regression and k-nearest neighbours, were trained for initial estimation. To improve the efficacy of stand-alone algorithms, their outputs were combined in CM structures using optimisation algorithms. This integration was applied through five optimisation algorithms, including genetic algorithm, ant colony, particle swarm, covariance matrix adaptation evolution strategy (CMA-ES) and Coyote optimisation algorithm. Considering the lowest error, the CM with CMA-ES showed superior performance. Subsequently, MVLR was employed to improve the CMs further. Employing MVLR to combine the CMs yielded a 57.85% decline in mean squared error and a 4.502% improvement in the correlation coefficient compared to the stand-alone algorithms. The results of the benchmark analysis validated the efficacy of this approach.

关键词： Fracture porosity Fullbore formation micro-imager Petrophysical well logs multi-variable linear regression Optimisation Committee machine

来源：评论

学校读者我要写书评

暂无评论

Short Term Load Forecasting using multiple linear regression for Big Data

Short Term Load Forecasting using Multiple Linear Regression...

引用

IEEE Symposium Series on Computational Intelligence (IEEE SSCI)

作者： Saber, Ahmed Yousuf Alam, A. K. M. Rezaul ETAP R&D Irvine CA 92618 USA Univ Asia Pacific Dhaka Bangladesh

ISBN: (纸本)9781538627266

This paper presents short term load forecasting using multi-variable linear regression (MLR) for big data. Load forecasting is very important for planning, operation, resource scheduling and so on in power system. Total electric demand dynamically changes in a power system and mainly depends on temperature, humidity, wind speed, human nature, regular activities, events, etc. input variables. For the help of sensors and data science, enough historical and future input data with good accuracy are easily available. On the other hand, linear regression is a proven method, widely used in industries for forecasting. It is deterministic and robust. However, it is slow for big data because it needs large size matrix operations. In this paper, linear regression is formulated for small number of variables with big data and multi-core parallel processing is applied in all matrix operations that allow unlimited historical big data and unlimited scenarios in acceptable execution time limit. Mean absolute percent error is 3.99% of real field recorded data shown in Simulation and Result section.

关键词： multi-variable linear regression Short Term Load Forecasting multi-core Parallel Processing Big Data

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the importance of various operating and sludge property parameters to the fouling of membrane bioreactors

引用

WATER SCIENCE AND TECHNOLOGY 2011年第6期64卷 1340-1346页

作者： Sun, F. Y. Li, X. Y. Univ Hong Kong Dept Civil Engn Hong Kong Hong Kong Peoples R China Shenzhen Grad Sch Harbin Inst Technol Shenzhen 518055 Peoples R China

A single-fibre microfiltration system was employed to investigate the importance of various operating and sludge property parameters to the membrane fouling during sludge filtration. The sludge was obtained from a submerged membrane bioreactor (SMBR). A series of comparative and correlative filtration and fouling tests were conducted on the influence of the operating variables, sludge properties and the liquid-phase organic substances on the membrane fouling development. The test results were analysed statistically with Pearson's correlation coefficients and the stepwise multi-variable linear regression. According to the statistical evaluation, the membrane fouling rate has a positive correlation with the biopolymer cluster (BPC) concentration, sludge concentration (mixed liquor suspended solids, MLSS), filtration flux and viscosity, a negative correlation with the cross-flow velocity, and a weak correlation with the extracellular polymeric substances and soluble microbial products. BPC appear to be the most important factor to membrane fouling development during the sludge filtration, followed by the filtration flux and MLSS concentration. The cross-flow rate also is important to the fouling control. It is argued that, during membrane filtration of SMBR sludge, BPC interact with sludge flocs at the membrane surface to facilitate the deposition of the sludge cake layer, leading to serious membrane fouling.

关键词： biopolymer clusters membrane bioreactor membrane fouling microfiltration multi-variable linear regression

来源：评论

学校读者我要写书评

暂无评论

Amino acid profiles and quantitative structure-property relationships for malts and beers

引用

FOOD RESEARCH INTERNATIONAL 2010年第4期43卷 965-971页

作者： Pomilio, Alicia B. Duchowicz, Pablo R. Giraudo, Miguel A. Castro, Eduardo A. Univ Buenos Aires Fac Farm & Bioquim Div Quim Estruct & Espectroscopia PRALIBCONICET RA-1113 Buenos Aires DF Argentina Univ Nacl La Plata INIFTA CONICET CCT La Plata La Plata Buenos Aires Argentina Univ Nacl Lanus Buenos Aires DF Argentina

Experimental amino acid concentrations of blonde and black commercial beers, brewed in Argentina, as well as national malts were subjected for the first time to Quantitative Structure-Property Relationships (QSPRs). Thus, Dragon theoretical descriptors were derived for a set of optimised amino acid structures with the purpose of assessing QSPR models. We used the statistical Replacement Method for designing the best multi-parametric linear regression models, which included structural features selected from a pool containing 1497 constitutional-, topological-, geometrical-, and electronic-type molecular descriptors. In this work QSPR results were in good agreement with experimental amino acid profiles, thus demonstrating the predictive power of the designed QSPRs. QSPR-modelling was used to predict aminograms, and was also used to estimate non-available amino acid concentrations for these malts, and beers. The developed QSPR approach showed to be an useful tool for discriminating among blonde and dark beers, and malts. This is a new application of the QSPR theory to food, in particular to chemical biomarkers of malts and beers. (C) 2010 Elsevier Ltd. All rights reserved.

关键词： Quantitative structure-property relationships multi-variable linear regression Replacement method Aminograms Malts Blonde and black beers

来源：评论

学校读者我要写书评

暂无评论

Investigation into micro abrasive intermittent jet machining

引用

INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE 2005年第7-8期45卷 873-879页

作者： Zhang, L Kuriyagawa, T Yasutomi, U Zhao, J Jilin Univ Sch Mech Sci & Engn Changchun 130025 Peoples R China Tohoku Univ Dept Mechatron & Precis Engn Aoba Ku Sendai Miyagi 9808579 Japan

In the machining of small holes by the conventional micro abrasive jet machining, the colliding abrasives accumulate in the bottom of the hole, preventing the direct impact of successive abrasives onto the workpiece. As a result, the machining efficiency decreases as the machining progresses. This paper introduces a new method of micro abrasive jet machining, called micro abrasive intermittent jet machining (MAIJM), in which there exists a period of time during which no abrasive is injected into the gas stream from the nozzle so that the continuous flow of gas without abrasives from the nozzle could blow away any abrasives that have accumulated in the hole. Empirical models are developed for evaluation of the effect of MAIJM process parameters on the shape of the machined holes by proper design of experiments based on a Taguchi orthogonal array and by multi-variable linear regression. Further experiments are conducted to confirm the validity of the developed statistical model by comparing the model predictions with the experimental results. (c) 2004 Elsevier Ltd. All rigts reserved.

关键词： micro abrasive intermittent jet machining Taguchi method multi-variable linear regression

来源：评论

学校读者我要写书评

暂无评论

Quantitative structure-property relationship analyses of aminograms in food: Hard cheeses

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 2011年第2期107卷 384-390页

作者： Duchowicz, Pablo R. Giraudo, Miguel A. Castro, Eduardo A. Pomilio, Alicia B. Univ Nacl La Plata CCT La Plata CONICET Inst Invest Fisicoquim Teor & Aplicadas INIFTA La Plata Buenos Aires Argentina Univ Nacl Lanus Lanus Buenos Aires Argentina Univ Buenos Aires Fac Farm & Bioquim CONICET UBAPRALIB RA-1113 Buenos Aires DF Argentina

The concentrations of the amino acids of Reggianito Argentino and Goya full-ripened industrial Argentine hard cheeses were subjected to quantitative structure-property relationship (QSPR) models. We used the statistical Replacement Method technique for designing the best multi-parametric linear regression models, which included structural features selected from a pool containing 1497 molecular descriptors. Predicted QSPR values were in good agreement with experimental amino acid profiles carried out in our laboratories. The developed approach is of practical value, especially to assign unknown analyte concentrations for Reggianito Argentino and Goya cheeses, and to establish whether any cheese sample belongs to these kinds of hard cheeses. (C) 2011 Elsevier B.V. All rights reserved.

关键词： Quantitative structure-property relationship theory Reggianito Argentino and Goya cheeses Aminograms multi-variable linear regression Replacement method

来源：评论

学校读者我要写书评

暂无评论

Investigation into electrorheological fluid-assisted polishing

引用

INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE 2005年第12-13期45卷 1461-1467页

作者： Zhang, L Kuriyagawa, T Kaku, T Zhao, J Jilin Univ Sch Mech Sci & Engn Changchun 130025 Jilin Province Peoples R China Tohoku Univ Dept Mechatron & Precis Engn Aoba Ku Sendai Miyagi 9808579 Japan

Electrorheological fluid (ER fluid) is a functional fluid with the property that its viscosity can vary with the applied electric field strength. This paper investigates a polishing method using the electrorheological fluid, known as ER fluid-assisted polishing, for the finishing of micro dies of tungsten carbide alloy, which are used for the mass production of micro aspheric glass lens. The machining principle of the ER fluid-assisted polishing is introduced. By proper design of experiments based on a Taguchi orthogonal array and by multi-variable linear regression, empirical models are developed for evaluation of the effect of the process parameters on the material removal depth and surface roughness obtained in the ER fluid-assisted polishing. Further experiments are conducted to confirm the validity of the developed statistical model by comparing the model predictions with the experimental results and meanwhile the influences of the process parameters on the polishing performance are revealed. (c) 2005 Elsevier Ltd. All rights reserved.

关键词： electrorheological fluid polishing Taguchi method multi-variable linear regression

来源：评论

学校读者我要写书评

暂无评论

ESTIMATING CAPITAL AND OPERATIONAL COSTS OF BACKHOE SHOVELS

引用

JOURNAL OF CIVIL ENGINEERING AND MANAGEMENT 2012年第3期18卷 378-385页

作者： Sayadi, Ahmad Reza Lashgari, Ali Fouladgar, Mohammad Majid Skibniewski, Miroslaw J. Tarbiat Modares Univ Dept Min Engn Tehran Iran Bialystok Tech Univ Dept Management PL-16001 Kleosin Poland

Material loading is one of the most critical operations in earthmoving projects. A number of different equipment is available for loading operations. Project managers should consider different technical and economic issues at the feasibility study stage and try to select the optimum type and size of equipment fleet, regarding the production needs and project specifications. The backhoe shovel is very popular for digging, loading and flattening tasks. Adequate cost estimation is one of the most critical tasks in feasibility studies of equipment fleet selection. This paper presents two different cost models for the preliminary and detailed feasibility study stages. These models estimate the capital and operating cost of backhoe shovels using uni-variable exponential regression (UVER) as well as multi-variable linear regression (MVLR), based on principal component analysis. The UVER cost model is suitable for quick cost estimation at the early stages of project evaluation, while the MVLR cost function, which is more detailed, can be useful for the feasibility study stage. Independent variables of MVLR include bucket size, digging depth, dump height, weight and power. Model evaluations show that these functions could be a credible tool for cost estimations in prefeasibility and feasibility studies of mining and construction projects.

关键词： loading equipment backhoe shovel cost estimation multi-variable linear regression principal component analysis mining and construction

来源：评论

学校读者我要写书评

暂无评论

QSPR analyses for aminograms in food: Citrus juices and concentrates

引用

FOOD CHEMISTRY 2010年第3期123卷 917-927页

作者： Pomilio, Alicia B. Giraudo, Miguel A. Duchowicz, Pablo R. Castro, Eduardo A. Univ Buenos Aires Fac Farm & Bioquim CONICET PRALIB RA-1113 Buenos Aires DF Argentina Univ Nacl Lanus Lanus Buenos Aires Argentina Univ Nacl La Plata CCT La PlataCONICET INIFTA La Plata Buenos Aires Argentina

Dragon theoretical descriptors were derived for a set of optimised amino acid structures, with the purpose of establishing quantitative structure-property relationship (QSPR) models to predict aminograms for 100% natural fresh juices and concentrates of Navel and Valencia oranges, and Eureka lemon. We used the statistical replacement method technique for designing the best multi-parametric linear regression models, which included structural features selected from a pool containing 1497 constitutional, topological, geometrical, or electronic types of molecular descriptors. The prediction results achieved in this work were in most cases in good agreement with experimental amino acid profiles obtained in our laboratories by a validated HPLC procedure, thus demonstrating the predictive power of the designed QSPR. The developed approach is of practical value, especially when it is not possible to assign the analyte concentration with an accurate degree of certainty. (C) 2010 Elsevier Ltd. All rights reserved.

关键词： QSPR theory Amino acids Citrus juices and concentrates Navel and Valencia oranges Eureka lemon Aminograms multi-variable linear regression Replacement method

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：