检索结果-内蒙古大学图书馆

Building optimal regression tree by ant colony system-genetic algorithm: Application to modeling of melting points

ANALYTICA CHIMICA ACTA 2011年第1-2期704卷 57-62页

作者： Hemmateenejad, Bahram Shamsipur, Mojtaba Zare-Shahabadi, Vali Akhond, Morteza Shiraz Univ Dept Chem Shiraz Iran Shiraz Univ Med Sci Med & Nat Prod Chem Res Ctr Shiraz Iran Razi Univ Dept Chem Kermanshah Iran Islamic Azad Univ Mahshahr Branch Mahshahr Iran

The classification and regression trees (CART) possess the advantage of being able to handle large data sets and yield readily interpretable models. A conventional method of building a regression tree is recursive partitioning, which results in a good but not optimal tree. Ant colony system (ACS), which is a metaheuristic algorithm and derived from the observation of real ants, can be used to overcome this problem. The purpose of this study was to explore the use of CART and its combination with ACS for modeling of melting points of a large variety of chemical compounds. Genetic algorithm (GA) operators (e.g., cross averring and mutation operators) were combined with ACS algorithm to select the best solution model. In addition, at each terminal node of the resulted tree, variable selection was done by ACS-GA algorithm to build an appropriate partial least squares (PLS) model. To test the ability of the resulted tree, a set of approximately 4173 structures and their melting points were used (3000 compounds as training set and 1173 as validation set). Further, an external test set containing of 277 drugs was used to validate the prediction ability of the tree. Comparison of the results obtained from both trees showed that the tree constructed by ACS-GA algorithm performs better than that produced by recursive partitioning procedure. (C) 2011 Elsevier B.V. All rights reserved.

关键词： Ant colony system classification and regression tree Genetic algorithm Melting points Quantitative structure-property relationship

来源：评论

学校读者我要写书评

暂无评论

A demand trend change early warning forecast model for the city of Sao Paulo multi-airport system

引用

TRANSPORTATION RESEARCH PART A-POLICY AND PRACTICE 2014年 65卷 23-32页

作者： Scarpel, Rodrigo Arnaldo ITA Sao Jose Dos Campos Brazil

The need of accurate forecasts of air passenger numbers to assist managerial decision making for both short and long terms is well recognized and a central problem on both short and long term forecasting is how to handle future trend. The aim of this paper is to develop a demand trend change early warning forecast model (EWFM) for the city of Sao Paulo multi-airport system (SPMARs). For SPMARs the EWFM is based on the combination of leading indicators and alarms against possible occurrence of changes on trend component of the monthly number of domestic air passengers. A topdown induction procedure is employed to identify leading indicators to provide an interpretable prediction procedure to support the development of scenarios for future demand trend. Results show that changes on such demand trend are mostly associated to changes on the economic activity and six different scenarios were built combining the identified leading indicators. The EWFM was employed to assist managerial decision making for both short and long terms in order to evaluate different alternatives to prevent congestion delay occurrences and to support infrastructure planning. (C) 2014 Elsevier Ltd. All rights reserved.

关键词： Scenarios Short-term fluctuations Long-term forecasting classification and regression tree Air passenger numbers

来源：评论

学校读者我要写书评

暂无评论

Hybridized intelligent multi-class classifiers for rockburst risk assessment in deep underground mines

引用

NEURAL COMPUTING & APPLICATIONS 2024年第4期36卷 1681-1698页

作者： Shirani Faradonbeh, Roohollah Vaisey, Will Sharifzadeh, Mostafa Zhou, Jian Curtin Univ WA Sch Mines Minerals Energy & Chem Engn Kalgoorlie WA 6430 Australia Cent South Univ Sch Resources & Safety Engn Changsha 410083 Peoples R China

The rockburst hazard induced by the extreme release of the stress concentrated in rock mass in deep underground mines poses a significant threat to the safety and economy of the mining projects. Therefore, properly managing this hazard is critical for ensuring rock engineering projects' sustainability. This study proposes comprehensible and practical classifiers for rockburst risk level appraisal by hybridizing K-means clustering with gene expression programming, GEP, logistic regression, LR, and classification and regression tree, CART (i.e., K-mean-GEP-LR and K-means-CART classifiers). A database containing 246 rockburst events with four risk levels of none, light, moderate, and severe was compiled from previous practices. Preliminary statistical analyses were conducted to detect the extreme outliers and determine the critical rockburst indicators. The K-means clustering analysis was performed to identify the main clusters within the database and relabel the rockburst events. The GEP algorithm was then utilized to develop binary models for predicting the occurrence of each class. Then, the likelihood of each class occurrence was determined using LR. Furthermore, the K-means clustering was combined with the CART algorithm to provide another visual tree structure model. The classifiers' performance evaluation showed 96% and 95% accuracy values in the training and testing stages, respectively, for the K-means-GEP-LR model, while the accuracy values of 98.8% and 93.0% were obtained for the foregoing stages for the K-means-CART classifier. The results showed the robustness and high classification capability of both models. MatLab codes were also provided for the K-means-GEP-LR model, which assists other researchers/engineers in implementing the model in practice.

关键词： Rockburst risk level Gene expression programming Logistic regression classification and regression tree Multi-class classification

来源：评论

学校读者我要写书评

暂无评论

Management zone delineation based on soil properties measured during the reproductive stage of rice in the field

引用

LAND DEGRADATION & DEVELOPMENT 2021年第10期32卷 3106-3121页

作者： Wang, Mingming Tavakkoli, Ehsan Rengasamy, Pichu Huang, Lihua Ma, Hongyuan Yang, Fu Wei, Tianjiao Lu, Xinrui Xu, Zhongchun Fang, Yunying Liang, Zhengwei Chinese Acad Sci Northeast Inst Geog & Agroecol Changchun 130102 Jilin Peoples R China Chinese Acad Sci Daan Sodic Land Expt Stn Daan Peoples R China Chinese Acad Sci Key Lab Mollisols Agroecol Changchun Peoples R China Univ Adelaide Adelaide SA Australia Wagga Wagga Agr Inst NSW Dept Primary Ind Wagga Wagga NSW Australia Guizhou Univ Sch Publ Adm Guiyang Peoples R China Elizabeth Macarthur Agr Inst NSW Dept Primary Ind Menangle NSW Australia

Identification of key soil properties is an essential prerequisite to delineating the management zone (MZ), which is traditionally done by selecting soil parameters before crop planting. However, soil properties during sensitive stages of crop growth may have a greater effect on the MZ delineation than those before planting. This study is aimed to determine whether inclusion of soil properties measured in surface layers during the reproductive stage of rice could enhance the appropriateness of MZ delineation based on sodic/saline-sodic paddy fields. When including soil variables during the reproductive stage, with/without soil variables before planting, a similar MZ pattern (MZ pattern 3) was generated. Furthermore, when including soil variables during the reproductive stage and rice yield components, with/without soil variables before planting, another similar MZ pattern (MZ Pattern 4) was generated. Compared with other patterns, the MZ pattern 4 showed higher relative variances for rice yield and the mean of its most important yield-influencing factors, with lower coefficient of variation (CV) in all MZs compared with the whole-paddock CV. Likewise, this pattern showed improvement in discriminating soil and rice variables among MZs. These findings confirm that inclusion of soil properties during the reproductive stage of rice has potential for enhancing the appropriateness of MZ delineation. This study also necessitates inclusion of carbonate-derived variables when delineating MZs in sodic/saline-sodic paddy fields. Our results encourage further investigation of the role of soil properties in surface soil layers at critical crop growth stages in MZ delineation under multiple soil and climatic conditions.

关键词： classification and regression tree management zone delineation salt‐ affected soil sampling depth sensitive crop growth stages

来源：评论

学校读者我要写书评

暂无评论

A comparison of advanced computational models and experimental techniques in predicting blast-induced ground vibration in open-pit coal mine

引用

ACTA GEOPHYSICA 2019年第4期67卷 1025-1037页

作者： Hoang Nguyen Xuan-Nam Bui Moayedi, Hossein Duy Tan Univ Inst Res & Dev Da Nang 550000 Vietnam Hanoi Univ Min & Geol Min Fac Dept Surface Min Duc Thang Ward 18 Pho Vien Hanoi Vietnam Hanoi Univ Min & Geol Ctr Min Electromech Res Duc Thang Ward 18 Pho Vien Hanoi Vietnam Ton Duc Thang Univ Dept Management Sci & Technol Dev Ho Chi Minh City Vietnam Ton Duc Thang Univ Fac Civil Engn Ho Chi Minh City Vietnam

Green mining is an essential requirement for the development of the mining industry. Of the operations in mining technology, blasting is one of the operations that significantly affect the environment, especially ground vibration. In this paper, four artificial intelligence (AI) models including artificial neural network (ANN), k-nearest neighbor (KNN), support vector machine (SVM), and classification and regression tree (CART) were developed as the advanced computational models for estimating blast-induced ground vibration in a case study of Vietnam. Some empirical techniques were applied and developed to predict ground vibration and compared with the four AI models as well. For this research, 68 events of blasting were collected;80% of the whole datasets were used to build the mentioned models, and the rest 20% were used for testing/checking the models' performances. Mean absolute error (MAE), determination coefficient (R-2), and root-mean-square error (RMSE) were used as the standards to evaluate the quality of the models in this study. The results indicated that the advanced computational models were much better than empirical techniques in estimating blast-induced ground vibration in the present study. The ANN model (2-6-8-6-1) was introduced as the most superior model for predicting ground vibration with an RMSE of 0.508, R-2 of 0.981 and MAE of 0.405 on the testing dataset. The SVM, CART, and KNN models provided poorer performance with an RMSE of 1.192, 2.820, 1.878;R-2 of 0.886, 0.618, 0.737;and MAE of 0.659, 1.631, 0.762, respectively.

关键词： Support vector machine classification and regression tree k-nearest neighbor Artificial neural network Ground vibration Open-pit mine

来源：评论

学校读者我要写书评

暂无评论

Exploring correlations in gene expression microarray data for maximum predictive-minimum redundancy biomarker selection and classification

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2013年第10期43卷 1437-1443页

作者： Arevalillo, Jorge M. Navarro, Hilario Univ Nacl Educ Distancia Dept Stat Operat Res & Numer Anal E-28040 Madrid Spain

An important issue in the analysis of gene expression microarray data is concerned with the extraction of valuable genetic interactions from high dimensional data sets containing gene expression levels collected for a small sample of assays. Past and ongoing research efforts have been focused on biomarker selection for phenotype classification. Usually, many genes convey useless information for classifying the outcome and should be removed from the analysis;on the other hand, some of them may be highly correlated, which reveals the presence of redundant expressed information. In this paper we propose a method for the selection of highly predictive genes having a low redundancy in their expression levels. The predictive accuracy of the selection is assessed by means of classification and regression trees (CART) models which enable assessment of the performance of the selected genes for classifying the outcome variable and will also uncover complex genetic interactions. The method is illustrated throughout the paper using a public domain colon cancer gene expression data set. (C) 2013 Elsevier Ltd. All rights reserved.

关键词： Microarray data Gene expression Biomarker selection classification and prediction Redundancy classification and regression tree

来源：评论

学校读者我要写书评

暂无评论

BiMM tree: a decision tree method for modeling clustered and longitudinal binary outcomes

引用

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION 2020年第4期49卷 1004-1023页

作者： Speiser, Jaime Lynn Wolf, Bethany J. Chung, Dongjun Karvellas, Constantine J. Koch, David G. Durkalski, Valerie L. Wake Forest Sch Med Dept Biostat Sci Winston Salem NC 27157 USA Med Univ South Carolina Dept Publ Hlth Sci Charleston SC USA Univ Alberta Div Hepatol Edmonton AB Canada Univ Alberta Div Crit Care Med Edmonton AB Canada Med Univ South Carolina Dept Med Div Gastroenterol & Hepatol Charleston SC USA

Clustered binary outcomes are frequently encountered in clinical research (e.g. longitudinal studies). Generalized linear mixed models (GLMMs) for clustered endpoints have challenges for some scenarios (e.g. data with multi-way interactions and nonlinear predictors unknown a priori). We develop an alternative, data-driven method called Binary Mixed Model (BiMM) tree, which combines decision tree and GLMM within a unified framework. Simulation studies show that BiMM tree achieves slightly higher or similar accuracy compared to standard methods. The method is applied to a real dataset from the Acute Liver Failure Study Group.

关键词： classification and regression tree clustered data decision tree longitudinal data mixed effects

来源：评论

学校读者我要写书评

暂无评论

The Knowledge Discovery of the Nuclear Power Issue Using: the Artificial Intelligence Model: An Example of the CART and the SVM

引用

JOURNAL OF INTERNET TECHNOLOGY 2016年第6期17卷 1071-1082页

作者： Chung, Yueh-Shiun Ho, Mei Hsiu-Ching Huang, Sun-Jen Liang, Shih-Wu Natl Taiwan Univ Sci & Technol Dept Informat Management Taipei Taiwan Natl Taiwan Univ Sci & Technol Grad Inst Technol Management Taipei Taiwan Shih Hsin Univ Dept Publ Relat & Advertising Taipei Taiwan

After the nuclear accidents in the Fukushima Daiichi Nuclear Power Plant, the public has become increasingly concerned about nuclear power policies. We employed the CART and the SVM methods to establish and compare classification patterns in order to reveal obscure information in the survey data of Nuclear Power Policy'. Our results showed that the total classification accuracy of the CART is higher than that of SVM or logistic regression. 48.87% of the Taiwanese public opposed nuclear power, 34.16% supported nuclear power, and 16.97% did not respond to the question. However, the CART analysis showed that among the non-respondents, 56% supported nuclear power and 44% opposed its use. The two primary factors influencing the opinion for nuclear power are "satisfaction with the safety of nuclear power" and "improvement in safety inspection and disaster prevention standards in nuclear power plants." Therefore, by improving the safety of nuclear power plant, the government might regain public support for nuclear power.

关键词： Artificial intelligence classification and regression tree Support vector machine Logistic regression Nuclear power issue

来源：评论

学校读者我要写书评

暂无评论

A novel dendrochronological approach reveals drivers of carbon sequestration in tree species of riparian forests across spatiotemporal scales

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2017年 574卷 1261-1275页

作者： Rieger, Isaak Kowarik, Ingo Cherubini, Paolo Cierjacks, Arne Tech Univ Berlin Dept Ecol Ecosyst Sci Plant Ecol Rothenburgstr 12 D-12165 Berlin Germany Berlin Brandenburg Inst Adv Biodivers Res BBIB D-14195 Berlin Germany WSL Swiss Fed Inst Forest Snow & Landscape Res Zurcherstr 111 CH-8903 Birmensdorf Switzerland Univ Hamburg Bioctr Klein Flottbek Biodivers Useful Plants Ohnhorststr 18 D-22609 Hamburg Germany

Aboveground carbon (C) sequestration in trees is important in global C dynamics, but reliable techniques for its modeling in highly productive and heterogeneous ecosystems are limited. We applied an extended dendrochronological approach to disentangle the functioning of drivers from the atmosphere (temperature, precipitation), the lithosphere (sedimentation rate), the hydrosphere (groundwater table, river water level fluctuation), the biosphere (tree characteristics), and the anthroposphere (dike construction). Carbon sequestration in aboveground biomass of riparian Quercus robur L and Fraxinus excelsior L was modeled (1) over time using boosted regression tree analysis (BRT) on cross-datable trees characterized by equal annual growth ring patterns and (2) across space using a subsequent classification and regression tree analysis (CART) on cross-datable and not cross-datable trees. While C sequestration of cross-datable Q robur responded to precipitation and temperature, cross-datable F. excelsior also responded to a low Danube river water level. However, CART revealed that C sequestration over time is governed by tree height and parameters that vary over space (magnitude of fluctuation in the groundwater table, vertical distance to mean river water level, and longitudinal distance to upstream end of the study area). Thus, a uniform response to climatic drivers of aboveground C sequestration in Q robur was only detectable in trees of an intermediate height class and in taller trees (>21.8 m) on sites where the groundwater table fluctuated little <= 0.9 m). The detection of climatic drivers and the river water level in F. excelsior depended on sites at lower altitudes above the mean river water level (<= 2.7 m) and along a less dynamic downstream section of the study area. Our approach indicates unexploited opportunities of understanding the interplay of different environmental drivers in aboveground C sequestration. Results may support species-specific and locally

关键词： Boosted regression tree Carbon sequestration classification and regression tree Climate Danube River Dendrochronology

来源：评论

学校读者我要写书评

暂无评论

Estimating the Relationship between Landslide Area and Slope Unit Characteristics through classification and regression trees

引用

Journal of Chinese Soil and Water Conservation 2023年第4期54卷 264-274页

作者： Wu, Chun-Yi Chen, Ya-Xin Chang, Wei-Chun Department of Soil and Water Conservation National Chung Hsing University Taichung Taiwan

Taiwan has unique geographical and geological features. In recent years, climate change has led to the increased frequency of intense rainfall events, leading to sediment disasters on slopelands. In this study, classification and regression tree models, including a landslide area model and a landslide susceptibility model, were established to predict landslide areas in a watershed and to estimate the spatial distribution and scale of landslides. To develop a landslide area predictive model, data were collected on 24 typhoon-triggered landslide inventories in the Shihmen Reservoir watershed and the landslide area of slope units as well as on 12 physiographic factors and 2 rainfall factors. The model was then evaluated using four methods, and a comparison of characteristics was conducted to verify the prediction results. Subsequently, a landslide susceptibility model was established to calculate the landslide susceptibility value of each slope unit and to convert it into a landslide ratio. The predicted landslide area of each slope unit was then combined with the landslide ratio for predicting the landslide area for the entire watershed. The results indicated that among all models, the predicted landslide area model provided the most accurate results, with R² values of 0.989 and 0.500 for the training and testing sets, respectively. These results indicated that the model not only estimated the landslide area of the entire watershed but also provided information on the spatial distribution of landslides. © 2023 Chinese Soil and Water Conservation Society. All rights reserved.

关键词： classification and regression tree landslide area analysis Shihmen Reservoir watershed

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：