检索结果-内蒙古大学图书馆

A new method of diesel fuel brands identification: SMOTE oversampling combined with XGBoost ensemble learning

FUEL 2020年 282卷 118848-118848页

作者： Wang, Shutao Liu, Shiyu Zhang, Jingkun Che, Xiange Yuan, Yuanyuan Wang, Zhifang Kong, Deming Yanshan Univ Measurement Technol & Instrumentat Key Lab Hebei Qinhuangdao 066004 Hebei Peoples R China

Using proper diesel brand is the key to ensure the normal operation of diesel engine. It is even more important to identify the brands of diesel oil effectively. This paper presented a new model of near infrared spectroscopy (NIRS) identification of diesel oil brands that combined tree-based feature selection, Synthetic Minority Oversampling Technique (SMOTE) and Extreme Gradient Boosting (XGBoost) ensemble learning in order to achieve the goal of high accuracy and rapidity. To further demonstrate the practical effect of the proposed ensemble method, it was compared with a single decision tree (DT) classifier based on classification and regression tree (CART) algorithm. As a result, the recognition rate of tree-SMOTE-XGBoost model proposed in this paper was 19.33% higher than that of XGBoost model, and 9.25% higher than that of tree-SMOTE-DT model. More importantly, it can ensure the accuracy of each class under the premise of serious imbalance of classes. The proposed method saves manpower and material resources, and provides a new alternative approach for diesel brands identification.

关键词： Diesel oil brands Near infrared spectroscopy SMOTE XGBoost classification and regression tree Identification

来源：评论

学校读者我要写书评

暂无评论

A Comparative Assessment Between Three Machine Learning Models and Their Performance Comparison by Bivariate and Multivariate Statistical Methods in Groundwater Potential Mapping

引用

WATER RESOURCES MANAGEMENT 2015年第14期29卷 5217-5236页

作者： Naghibi, Seyed Amir Pourghasemi, Hamid Reza Tarbiat Modares Univ Coll Nat Resources Dept Watershed Management Engn Noor Mazandaran Iran Shiraz Univ Coll Agr Dept Nat Resources & Environm Engn Shiraz Iran

As demand for fresh groundwater in the worldwide is increasing, delineation of groundwater spring potential zones become an increasingly important tool for implementing a successful groundwater determination, protection, and management programs. Therefore, the objective of current study is to evaluate the capability of three machine learning models such as boosted regression tree (BRT), classification and regression tree (CART), and random forest (RF), and comparison of their performance by bivariate (evidential belief function (EBF)), and multivariate (general linear model (GLM)) statistical methods in the groundwater potential mapping. This study was carried out in the Beheshtabad Watershed, Chaharmahal-e-Bakhtiari Province, Iran. In total, 1425 spring locations were detected in the study area. Seventy percent of the spring locations were used for model training, and 30 % for validation purposes. Fourteen conditioning-factors were considered in this investigation, including slope angle, slope aspect, altitude, plan curvature, profile curvature, slope length (LS), stream power index (SPI), topographic wetness index (TWI), distance from rivers, distance from faults, river density, fault density, lithology, and land use. Using the above conditioning factors and different algorithms, groundwater potential maps were generated, and the results were plotted in ArcGIS 9.3. According to the results of success rate curves (SRC), values of area under the curve (AUC) for the five models vary from 0.692 to 0.975. In contrast, the AUC for prediction rate curves (PRC) ranges from 77.26 to 86.39 %. The CART, BRT, and RF machine learning techniques showed very good performance in groundwater potential mapping with the AUC values of 86.39, 86.12, and 86.05 %, respectively. By the way, The GLM and EBF models in comparison by machine learning models showed weaker performance in spring groundwater potential mapping by the AUC values of 77.26, and 67.72 %, respectively. The proposed me

关键词： Groundwater potential mapping Boosted regression tree classification and regression tree Random forest General linear model Evidential belief function GIS

来源：评论

学校读者我要写书评

暂无评论

Offline and online fault detection and diagnosis of induction motors using a hybrid soft computing model

引用

APPLIED SOFT COMPUTING 2013年第12期13卷 4493-4507页

作者： Seera, Manjeevan Lim, Chee Peng Ishak, Dahaman Singh, Harapajan Intel Technol Bayan Lepas Penang Malaysia Deakin Univ Waurn Ponds Vic Australia Univ Sains Malaysia Nibong Tebal Penang Malaysia Univ Teknol MARA Permatang Pauh Penang Malaysia

In this paper, a hybrid soft computing model comprising the Fuzzy Min-Max (FMM) neural network and the classification and regression tree (CART) for motor fault detection and diagnosis is described. Specifically, the hybrid model, known as FMM-CART, is used to detect and classify fault conditions of induction motors in both offline and online environments. A series of experiments is conducted, whereby the Motor Current Signature Analysis (MCSA) method is applied to form a database containing stator current signatures under different motor conditions. The signal harmonics from the power spectral density (PSD) are extracted, and used as the discriminative input features for fault classification with FMM-CART. Three main induction motor conditions, viz, broken rotor bars, stator winding faults, and unbalanced supply, are used to evaluate the effectiveness of FMM-CART. The results indicate that FMM-CART is able to detect motor faults in the early stage, in order to avoid further damage to the induction motor as well as the overall machine or system that uses the motor in its operations. (C) 2013 Elsevier B.V. All rights reserved.

关键词： Fault detection and diagnosis Fuzzy Min-Max neural network classification and regression tree Induction motor Motor Current Signature Analysis

来源：评论

学校读者我要写书评

暂无评论

Digital mapping of topsoil pH by random forest with residual kriging (RFRK) in a hilly region

引用

SOIL RESEARCH 2019年第4期57卷 387-396页

作者： Wang, Lei Wu, Wei Liu, Hong-Bin Southwest Univ Coll Resources & Environm Chongqing 400715 Peoples R China Southwest Univ Coll Comp & Informat Sci Chongqing 400715 Peoples R China

Soil pH is a vital attribute of soil fertility. The accurate and efficient prediction of soil pH can provide the necessary basic information for agricultural development. In the present study, random forest with residual kriging (RFRK) was used to predict soil pH based on stratum, climate, vegetation and topography in a hilly region. The performance of RFRK was compared with those of the classification and regression tree (CART) and the random forest (RF). Comparative results showed that RFRK provided the best performance. The corresponding values of Lin's concordance correlation coefficient, coefficient of determination, mean absolute error and root mean square error were as follows: 0.70, 0.51, 0.44 and 0.61 for CART;0.80, 0.70, 0.34 and 0.48 for RF;and 0.88, 0.80, 0.25 and 0.39 for RFRK. Stratum and average annual temperature were the most important factors affecting the soil pH in the study area. Results indicate that RFRK is a feasible and reliable tool for predicting soil pH in hilly regions.

关键词： classification and regression tree digital soil mapping soil pH

来源：评论

学校读者我要写书评

暂无评论

A hybrid intelligent system for medical data classification

引用

EXPERT SYSTEMS WITH APPLICATIONS 2014年第5期41卷 2239-2249页

作者： Seera, Manjeevan Lim, Chee Peng Intel Technol George Town Malaysia Deakin Univ Ctr Intelligent Syst Res Geelong Vic 3217 Australia

In this paper, a hybrid intelligent system that consists of the Fuzzy Min-Max neural network, the classification and regression tree, and the Random Forest model is proposed, and its efficacy as a decision support tool for medical data classification is examined. The hybrid intelligent system aims to exploit the advantages of the constituent models and, at the same time, alleviate their limitations. It is able to learn incrementally from data samples (owing to Fuzzy Min-Max neural network), explain its predicted outputs (owing to the classification and regression tree), and achieve high classification performances (owing to Random Forest). To evaluate the effectiveness of the hybrid intelligent system, three benchmark medical data sets, viz., Breast Cancer Wisconsin, Pima Indians Diabetes, and Liver Disorders from the UCI Repository of Machine Learning, are used for evaluation. A number of useful performance metrics in medical applications which include accuracy, sensitivity, specificity, as well as the area under the Receiver Operating Characteristic curve are computed. The results are analyzed and compared with those from other methods published in the literature. The experimental outcomes positively demonstrate that the hybrid intelligent system is effective in undertaking medical data classification tasks. More importantly, the hybrid intelligent system not only is able to produce good results but also to elucidate its knowledge base with a decision tree. As a result, domain users (i.e., medical practitioners) are able to comprehend the prediction given by the hybrid intelligent system;hence accepting its role as a useful medical decision support tool. (C) 2013 Elsevier Ltd. All rights reserved.

关键词： Fuzzy Min-Max neural network classification and regression tree Random forest Hybrid intelligent systems Medical decision support

来源：评论

学校读者我要写书评

暂无评论

Estimating cavity tree abundance by stand age and basal area, Missouri, USA

引用

FOREST ECOLOGY AND MANAGEMENT 2003年第1-3期179卷 231-242页

作者： Fan, ZF Larsen, DR Shifley, SR Thompson, FR Univ Missouri Sch Nat Resources Columbia MO 65211 USA Univ Missouri Sch Nat Resources Columbia MO 65211 USA Univ Missouri USDA FS N Cent Res Stn Columbia MO 65211 USA

We analyzed cavity tree distribution among Missouri Forest Inventory and Analysis (FIA) plots using the nonparametric classification and regression tree (CART) model and Weibull probability density function (pdf). Fifty-nine per cent (2370) of the 4052 Forest Inventory and Analysis plots (aged 1-160 years) had at least one cavity tree. The overall odds ratio of a plot with cavity trees (odds of a plot having cavity trees/odds of a plot with no cavity trees) across the five survey units of the entire state was 1.4. Three and four disjoint clusters (nodes) which differ significantly in cavity tree distribution were identified by CART using the two most discriminating stand level indicator variables: age and basal area, respectively. Cavity tree density distribution within each cluster was further described by the Weibull pdf. Cavity tree density per hectares varied considerably among stands (plots) of the same age or density, and the number of cavities for a given size or age class was distributed in an asymmetric form (primarily reverse-J shape). CART partitioning and Weibull fitting, in combination, provide an intuitive way to depict cavity tree distribution (variation) by important stand indicator variables such as age and basal area. This information can help forest managers and planners formulate management guidelines and results can be linked with forest landscape planning efforts, regional inventories, wildlife habitat modeling, and landscape simulation to evaluate or predict the consequences of different management alternatives. (C) 2002 Elsevier Science B.V. All rights reserved.

关键词： classification and regression tree Weibull probability density function forest inventory and analysis (FIA) cavity tree stand age basal area

来源：评论

学校读者我要写书评

暂无评论

Liquid floodback detection for scroll compressor in a VRF system under heating mode

引用

APPLIED THERMAL ENGINEERING 2017年 114卷 921-930页

作者： Wang, Jiangyu Li, Guannan Chen, Huanxin Liu, Jiangyan Guo, Yabin Hu, Yunpeng Li, Jiong Huazhong Univ Sci & Technol Sch Energy & Power Engn Dept Refrigerat & Cryogen Engn Wuhan 430074 PR Peoples R China Wuhan Business Univ Wuhan 430056 PR Peoples R China State Key Lab Compressor Technol Hefei 230031 PR Peoples R China

Liquid floodback leads to negative consequences, such as extra energy consumption, comfort degradation for building occupants, and mechanical failure of compressors. Fault detection and diagnosis of liquid floodback at incipient stage are necessary for variable refrigerant flow (VRF) systems. This study proposes decision tree models to detect and diagnose the liquid floodback of the scroll compressor in a VRF system. First, feature selection through correlation analysis was performed to remove redundant variables. Second, classification and regression tree (CART) was used to develop decision tree models for detecting liquid floodback. Third, two faults that cause liquid floodback were examined, and another CART model was established to diagnose fault causes when a fault occurred. The CART models demonstrated desirable performance in floodback FDD. The rules extrapolated from the two data-driven models were in agreement with domain knowledge. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： classification and regression tree Fault detection and diagnosis Variable refrigerant flow Refrigerant overcharge Compressor liquid floodback Heating mode

来源：评论

学校读者我要写书评

暂无评论

Comparison of CART- and MLP-based power system transient stability preventive control

引用

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 2013年第1期45卷 129-136页

作者： Lin, Yu-Jen I Shou Univ Dept Elect Engn Kaohsiung Taiwan

This paper compares the power system transient stability preventive controls based on classification and regression tree (CART) and multilayer perceptron (MLP). CART is a branch of the decision trees (DTs) algorithms, which have been applied extensively in the literature for preventive control design due to their transparent character of interpreting inference procedures. Recent research has shown that multilayer perceptron (MLP), a member of artificial neural networks (ANNs) family, can also be employed to design preventive control since explaining internal mapping relationship becomes possible. This paper first briefs the essentials of CART and MLP, and then follows the numerical study on a three-generator six-bus power system. Transient stability preventive controls are designed by CART and MLP, and are compared afterwards. The finding shows that preventive controls developed by both approaches think alike. They are even complementary. (c) 2012 Elsevier Ltd. All rights reserved.

关键词： Transient stability Preventive control classification and regression tree Multilayer perceptron

来源：评论

学校读者我要写书评

暂无评论

Nonparametric approaches for estimating regional lake nutrient thresholds

引用

ECOLOGICAL INDICATORS 2015年 58卷 225-234页

作者： Huo, Shouliang Ma, Chunzi Xi, Beidou He, Zhuoshi Su, Jing Wu, Fengchang Chinese Res Inst Environm Sci State Key Lab Environm Criteria & Risk Assessment Beijing 100012 Peoples R China

Nonparametric approaches including a classification and regression tree (CART), a nonparametric change-point analysis (nCPA) and a Bayesian hierarchical modeling (BHM) method were developed to determine ecoregional nutrient response thresholds. A CART analysis revealed that hierarchical structure was important for predicting Chl a concentrations from total nitrogen (TN) and total phosphorus (TP). The nCPA and BHM methods confirmed the CART results for each node in the tree, and the 90% confidence interval for each threshold was calculated to quantify uncertainty. The CART, nCPA, and BHM methods suggested that the nutrient criteria differed significantly within certain nutrient ecoregions and that numerical nutrient criteria of 0.0150-0.222 mg/L TP and 0.300-1.766 mg/L TN may control Chl a concentrations in the various lake ecoregions. The results of this analysis suggest that the integration of CART, nCPA and BHM might be useful for determining nutrient thresholds. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： Nutrient threshold classification and regression tree Nonparametric changepoint analysis Bayesian hierarchical modeling Lake ecoregion

来源：评论

学校读者我要写书评

暂无评论

Integrated Learning via Randomized Forests and Localized regression With Application to Medical Diagnosis

引用

IEEE ACCESS 2019年 7卷 18727-18733页

作者： Ogunleye, Adeola Wang, Qing-Guo Marwala, Tshilidzi Univ Johannesburg Fac Engn & Built Environm Inst Intelligent Syst Johannesburg South Africa Univ Johannesburg Fac Engn & Built Environm Johannesburg South Africa

The tree-based machine learning functions on the divide-and-conquer principle and is known to perform well in certain applications. In this paper, we first give a new data partitioning rule using the mean of the data columns to grow the tree till the child nodes are small in size. Then, the local regression is applied to leave nodes to enhance the resolution of the node outputs. Randomization is introduced at tree growth and forest creation. The local prediction accuracies on the leaves are used to select a subset of the test data for actual predictions. The case study on the diagnosis of autistic spectrum disorder shows that the proposed method achieves the prediction accuracy of the ensemble at above 96% with reduced variance, which is much better than those reported in the literature.

关键词： classification and regression tree hybrid expert system decision tree

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：