检索结果-内蒙古大学图书馆

7th Asian Conference on Intelligent Information and Database Systems (ACIIDS)

作者： Cheng, Shou-Hsiung Chien Kuo Technol Univ Dept Informat Management Changhua 500 Taiwan

ISBN: (纸本)9783319157023;9783319157016

This study presents a hybrid model to predict stock returns. The following are four main steps in this study: First, logistic stepwise regression theory is used to find out the core financial indicators by computing the importance of financial indicators affecting the ups and downs of a stock price. Second, based on the core of the financial indicators coupled with the technology of classification and regression tree, a hybrid classificatory model is established. Third, the predictable rules that affect the ups and downs of a stock price are obtained by employing the proposed hybrid classificatory model. Fourth, we use the established rules to sift out the sound investing targets to invest and calculate the rates of investment. These results of simulated investment reveal that the average rates of reward are far larger than the mass investment rates.

关键词： Stock returns Financial indicators Logistic stepwise regression classification and regression tree

来源：评论

学校读者我要写书评

暂无评论

Predicting Early Mortality After Acute Variceal Hemorrhage Based on classification and regression tree Analysis

引用

CLINICAL GASTROENTEROLOGY AND HEPATOLOGY 2009年第12期7卷 1347-1354页

作者： Augustin, Salvador Muntaner, Laura Altamirano, Jose T. Gonzalez, Antonio Saperas, Esteban Dot, Joan Abu-Suboh, Monder Armengol, Josep R. Malagelada, Joan R. Esteban, Rafael Guardia, Jaime Genesca, Joan Univ Autonoma Barcelona Hosp Univ Vall Hebron Inst Recerca Vall Hebron Liver UnitDept Internal Med Barcelona 08035 Spain Univ Autonoma Barcelona Hosp Univ Vall Hebron Inst Recerca Vall Hebron Dept Gastroenterol Barcelona 08035 Spain Univ Autonoma Barcelona Hosp Univ Vall Hebron Inst Recerca Vall Hebron Digest Endoscopy ServCIBEREHD Barcelona 08035 Spain

BACKGROUND & AIMS: Available prognostic models for mortality after an acute variceal hemorrhage have limitations that restrict their clinical value. We assessed the performance of a novel prognostic approach based on classification and regression tree (CART) analysis. METHODS: Logistic regression (LR) and CART analyses were performed to identify prognostic models for mortality at 6 weeks in a single-center cohort of 267 consecutive patients with acute variceal bleeding. Receiver operating characteristic (ROC) curves were constructed to assess the performance of the models. Prognostic models were fitted and validated by split-sample technique (training set, 164 patients, 2001-2005;test set, 103 patients, 2006-2008). RESULTS: After 6 weeks, 21% of patients experienced rebleeding and 24% died. The best LR model was based on Child-Pugh score, creatinine level, bacterial infection, and hepatocellular carcinoma. CART analysis provided a simple algorithm based on the combined use of just 3 variables (Child-Pugh score, creatinine level, and bacterial infection), allowing accurate early discrimination of 3 distinct prognostic subgroups with 8% (low risk), 17% (intermediate), and 50% to 73% (high) mortality. Its accuracy was similar to the LR model (area under the ROC curves, 0.81 vs 0.84;P = .17) and better than that of Child-Pugh (0.75;P = .05) and model for end-stage liver disease (0.74;P = .05). The prognostic accuracy of both LR and CART models was validated in the test set (area under the ROC curve values, 0.81 and 0.83, respectively). CONCLUSIONS: A simple CART algorithm based on Child-Pugh score, creatinine level, and infection allowed an accurate predictive assessment of 6-week mortality after acute variceal bleeding.

关键词： AUROC area under the receiver operating characteristic curve CART classification and regression tree EST endoscopic sclerotherapy EVL endoscopic variceal ligation HCC hepatocellular carcinoma LR logistic regression MELD Model for End-Stage Liver Disease PI prognostic index R N 2 Nagelkerke's coefficient of determination ROC receiver operating characteristic

来源：评论

学校读者我要写书评

暂无评论

Real-time Prediction of Information Search Channel Using Data Mining Techniques 1

Real-time Prediction of Information Search Channel Using Dat...

引用

International Conference on Green Computing and Internet of Things (ICGCIoT)

作者： Khatwani, Gaurav Srivastava, Praveen Ranjan Indian Inst Management IT Syst Rohtak Haryana India

ISBN: (纸本)9781467379106

One of the biggest challenges associated with using the Internet as a real-time marketing vehicle concerns digital media fragmentation. The vast amount of potential media sources and platforms that are available to marketers entails that it can be very difficult to formulate a succinct strategy through which they can interact with the existing and potential customers. While a large number of businesses typically use consumer's previous actions as a means of understanding their information search behavior, very little is understood about how demographics influence information search and the use of various digital platforms. Previous research has focused on identifying these demographic factors but, as yet, no one has developed a real-time model that is capable of predicting consumer's information search preferences. This research considers four information search channels: personal, marketer-dominated, neutral and experiential channels, and assesses the extent to which existing classification techniques, such as classification and regression tree, neural networks and support vector machines, can be effectively employed to forecast individual's search preferences according to their demographic context. It is envisaged that the development of a method that can accurately forecast search behavior will help organizations to ensure that they allocate marketing resources in an efficient and effective manner.

关键词： Neural network Support vector machine classification and regression tree Information search channels

来源：评论

学校读者我要写书评

暂无评论

Measurement and Modeling of Job Stress of Electric Overhead Traveling Crane Operators

引用

SAFETY AND HEALTH AT WORK 2015年第4期6卷 279-288页

作者： Krishna, Obilisetty B. Maiti, Jhareswar Ray, Pradip K. Samanta, Biswajit Mandal, Saptarshi Sarkar, Sobhan DuPont Co Inc Hyderabad Andhra Pradesh India Indian Inst Technol Dept Ind & Syst Engn Kharagpur 721302 W Bengal India Indian Inst Technol Dept Min Engn Kharagpur W Bengal India

Background: In this study, the measurement of job stress of electric overhead traveling crane operators and quantification of the effects of operator and workplace characteristics on job stress were assessed. Methods: Job stress was measured on five subscales: employee empowerment, role overload, role ambiguity, rule violation, and job hazard. The characteristics of the operators that were studied were age, experience, body weight, and body height. The workplace characteristics considered were hours of exposure, cabin type, cabin feature, and crane height. The proposed methodology included administration of a questionnaire survey to 76 electric overhead traveling crane operators followed by analysis using analysis of variance and a classification and regression tree. Results: The key findings were: (1) the five subscales can be used to measure job stress;(2) employee empowerment was the most significant factor followed by the role overload;(3) workplace characteristics contributed more towards job stress than operator's characteristics;and (4) of the workplace characteristics, crane height was the major contributor. Conclusion: The issues related to crane height and cabin feature can be fixed by providing engineering or foolproof solutions than relying on interventions related to the demographic factors. Copyright (C) 2015, Occupational Safety and Health Research Institute. Published by Elsevier Ltd.

关键词： classification and regression tree electrical overhead traveling crane operation job stress modeling

来源：评论

学校读者我要写书评

暂无评论

Incident Duration Model on Urban Freeways Based on classification and regression tree

Incident Duration Model on Urban Freeways Based on Classific...

引用

2nd International Conference on Intelligent Computation Technology and Automation

作者： Zhao Xiaoqiang Li Ruimin Yu Xinxin Tsinghua Univ Inst Transportat Engn Beijing 100084 Peoples R China

ISBN: (纸本)9780769538044

Effective incident management requires accurate prediction of incident duration. In this paper, classification and regression tree (CART) is employed to model the incident duration. All 65000 incident records from Beijing Transportation Management Bureau are used for model establishment and another 8000 records for validation. The average relative error of the CART model is 29.5197%. It shows that the reliability of the model is quite satisfactory. The average relative error of the prediction on different ring roads of Beijing is approximately the same.

关键词： Decision tree classification and regression tree Incident duration Mutiple linear regression

来源：评论

学校读者我要写书评

暂无评论

Statistical Analyses of Field Serviceability of Throw-and-Roll Pothole Patches

引用

JOURNAL OF TRANSPORTATION ENGINEERING 2015年第9期141卷 04015017-04015017页

作者： Dong, Qiao Dong, Chunjiao Huang, Baoshan Univ Tennessee Ctr Transportat Res Knoxville TN 37996 USA Univ Tennessee Dept Civil & Environm Engn Knoxville TN 37996 USA

In order to evaluate the effectiveness of different pothole patching methods and materials, it is necessary to conduct a long-term field survey of patches installed at different environmental and traffic conditions. The research reported in this paper investigated the service life of different throw-and-roll pothole patches through a 14-month field survey. Three statistical methods, including (1) logistic regression, (2) classification tree, and (3) survival analysis, were employed to characterize the influence of different factors on the service life of installed patches, and to identify the performance of different patching materials. The factors investigated in the research reported in this paper included the length, width, and depth of patches;traffic level;speed limit;and freeze times. All the three statistical methods identified similar trends of the significance of factors and performance rankings of materials. Generally, patches installed on road sections with less freeze cycles, lower speed limit, and lower traffic level had significantly longer service life. A cold bag mix had significantly longer service life. In addition, the classification tree method indicated that significant influences of weather conditions and materials on the service life of patches were only observed around 1 year after the installation, indicating the necessity of the long-term survey. (C) 2015 American Society of Civil Engineers.

关键词： Pothole Patching Pavement maintenance Logistic regression classification and regression tree Survival analysis

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

Real-time Prediction of Information Search Channel Using Data Mining Techniques

Real-time Prediction of Information Search Channel Using Dat...

引用

International Conference on Green Computing and Internet of Things

作者： Gaurav Khatwani Praveen Ranjan Srivastava IT Systems Indian Institute of Management

ISBN: (纸本)9781467379113

关键词： Neural network Support vector machine classification and regression tree Information search channels

来源：评论

学校读者我要写书评

暂无评论

A data mining based approach for travel time prediction in freeway with non-recurrent congestion

引用

NEUROCOMPUTING 2014年 133卷 74-83页

作者： Li, Chi-Sen Chen, Mu-Chen Natl Chiao Tung Univ Dept Transportat & Logist Management Taipei 100 Taiwan

This study integrates three data mining techniques, K-means clustering, decision trees, and neural networks, to predict the travel time of freeway with non-recurrent congestion. By creating dummy variables and identifying important variables, not only is the prediction performance increased without increasing investment in equipment, but also important variables are obtained concerning the important locations of equipment in order to effectively assist public transit agencies with system maintenance. The experimental results for a segment of 36.1 km of National Freeway No. 1, Taiwan, with non-recurrent congestion show that, whether or not the data generated by the Electronic Toll Collection (etc) system is used as input variables, the travel time prediction method developed in this study is able to improve the prediction performance. Meanwhile, the proposed approach also reduces the percentage of samples with mean absolute percentage error (MAPE) > 20%. Furthermore, in this study, important variables are extracted from the decision tree in order to predict the travel time. Finally, the prediction models constructed in accordance with six scenarios are highly accurate due to the low MAPE values, which are from 6% to 9%. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Travel time prediction Non-recurrent congestion K-means classification and regression tree Neural networks

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

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：