检索结果-内蒙古大学图书馆

作者： Anqi Shi Baotian Dong Fangcan Zhao Yang Wang School of Traffic and Transportation Beijing Jiaotong University

Railway transportation is an important part of China's transportation system. Due to the original business model of railway, its punctuality is poor. In addition, the current calculation method of dwell time of railway freight cars is still be the general old-fashioned algorithm. In order to improve the punctuality of dwell time of cars at the station, this paper takes the terminal as an example, and puts forward a prediction model based on gradient boosting regression tree. The influencing factors of cars' dwell time in terminal are characterized. Six influencing factors are selected, i.e. car number, goods type, car type, start station, end station and train number. The six discrete characteristics are quantified. The six characteristics are combined into input vectors, and the data in 2016 and July 2017 are selected for prediction. The experimental results show that the model has a good prediction effect.

关键词： gradient boosting regression tree Railway Freight Dwell Time

来源：评论

学校读者我要写书评

暂无评论

Assessing the biochemical oxygen demand using neural networks and ensemble tree approaches in South Korea

引用

JOURNAL OF ENVIRONMENTAL MANAGEMENT 2020年 270卷 110834-110834页

作者： Kim, Sungwon Alizamir, Meysam Zounemat-Kermani, Mohammad Kisi, Ozgur Singh, Vijay P. Dongyang Univ Dept Railrd Construct & Safety Engn Yeongju 36040 South Korea Islamic Azad Univ Dept Civil Engn Hamedan Branch Hamadan Hamadan Iran Shahid Bahonar Univ Kerman Dept Water Engn Kerman Iran Ilia State Univ Dept Civil Engn Tbilisi Georgia Texas A&M Univ Water Engn Dept Biol & Agr Engn College Stn TX 77843 USA Texas A&M Univ Zachry Dept Civil Engn College Stn TX 77843 USA UAE Univ Natl Water Ctr Al Ain U Arab Emirates

The biochemical oxygen demand (BOD), one of widely utilized variables for water quality assessment, is metric for the ecological division in rivers. Since the traditional approach to predict BOD is time-consuming and inaccurate due to inconstancies in microbial multiplicity, alternative methods have been recommended for more accurate prediction of BOD. This study investigated the capability of a novel deep learning-based model, Deep Echo State Network (Deep ESN), for predicting BOD, based on various water quality variables, at Gongreung and Gyeongan stations, South Korea. The model was compared with the Extreme Learning Machine (ELM) and two ensemble tree models comprising the gradient boosting regression tree (GBRT) and Random Forests (RF). Diverse water quality variables (i.e., BOD, potential of Hydrogen (pH), electrical conductivity (EC), dissolved oxygen (DO), water temperature (WT), chemical oxygen demand (COD), suspended solids (SS), total nitrogen (TN), and total phosphorus (T-P)) were utilized for developing the Deep ESN, ELM, GBRT, and RF with five input combinations (i.e., Categories 1-5). These models were evaluated by root mean square error (RMSE), NashSutcliffe efficiency (NSE), coefficient of determination (R-2), and correlation coefficient (R). Overall evaluations suggested that the Deep ESNS model provided the most reliable predictions of BOD among all the models at both stations.

关键词： Biochemical oxygen demand Deep echo state network Extreme learning machine gradient boosting regression tree Random forests Water quality prediction

来源：评论

学校读者我要写书评

暂无评论

Ad Blocking Whitelist Prediction for Online Publishers

Ad Blocking Whitelist Prediction for Online Publishers

引用

IEEE International Conference on Big Data (Big Data)

作者： Zhao, Shuai Kalra, Achir Wang, Chong Borcea, Cristian Chen, Yi New Jersey Inst Technol Newark NJ 07102 USA Forbes Media Jersey City NJ USA S&P Global Albany NY USA

ISBN: (纸本)9781728108582

The fast increase in ad blocker usage results in large revenue loss for online publishers and advertisers. Many publishers initialize counter-ad-blocking strategies, where a user has to choose either whitelisting the publisher's web site in their ad blocker or leaving the site without accessing the content. This paper aims to predict the user whitelisting behavior, which can help online publishers to better assess users' interests and design corresponding strategies. We present several techniques for personalized whitelist prediction for a target user and a target web page. Our prediction models are evaluated on real-world data provided by a large online publisher, Forbes Media. The best prediction performance was achieved using the gradient boosting regression tree model, which also demonstrated robustness and efficiency.

关键词： online advertising user behavior prediction ad blocking gradient boosting regression tree

来源：评论

学校读者我要写书评

暂无评论

On the Selection of Features for the Prediction Model of Cultivation of Sweet Potatoes at Early Growth Stage

On the Selection of Features for the Prediction Model of Cul...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Shu, LihChyun Hsiao, Bo Liou, Yi-Hsin Tsai, Yi-Lin Natl Cheng Kung Univ Coll Management Ctr Innovat FinTech Business Models Tainan Taiwan Chang Jung Christian Univ Sch Informat & Design Tainan Taiwan Natl Cheng Kung Univ Coll Management Tainan Taiwan

ISBN: (纸本)9781728124858

With the changes in the agricultural environment, the cultivation of sweet potatoes today cannot be managed extensively as in the early days. The increase in production costs makes it necessary for enterprises that manage agricultural lands to estimate the premium grade yield more accurately, reduce the risk and cost of supply shortages, and even further improve premium grade yield and maximize the value of agricultural properties. In the past, the forecast of premium grade yield used manual inspection and field sampling to judge the growth status of sweet potato and infer the final output of premium-grade sweet potatoes, but such an estimation method requires long-term tracking and could not do early supply planning. Therefore, this study aims to develop a prediction model for sweet potato production, using cultivation information provided by a sweet potato depot manufacturer in Taiwan, agro-meteorological information provided by an agricultural improvement farm in Taiwan, and the wholesale price of sweet potato provided by Taiwan Council of Agriculture. Combining the information from the planting day to 4 days after planting, we determine the features of the model that predicts excellent potato yield during the early planting stage of sweet potatoes. We investigate hierarchical feature clustering and simulated annealing feature selection, removing features that are unrelated to yield prediction, and redundant features that are highly correlated with other features. Our results show that the 3-day-after-planting information may provide predictable information in the feature selection stage, and the wholesale price of sweet potato was found to be related to the premium-grade yield in the experiment.

关键词： feature selection feature grouping simulated annealing gradient boosting regression tree

来源：评论

学校读者我要写书评

暂无评论

A Prediction Method of Five-Axis Machine Tool Energy Consumption with GBRT Algorithm 5

A Prediction Method of Five-Axis Machine Tool Energy Consump...

引用

5th IEEE International Conference on Mechatronics System and Robots (ICMSR)

作者： Chen, Tao Shang, Hai Bi, Qingzhen Shanghai Jiao Tong Univ Sch Mech Engn Shanghai Peoples R China

ISBN: (纸本)9781728122236

As the main carrier of the manufacturing industry, energy consumption of machine tools has been studied by more and more scholars. In this paper, a new method to predict energy consumption of five-axis machine center is proposed. Firstly, the energy consumption model of each component is established under the unload condition. Then the model of milling energy is established based on the gradient boosting regression tree (GBRT) algorithm, and the importance of each processing parameter on energy consumption is analyzed. Finally, a milling experiment is used to verify the accuracy of the model.

关键词： energy consumption five-axis machine center machine learning gradient boosting regression tree

来源：评论

学校读者我要写书评

暂无评论

Pressure drop in pipe flow of cemented paste backfill: Experimental and modeling study

引用

POWDER TECHNOLOGY 2018年 333卷 9-18页

作者： Qi, Chongchong Chen, Qiusong Fourie, Andy Zhao, Jianwen Zhang, Qinli Univ Western Australia Sch Civil Environm & Min Engn Perth WA Australia Cent S Univ Sch Resources & Safety Engn Changsha Hunan Peoples R China

Advances in pipe transportation have contributed significantly to the application of cemented paste backfill (CPB). However, the pressure drop during pipe transportation with complex circuit shapes has not been fully investigated. Currently, research in the field is largely experiment-centered, where extensive test loop experiments need to be performed for a specific CPB material. By comparison, computational modeling of the pressure drop during pipe transportation through complex circuits is still in its infancy and is hindered by the challenges of technique availability and data scarcity. In this article, we present a framework for investigating and modeling the pressure drop of CPB during pipe transportation with complex circuit shapes. A test loop system was used to investigate the pressure drop of CPB under different influencing variables. Based on the experimental data, gradient boosting regression tree (GBRT) was utilized to develop a prediction model for the CPB pressure drop in the pipe loop. We first discussed the effect of solids content, cement-tailings ratio, inlet pressure, and circuit shape on the CPB pressure drop. The feasibility of GBRT modeling was demonstrated by comparing the predicted pressure drop with the experimental result on both the training and testing sets. We also investigated the relative importance of influencing variables on the pressure drop of CPB. Harnessing such a modeling approach extends recent efforts to determine the pressure drop during CPB pipe transportation and can significantly accelerate the application of CPB in the future. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Pipe flow Cemented paste backfill Pressure drop Test loop gradient boosting regression tree Variable importance

来源：评论

学校读者我要写书评

暂无评论

Forecasting Road Surface Temperature in Beijing Based on Machine Learning Algorithms 18

Forecasting Road Surface Temperature in Beijing Based on Mac...

引用

3rd International Conference on Crowd Science and Engineering (ICCSE)

作者： Liu, Bo Shen, Libin You, Huanling Dong, Yan Li, Jianqiang Li, Yong Lang, Jianlei Gu, Rentao Beijing Univ Technol Beijing Adv Innovat Ctr Future Internet Technol Beijing 100124 Peoples R China Beijing Univ Technol Fac Informat Technol Sch Software Engn Beijing 100124 Peoples R China China Meteorol Adm Inst Urban Meteorol Beijing 100089 Peoples R China Beijing Meteorol Serv Ctr Beijing 100089 Peoples R China Beijing Univ Technol Key Lab Beijing Reg Air Pollut Control Beijing 100124 Peoples R China Beijing Univ Technol Coll Environm & Energy Engn Beijing 100124 Peoples R China Beijing Univ Posts & Telecommun Sch Informat & Commun Engn Beijing Lab Adv Informat Networks Beijing 100876 Peoples R China

ISBN: (纸本)9781450365871

With the influence of extreme weather, road surface temperature (RST), which threatens the safety of people's travel, has attracted more and more attention to the government and citizens. However, traditional methods are hard to meet real-time requirements in forecasting RST. In order to improve the predictive accuracy of RST and meet the real-time requirement, this paper compares three different machine learning algorithms including, Least Absolute Shrinkage and Selection Operator (LASSO), Random Forest (RF) and gradient boosting regression tree (GBRT). Using the RST data and BJ-RUC (Beijing-rapidly update cycle) data during November 2012 and June 2015, the performance of three models is evaluated. The experimental results show that GBRT performs the best and its MSE is 6.7853.

关键词： Random Forest gradient boosting regression tree LASSO road surface temperature

来源：评论

学校读者我要写书评

暂无评论

Estimating Surface Downward Shortwave Radiation over China Based on the gradient boosting Decision tree Method

引用

REMOTE SENSING 2018年第2期10卷 185-185页

作者： Yang, Lu Zhang, Xiaotong Liang, Shunlin Yao, Yunjun Jia, Kun Jia, Aolin Beijing Normal Univ Fac Geog Sci State Key Lab Remote Sensing Sci Beijing 100875 Peoples R China Univ Maryland Dept Geog Sci College Pk MD 20742 USA

Downward shortwave radiation (DSR) is an essential parameter in the terrestrial radiation budget and a necessary input for models of land-surface processes. Although several radiation products using satellite observations have been released, coarse spatial resolution and low accuracy limited their application. It is important to develop robust and accurate retrieval methods with higher spatial resolution. Machine learning methods may be powerful candidates for estimating the DSR from remotely sensed data because of their ability to perform adaptive, nonlinear data fitting. In this study, the gradient boosting regression tree (GBRT) was employed to retrieve DSR measurements with the ground observation data in China collected from the China Meteorological Administration (CMA) Meteorological Information Center and the satellite observations from the Advanced Very High Resolution Radiometer (AVHRR) at a spatial resolution of 5 km. The validation results of the DSR estimates based on the GBRT method in China at a daily time scale for clear sky conditions show an R-2 value of 0.82 and a root mean square error (RMSE) value of 27.71 Wm(-2) (38.38%). These values are 0.64 and 42.97 Wm(-2) (34.57%), respectively, for cloudy sky conditions. The monthly DSR estimates were also evaluated using ground measurements. The monthly DSR estimates have an overall R-2 value of 0.92 and an RMSE of 15.40 Wm(-2) (12.93%). Comparison of the DSR estimates with the reanalyzed and retrieved DSR measurements from satellite observations showed that the estimated DSR is reasonably accurate but has a higher spatial resolution. Moreover, the proposed GBRT method has good scalability and is easy to apply to other parameter inversion problems by changing the parameters and training data.

关键词： downward shortwave radiation machine learning gradient boosting regression tree AVHRR CMA

来源：评论

学校读者我要写书评

暂无评论

A gradient boosting method to improve travel time prediction

引用

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES 2015年第PartB期58卷 308-324页

作者： Zhang, Yanru Haghani, Ali Univ Maryland Dept Civil & Environm Engn College Pk MD 20740 USA

tree based ensemble methods have reached a celebrity status in prediction field. By combining simple regression trees with 'poor' performance, they usually produce high prediction accuracy. In contrast to other machine learning methods that have been treated as black-boxes, tree based ensemble methods provide interpretable results, while requiring little data preprocessing, are able to handle different types of predictor variables, and can fit complex nonlinear relationship. These properties make the tree based ensemble methods good candidates for solving travel time prediction problems. However, applications of tree-based ensemble algorithms in traffic prediction area are limited. In this paper, we employ a gradient boosting regression tree method (GBM) to analyze and model freeway travel time to improve the prediction accuracy and model interpretability. The gradient boosting tree method strategically combines additional trees by correcting mistakes made by its previous base models, therefore, potentially improves prediction accuracy. Different parameters' effect on model performance and correlations of input-output variables are discussed in details by using travel time data provided by INRIX along two freeway sections in Maryland. The proposed method is, then, compared with another popular ensemble method and a bench mark model. Study results indicate that the GBM model has its considerable advantages in freeway travel time prediction. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： Short-term forecasting Travel time Ensemble learning Machine learning gradient boosting regression tree Random forest

来源：评论

学校读者我要写书评

暂无评论

面向LTR的GBRT优化及其并行化

面向LTR的GBRT优化及其并行化

引用

作者：金磊南京大学

学位级别：硕士

随着互联网的快速发展,近年来网络上的文档数据量呈几何级数增长。快速增长的网络信息量带来了高效检索信息的需求。搜索引擎在网络信息检索任务中扮演了重要角色。学习排序(Learning to Rank,以下简称LTR),作为搜索引擎相关应用背后的... 详细信息

随着互联网的快速发展,近年来网络上的文档数据量呈几何级数增长。快速增长的网络信息量带来了高效检索信息的需求。搜索引擎在网络信息检索任务中扮演了重要角色。学习排序(Learning to Rank,以下简称LTR),作为搜索引擎相关应用背后的重要技术支撑,主要解决对搜索结果的相关性进行排序的问题。搜索结果的排序结果对检索的性能和体验影响很大,因此LTR技术获得了众多了关注,取得了长足的发展,各种相关的算法也层出不穷。然而,随着数据量的进一步大幅度增大,近年来,在关注算法精度的同时,越来越多的研究人员开始关注LTR训练算法的效率问题。GBRT(gradient boosting regression tree),作为LTR领域最重要的算法之一,同样也面临着大数据时代的挑战。GBRT训练具有顺序性、并行粒度低等特点,导致在数据规模增大时其训练效率的问题越来越突出。2013年,百度甚至将“GBDT的并行化训练研究”1作为百度最有价值的研究课题之一向学术界公开征集解决方案2,本文研究内容即为课题组成功申请的百度GBRT并行化训练课题基础上的研究工作。基于上述背景和所申请的百度课题,本文以不降低算法的精度、提升算法的训练速度为目标对GBRT的训练并行化展开了研究。本文的研究工作主要包括训练算法优化和算法并行化两大部分。第一部分,在算法优化上,本文提出了基于K-Means直方图近似的并行化训练算法KH-GBRT以加速训练过程。gradient boosting框架具有本质上的顺序性,难以并行化,且GBRT算法训练最耗时的部分是在单棵回归树的训练过程,因此本文并行化的关注点主要在单棵回归树的训练上。首先,我们提出了基于K-Means直方图的近似构造算法并把它和回归树算法相结合降低了回归树训练过程中分裂点寻优过程的时间复杂度,并提高了寻优过程的并行粒度,加速了训练过程;进一步地,为了避免K-Means直方图近似算法带来的精度损失,本文将核函数密度估计和K-Means直方图算法相结合,提出了一套基于K-Means直方图的核函数概率密度估计算法,该算法提高了 K-Means直方图密度估计的准确性,并间接提升了训练精度。第二部分,在并行化方案上,我们分别针对MPI和适合迭代计算的大数据处理框架Spark的特点提出了两套并行化方案。MPI具有接口灵活,运行效率高优点;而Spark具有高容错性,可编程性好,代码移植简单的优点,它们根据不同的需求有不同的应该场景。我们在LTR的公开评测数据集和百度内部大规模数据集上进行了一系列实验,以评估本文并行化优化算法的效果。结果显示,本文提出的基于MPI并行化的KH-GBRT算法和先前文献中已有的最快的大规模分布式GBRT算法相比,取得了 1.49-1.54倍的加速,同时精度上也有所提升;在可扩展性上,也取得了近乎线性的可扩展性效果。同时和中文搜索引擎百度使用的GBRT算法相比,本文并行算法获得了 1.6-2.13倍的加速和更好的训练精度。而基于Spark并行化的KH-GBRT算法,虽然训练速度上和MPI版本相比稍逊一些,但其在容错性和可编程性上更胜一筹,并且在实验中显示了准线性、甚至超线性的可扩展性效果。

关键词： Learning to Rank gradient boosting regression tree K-Means 直方图核函数密度估计并行化 MPI Spark

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：