检索结果-内蒙古大学图书馆

Combining random forest and support vector machines for object-based rural-land-cover classification using high spatial resolution imagery

引用

JOURNAL OF APPLIED REMOTE SENSING 2019年第1期13卷

作者： Xu, Saiping Zhao, Qianjun Yin, Kai Zhang, Feifei Liu, Dingbang Yang, Guang Chinese Acad Sci Inst Remote Sensing & Digital Earth Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Tsinghua Univ Dept Automat Beijing Peoples R China

Land-cover classification using remote sensing imagery is an important part of environmental research because it provides baseline information for ecological vulnerability and risk assessment, disaster management, landscape conservation, local and regional planning, and so on. Rural-land-cover classification is challenging for both object-based image analysis methods and classifiers. The objective of this study is to improve the object-oriented classification accuracy of rural land cover by combining two models based on high spatial resolution imagery. We apply the C5.0 algorithm in R to combine support vector machines (SVMs) and random forest (RF) to create the model RS_C5.0. The effectiveness of the model combination is assessed by comparing the classification results with the state-of-the-art machine learning algorithm, namely extreme gradient boosting (xgboost). The comparisons are done based on the classification results of both the study area and the case area. Results show that in the classification of the study area, RF performs slightly better than SVM, and xgboost performs worse than RF but better than SVM. However, in the classification of the case area, SVM performs slightly better than RF and both SVM and RF perform better than xgboost. Furthermore, RS_C5.0 obtains the highest overall accuracies and kappa coefficients in the classifications of both the study area and the case area. In terms of training time, xgboost runs the slowest in the classifications of both the study area and the case area. SVM and RF as well as the combined model (RS_C5.0) run much faster than xgboost classifier. To summarize, the combination of SVM and RF classifiers using C5.0 algorithm is found to be a fast and effective way to improve rural-land-cover classification. (C) 2019 Society of Photo-Optical Instrumentation Engineers (SPIE)

关键词： random forest support vector machines C5.0 algorithm xgboost algorithm object-based image analysis

来源：评论

学校读者我要写书评

暂无评论

Risk prediction of household mite infestation based on machine learning

引用

BUILDING AND ENVIRONMENT 2020年 183卷

作者： Pei, Jingjing Gong, Jinlian Wang, Zhiqiang Tianjin Univ Sch Environm Sci & Engn Tianjin Key Lab Indoor Air Environm Qual Control Tianjin 300072 Peoples R China Tianjin Univ Commerce Tianjin Key Lab Refrigerat Technol Tianjin 300134 Peoples R China

House dust mites produce the allergens causing allergic diseases. Predicting risk level of mites infestation through environmental conditions instead of using complex detection methods can increasing people's attention to mites and avoid huge detection cost. Mite allergens Der 1 (Der f 1 + Der p 1) in 101 residential apartments in different regions of China were measured. Indoor environmental parameters were continuously monitored and occupant surveys were also collected. Der 1 over 2000 ng/g is defined as mite infestation risk level. Compared with logistic regression and support vector machine (SVM), the prediction results of the extremely gradient boosting (xgboost) model are more accurate (ACC = 0.838, Recall = 0.844) and highly interpretable, thus it is the most suitable method for mite risk level prediction. Indoor environment data of other cities in China were collected for prediction, "risk level map of mite infestation in China" was produced. The predicted results showed that risk level of mite infestation in southern China are generally higher than in northern cities. Based on the well-trained xgboost prediction model, the relationship between input features and probability of mite infestation reaching risk level (P-R=1) can be found: 1) "mite active breeding zone" was defined with temperature between 11 and 30 degrees C and relative humidity 53%-80%, where P-R=1 exceeds 70%. 2) Increasing frequency of cleaning (both washing cleaning and vacuum cleaning) is effective for reducing risk level of mite infestation, but in humid environments (where relative humidity exceeds 53%) the effectiveness of cleaning is limited.

关键词： Mite allergen Indoor environment Risk level prediction Machine learning xgboost algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Construction of Key Personnel Judgment Model Through Data Label

Research on Construction of Key Personnel Judgment Model Thr...

引用

作者： Wei Li Changmin Chen Yi Li Wuhan FiberHome Digital Technology Co. LtdChina Information Communication Technologies Group Corporation School of Mathematical Sciences Huaibei Normal University

Key personnel are important business objects in the management and control of public security *** big data and machine learning technology,it is of great significance to model the years of police’s experience on research and judgment for the actual combat and the construction of Public Security Prevention and Control *** at the problem of complicated data type and low quantization degree of public security data,which makes it inconvenient to use machine learning for model analysis directly,a method of constructing public security personnel label system is proposed in this paper to transform complex business data into quantized label features,and on this basis,a key personnel judgement model is constructed by using FP-Growth and xgboost *** comparative analysis,the research results show that the judgment model proposed in this paper is better than the traditional business integral model and logistic regression algorithm in Accuracy,Precision and Recall,which can better serve the actual police combat.

关键词： Key personnel xgboost algorithm FP-Growth algorithm label system

来源：评论

学校读者我要写书评

暂无评论

Prediction of Double-High Biochemical Indicators Based on LightGBM and xgboost

Prediction of Double-High Biochemical Indicators Based on Li...

引用

作者： Yingying Song Xueli Jiao Yuheng Qiao Xinrui Liu Yiding Qiang Zhiyong Liu Lin Zhang College of Computer Science and Technology Jilin University College of Software Jilin University Information Science and Technology College Northeast Normal University

In recent years,cardiovascular and cerebrovascular diseases have seriously jeopardized people's ***-high,that is,the collective name of hyperlipidemia and hypertension,is one of the main causes of cardiovascular and cerebrovascular diseases in clinical *** order to predict the risk of cardiovascular and cerebrovascular diseases,various countries have developed disease risk prediction models which is suitable for their own *** order to predict the probability of diseases caused by double-high,we analyze the effects of different features and their weights on double-high diseases by Machine Learning,and propose a double-high diseases prediction model based on the LightGBM algorithm and the xgboost *** this paper,the prediction model is constructed by the user's physical examination data,and five biochemical indicators such as systolic blood pressure,diastolic blood pressure,serum triglyceride,serum high-density lipoprotein and serum lowdensity lipoprotein are used as the auxiliary judgment ***,the model fusion is performed according to the results of the *** mean square error(MSE) after calculating the logarithm of the predicted value and the true value is used as the evaluation criteria,and the probability that the users are suffering from double-high disease is predicted based on this.

关键词： LightGBM algorithm xgboost algorithm double-high biochemical index prediction

来源：评论

学校读者我要写书评

暂无评论

A New Approach for Power-Saving Analysis in Consumer Side Based on Big Data Mining

A New Approach for Power-Saving Analysis in Consumer Side Ba...

引用

IEEE-Power-and-Energy-Society General Meeting (PESGM)

作者： Chen, Haiwen Wang, Shouxiang Tian, Yingjie Tianjin Univ Minist Educ Key Lab Smart Grid Tianjin 300072 Peoples R China State Grid Shanghai Elect Power Res Inst Org Shanghai 200122 Peoples R China

ISBN: (纸本)9781538677032

With the development of smart grid, power companies have accumulated massive amounts of data including running data of electricity distribution and multi-dimensional data about meteorology, users' file and social economy. In this article, we propose a power-saving analysis method based on big data mining. Firstly, all users belonging to the same industry should be extracted, then high-dimension data would be clustered based on the indexes describing the characteristic of electricity consumption. Secondly, the benchmark user will be selected based on the comprehensive assessment. So each user's power-saving potential can be calculated compared with the benchmark user, then the power-saving sensitivity coefficients can be calculated by using partial least squares regression, which leads to effective energy-saving strategies. Finally, the electricity saving prediction model is established by the xgboost algorithm. The analysis process is performed with field data and a power-saving analysis platform is applied in Shanghai demonstrating the method's effectiveness.

关键词： Power-saving analysis high-dimension data clustering sensitivity coefficients partial least squares regression xgboost algorithm

来源：评论

学校读者我要写书评

暂无评论

Using Climate Factors to Predict the Outbreak of Dengue Fever 7

Using Climate Factors to Predict the Outbreak of Dengue Feve...

引用

7th International Conference on Digital Home (ICDH)

作者： Jia, Nan Liao, Xianyi Chen, Jie Chen, Xiangping Chen, Jing Dong, Guanghui Liu, Kangkang Hu, Gang Hebei GEO Univ Sch Management Sci & Engn Shijiazhuang 050031 Hebei Peoples R China Sun Yat Sen Univ Natl Engn Res Ctr Digital Life Sch Data & Comp Sci Guangzhou 510006 Guangdong Peoples R China Guangzhou Univ Chinese Med Affiliated Hosp 1 Guangzhou 510405 Guangdong Peoples R China CMA Guangzhou Inst Trop & Marine Meteorol Guangzhou 510080 Guangdong Peoples R China Sun Yat Sen Univ Sch Publ Hlth Dept Prevent Med Guangzhou Key Lab Environm Pollut & Hlth Risk Ass Guangzhou 510080 Guangdong Peoples R China Sun Yat Sen Univ Policy Res Off Guangzhou 510275 Guangdong Peoples R China

ISBN: (纸本)9781538694961

Dengue fever is a kind of serious infectious disease associating with climate. It spreads in Guangzhou with numerous cases including mortality records over the last ten years. Thus, analyzing and predicting the dengue fever to avoid an dengue outbreak and reduce the personal safety loss is urgent and necessary. In this paper, we build a prediction model based on XGBoosst algorithm to explore the relationships between multiple climate factors (such as temperature, humidity, rainfall, etc.) and incidence of dengue fever. The encouraging experimental results demonstrate the feasibility and effectiveness of our prediction model.

关键词： dengue forecast model xgboost algorithm climate factors feature extraction

来源：评论

学校读者我要写书评

暂无评论

Research on Airport Taxi Optimization Scheduling based on Artificial Intelligence

Research on Airport Taxi Optimization Scheduling based on Ar...

引用

作者： Ye Zhao School of North China Electric Power University

With the rapid development of China's transportation industry, aircraft has become one of the important means of transportation for people to travel. Due to the particularity of aircraft, the construction of airport is located in the periphery of the city, so the taxi has become an important public transportation tool to connect the airport and the city. Taxi drivers will be faced with two choices: go to the arrival area and wait in line to take them back to the city, or leave the airport empty and return to the city. Therefore, how to reasonably optimize and schedule the number of cars and passengers to maximize the interests of taxi drivers has become an important issue.

关键词： TDABC modeling method Interpolation and fitting xgboost algorithm

来源：评论

学校读者我要写书评

暂无评论

考虑竞争的电影首映日票房集成预测模型研究

引用

管理科学 2021年第4期

作者：唐中君吴凡倪浪

电影首映日票房预测对该日排片、后续放映日票房及总票房有显著影响。本文在构建考虑竞争的电影首映日票房预测变量集的基础上，建立首映日票房集成预测模型。首先使用多元线性回归（multiple linear regression，MLR）、支持向量回归（... 详细信息

电影首映日票房预测对该日排片、后续放映日票房及总票房有显著影响。本文在构建考虑竞争的电影首映日票房预测变量集的基础上，建立首映日票房集成预测模型。首先使用多元线性回归（multiple linear regression，MLR）、支持向量回归（support vector regression，SVR）、套索回归（Least absolute shrinkage and selection operator，Lasso）和极端梯度提升（Extreme Gradient Boosting，xgboost）等算法建立基学习器，随后使用xgboost算法作为原学习器构建堆栈集成预测模型，最后利用收集到的数据进行对比实验。实验证明，加入竞争变量的电影首映日票房预测变量集适用于首映日票房预测；相比单一模型，该集成预测模型的准确性、泛化性能和稳定性均有提升，相比较传统预测方法对首映日票房预测更准确。提出的集成预测模型有助于提升首映日票房排片的有效性。

关键词：映前票房预测首映日票房集成模型堆栈泛化 xgboost算法　　premiere release prediction release day box office ensemble model stack generalization xgboost algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of the xgboost on the Assessment of Transient Stability of Power System

Application of the XGBOOST on the Assessment of Transient St...

引用

International Conference on Electronical, Mechanical and Materials Engineering

作者： Sen Shen Qunying Liu Xinchen Tao Shaojian Ni dept.School of Optoelectronic Science and Engineering University of Electronic Science and Technology of China dept.School of Automation Engineering University of Electronic Science and Technology of China

ISBN: (纸本)9781510882584

In the context of big data, machine learning plays an important role in many fields. With the increasing scale of power system and capacity of power grid, it becomes more and more complicated to accurately evaluate the transient stability of power system. In this paper, a power system transient stability assessment method based on xgboost algorithm is proposed. The xgboost algorithm is introduced to train the decision tree model and evaluate the transient stability of power system by converting the simulated power system operating data into the characteristic variables of power system. The results show that the training model of the algorithm can solve this kind of problem accurately and quickly.

关键词： machine learning power system xgboost algorithm transient stability

来源：评论

学校读者我要写书评

暂无评论

An Accident Prediction Approach Based on xgboost 12

An Accident Prediction Approach Based on XGBoost

引用

12th International Conference on Intelligent Systems and Knowledge Engineering (IEEE ISKE)

作者： Shi, Xuehuai Li, Qianmu Qi, Yong Huang, Tiantian Li, Jianmei Nanjing Univ Sci & Technol Sch Comp Sci & Technol Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781538618295

As an important threat to public security, urban fire accident causes huge economic loss and catastrophic collapse. Predicting and analyzing the interior rule of urban fire accident from its appearance needed to be solved in the field. In this paper, we propose a new urban fire accident prediction approach based on xgboost. The method determines the predictive indexes in a quantitative and qualitative way from different characteristics in various kinds of fire accidents. For screening the features we need, we adopt the feature selection algorithm based on association rules. For data cleaning, we use a method based on Box-Cox transformation that transforms the continual response variables from the feature space for removing the dependencies on unobservable errors and the predictor variable to some extent. Then we use the data to train the model based on xgboost to obtain the best prediction accuracy. Experiments show that the method provides a feasible solution to urban fire accident prediction. The method contributes to improving the public security situation, we have added the method and related model to the City in a box (TM), Shenzhen Aerospace Smart City System Technology Co.,Ltd.

关键词： Box-Cox Transformation xgboost algorithm Accident Prediction

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：