Mapping landslide susceptibility at the Three Gorges Reservoir, China, using gradient boosting decision tree,random forest and information value models

This work was to generate landslide susceptibility maps for the Three Gorges Reservoir(TGR) area, China by using different machine learning models. Three advanced machine learning methods, namely, gradient boosting decision tree(GBDT), random forest(RF) and information value(InV) models, were used, and the performances were assessed and compared. In total, 202 landslides were mapped by using a series of field surveys, aerial photographs, and reviews of historical and bibliographical data. Nine causative factors were then considered in landslide susceptibility map generation by using the GBDT, RF and InV models. All of the maps of the causative factors were resampled to a resolution of 28.5 m. Of the 486289 pixels in the area,28526 pixels were landslide pixels, and 457763 pixels were non-landslide pixels. Finally, landslide susceptibility maps were generated by using the three machine learning models, and their performances were assessed through receiver operating characteristic(ROC) curves, the sensitivity, specificity,overall accuracy(OA), and kappa coefficient(KAPPA). The results showed that the GBDT, RF and In V models in overall produced reasonable accurate landslide susceptibility maps. Among these three methods, the GBDT method outperforms the other two machine learning methods, which can provide strong technical support for producing landslide susceptibility maps in TGR.

Attribute Reduction in Interval and Set-Valued Decision Information Systems

In many practical situation, some of the attribute values for an object may be interval and set-valued. This paper introduces the interval and set-valued information systems and decision systems. According to the semantic relation of attribute values, interval and set-valued information systems can be classified into two categories: disjunctive (Type 1) and conjunctive (Type 2) systems. In this paper, we mainly focus on semantic interpretation of Type 1. Then, we define a new fuzzy preference relation and construct a fuzzy rough set model for interval and set-valued information systems. Moreover, based on the new fuzzy preference relation, the concepts of the significance measure of condition attributes and the relative significance measure of condition attributes are given in interval and set-valued decision information systems by the introduction of fuzzy positive region and the dependency degree. And on this basis, a heuristic algorithm for calculating fuzzy positive region reduction in interval and set-valued decision information systems is given. Finally, we give an illustrative example to substantiate the theoretical arguments. The results will help us to gain much more insights into the meaning of fuzzy rough set theory. Furthermore, it has provided a new perspective to study the attribute reduction problem in decision systems.

Remote Sensing Image Classification Based on Decision Tree in the Karst Rocky Desertification Areas: A Case Study of Kaizuo Township

Karst rocky desertification is a phenomenon of land degradation as a result of affection by the interaction of natural and human factors.In the past,in the rocky desertification areas,supervised classification and unsupervised classification are often used to classify the remote sensing image.But they only use pixel brightness characteristics to classify it.So the classification accuracy is low and can not meet the needs of practical application.Decision tree classification is a new technology for remote sensing image classification.In this study,we select the rocky desertification areas Kaizuo Township as a case study,use the ASTER image data,DEM and lithology data,by extracting the normalized difference vegetation index,ratio vegetation index,terrain slope and other data to establish classification rules to build decision trees.In the ENVI software support,we access the classification images.By calculating the classification accuracy and kappa coefficient,we find that better classification results can be obtained,desertification information can be extracted automatically and if more remote sensing image bands used,higher resolution DEM employed and less errors data reduced during processing,classification accuracy can be improve further.

Generating Decision Trees Method Based on Improved ID3 Algorithm

The ID3 algorithm is a classical learning algorithm of decision tree in data mining.The algorithm trends to choosing the attribute with more values,affect the efficiency of classification and prediction for building a decision tree.This article proposes a new approach based on an improved ID3 algorithm.The new algorithm introduces the importance factor λ when calculating the information entropy.It can strengthen the label of important attributes of a tree and reduce the label of non-important attributes.The algorithm overcomes the flaw of the traditional ID3 algorithm which tends to choose the attributes with more values,and also improves the efficiency and flexibility in the process of generating decision trees.

Research on the Intelligent Distribution System of College Dormitory Based on the Decision Tree Classification Algorithm

The trend toward designing an intelligent distribution system based on students’individual differences and individual needs has taken precedence in view of the traditional dormitory distribution system,which neglects the students’personality traits,causes dormitory disputes,and affects the students’quality of life and academic quality.This paper collects freshmen's data according to college students’personal preferences,conducts a classification comparison,uses the decision tree classification algorithm based on the information gain principle as the core algorithm of dormitory allocation,determines the description rules of students’personal preferences and decision tree classification preferences,completes the conceptual design of the database of entity relations and data dictionaries,meets students’personality classification requirements for the dormitory,and lays the foundation for the intelligent dormitory allocation system.

Ordinal Decision Trees

In many decision making tasks,the features and decision are ordinal.Several ordinal classification learning algorithms have been developed in recent years,it is shown that these algorithms are sensitive to noisy samples and do not work in real-world applications.In this work,we propose a new measure of feature quality, called rank mutual information.Then,we design an ordinal decision tree(REOT) construction technique based on rank mutual information.The theoretic and experimental analysis shows that the proposed algorithm is effective.

Decision-tree induction from self-mapping space based on web

An improved decision tree method for web information retrieval with self-mapping attributes is proposed.The self-mapping tree has a value of self-mapping attribute in its internal node,and information based on dissimilarity between a pair of mapping sequences.This method selects self-mapping which exists between data by exhaustive search based on relation and attribute information.Experimental results confirm that the improved method constructs comprehensive and accurate decision tree.Moreover,an example shows that the self-mapping decision tree is promising for data mining and knowledge discovery.

An Analysis of the Value of Additional Information Provided by Water Quality Measurement Network

European Community policy concerning water is placing increasing demands on the acquisition of information about the quality of aquatic environments. The cost of this information has led to a reflection on the rationalization of monitoring networks and, therefore, on the economic value of information produced by these networks. The aim of this article is to contribute to this reflection. To do so, we used the Bayesian framework to define the value of additional information in relation to the following three parameters: initial assumptions (prior probabilities) on the states of nature, costs linked to a poor decision (error costs) and accuracy of additional information. We then analyzed the impact of these parameters on this value, particularly the combined role of prior probabilities and error costs that increased or decreased the value of information depending on the initial uncertainty level. We then illustrated the results using a case study of a stream in the Bas-Rhin department in France.

Classification Method for Dongting Lake Wetland Based on Geographic Information

[Objective] This study aimed to improve the accuracy of remote sensing classification for Dongting Lake Wetland.[Method] Based on the TM data and ground GIS information of Donting Lake,the decision tree classification method was established through the expert classification knowledge base.The images of Dongting Lake wetland were classified into water area,mudflat,protection forest beach,Carem spp beach,Phragmites beach,Carex beach and other water body according to decision tree layers.[Result] The accuracy of decision tree classification reached 80.29%,which was much higher than the traditional method,and the total Kappa coefficient was 0.883 9,indicating that the data accuracy of this method could fulfill the requirements of actual practice.In addition,the image classification results based on knowledge could solve some classification mistakes.[Conclusion] Compared with the traditional method,the decision tree classification based on rules could classify the images by using various conditions,which reduced the data processing time and improved the classification accuracy.

IT Project Evaluation and Investment Decision

There are many kinds of real options,which are valuable,in each phase of the lifetime of an information technology(IT)project.However,in the current IT investment decision theory,real options that embedded in IT projects are not considered. In this paper, the process of IT project decision and implementation is fully analyzed, the real options that may be embedded in an IT project are identified, and a real option analysis (ROA) method is proposed for evaluation of an IT project under uncertain business environment. ROA employs Black-Scholes expansion model and cancels the assumption that the cost of project is certain. The numerical example manifests that the ROA can better evaluate IT project and select the IT investment alternative. Finally, a road map is provided to help selecting the suitable evaluation method to make IT investment decision.

A Boosted Tree-Based Predictive Model for Business Analytics

Business Analytics is one of the vital processes that must be incorpo-rated into any business.It supports decision-makers in analyzing and predicting future trends based on facts(Data-driven decisions),especially when dealing with a massive amount of business data.Decision Trees are essential for business ana-lytics to predict business opportunities and future trends that can retain corpora-tions’competitive advantage and survival and improve their business value.This research proposes a tree-based predictive model for business analytics.The model is developed based on ranking business features and gradient-boosted trees.For validation purposes,the model is tested on a real-world dataset of Universal Bank to predict personal loan acceptance.It is validated based on Accuracy,Precision,Recall,and F-score.The experimentfindings show that the proposed model can predict personal loan acceptance efficiently and effectively with better accuracy than the traditional tree-based models.The model can also deal with a massive amount of business data and support corporations’decision-making process.

An Ethical Approach to Decision Design

This paper describes an approach to ethical decision design. It discusses the use of several mathematical tools applicable to the world of economics and business. It then demonstrates how the tools analogously extend themselves to making ethical decisions as supported by personal values. A review of the mathematics, including the design of a decision tree, the concept of mathematical expectation, and mathematical modeling are included.

基于多信息融合的换流站直流设备健康状态决策树评价模型

针对换流站直流设备间交互信息融合能力较差、小样本与大样本难以均衡的问题,设计基于多信息融合的换流站直流设备健康状态决策树评价模型。使用同质多传感器多信息数据融合方法对多信息实施融合处理;利用k近邻方法和层次聚类方法划分换流站直流设备健康状态量,提取健康状态量的有效信息作为输入,构建决策树评价模型,输出换流站直流设备健康状态评价结果。实验结果表明,该模型具备较好的多信息融合能力和样本均衡能力,且可从不同角度实现换流站直流设备健康状态评价,评价结果较为准确。

人工智能在图书馆的应用及风险防范

在信息技术快速发展的背景下,人工智能技术已广泛应用于图书馆,极大地提升了管理效率和服务质量,同时也带来了复杂多变的安全风险。如何应对图书馆智能化过程中可能出现的安全威胁,成为一个亟待解决的问题。在分析人工智能理论及其在图书馆的应用和人工智能技术驱动的图书馆场景化服务体系架构的基础上,探讨了人工智能引发的安全威胁及其成因,并通过机器学习技术构建图书馆智能安全防御系统,利用决策树和随机森林方法,建立一种图书馆智能化安全防御模型,旨在为人工智能在图书馆的有效应用提供一定的理论参考。

基于GF-5卫星的西藏珠勒—芒拉地区矿物蚀变信息提取及找矿前景分析

【研究目的】近年来,遥感在地质调查和矿产勘查领域取得了广泛的应用,基于多光谱遥感数据的蚀变矿物填图为地质找矿工作提供了重要技术支撑,然而基于国产高光谱遥感数据在此领域的研究却为数不多。高分五号(GF-5)较小的波谱间隔提供了相比于多光谱更为丰富的目标地物波谱信息,为矿物的精细识别提供了良好的数据源。本文主要基于GF-5开展西藏革吉南地区的矿物蚀变信息提取,同时结合Landsat-8、ASTER多光谱数据提取结果叠加对比,综合野外调查验证,进一步深化遥感在地质矿产资源调查领域的应用。【研究方法】基于多光谱数据建立了不同类别蚀变矿物的光谱指数模型,在GF-5数据蚀变信息提取方面,摒弃了传统的光谱角匹配等方法,提出了基于决策树分类辅助混合调谐匹配滤波技术进行矿化蚀变信息的提取方法,最后综合区域构造、蚀变信息提取结果等要素,圈定成矿有利区,并开展野外调查验证。【研究结果】基于Landsat-8、ASTER两种多光谱数据对铁染、羟基类(Mg-OH、Al-OH)、碳酸盐类矿物信息进行了增强与提取;基于GF-5数据识别出了方解石、钠云母、普通白云母、多硅白云母、明矾石、高岭石、地开石、绿帘石8种蚀变矿物。【结论】结合不同数据源的提取与叠加结果,证实了本文提出的矿化蚀变信息提取方法的可行性。根据野外验证情况综合揭示了该地区发育高硫型浅成低温热液蚀变矿物组合,具有斑岩-浅成低温热液矿床的成矿潜力。本文认为高光谱与多光谱数据相结合有助于后续蚀变分带的分析与更精确的成矿预测,从而更好地服务于矿产勘查工程等领域。

基于云计算的高校学生信息分类管理系统设计

现今高校学生信息体量较大,难以进行准确的信息分类管理,因此提出基于云计算的高校学生信息分类管理系统设计研究。设计系统体系结构,改进云计算技术中的决策树算法构造;以支持度与置信度最小化为目标,裁剪不准确、不频繁的决策规则;将学生信息输入至改进后的决策树中,获得学生信息分类结果,制定学生信息管理相关功能,实现高校学生信息的分类管理。测试数据显示:应用设计系统获得的学生信息分类错误率最小值为0.9%,学生信息管理规模最大值为148 GB,充分证实设计系统能够准确进行学生信息分类管理。

管理层讨论与分析能预示企业违约吗?——基于中国股市的实证分析

采用文本挖掘技术,对上市公司年报中的管理层讨论与分析(MD&A)内容进行文本分析,从文本相似度、文本可读性、文本语调以及管理层预期的角度构建了MD&A评价体系。通过构建代价敏感GBDT(csGBDT)模型,考察多维管理层讨论与分析指标对企业违约预测的影响,并进一步分析了对企业违约状态有重要影响的MD&A指标及其对违约状态作用的边际效应。研究表明:MD&A指标可以作为替代性数据源准确预测上市公司违约状态;MD&A指标相比传统违约预测变量的预测效果较差;MD&A指标在传统违约判别指标基础上提供了额外的信息含量;csGBDT模型显著提高了对企业(尤其是对违约企业)的判别能力,在违约预测的大数据方法中具有明显优势。在众多管理层讨论与分析指标中,对企业违约有重要影响的MD&A指标依次为:与前一年相比文本相似度、词汇总量、情感语调2、词汇总量/句子数量、情感语调1和管理层是否发出业绩预测。本文将企业违约预测的研究边界从结构化数据拓展到非结构化文本数据,有助于抑制信息不对称导致的企业违约风险。

基于GF-1卫星影像数据融合的冬小麦田空间信息提取

为给高标准农田建设规划和粮食安全生产措施的制定提供准确信息,在对国产GF-1/PMS卫星影像进行辐射定标、大气校正、几何校正和裁剪等预处理的基础上,经过影像融合提取了高标准麦田多地物的点像元光谱信息,通过分析不同地物光谱特征,利用波段反射率、归一化差值植被指数(NDVI)和差值植被指数(DVI)构建植被光谱特征指标阈值,进而对冬小麦田及非麦田进行分类,以获取高标准麦田的空间分布信息。结果表明,光谱特征指标选择BR_(4)>0.3、NDVI>0.619和DVI>0.317,可以较准确地从影像中识别出冬小麦田,并减少田间道路被误判为冬小麦田像元。在非麦田分类中,选择BR_(3)>0.15和BR_(4)>0.2,可将建筑用地与河流(沟渠)区分开。利用田间样方统计面积和遥感提取面积进行精度验证,总体精度可达97.33%,说明通过中、高空间分辨率遥感数据融合,结合多重光谱特征指标建立合理的分类阈值,可以准确提取冬小麦田及非麦田的分布信息。

基于决策树的社交网络隐式用户行为数据挖掘方法

为了解决社交网络隐式用户行为数据挖掘过程中关联相似性计算较为困难的问题,提出了基于决策树的社交网络隐式用户行为数据挖掘方法。将社交网络视为包含不同维度的向量空间,计算特定维度上用户的兴趣空间和兴趣点。确定样本属性集后,根据已知行为数据建立测试分支,计算该分支下子集的属性权重,不断迭代直至挖掘到同等属性的数据点为止。测试结果表明:该方法可对不同种类隐式用户行为精准挖掘,目标行为数据查找效果较好,实用性较强。

基于属性值变化的动态三支冲突分析

冲突分析有利于信息系统的问题处理。为了促进相关动态学习,将冲突分析模型推广到动态形式信息系统中,并结合三支决策思想研究基于属性值变化的动态三支冲突分析。首先,考虑单行属性值变化,研究距离矩阵的变化,得到关于冲突集、中立集、联合集的三支分析模型的变化结果。其次,类似考虑多行属性值变化,得到对应的三支分析模型的变化规律,并由此设计相关的动态更新算法。进而,针对列属性值变化,基于形式信息系统来转换成行属性值变化,从而调用行值动态更新方法。最后,实例分析说明了所得动态三支冲突分析的性质与算法的有效性。