基于模糊粗糙集的压缩近邻规则比较分析-comparative analysis of compressed nearest neighbor rules based on fuzzy rough set.docxVIP
- 1、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。。
- 2、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
- 4、该文档为VIP文档,如果想要下载,成为VIP会员后,下载免费。
- 5、成为VIP后,下载本文档将扣除1次下载权益。下载后,不支持退款、换文档。如有疑问请联系我们。
- 6、成为VIP后,您将拥有八大权益,权益包括:VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
- 7、VIP文档为合作方或网友上传,每下载1次, 网站将根据用户上传文档的质量评分、类型等,对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
查看更多
基于模糊粗糙集的压缩近邻规则比较分析-comparative analysis of compressed nearest neighbor rules based on fuzzy rough set
优秀毕业论文
精品参考文献资料
摘 要
摘 要
近邻规则是模式识别、机器学习、数据挖掘中广泛使用的一种基于样本实例的分类 方法,该算法通过从训练集中寻找与待分类样本最近的样本来确定其类别。然而近邻规 则的一个最大的缺点是在计算未见样本的所属类别时,需要计算该未见样本与训练集中 所有样本的距离,算法的时间复杂度和空间复杂度都很高。另一方面,在判断未见样本 的所属类别时,训练集里的所有样本都被看成是同等重要的。那么,如果训练集中的样 本存在不一致性,近邻规则的性能会大大降低。针对以上两个问题,降低训练集的规模 成为近邻规则的研究热点。
模糊粗糙集是将粗糙集和模糊集结合起来处理不精确和不确定信息的数学理论。目 前关于模糊粗糙集的研究主要集中在模糊粗糙集的定义及其约简上。从模糊粗糙集的定 义中可以得出样本隶属于上近似集合、下近似集合以及边界域集合的程度,而这些隶属 度表明了样本的重要程度。本文提出了两种基于模糊粗糙集的模糊压缩近邻规则(CF K-NN1 和 CF K-NN2)和一种改进模糊近邻规则,并对不同的压缩近邻规则进行了比较 研究。这两种压缩规则包含三个步骤:
(1)利用模糊粗糙集技术求得一个模糊属性约简;
(2)分别从模糊粗糙集正域(边界域)中选取样本子集;
(3)从样本子集中抽取模糊分类规则。 在若干数据集上得到的实验结果以及对实验结果的统计分析证实了两种方法是可
行的、有效的,并且优于之前学者提出的压缩近邻规则,比如 CNN,RNN,ICF 等。比 较研究得出了以下结论:算法 CFK-NN1 选择的样本个数比算法 CF K-NN2,CNN,RNN 和 ENN 选择的少,比算法 ICF 和 MCS 选择的多。算法 CF K-NN1 的测试精度比算法 CF K-NN2 的测试精度稍高,但两个算法的测试精度都高于其他算法。
关键词 近邻规则 粗糙集 模糊集 模糊粗糙集 样本选择
II
II
Abstract
Abstract
The NN algorithm is a simple and well-known learning scheme based on the instances which classifies an unseen instance by finding its closest neighbor in training set. Due to its simplicity and effectiveness, it is widely used in many fields, such as pattern recognition, machine learning and data mining. However, the main drawback of NN is the whole training set must be stored in the computer to classify an unseen instance, and its distance to each one of the stored instances is computed, so that the time complexity and space complexity is high. Another problem encountered in NN is that all of instances in training set are considered equally important. When the instances with different class labels are overlapped, the performance of the NN algorithm will degrade greatly. To overcome the drawbacks above, reducing the dimensions of the datasets becomes hot.
Fuzzy rough set is a mathematical theory which is combining fuzzy set and rough set and dealing with information with imprecision and vagueness. At the present time, the research of fuzzy rough set focus on the definition and reduct methods. From the definition of upper approximation, lower approx
您可能关注的文档
- 基于锚杆传力性能的铁底板锚固设计分析-design and analysis of iron floor anchorage based on bolt force transmission performance.docx
- 基于满意度的人居环境宜居性评价——以兰州市为例-evaluation of livability of human settlements based on satisfaction —— a case study of lanzhou city.docx
- 基于猫群算法的无线传感器网络路由优化算法分析-analysis of routing optimization algorithm for wireless sensor networks based on cat group algorithm.docx
- 基于慢正电子束流技术制备sio,2薄膜的应用-application of sio _ 2 thin films prepared by slow positron beam current technology.docx
- 基于媒体感知arq的无线视频流qos保障分析-qos guarantee analysis of wireless video stream based on media aware arq.docx
- 基于锚节点的无线传感器网络定位技术分析-analysis of localization technology in wireless sensor network based on anchor node.docx
- 基于煤化工行业的供应链绩效评价分析-analysis of supply chain performance evaluation based on coal chemical industry.docx
- 基于满意度的科研人员全面薪酬激励研究——以西安市高新技术企业为例-research on incentive mechanism of comprehensive remuneration of scientific research personnel based on satisfaction —— taking xi 'an high-tech enterprises as an example.docx
- 基于煤矿本质安全管理体系的员工不安全行为分析-analysis of employees' unsafe behaviors based on coal mine intrinsic safety management system.docx
- 基于锚杆组群工作荷载无损检测的巷道围岩稳定性分析-stability analysis of roadway surrounding rock based on nondestructive testing of anchor group working load.docx
- 基于模糊层次分析法的康保协合风电场项目综合评价分析-comprehensive evaluation and analysis of kangbao wind farm project based on fuzzy analytic hierarchy process.docx
- 基于模糊多属性-topsis法的矿井通风系统优化分析-optimization analysis of mine ventilation system based on fuzzy multiple attributes - tops is method.docx
- 基于模糊粗糙集方法的国际工程项目承包风险评价分析-risk evaluation and analysis of international project contracting based on fuzzy rough set method.docx
- 基于模糊分析法的煤炭企业可持续成长能力评价分析-evaluation and analysis of sustainable growth ability of coal enterprises based on fuzzy analysis method.docx
- 基于模糊多属性决策和递阶质量屋汽车轻量化材料选择方法-automobile lightweight material selection method based on fuzzy multi-attribute decision-making and hierarchical quality house.docx
- 基于模糊概念图知识表示的专家系统的分析-analysis of expert system based on fuzzy concept map knowledge representation.docx
- 基于模糊方法的粗糙支持向量机算法分析-analysis of rough support vector machine algorithm based on fuzzy method.docx
- 基于模糊关联规则的入侵检测系统分析-analysis of intrusion detection system based on fuzzy association rules.docx
- 基于模糊灰色理论家电产品生命周期绿色性评价方法的分析-analysis of green evaluation method of household appliance product life cycle based on fuzzy grey theory.docx
- 基于模糊积分的协作频谱感知技术分析-analysis of cooperative spectrum sensing technology based on fuzzy integral.docx
文档评论(0)