现代模式识别 - Read（Modern pattern recognition - Read）.docVIP

下载本文档

3
0
约1.37万字
约 51页
2017-07-24 发布于河南
举报
版权申诉

现代模式识别 - Read（Modern pattern recognition - Read）.doc

1、有哪些信誉好的足球投注网站（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

现代模式识别 - Read（Modern pattern recognition - Read）

现代模式识别 - Read（Modern pattern recognition - Read） Data worth having From the usual study, accumulation and summary Where there is a problem, there must be some Please also criticize and correct me! Modern pattern recognition Algorithm implementation The principle of Parzen window method: In statistical decision making Class probability density p (x / WI), class probability density P (WI) or posterior probability P (WI / x) need to be known But in practical application The knowledge is often unknown or incomplete This requires determination of samples based on samples from this class Estimated sequence: (1) To estimate P (x) Its with N V Of In theory To hasten into P (x) It must have its volume V to be near zero Meanwhile, let N Infinity The Parzen window reduces the volume VN of the region sequence by a function of N with the increase of N for example At this point, both / and N should be appropriately limited So as to converge to P (x) In n-dimensional feature space We take an n-dimensional hypercube region Its edge length is hN Its volume therefore N samples fall into the cubes number of samples Replace the upper (1) formula Probabilistic density estimation at x points is available: among (x) window functions that satisfy the following two conditions: In 1. In 2. Easy to know Condition 1 guarantees non negative Condition 2 guarantee Procedures used in four window functions: 1. square window function: 2. normal window function 3. exponential window function 4. trigonometric window function Two, the concrete realization 1., this method is implemented in MATLAB The result is as follows H1 = 0.25, H1 = 1, H1 = 4 N = 1 N = 16 H1 = 0.25, H1 = 1, H1 = 4 N = 256 N = H-infinity As can be seen from the result of the graph The larger the sample size The more accurate the estimate is At the same time, when the N is small, the window width is chosen to estimate the result properly Have some influence When N is small The window function has a great influence on the estimation re