- 1、本文档共19页,可阅读全部内容。
- 2、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。
- 3、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。
- 4、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)。
查看更多
2012年国际数学建模一等奖(英文版).pdf
Team #15879 Page 1 of 19
Team Control Number
For office use only For office use only
T1 ________________ 15879 F1 ________________
T2 ________________ F2 ________________
T3 ________________ F3 ________________
Problem Chosen
T4 ________________ F4 ________________
A
Small Leaf, Big World
Abstract
This paper attempts to analyze the factors that influence the shapes and leaves mass.
Firstly, this paper deals with the classification of the leaves. Here, by taking the leaves
of tobacco as example, the first model SOM (Self-Organizing Feature Map neural network),
which possesses clustering capability, is established. Then SOM with 6×6 neurons is
utilized to train the first 14 types of tobacco leaves for 10 to 1,000 times. When the training
process is concluded, the 15th type, with its parameters being introduced, can be explicitly
and accurately placed under the category of the 11th.
Secondly, to tackle the problem of overlapping, we build the planning model of
maximal net photosynthesis rate. By means of genetic algorithm, the maximal net
photosynthesis rate is 4271mmol.cm-2s-1. Accordingly, the leaf distribution mode is superior
to the one that only targets at th
文档评论(0)