87.txt

This complete matlab for neural network

发信人: NAOMIELIE (雁来红), 信区: DataMining
标  题: Re: 最近来了几个新面孔阿，?迎
发信站: 南京大学小百合站 (Fri Mar 28 23:45:58 2003)

I think Ke Wang's method based on association rule mining for xml schema
mining is quite inefficient, for a friend of mine used to test it in details.


The two papers on vldb2000 (?) about xmill and xtract are interesting 
for this topic. One is based on xml indexing techniques (dataguide and
inversed dataguide), the other one is based on generalization techniques.

:)

【 在 suelove 的大作中提到: 】
: semistructured data mining is quite popular.
: you can also considering XML mining, schema extraction/mining.
: for this research topic, the main method will be used is association rule ..
: ng.
: 
: for text clustering, you must be good at statistics. this is what I know.
: 
: Actually my research is about web mining.
: 
: 
: 【 在 knife 的大作中提到: 】
: : 呵呵，我是新人，论文想在web内容?掘和文本?掘之间选一个方向，
: : 感?web内容?掘中的结?化和半结?化?掘可能会比较好做一点，但
: : 多媒体?掘这一块一点也不?，所以还在犹豫是不是就做文本?掘算了，
: : 但不论是做web内容?掘还是文本?掘，最头疼的一块就是文本的预?理，主要是
: : 怎?提取特征值，?位大虾在这方面有所指教的话将不胜感激。

--

※ 来源:．南京大学小百合站 http://bbs.nju.edu.cn [FROM: 210.172.103.218]