查看Downloads的源代码

==WebMind 浏览器==

WebMind浏览器是WSI实验室开发的个性化的浏览器。该浏览器集成了意图预测与推荐和心理预测模型，模型的主要功能是通过分析您最近会话内的浏览动作来预测您的信息需求以及心理状态，并根据此意图和心理来生成推荐信息。点击右上角的两个图片分别可以获取当前你的心理状态以及系统为您生成的推荐页面。欢迎使用，点击此处[http://wsi.gucas.ac.cn/webmind/WebMind-v1.43.rar 下载]，点击此处[http://wsi.gucas.ac.cn/webmind/WebMind-v3.pdf 下载使用指南]，如有问题请联系：webmind.wsi@gmail.com

[[Image:screenshot1.jpg|center]]

[[Image:recommendshot1.jpg|center]]

==Medline Search==

Medline search is a portal based on medline search. Here, we want to provide personalized services beyond generic search, ...

==CiteSeerX @ GUCAS==

CiteSeerX@GUCAS is a cooperator site of CiteSeerX at PSU. We plan to integrate behavior analysis with search, that is, to predict the user's intention based on his/her search behavior to refine the search. Please visit [http://wsi.gucas.ac.cn/citeseerx/index;jsessionid=A77F1419DB3FD390EE20EA66DD2E1735 here ]...

==WebFuret --- An Intelligent Web Browser==

WebFuret is an intelligent Web browser which can recommend pages relevant to the user's current search task without burdening the user with explicit input. It's Passive, Effective and Complete-Web ...

==WebIC --- An Effective Complete-Web Recommender System==

WebIC is an IE-Based browser which is expected to predict IC-Pages for web users ... can also be used for annotation [http://wsi.gucas.ac.cn/webic/ ...]

==Association Rule(Apriori)==

This is my implementation of Apriori in:

R. Agrawal, R. Srikant, Fast Algorithms for Mining Association Rules, Proc. of the 20th Int'l Conference on Very Large Databases, Santiago, Chile, Sept. 1994. Expanded version available as IBM Research Report RJ9839, June 1994.

==Sequential Pattern(WAP)==

This is my implementation of:

J. Pei, J. Han, B. Mortazavi-Asl, and H. Zhu `` Mining Access Patterns Efficiently from Web Logs (PDF), Proc. 2000 Pacific-Asia Conf. on Knowledge Discovery and Data Mining (PAKDD'00), Kyoto, Japan, April 2000.

==AIE(Annotation Internet Explorer)==

AIE is the software that I have developed for our travel study, you can take it as "Annotation Internet Explorer" or "AI Explorer". It is a IE-like browser, and I add other functions beside the navigation, such as report, checking, and submit. The goal of the software is to collect log files in client for my research on Web Usage Mining. So any action of the user's navigation will be recorded, so even if the user clicks Back or Forward button, the entry will be recorded in the log file.

The system is developed in Windwos NT 4.0, Microsoft IE 5.0, Visual C++ 6.0.

The software is for research now. And if you want to use it in your research, or want source code, please contact us.

==DMTalker==

DMTalker is a software for Mandarin sentence prosodic rules mining and Text-To-Speech, and it is implemented on Borland C++Builder 3.0.

The pitch models which are now being used in Mandarin Text-To-Speech are extracted by linguistics experts, and they are described qualitatively and with low precise. To acquire more accurate prosodic rules, data mining is employed to extract pitch models from actual speech, and the result is encouraging. The preprocessing of the prosodic rules data mining includes text analysis, time-wrapping, moving average, and normalization, and typical pitch series have been extracted by clustering analysis on the preprocessed pitch arrays for discretion. Decision tree(C4.5) and neural network have been used for extracting pitch variation patterns from preprocessed train data.