Posted by turbogeek
on December 14, 2004 at 8:03 AM PST
Two more projects have been added to the Global Education and Learning Community (GELC) at java.net. This week we have a new project based on JXTA P2P for bioinformatics. The second project is neural networks that will help categorize poems after their authors. Take a look and see if there is a project you are interested in and email the owners on how you can help out. Remember this is a community and participation is what this place is all about.
Chinook is a peer-to-peer (P2P) bioinformatics service. The goal of the Chinook platform is to facilitate exchange of analysis techniques within a local community and/or worldwide. Chinook operates by turning command-line applications into services which are broadcast over a virtual network. Currently, there are over 25 analysis services that have been made "Chinook-ready". These range from alignment to regulation prediction algorithms. Furthermore, Chinook is designed to make it extremely easy to add new services. Chinook clients can be operated from Java, Perl, or within applications like Sockeye. (And soon Pegasys, and OrthoSeq). All user's guides and manuals are currently available via checkout of source.
I intend to create various neural networks that will help categorize poems after their authors. In the first phase I’m going to use letter patterns to do that, as per a paper by Johan F. Hoorn, Stefan L. Frank, Wojtek Kowalczyk and Floor Van Der Ham. Unlike in their research, I want to use self organizing maps, not supervised feed-forward networks. In a second phase, I’ll replace the letter combination input with some NLP analysis, though exactly how I still have to document myself. Practical purposes of this application would be to categorize popular poems (creations with multiple authors - folklore), to help in settling authorship disputes etc. In future, I want to expand this to prose and even music. The development will be done in Java 5.