• LOGIN

MLBio+ Laboratory - Machine Learning in Biomedical Informatics

Home

Navigation

  • MLBio+ Laboratory
  • Classes
  • Feed aggregator

Contact Me

Office: 4423 Engr Building
Office Hours: T 4:00-5:00 pm
rangwala@cs.gmu.edu
703-993-3826

Project Ideas

The project gives you an opportunity to explore in depth a particular topic/area of the course that interests you. The topic of the project, of course, should be related to the material covered in class, but otherwise you are free to select the specific topic. Possible types of projects include:

  • An application research project: The project demonstrates the application of some techniques discussed in class in an application domain (e.g., text mining, bioinformatics, computer vision, image processing, artificial intelligence etc.). Properties, drawbacks, advantages of the used techniques are analyzed within the context of the explored application domain.
  • A theoretical or methodological research project: A study of different classes of models and approaches; proving either theoretically or experimentally properties of known algorithms; designing a new approach. The book website provides these term projects and resources that you might want to consider for your project.
  • Examples of projects include :

    1. Application Paper in Bioinformatics has a decision tree with cost-sensitive classification.
    2. Prof. Angelos Stavrou suggested an intrusion detection problem in network traffic data. Currently the system uses an expert of weak classifiers, which could be potentially boosted using ensemble methods. Here is the paper for an introduction .
    3. Bioinformatic Projects related to my research include the problem of sequence classification i.e., classify a protein sequence into multiple classes. Here are pointers to the work of remote homology detection . Related to this is the task of annotating residues using neighboring residues. Check out PROSAT and MONSTER
    4. Netflix Movie Recommendation System. Its a sequential data mining project. There are a whole bunch of papers/talks on what people have done for the Netflix competition. Please see the link.
    5. Some more data mining contests. ICMD 2007 contest , ECML 2008 Spam Detection in Social Bookmark contest and ECML 2006 Spam Email Detection Challenge.
    6. this year's KDD CUP 2008 or the previous KDD cup competitions.

User login

  • Request new password

News Highlights

  • Syed F to join the Lab.
  • Paper Accepted at Journal of Chemical Information & Modeling
  • Huzefa to serve on program committee for SIAM Data Mining Conference 2010 (SDM 2010)
  • Huzefa to serve on program committee for HiCOMB 2010
  • New funding received from NSF IIS for bridging chemical and biological spaces.
  • Two open positions for graduate students (MLBio+ Laboratory)
  • Ammar submits his 1st paper!
  • Salman's paper accepted at WISM-AICI 2009.
  • Huzefa presents 2 posters at ISMB 2009
  • Sheng Li and Anveshi join the lab this Fall
more

Bioinformatics & Data Mining

  • PrePrint: Skewed Rotation Symmetry Group Detection
  • PrePrint: Object Detection with Discriminatively Trained Part Based Models
  • PrePrint: Large Scale Discovery of Spatially Related Images
  • PrePrint: Epitomic Location Recognition
  • PrePrint: Class Conditional Nearest Neighbor for Large Margin Instance Selection
more

(c) Rangwala 2008, George Mason University, Fairfax, VA