Project suggestions for CS 4033/5033 Fall 2009

The following list of project suggestions is intended to get your project ideas started. Please feel free to come up with your own project ideas as well! Also, feel free to take one of these projects and modify it. Examine the previous year's suggestions for even more project ideas.

Predicting convectively induced turbulence

• The main question for this project is: Can we improve the prediction of convectively induced turbulence?
  • We've had two major airline accidents in the news this summer related to turbulence. One caused the loss of life of everyone on board and one only injuries. In both cases, thunderstorms (convection) were the root cause of the turbulence.
  • The current turbulence prediction product (called the Graphical Turbulence Guidance) is available here
• This year's annual contest for the AMS annual meeting is to predict turbulence for convectively induced turbulence from the summer of 2006. The details for the contest are here. Previous contests have involved monetary prizes which may happen again this year (they are looking for a sponsor).

Automatically detecting heatbursts and drylines (and fronts?)

• Living in Oklahoma provides us with some of the strangest and fastest weather changes in the country. In addition, Oklahoma is home to the densest observing network of ground-based weather stations in the country. In this project, you would combine information from the Oklahoma Mesonet with stored radar data to understand and automatically detect various aspects of severe weather. Ideas include but are not limited to detecting drylines, heatbursts, and fronts.

Understanding the dynamics of severe storms

• I have over 6 TB of simulated supercell thunderstorms available for study. I have several research projects using this data already and am quite open to ideas. Suitable machine learning project ideas include learning bayesian networks to predict storm dynamics (likely a dynamic bayesian network), learning decision trees to predict a particular aspect of storm classification, learning a probability model of how storms move, etc. Talk to me for more ideas if you are interested!

Viral networking (or other social networking projects)

• Imgine developing a new product at a startup company. You believe the product is great but you need to find the best way to market it. It is particularly well suited to a particular population and you need to find the best people to give your limited number of demo products to. In this project, you could analyze your social network (e.g. a facebook network?) to find the best people to market the product to.

Public health prediction

• Many public health datasets have properties that can be examined and predicted using machine learning.
  • One such data set is from the National Longitudinal Study of Adolescent Health.
  • Another data set is the Oklahoma Department of Public Health. I have a few of these data sets available (talk to me if you want to use them) but you can also download lots of aggregate statistics for free.
  • The Vaccine Adverse Event Reporting System is another public health data set that you can download.
  • There are tons more - if you have an interest in public health data, you can likely find a publically available data set to use for learning.

iPhone application

• We have a educational licene for iPhone development (I'm using it in my other class) and anyone who wants to try iPhone app development using ML is welcome. Since this is a hard platform to write for unless you already know objective C, you'll need to talk to me about this but it could be neat!

Facebook app

• I'm sure you can think of fun applications for facebok that use machine learning. Think about your social networks and what you might be able to do with them!

SimWar

• This comes from a talk on google video: a design for a game called SimWar. Scroll to 44"45 in the video.

This page written by amcgovern [at] ou.edu.

Last updated: May 23, 2016 1:59 PM