The ACM Intelligent User Interfaces (IUI) Conference is an annual research conference that merges the areas of Human-Computer Interaction (HCI) and Artificial Intelligence (AI). Each year, a variety of papers are presented and published that demonstrate all sorts of interesting and sometimes entertaining interfaces. Here are links to lists of papers from recent years, take a look (and click the "Table of Contents" tab when you get there):
This project will initially begin with a larger group of students (perhaps 12). Each student will find a paper of interest, and present it to the rest of the group. Discussion will follow regarding the interest among other students and the feasibility of doing the project. After the presentations, the students will coalesce into subgroups of approximately 4 students each. Each subgroup will pick one of the papers to work with, and implement the project.
It should be noted that many of these papers have a significant algorithmic component to them, and so understanding and possibly implementing AI or optimization-based algorithms will likely form an important part of the project that you'll do.
What might some of these projects be? I don't want to supply examples that you'll do, because I want the team members to find projects. Therefore, I've picked a few really old ones (from IUI 2000) to illustrate the concept; you'll pick something more recent. These projects may or may not be sized appropriately for the team at hand, and thus perhaps might need tweaking; I've merely included them here to give you ideas of the sorts of things you might find.
Jabberwocky: you don't have to be a rocket scientist to change slides for a hydrogen combustion lecture: an interface for detecting the words in a slide presentation, and automatically advancing slides for you based on what you say. (This paper uses a probabilistic phrase extraction approach, which you would need to learn about and implement.)
A Calendar with Common Sense: a plugin to calendar apps that will point out problems with your appointments. Examples provided are "You are eating breakfast at 3am?" and "You are taking Lin who is a vegetarian to a steakhouse?" (This paper extracts information from appointments via queries to a pre-built lexicon/ontology, and also a set of template-based representation schemes to model common sense.)
You'll be expected to produce the following two deliverables associated with your project:
Students will have some flexibility to pick projects that fit their backgrounds, so there is no particular expertise required.