40 likes | 226 Views
FYP Projects (2014-2015). Prof. Dahua Lin dhlin@ttic.edu. Paper Recommendation System. Find relevant papers from a large database Topic relevance + Keyword matching + Impact factors + … Get exposed to real-world data analysis applications Required experience with MATLAB or Python
E N D
FYP Projects (2014-2015) Prof. Dahua Lin dhlin@ttic.edu
Paper Recommendation System • Find relevant papers from a large database • Topic relevance + Keyword matching + Impact factors + … • Get exposed to real-world data analysis applications • Required experience with MATLAB or Python • 2 – 3 students
Github Activity Analysis • Github is the most active platform for open source development. • A lot of interesting aspects to analyze: • trends of open source movement • relations between developers • which new programming languages are taking off? • Students will learn how to analyze large social networks and discover useful patterns from unstructured data. • Familiarity with git is not required. • 2 – 3 students
Distributed Data Clustering • Clustering: detect groups of similar data • Traditional methods rely on centralized settings • Not feasible for Big Data • Goal: explore new methods to perform clustering under distributed settings • Programming with C++ or Python. • 2 – 3 students