IDA Projects
At IDA@SMU we are currently working on the following projects:
Classification Methods for Large Scale Genomic and Metagenomic Data
- QuasiAlign: Position Sensitive P-Mer Frequency Clustering with Applications to Classification and Differentiation. Fast alignment-free methods to provide alignment-like information for genetic sequences. > read more about QuasiAlign
- EMMSA: Extensible Markov Model for Sequence Analysis. EMM based techniques to analysis DNA/RNA sequences. > read more about EMMSA
-
Modeling the Temporal/order Structure of Massive Data Streams
- TRACDS: Temporal Relationships Among Clusters in Data Streams. Develop techniques to efficiently incorporate temporal ordering into the data stream clustering process and prove its usefulness on large, high-throughput data streams. > read more about TRACDS
- PIIH: Learning Prediction Intensity Interval model for Hurricanes. We apply TRACDS to improve the prediction of hurricane intensity. > read more about PIIH
- EMM: Extensible Markov Model: Time-evolving Markov chains. > read more about EMM
-
Recommender Systems
- recommenderlab: Top-N Recommendation Algorithms for 0-1 Data. Infrastructure for top-N recommendation algorithms for 0-1 data. > read more about recommenderlab
Visual Analytics
- arules: Mining and Visualizing Association Rules using R. Infrastructure for analyzing interesting patterns including frequent itemsets, association rules, frequent sequences and for building applications like associative classification. > read more about arules
- seriation: Reordering in Visualization. Develop new visualization techniques based on reordering elements. > read more about seriation