Data SCience Ensemble

The DSC Ensemble is a research group formed by four faculty members at the USA School of Computing (SoC); the goal is to enhance the research productivity of the members and their students within big data, machine learning, data mining, and data science. The DSC ensemble is accomplishing this by (a) sharing resources (data, software, and hardware), (b) collaborating on projects and ideas, and (c) creating a site for providing information about the group and their project.

Students

Research

    Focus Areas

    • Machine Learning/Data Mining
      • Anomaly detection
      • Biomedical imagery
      • Biological sequences
      • Pattern mining
      • Sequence mining
    • Ontology
      • Gene ontologies
      • Ontology generation
      • Semantic reasoning
    • Information System Management
      • Policy/procedure development and consequences
      • Big Data Management

    Current and Recent Projects

    • Machine Learning/Data Mining
      • Action rules
      • Alzheimer's disease prediction
      • Automated cell tracking and anomaly detection
      • Flu tracking via prescriptions
      • Link prediction
      • Mutation correlation engine
      • Novel Sequence Representations
      • Signal peptide prediction
      • Social media analysis
      • Targeted association mining
    • Ontology

Laboratory

  • DSC maintains a lab in Room 3323 at Shelby Hall.
  • Software
    • Biological
      • FastaX-Toolkit
      • seqtk
      • SAMtools
      • CellProfiler
      • ImageJ - Fiji version
      • Bowtie
    • Data Mining
      • WEKA