Visual Analytics is not same as visualization (tools for data layout) and it is not equal to data analysis. It is about: (a) seamlessly integrating data analysis with visualization; (b) involving human experts in the loop to provide feedbacks for improving further data analysis; and (c) leveraging human advices to enhance data analysis and knowledge discovery for achieving better interpretation and understanding of big data.
Visual Analytics could be meaningful for big data analysis: (a) Before performing data analysis, we may not know the principles of big data, interactive data exploration could help; (b) After performing data analysis, visual analytics can provide better interpretation of data and discovered knowledge; (c) If we make mistakes on hypothesis making, visual analytics can provide further chance to correct our mistakes or even generate more intuitive hypothesese.
Course Components:
Data Analytics Tools: (a) Feature Extraction for Discriminative Data Representation; (b) Unsupervised Learning for Knowledge Discovery from Big Data; (c) Supervised Learning for Knowledge Discovery from Big Data.
Visualization Tools for Data & Knowledge Assessment: (a) Multidimensional Scaling; (b) Temposal Data Visualization; (c) Graph Visualization; (d) Tree Visualization; (e) Human-System Interaction.
Visual Analytics: Interaction between Data Analyics and Data/Knowledge Visualization
Deep Learning for Visual Analytics
Visual Analytics for Big Data Applications
Future Trends of Visual Analytics
Suggested Text Books (optional):
Munzner, Tamara. Visualization Analysis and Design. CRC Press, 2014.
Matthew Ward, Georges Grinstein, and Daniel Keim. Interactive Data Visualization – Foundations, techniques, and applications. 1st or 2nd edition
Daniel A. Keim, Jörn Kohlhammer, Geoffrey Ellis, and Florian Mansmann: Mastering the Information Age - Solving Problems with Visual Analytics
Colin Ware. Information Visualization: Perception for Design (2nd Edition). Morgan-Kaufmann, 2004.
Edward Tufte. The Visual Display of Quantitative Information (2nd Edition). Graphics Press, 2001.
Others
Articles and journal papers.
Grading Format:
Project Implementation & Presentation: 20%-40% (20% bonus could be applied for wonderful project implementation)
Homeworks & Attendances: 20%
Mid-term and Final Tests: 60% (25% for mid-term and 35% for final)
Classroom:
Woodward Hall 135
Class Time:
Monday 2:30PM-5:15PM
Instructor Office Hours:
Monday 11:00AM-12:30PM; 5:30PM-7:00PM or make appointment
Class TA:
Name: Tinghao Feng, tfeng1@uncc.edu
Office Location: Woodward Hall 404 (4th floor)
Office Hours: Monday 11:00AM-12:30PM; Friday 11:00AMM-12:30PM or make appointment
Final Test: Dec. 10, 2018, 2:00PM-4:30PM, (one page note is allowed)
Course Projects:
Project Description (you can start as early as possible and we will introduce projects at 10/1/2018).
Every student should select one of four projects for implementation.
Project Implementation Requirements: Each project implementation should include the following key compnents: (a) data analysis or feature extraction tools for discriminative data representation; (b) knowledge discovery tools for data abstraction and summarization; (c) visualization tools for interactive assessment of data & discovered knowledge or learned classifiers; (d) human-system interaction tools for involving human experts in the loop to provide their adavices for data analysis and visualization and transforming human advices into computer-understandable signals; (e) solutions for leveraging human advices to improve data analysis and visualization simultaneously.
Course Schedule (Weekly Topics & Assignments):
First Week: 8/20/2018
No Class! (I have to attend New Student Convocation 8:00 AM to 5:00 PM)