General Info:
Instructor: Prof.
Klaus Mueller
Office hours: Tu Thu 4-5pm (office, zoom by appointment)
Phone: 2-1524 (leave message, but better send email)
Email:
mueller@cs.stonybrook.edu
TA: please see pinned postings on Blackboard and Piazza
Office hours:
Phone: none
Email:
Meeting time and venue:
TuTh 8:15-9:35pm (Staller Center M0113)
Summary:
Visualization plays an increasingly important role in the understanding of the massive data that are nowadays being collected in almost any domain – science, medicine, business, commerce, finance, social networks, and many more. As such, visualization is often deeply integrated into the analytics tools developed for data science. This course is an introduction to both the foundations and applications of this emerging paradigm, known as visual analytics. It will begin with the basics – visual perception, cognition, human-computer interaction, the sense-making process, data mining, computer graphics, and information visualization. It will then move to discuss how these elementary techniques are coupled into an effective visual analytics pipeline that allows humans to interactively think with data and gain insight. Students will get hands-on experience via several programming projects, using python for data analytics and the popular javascript library D3.js for interactive information visualization directly in the web browser. In addition, students will also gain practical experience with a state of the art volume renderer for the visualization of medical data.
ABET course outcomes:
- An ability to transform spatial and non-spatial data from science, medicine, business, commerce, etc. into interactive visual representations.
- An understanding of the perceptual and cognitive reasoning processes that occur in humans when exploring visual artifacts derived from data to gain insight into the underlying phenomena.
- Working knowledge of principles and methods in human-computer interaction, data mining, computer graphics, and information visualization as applied to visual sense-making and data analytics.
- Practical experience with a number of popular public-domain data analysis and visualization packages and libraries.
Prerequisites:
CSE 219 (Computer Science III); AMS 210 or
MAT 211 (Linear Algebra), AMS 310 (Survey of Probability and Statistics)
Working knowledge in Java programming
Texts:
Required:
- "Interactive Data Visualization: Foundations, Techniques, and Applications, Second Edition" by M. Ward, G. Grinstein, and D. Keim, 2015
- "Data Mining: The Textbook" by Charu Aggarwal, Springer, 2015
For additional reference and on
reserve in the Science & Engineering library:
- "Visual Thinking for
Design" by Colin Ware, Morgan-Kaufman, 2008.
- "Visualization Analysis and Design" by Tamara Munzner, AK Peters, 2014.
- "Now You See It: Simple Visualization Techniques for Quantitative Analysis" by Stephen Few, Analytics Press, 2009.
- "Data Science for Business: What You Need to Know About Data Mining and Data-Analytic Thinking" by F. Provost and T. Faucett, O'Reilly Media, 2013
- "Visual Computing for Medicine: Theory, Algorithms, and Applications" by Bernhard Preim and Charl Botha, Elsevier, 2013.
- "Computer Graphics: Principles and Practice -
Second Edition in C" by J. D. Foley, A. van Dam, S.K. Feiner, J.F.
Hughes, Addison-Wesley, 1995.
- "Visualization Toolkit" by W. Schroeder, K.
Martin, and W. Lorensen, 2nd ed., Prentice Hall, 1998.
- "Digital Image Processing" by R. Gonzales and R.
Wood, Prentice-Hall, 2002.
- "The Visual Display of Quantitative Information"
by E. Tufte, Graphics Press, 1983.
- "Envisioning Information" by E. Tufte, Graphics
Press, 1990.
- "Explanations: Images and Quantities, Evidence
and Narrative" by E. Tufte, Graphics Press, 1997.
- "Real-Time Volume Graphics" by K. Engel et al. AK Peters, 2006.
Grading:
Lab assignments: 30% (MOSS for code plagiarism checks)
Midterm exam: 30%
Final exam: 40%
Lab assignments:
There will be five lab assignments to provide you with hands-on experience in visual data analytics. You will use python for data analytics and the popular javascript library D3.js for interactive information visualization directly in the web browser.The lab assignements will be:
- Project 1 (5%): Find a sufficiently complex dataset about a topic you find interesting. Ideally you would find multiple datasets that address a common topic but from different viewpoints and aspects. Then you would fuse them together to gain more explanatory power.
- Project 2 (5%): Preprocess the dataset from project 1 and implement some first interactive visualizations. Make a demo video and write a report.
- Project 3 (5%): Implement some more advanced data processing and interactive visualization algorithms. Make a demo video and write a report.
- Project 4 (5%): Interlude project on scientific visualization of volumetric data with a spatial context, using a public domain software package. Make a demo video and write a report.
- Project 5 (10%): Make a complete dashboard of brushable interlinked and interactive visualizations that show the different aspects of your data, and the relations among them, in a compelling way and allow insightful data explorations. Make a demo video and write a report.