Visualization of Trends and Patterns in Large Data Sets

Back to all technologies
Download as PDF
2014-MCKA-66643
With the advent of big data and the massive amounts of information digitally stored by companies and organizations, it is difficult to efficiently sift through the data and glean useful behaviors, trends, and information. Data sets are usually formatted in a longitudinal list, which makes it difficult and time consuming to analyze the information with multiple dimensions such as location and time.

Researchers at Purdue University have developed an algorithm that sorts digital data and formats it into a 2D time/space heat map. The heat map is a grid of colored boxes, which visualizes information that occurs at specific times and locations. Each cell is assigned a color based on the number of events that occurred at that time and location. This algorithm takes data in a dilute form and transforms it into a data set that can be easily visualized and operated upon by image recognition programs. This allows the end user to quickly recognize behavioral patterns and trends in the data, which could help improve their business or organization.

Advantages:
-Provides quick and efficient analysis of data
-Analyzes data using multiple dimensions

Potential Applications:
-Data analysis
-Data visualization
Jun 21, 2018
Copyright
United States
(None)
(None)
Purdue Office of Technology Commercialization
1801 Newman Road
West Lafayette, IN 47906

Phone: (765) 588-3475
Fax: (765) 463-3486
Email: otcip@prf.org