Spatiotemporal Data Mining and Visualization for Smart Cities

By Ariana Galindo
Slide 1: Title slide for Spatiotemporal Data Mining and Visualization for Smart Cities by Ariana Galindo

Slide-1

REU student: Ariana Galindo, Florida Atlantic University

REU mentor: Dr. Jang, Florida Atlantic University

Slide 2: Importance of data mining and visualization for smart city applications

Slide-2

Importance

  • Data mining is essential for extracting meaningful patterns and insights from complex datasets.
  • Visualization provides an intuitive way to comprehend and interpret data effectively.
  • The combination of data mining and visualization is valuable for city planning and management.
  • It helps optimize urban development and facilitates the sustainable growth of cities.
Slide 3: Research objectives covering interactive visualizations and pattern mining applications

Slide-3

Objectives

1. Applications of interactive front-end 2D/3D data visualizations:

  • Traffic management: insights into traffic flow, and congestion patterns.
  • Urban planning: Identify potential design issues, evaluate building heights and locations.

2. Infrastructure integrity pattern mining with clustering:

  • Analyze large datasets to reveal hidden insights and patterns.
Slide 4: Interactive front-end 2D data visualization using Leaflet to show Manhattan's density regions

Slide-4

Interactive front-end 2D data visualization

  • Leaflet is utilized to create a 2D web map of Manhattan.
  • The map's focus is to showcase the city's densest regions, determined by a specific attribute.
Slide 5: Interactive front-end 3D data visualization using Cesium to create Miami building visualization

Slide-5

Interactive front-end 3D data visualization

  • Cesium is utilized to create a 3D web map of Miami.
  • The buildings are depicted with their respective features, and the visualization is enhanced through functions available in the dropdown menu.
Slide 6: Infrastructure integrity pattern mining using DBSCAN clustering algorithm

Slide-6

Infrastructure integrity pattern mining

  • Clustering using the DBSCAN algorithm in python, focuses on five specific attributes for analysis
  • Segmentation of polygons on the map into separate groups by colors
  • Visual representation highlights densest regions in the area with leaflet.
Slide 7: Research conclusions highlighting contributions to smart city advancement

Slide-7

Conclusion

  • From these powerful processing tools and visualization techniques, this project contributes to the advancement of smart city.
  • A key to understanding urban dynamics and uncovering essential patterns within the city's data for a smart city.
Slide 8: Questions and feedback session invitation

Slide-8

Questions & Feedback

Thank you for your attention. Questions and feedback are welcome.

Last slide: Contains plain text stating 'End of presentation. Click the right arrow to return to beginning of slide show.'

End of Presentation

Click the right arrow to return to the beginning of the slide show.

For a downloadable version of this presentation, email: I-SENSE@FAU.

Additional Information
The Institute for Sensing and Embedded Network Systems Engineering (I-SENSE) was established in early 2015 to coordinate university-wide activities in the Sensing and Smart Systems pillar of FAU’s Strategic Plan for the Race to Excellence.
Address
Florida Atlantic University
777 Glades Road
Boca Raton, FL 33431
i-sense@fau.edu