Smart City Data Analysis via Visualization of Correlated Attribute Patterns

Urban conditions are monitored by a wide variety of sensors that measure several attributes, such as temperature and traffic volume. The correlations of sensors help to analyze and understand the urban conditions accurately. The correlated attribute pattern (CAP) mining discovers correlations among...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-04
Main Authors: Sasaki, Yuya, Hori, Keizo, Nishihara, Daiki, Ohashi, Sora, Wakuta, Yusuke, Harada, Kei, Onizuka, Makoto, Arase, Yuki, Shimojo, Shinji, Doi, Kenji, He Hongdi, Zhong-Ren, Peng
Format: Article
Language:English
Subjects:
Data analysis
Data mining
Interactive systems
Sensors
Smart cities
Traffic volume
Visualization
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Urban conditions are monitored by a wide variety of sensors that measure several attributes, such as temperature and traffic volume. The correlations of sensors help to analyze and understand the urban conditions accurately. The correlated attribute pattern (CAP) mining discovers correlations among multiple attributes from the sets of sensors spatially close to each other and temporally correlated in their measurements. In this paper, we develop a visualization system for CAP mining and demonstrate analysis of smart city data. Our visualization system supports an intuitive understanding of mining results via sensor locations on maps and temporal changes of their measurements. In our demonstration scenarios, we provide four smart city datasets collected from China and Santander, Spain. We demonstrate that our system helps interactive analysis of smart city data.
ISSN:2331-8422