search for




 

Analysis of PM10 data using spatio-temporal correlation clustering and time series similarity
Journal of the Korean Data & Information Science Society 2021;32:1259-79
Published online November 30, 2021;  https://doi.org/10.7465/jkdi.2021.32.6.1259
© 2021 Korean Data and Information Science Society.

Sungdon Kim1 · Yongjin Jeon2 · Haejune Oh3

123Department of Information and Statistics, Gyeongsang National University
Correspondence to: 1 Graduate student, Department of Information and Statistics, Gyeongsang National University, Jinju 52828, Korea.
2 Graduate student, Department of Information and Statistics, Gyeongsang National University, Jinju 52828, Korea.
3 Corresponding author: Assistant professor, Department of Information and Statistics, Gyeongsang National University, Jinju 52828, Korea. E-mail: hjoh@gnu.ac.kr
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (NRF-2020R1G1A1A01014362).
Received October 2, 2021; Revised November 3, 2021; Accepted November 22, 2021.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
Spatio-temporal clustering has drawn much attention from many researchers in spatio-temporal analysis. Gao et al. (2019) attempted to cluster spatio-temporal data by transforming Moran’s I and Local Moran’s I, which are often used for clustering of spatial data. This study analyze PM10 data using the traditional spatial clustering method and that of Gao et al. (2019). To check the adequacy of these clusters, we compare the time series similarity of PM10 data within each cluster using Dynamic Time Warping(DTW) and the Longest Common SubSequence(LCSS) among time series similarity measures. Furthermore, we verify that the time series similarity increases when the clusters are spatially more finely divided using the k-means algorithm.
Keywords : Dynamic time warping, longest common subsequence, particulate matter, spatio-temporal clustering, time series similarity.