TY - JOUR
T1 - SAFE: A Share-and-Aggregate Bandwidth Exploration Framework for Kernel Density Visualization
T2 - 48th International Conference on Very Large Data Bases, VLDB 2022
AU - Chan, Tsz Nam
AU - Ip, Pak Lon
AU - U, Leong Hou
AU - Choi, Byron
AU - Xu, Jianliang
N1 - Funding Information:
This work was supported by the National Key Research and Development Plan of China (No.2019YFB2102100), the Science and Technology Development Fund Macau (SKL-IOTSC-2021-2023, 0015/2019/AKP), University of Macau (MYRG2019-00119-FST), IRCMs/19-20/H01, RIF R2002-20F, Research Grants Council of Hong Kong (projects 12200021, 12201520, C6030-18GF), and Guang-dong Basic and Applied Basic Research Foundation (Project No. 2019B1515130001).
PY - 2021/11
Y1 - 2021/11
N2 - Kernel density visualization (KDV) has been the de facto method in many spatial analysis tasks, including ecological modeling, crime hotspot detection, traffic accident hotspot detection, and disease outbreak detection. In these tasks, domain experts usually generate multiple KDVs with different bandwidth values. However, generating a single KDV, let alone multiple KDVs, is time-consuming. In this paper, we develop a share-and-aggregate framework, namely SAFE, to reduce the time complexity of generating multiple KDVs given a set of bandwidth values. On the other hand, domain experts can specify bandwidth values on the fly. To tackle this issue, we further extend SAFE and develop the exact method SAFEall and the 2-approximation method SAFEexp which reduce the time complexity under this setting. Experimental results on four large-scale datasets (up to 4.33M data points) show that these three methods achieve at least one-order-of-magnitude speedup for generating multiple KDVs in most of the cases without degrading the visualization quality.
AB - Kernel density visualization (KDV) has been the de facto method in many spatial analysis tasks, including ecological modeling, crime hotspot detection, traffic accident hotspot detection, and disease outbreak detection. In these tasks, domain experts usually generate multiple KDVs with different bandwidth values. However, generating a single KDV, let alone multiple KDVs, is time-consuming. In this paper, we develop a share-and-aggregate framework, namely SAFE, to reduce the time complexity of generating multiple KDVs given a set of bandwidth values. On the other hand, domain experts can specify bandwidth values on the fly. To tackle this issue, we further extend SAFE and develop the exact method SAFEall and the 2-approximation method SAFEexp which reduce the time complexity under this setting. Experimental results on four large-scale datasets (up to 4.33M data points) show that these three methods achieve at least one-order-of-magnitude speedup for generating multiple KDVs in most of the cases without degrading the visualization quality.
UR - http://vldb.org/pvldb/volumes/15/paper/SAFE%3A%20A%20Share-and-Aggregate%20Bandwidth%20Exploration%20Framework%20for%20Kernel%20Density%20Visualization
UR - http://www.scopus.com/inward/record.url?scp=85126362493&partnerID=8YFLogxK
U2 - 10.14778/3494124.3494135
DO - 10.14778/3494124.3494135
M3 - Conference article
AN - SCOPUS:85126362493
SN - 2150-8097
VL - 15
SP - 513
EP - 526
JO - Proceedings of the VLDB Endowment
JF - Proceedings of the VLDB Endowment
IS - 3
Y2 - 5 September 2022 through 9 September 2022
ER -
