A deep trajectory clustering method based on sequence‐to‐sequence autoencoder model

Most existing trajectory clustering methods use point matching similarity measurement strategies to compare trajectory objects; however, such methods have poor similarity measurement accuracy, which reduces clustering quality. To address this research gap, this article considers a combination of tra...

Full description

Saved in:
Bibliographic Details
Published in:Transactions in GIS 2022-06, Vol.26 (4), p.1801-1820
Main Authors: Wang, Chao, Lyu, Fangzheng, Wu, Sensen, Wang, Yuanyuan, Xu, Liuchang, Zhang, Feng, Wang, Shaowen, Wang, Yongheng, Du, Zhenhong
Format: Article
Language:English
Subjects:
Centroids
Clustering
Measurement
Methods
Representations
Sequencing
Similarity
Vectors
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most existing trajectory clustering methods use point matching similarity measurement strategies to compare trajectory objects; however, such methods have poor similarity measurement accuracy, which reduces clustering quality. To address this research gap, this article considers a combination of trajectory‐feature learning and clustering. A deep trajectory clustering (DTC) method toward clustering‐friendly spaces is proposed to simultaneously learn trajectory representations (i.e., low‐dimensional vectors are used to represent trajectories) and cluster centroids, and further acquire the cluster assignments end to end. We first use a sequence‐to‐sequence autoencoder network for pretraining to obtain preliminary trajectory vectors, and then jointly optimize the learned representations and cluster centroids under the same framework. The effectiveness of DTC is demonstrated in synthetic datasets, and the learned representations in the real world can be used to identify hot routes in cities.
ISSN:1361-1682
1467-9671
DOI:10.1111/tgis.12905