Spatio-Temporal Trajectory Similarity Learning in Road Networks

Fang, Ziquan; Du, Yuntao; Xinjun, Zhu,; Hu, Danlei; Chen, Lu; Gao, Yunjun; Jensen, Christian S.

doi:10.1145/3534678.3539375

Cited by 29 publications

(23 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the Point-of-Interests (POIs) (small colored points) surrounding each stay point will be grouped by types, counted, and transformed into a sequence of context vectors. Compared with the road networks based preprocessing (that aligns the GPS point into the road networks) [5] or grid cells preprocessing (that partitions the whole space into equal blocks and re-maps the GPS point into the corresponding cell) [10] as the spatial context to calibrate the trajectory at geometry and geographic level, the surrounding POI information has two advantages to incorporate the spatial semantics and calibrate the trajectory at semantics level (e.g., the mobility goal): 1) it allows to easily consider similar mobility types with different transportation modalities (e.g. walking through non-road area to the school, taking subway to the school, and taking bus to the school are all school commutes) and diverse patterns (e.g.…”

Section: A Stay Points Sequencementioning

confidence: 99%

“…Even though some related methods are not limited to stay points sequence as the preprocessing step, we still include them to show the issue is widely ignored. After preprocessing, the raw trajectory is transferred into a sequence [5,10,21,22]. Then, two types of methods are applied.…”

Section: Revisit Existing Trajectory Representationmentioning

confidence: 99%

“…Learned representation based methods: The trajectory is first represented by a sequence and then encoded into a vector representation. The similarity between trajectory is calculated by vector similarity [5,10,12,20]- [22,24]. Markov chain based method [12,24] and recurrent neural networks (RNNs) [5,20]- [22] are the commonly used components.…”

Section: Revisit Existing Trajectory Representationmentioning

confidence: 99%

“…The similarity between trajectory is calculated by vector similarity [5,10,12,20]- [22,24]. Markov chain based method [12,24] and recurrent neural networks (RNNs) [5,20]- [22] are the commonly used components.…”

Section: Revisit Existing Trajectory Representationmentioning

confidence: 99%

“…The main goal of the prepossessing is to incorporate extra semantics to enrich or calibrate the information contained in the trajectory. Road networks based preprocessing [5], grid cells preprocessing [10], stay points sequence preprocessing [21] are commonly used methods. After preprocessing, exiting methods either use sequence based methods [2,9] or learned representation based methods [5,10,12,20]- [22,24] to generate representation.…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

Clustering Human Mobility with Multiple Spaces

Lin

Chiang

2022

2022 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

Human mobility clustering is an important problem for understanding human mobility behaviors (e.g., work and school commutes). Existing methods typically contain two steps: choosing/learning a mobility representation and applying a clustering algorithm to the representation. However, these methods rely on strict visiting orders in trajectories and cannot take advantage of multiple types of mobility representations. This paper proposes a novel mobility clustering method for mobility behavior detection. First, the proposed method contains a permutation-equivalent operation to handle sub-trajectories that might have different visiting orders but similar impacts on mobility behaviors. Second, the proposed method utilizes a variational autoencoder architecture to simultaneously perform clustering in both latent and original spaces. Also, in order to handle the bias of a single latent space, our clustering assignment prediction considers multiple learned latent spaces at different epochs. This way, the proposed method produces accurate results and can provide reliability estimates of each trajectory's cluster assignment. The experiment shows that the proposed method outperformed state-of-the-art methods in mobility behavior detection from trajectories with better accuracy and more interpretability.

show abstract

Section: A Stay Points Sequencementioning

confidence: 99%

Section: Revisit Existing Trajectory Representationmentioning

confidence: 99%

Section: Revisit Existing Trajectory Representationmentioning

confidence: 99%

Section: Revisit Existing Trajectory Representationmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Clustering Human Mobility with Multiple Spaces

Lin

Chiang

2022

2022 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

show abstract

Flexible Contact Correlation Learning on Spatio-Temporal Trajectories

Wang,

Chen,

Feng

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Construct Trip Graphs by Using Taxi Trajectory Data

Guo

Luo

et al. 2023

Data Sci. Eng.

View full text Add to dashboard Cite

The trip graph, which can model the residents’ taxi demands, consists of vertices used to indicate trips and edges used to indicate the follow-up relationships between trips. A trip $$v_j$$ v j is a tight follow-up trip of another trip $$v_i$$ v i , if a taxi can arrive at the departure location of $$v_j$$ v j within a time threshold $$\delta$$ δ after it finishes $$v_i$$ v i . However, for big cities, there are a large amount of trips every day and it is time consuming to construct a trip graph. In this paper, we propose efficient algorithms to construct trip graphs for big cities. When constructing a trip graph, the most expensive step is to connect the vertices if the tight follow-up relationships exist. To find out the tight follow-up trips fast, we design an index considering both spatial and temporal constraints. To designate appropriate search areas, we propose efficient methods to determine the distance-based search areas and the traffic-based search areas. We conduct experiments on real datasets, i.e., the taxi trajectories of Shanghai in 2015. The experimental results show that our algorithm can construct the trip graph about 40 times faster than the straightforward method. We also demonstrate the usages of the trip graph in green transportation applications, i.e., the minimum fleet analysis and the minimum total “idle” mileage analysis.

show abstract

Spatio-Temporal Trajectory Similarity Learning in Road Networks

Cited by 29 publications

References 20 publications

Clustering Human Mobility with Multiple Spaces

Clustering Human Mobility with Multiple Spaces

Flexible Contact Correlation Learning on Spatio-Temporal Trajectories

Construct Trip Graphs by Using Taxi Trajectory Data

Contact Info

Product

Resources

About