GPS trajectory clustering method for decision making on intelligent transportation systems

Reyes, Gary; Lanzarini, Laura Cristina; Hasperué, Waldo; Bariviera, Aurelio F.

doi:10.3233/jifs-179644

Cited by 9 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Ref. [30] leveraged the Hausdorff distance to calculate the similarity of line segments and then implemented the K-means clustering algorithm to cluster GPS trajectories for decision making on intelligent transportation systems. In [31], a 3D wireframe model was used to abstract the centroids of trajectories; a symmetric Euclidean distance based on the Hausdorff distance was applied to measure the similarity of these trajectories; and the agglomerative hierarchical clustering algorithm was adopted to cluster the trajectories.…”

Section: Distance-based Clustering Algorithmmentioning

confidence: 99%

Trajectory dimensionality reduction and hyperparameter settings of DBSCAN for trajectory clustering

Long

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

The density-based spatial clustering of application with noise (DBSCAN) algorithm has good robustness and is widely employed to cluster vehicle trajectories for vehicle movement pattern recognition. However, the distance or similarity between two trajectories varies from tens to hundreds of thousands, and there is no effective method for determining the values of the hyperparameters eps and MinPts of DBSCAN. In addition, with increasing sizes of trajectory datasets, some trajectory clustering methods that directly analyse points and line segments incur large computational costs and time overhead. To solve these two dilemmas, the authors propose an effective trajectory dimensionality reduction method and a DBSCAN hyperparameter initial value setting method. The trajectory dimensionality reduction algorithm processes trajectories with different lengths into the same dimensionality (the same number of feature points). The reserved points preserve the spatial and temporal information of these trajectories as much as possible. The DBSCAN hyperparameter initial value setting algorithm obtains the effective initial values of eps and MinPts for facilitating subsequent adjustments. Finally, we validate these proposed methods on two trajectory datasets collected from two real-world scenes, and the experimental results are promising and effective.

show abstract

Section: Distance-based Clustering Algorithmmentioning

confidence: 99%

Trajectory dimensionality reduction and hyperparameter settings of DBSCAN for trajectory clustering

Long

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…Según (Reyes et al, 2020), un algoritmo de clustering busca crear grupos con elementos que poseen características compartidas, ya sea en base a un centroide, del cual se pueden encontrar una cierta cantidad de puntos a cierta medida de distancia, con la cual se encuentra la similitud entre objetos; así como en base a un descriptor, que permitirá identificar las características únicas de cada grupo.…”

Section: Algoritmos De Clusteringunclassified

Identificación de patrones de congestionamiento vehicular utilizando algoritmos de agrupamiento de trayectorias basados en densidad

Reyes

Roldán²,

Macias³

et al. 2022

Inv. Tecn. Innov.

View full text Add to dashboard Cite

Contexto: Este trabajo se centra en identificar patrones de congestionamiento. Para ello se utilizan 3 conjuntos de datos de las ciudades de Beijing, Guayaquil y Roma. Método: Se efectúa la implementación del algoritmo Dyclee, modificado para agrupar celdas de trayectorias en base a velocidades, con el cual se realiza experimentos en los que se calculó adecuadamente los patrones de volumen de servicio e índice de operatividad en base a sus resultados. La modalidad de la investigación predominante es la bibliográfica. Sin embargo, el estudio también incluye características de una investigación de campo, debido a que los algoritmos fueron ejecutados con datos de trayectorias GPS de tres conjuntos de datos diferentes. Resultados: Para validar esta investigación se ejecutaron dos experimentos. En el primer experimento se determinó que el algortimo Dyclee calculó correctamente los patrones de congestionamiento. En el segundo experimento se encontró que TRADBSCAN obtuvo los mejores resultados con respecto a métricas de validación tomando en cuenta los parámetros establecidos. Conclusiones: Se concluyó que el algoritmo de clustering basado en densidad Dyclee, es capaz de identificar patrones de congestionamiento vehicular.

show abstract

“…Gary Reyes‐Zambrano et al. [21] propose a GPS trajectory clustering algorithm to analyse vehicle flow for decision‐making in intelligent transportation systems. Zhao et al.…”

Section: Introductionmentioning

confidence: 99%

“…Zhang et al [20] cluster GPS trajectory data to discover important locations and behaviour patterns of daily human activities. Gary Reyes-Zambrano et al [21] propose a GPS trajectory clustering algorithm to analyse vehicle flow for decision-making in intelligent transportation systems. Zhao et al [22] propose a maritime traffic pattern mining method for the large volume and complex distribution of ship AIS data.…”

mentioning

confidence: 99%

Mining regular behaviors based on spatiotemporal trajectory multi‐dimensional features

Jiang¹,

Liu

Liu³

et al. 2022

IET Radar Sonar & Navi

View full text Add to dashboard Cite

In the military and civilian surveillance domain, it is of great significance to mine regular behaviours of targets for situation awareness and command decision support. Most of the existing trajectory clustering algorithms only consider the similarity of spatial position of the trajectory, without sufficient multi-dimensional information such as time, course and velocity. Some approaches based on information fusion take these multi-dimensional information into account, but the features with different dimensions fused by weight coefficients are not robust and universal for different scenarios. In this paper, a regular behaviour mining method based on spatiotemporal trajectory multi-dimensional features and density clustering is proposed. Firstly, multi-dimensional Hausdorff similarity is defined to measure spatiotemporal trajectory from different feature dimensionalities. Different from methods based on information fusion, the proposed method defines trajectory density in feature similarity of different dimensions and adaptively determines parameters according to feature distribution in different dimensions. Experimental results in simulated and radar measured trajectory data show that the proposed method can be accurate and robust in clustering evaluation indexes such as Purity, Precision, Recall and Rand Index from different scenarios, which has a good application prospect in intelligent surveillance tasks.

show abstract

GPS trajectory clustering method for decision making on intelligent transportation systems

Cited by 9 publications

References 12 publications

Trajectory dimensionality reduction and hyperparameter settings of DBSCAN for trajectory clustering

Trajectory dimensionality reduction and hyperparameter settings of DBSCAN for trajectory clustering

Identificación de patrones de congestionamiento vehicular utilizando algoritmos de agrupamiento de trayectorias basados en densidad

Mining regular behaviors based on spatiotemporal trajectory multi‐dimensional features

Contact Info

Product

Resources

About