Clustering of Trajectory Data Using Hierarchical Approaches

Sabarish, B. A.; Karthi, R.; Kumar, T. Gireesh

doi:10.1007/978-3-319-71767-8_18

Cited by 7 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While in alternative approaches, one can consider the problem of clustering of the whole time series x i ∈ R t,f , e.g. clustering of trajectory data [45], or sub sequences of spatio-temporal data x t ∈ R s,w,f . A clustering model finds similar data points based on a distance function, such as euclidean distance.…”

Section: Problem Definitionmentioning

confidence: 99%

Clustering of Time Series Data with Prior Geographical Information

Azimi¹,

Regan²

2021

Preprint

View full text Add to dashboard Cite

Time Series data are broadly studied in various domains of transportation systems. Traffic data are a challenging example of spatio-temporal data, as it is multi-variate time series with high correlations in spatial and temporal neighborhoods. Spatio-temporal clustering of traffic flow data find similar patterns in both spatial and temporal domain, where it provides better capability for analyzing a transportation network, and improving related machine learning models, such as traffic flow prediction and anomaly detection. In this paper, we propose a spatio-temporal clustering model, where it clusters time series data based on spatial and temporal contexts. We propose a variation of a Deep Embedded Clustering (DEC) model for finding spatio-temporal clusters. The proposed model Spatial-DEC (S-DEC) use prior geographical information in building latent feature representations. We also define evaluation metrics for spatio-temporal clusters. Not only do the obtained clusters have better temporal similarity when evaluated using DTW distance, but also the clusters better represents spatial connectivity and dis-connectivity. We use traffic flow data obtained by PeMS in our analysis. The results show that the proposed Spatial-DEC can find more desired spatio-temporal clusters.

show abstract

Section: Problem Definitionmentioning

confidence: 99%

Clustering of Time Series Data with Prior Geographical Information

Azimi¹,

Regan²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The output of clustering, especially in relation to behavior prediction can be applied in destination prediction, urban planning, market research and location recommendation [13]. The open research issues include: finding appropriate features for trajectory representation, similarity measures and development of algorithms for spatial data clustering [14]. The key challenge is how to identify relevant class distinguishing features and how to select the most discriminate features to be used in building the classification model [15].…”

Section: Trajectory Miningmentioning

confidence: 99%

Anomaly Detection on Roads Using C-ITS Messages

Moso

Boutahala

Leblanc

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Cooperative Intelligent Transport Network is one of the most challenging issue in networking and computer science. In this area, huge amount of data are exchanged. Smart analysis of this collected data could be achieved for many purposes: traffic prediction, driver profile detection, anomaly detection, etc. Anomaly detection is an important issue for road operators. An anomaly on roads could be caused by various reasons: potholes, obstacles, weather conditions, etc. An early detection of such anomalies will reduce incident risks such as traffic jams, accidents. The aim of this paper is to collect message exchanges between vehicles and analyze trajectories. This analysis becomes difficult since a privacy principle is applied in the case of C-ITS. Indeed, each message sent is generated with an identifier of the sender. This identifier is kept only over a specified time interval thus one vehicle will have multiple identifiers. We first have to solve Trajectory-User Linking problem by chaining anonymous trajectories to potential vehicles by considering similarity in movement patterns. After that we apply various methods to check variations of trajectories from normal ones. When we observe some differences, we can raise an alarm about a potential anomaly. In order to check the validity of this work, we generated a large amount of messages exchanges by many vehicles using the Omnet ++simulator together with the Artery, Sumo plug-in. We applied various variations on some obtained trajectories. Finally, we ran our detection algorithm on the obtained trajectories using different parameters (angles, speed, acceleration) and obtained very interesting results in terms of detection rate.

show abstract