NNCluster: An Efficient Clustering Algorithm for Road Network Trajectories

Roh, Gook-Pil; Hwang, Seung-won

doi:10.1007/978-3-642-12098-5_4

“…The selection of a suitable clustering algorithm includes a density-based method [20,23,29], spectral clustering [30], a model-based method [12], or hierarchical clustering [31]. Lee et al [23] chose a density-based line-segment clustering algorithm for grouping similar line segments together.…”

Section: Related Work About Trajectory Clustering For Anomalous Trajmentioning

confidence: 99%

“…Then, they employed spectral clustering to group trajectories of similar spatial patterns. Roh et al [31] proposed a new trajectory clustering called NNCluster, a modified agglomerative hierarchical clustering that was chosen as a baseline algorithm, to reduce the number of distance computations during the clustering process. Density-based clustering methods need to calculate the density between objects.…”

Section: Related Work About Trajectory Clustering For Anomalous Trajmentioning

confidence: 99%

Detecting Anomalous Trajectories and Behavior Patterns Using Hierarchical Clustering from Taxi GPS Data

Wang

¹

,

Qin

²

,

Chen

³

et al. 2018

IJGI

View full text Add to dashboard Cite

Anomalous taxi trajectories are those chosen by a small number of drivers that are different from the regular choices of other drivers. These anomalous driving trajectories provide us an opportunity to extract driver or passenger behaviors and monitor adverse urban traffic events. Because various trajectory clustering methods have previously proven to be an effective means to analyze similarities and anomalies within taxi GPS trajectory data, we focus on the problem of detecting anomalous taxi trajectories, and we develop our trajectory clustering method based on the edit distance and hierarchical clustering. To achieve this objective, first, we obtain all the taxi trajectories crossing the same source-destination pairs from taxi trajectories and take these trajectories as clustering objects. Second, an edit distance algorithm is modified to measure the similarity of the trajectories. Then, we distinguish regular trajectories and anomalous trajectories by applying adaptive hierarchical clustering based on an optimal number of clusters. Moreover, we further analyze these anomalous trajectories and discover four anomalous behavior patterns to speculate on the cause of an anomaly based on statistical indicators of time and length. The experimental results show that the proposed method can effectively detect anomalous trajectories and can be used to infer clearly fraudulent driving routes and the occurrence of adverse traffic events.

show abstract

“…without considering the constrained road network. Other works [28] [29] [30] consider the network constraint to derive similarity measures but they only focus on the density aspect of the given trajectories such as object density [29], common road segments [28], shortest path distance [30]. Our approach can produce partial clustering but carefully considers the constrained road network focusing on both flow and density characteristics and avoids the expensive shortest path computation in its first two phases.…”

Section: Related Workmentioning

confidence: 99%

Road-Network Aware Trajectory Clustering: Integrating Locality, Flow, and Density

Han

¹

,

Liu

²

,

Omiecinski

³

2015

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

Abstract-Mining trajectory data has been gaining significant interest in recent years. However, existing approaches to trajectory clustering are mainly based on density and Euclidean distance measures. We argue that when the utility of spatial clustering of mobile object trajectories is targeted at road-network aware locationbased applications, density and Euclidean distance are no longer the effective measures. This is because traffic flows in a road network and the flow-based density characterization become important factors for finding interesting trajectory clusters. We propose NEAT a road-network aware approach for fast and effective clustering of trajectories of mobile objects travelling in road networks. Our approach carefully considers the traffic locality characterized by the physical constraints of the road network, the traffic flow among consecutive road segments, and the flow-based density to organize trajectories into spatial clusters in a comprehensive three-phase clustering framework. NEAT discovers spatial clusters as groups of sub-trajectories which describe both dense and highly continuous flows of mobile objects. We perform extensive experiments with mobility traces generated using different scales of real road networks. Experimental results demonstrate the flexibility of the NEAT system and show that NEAT is highly accurate and runs orders of magnitude faster than existing density-based trajectory clustering approaches.

show abstract

“…Although including traffic data, the approach in [28] uses Euclidean based distance and is unaware of the underlying road networks. Other works [25] [26] [27] consider the network constraints to derive similarity measures but they only focus on the density aspect of the given trajectories such as object density [26], common road segments [25], shortest path distance [27]. Our approach can produce partial clustering but carefully considers the constrained road network focusing on both flow and density characteristics and avoids the expensive shortest path computation in its first two phases.…”

Section: Related Workmentioning

confidence: 99%

NEAT: Road Network Aware Trajectory Clustering

Han

¹

,

Liu

²

,

Omiecinski

³

2012

2012 IEEE 32nd International Conference on Distributed Computing Systems

View full text Add to dashboard Cite

Abstract-Mining trajectory data has been gaining significant interest in recent years. However, existing approaches to trajectory clustering are mainly based on density and Euclidean distance measures. We argue that when the utility of spatial clustering of mobile object trajectories is targeted at road network aware location based applications, density and Euclidean distance are no longer the effective measures. This is because traffic flows in a road network and the flow-based density characterization become important factors for finding interesting trajectory clusters of mobile objects travelling in road networks. In this paper, we propose NEAT−a road network aware approach for fast and effective clustering of spatial trajectories of mobile objects travelling in road networks. Our method takes into account the physical constraints of the road network, the network proximity and the traffic flows among consecutive road segments to organize trajectories into spatial clusters. The clusters discovered by NEAT are groups of sub-trajectories which describe both dense and highly continuous traffic flows of mobile objects. We perform extensive experiments with mobility traces generated using different scales of real road network maps. Our experimental results demonstrate that the NEAT approach is highly accurate and runs orders of magnitude faster than existing density-based trajectory clustering approaches. I. INTRODUCTIONLocation-based services (LBSs) and applications are a rapidly growing field due to the pervasive use of GPS receivers and WiFi or location sensing technology embedded in mobile devices (e.g. cellular phones, automobiles). With shipments of smartphones projected to grow from 295 million units in 2010 to 1.2 billion units in 2015 1 , LBS revenue is forecasted to reach an annual global total of $10.3 billion in 2015, up from $2.8 billion in 2010 2 . Ubiquitous GPS/WiFi-enabled mobile devices generate a huge amount of trajectory data, which are sequences of time-ordered locations of mobile objects. There has been a lot of work on collecting, storing, indexing and querying trajectories of mobile objects. We refer to the trajectories of mobile objects in a road network as MO trajectories. Clustering trajectories of these objects provides the most value and has a wide range of LBS applications. For example, the resulting clusters would help provide knowledge about traffic flows as well as dense areas in a road network. Such knowledge is very useful for applications in vehicular ad hoc network (VANET) [6] [7], traffic monitoring [8], transportation planning [9] and location-based advertising [10]. We briefly present below two interesting application scenarios which show the usefulness of trajectory clustering and motivate us to study the

show abstract

NNCluster: An Efficient Clustering Algorithm for Road Network Trajectories

Cited by 38 publications

References 21 publications

Detecting Anomalous Trajectories and Behavior Patterns Using Hierarchical Clustering from Taxi GPS Data

Detecting Anomalous Trajectories and Behavior Patterns Using Hierarchical Clustering from Taxi GPS Data

Road-Network Aware Trajectory Clustering: Integrating Locality, Flow, and Density

NEAT: Road Network Aware Trajectory Clustering

Contact Info

Product

Resources

About