Detecting hotspots of urban residents’ behaviours based on spatio-temporal clustering techniques

Zhang, Pengdong; Deng, Min; Shi, Yan; Zhao, Lijun

doi:10.1007/s10708-016-9720-4

Cited by 9 publications

(11 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The O-D points can be clustered into pick-up clusters or drop-off clusters, and then the O-D lines among these clusters can be studied. Clustering methods can be classified into five main categories: (1) hierarchical methods; (2) partition-based methods; (3) density-based methods; (4) grid-based methods; and (5) model-based methods [27][28][29][30][31]. The K-means algorithm is a widely used partition-based clustering method [32].…”

Section: Origin-destination (O-d) Hotspot Clustering Modelmentioning

confidence: 99%

An Urban Road-Traffic Commuting Dynamics Study Based on Hotspot Clustering and a New Proposed Urban Commuting Electrostatics Model

Huang

Meng

et al. 2019

IJGI

View full text Add to dashboard Cite

With the recent rapid development of cities, the dynamics of urban road-traffic commuting are becoming more and more complex. In this research, we study urban road-traffic commuting dynamics based on clustering analysis and a new proposed urban commuting electrostatics model. As a case study, we investigate the characteristics of urban road-traffic commuting dynamics during the morning rush hour in Beijing, China, using over 1.3 million Global Positioning System (GPS) data records of vehicle trajectories. The hotspot clusters are identified using clustering analysis, after which the urban commuting electric field is simulated based on an urban commuting electrostatics model. The results show that the areas with high electric field intensity tend to have slow traffic, and also that the vehicles in most areas tend to head in the same direction as the electric field. The results above verify the validity of the model, in that the electric field intensity can reflect the traffic pressure of an area, and that the direction of the electric field can reflect the traffic direction in that area. This new proposed urban commuting electrostatics model helps greatly in understanding urban road-traffic commuting dynamics and has broad applicability for the optimization of urban and traffic system planning.

show abstract

Section: Origin-destination (O-d) Hotspot Clustering Modelmentioning

confidence: 99%

An Urban Road-Traffic Commuting Dynamics Study Based on Hotspot Clustering and a New Proposed Urban Commuting Electrostatics Model

Huang

Meng

et al. 2019

IJGI

View full text Add to dashboard Cite

show abstract

“…where I I denotes the interaction intensity, and r has the same meaning as in Equation (5). The larger I I is, the stronger the interaction between the two objects.…”

Section: The Calculation Of the Interaction Intensity Measures And Cementioning

confidence: 99%

“…This has caused a proliferation of rich and voluminous movement data. Specific types of movement data include transportation-related movement data [1][2][3][4][5], animal movement data [6][7][8], eye movement data [9], sports movement data [10][11][12], as well as natural phenomena movement data [13]. Benefiting from the large amount of tracked movement data, the analysis of movement data has become a state-of-the-art research theme in the community of geographical information science (GIScience).…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Approach Combining the Multi-Temporal Scale Spatio-Temporal Network with the Continuous Triangular Model for Exploring Dynamic Interactions in Movement Data: A Case Study of Football

Zhang

Beernaerts

Weghe

2018

IJGI

Self Cite

View full text Add to dashboard Cite

Benefiting from recent advantages in location-aware technologies, movement data are becoming ubiquitous. Hence, numerous research topics with respect to movement data have been undertaken. Yet, the research of dynamic interactions in movement data is still in its infancy. In this paper, we propose a hybrid approach combining the multi-temporal scale spatio-temporal network (MTSSTN) and the continuous triangular model (CTM) for exploring dynamic interactions in movement data. The approach mainly includes four steps: first, the relative trajectory calculus (RTC) is used to derive three types of interaction patterns; second, for each interaction pattern, a corresponding MTSSTN is generated; third, for each MTSSTN, the interaction intensity measures and three centrality measures (i.e., degree, betweenness and closeness) are calculated; finally, the results are visualized at multiple temporal scales using the CTM and analyzed based on the generated CTM diagrams. Based on the proposed approach, three distinctive aims can be achieved for each interaction pattern at multiple temporal scales: (1) exploring the interaction intensities between any two individuals; (2) exploring the interaction intensities among multiple individuals, and (3) exploring the importance of each individual and identifying the most important individuals. The movement data obtained from a real football match are used as a case study to validate the effectiveness of the proposed approach. The results demonstrate that the proposed approach is useful in exploring dynamic interactions in football movement data and discovering insightful information.

show abstract

“…Kernel density estimation of recreation activities, as denoted by the center of low-speed GPS segments, was applied to get the hotspots from the data. A similar kernel density-based clustering algorithm was proposed in Zhang et al [31] to detect urban residential hotspots from GPS data collected by floating cars. The results of kernel density estimation are illustrated in Figure 4, where the darker color represents a higher density of recreation activities.…”

Section: Experimental Data and Preliminary Analysismentioning

confidence: 99%

Spatio-Temporal Behavior Analysis and Pheromone-Based Fusion Model for Big Trace Data

Tang

Zou

Zhang

et al. 2017

IJGI

View full text Add to dashboard Cite

People leave traces of movements that might affect the behavior of others both online in cyberspace and offline in real space. Previous studies, however, have used only questionnaires, network data, or GPS data to study spatio-temporal behaviors, ignoring the relationship between online and offline activities, and overlooking the influence of previous activities on future behaviors. We propose a Pheromone-based Fusion Model, viewing human behaviors as similar to insect foraging behaviors to model spatio-temporal recreational activity patterns, on and offline. In our model, website data were combined with GPS data to evaluate the attractiveness of destinations over time using twenty-nine landscapes in Beijing, China; big website data and GPS trajectories were gathered from 181 users for 57 months. The datasets were portioned into two periods. Online and offline recreational pheromones were calculated from the first period, and the visitation rates were extracted from the second period. These data were subsequently applied in a regression analysis to determine unknown parameters and estimate the attractiveness of destinations. The proposed method was compared with two other approaches that use either GPS data or online data alone, in order to verify effectiveness. The results show that the proposed method can estimate future behaviors, based on real world and online past actions.

show abstract

Detecting hotspots of urban residents’ behaviours based on spatio-temporal clustering techniques

Cited by 9 publications

References 31 publications

An Urban Road-Traffic Commuting Dynamics Study Based on Hotspot Clustering and a New Proposed Urban Commuting Electrostatics Model

An Urban Road-Traffic Commuting Dynamics Study Based on Hotspot Clustering and a New Proposed Urban Commuting Electrostatics Model

A Hybrid Approach Combining the Multi-Temporal Scale Spatio-Temporal Network with the Continuous Triangular Model for Exploring Dynamic Interactions in Movement Data: A Case Study of Football

Spatio-Temporal Behavior Analysis and Pheromone-Based Fusion Model for Big Trace Data

Contact Info

Product

Resources

About