Month: December 2018

In the Mobile Age, with the widespread use of location-awareness devices, it is possible to collect large-scale location-awareness datasets, such as mobile phone data, GPS-enabled taxi trajectories, and location-based social media data, to sense complex human movements and human-environment interactions in urban space. Here are some examples of research that we have been working on.

(1) Discovering Spatial Interaction Communities from Mobile Phone Data

This research attempts to explore and interpret patterns embedded in the network of phone‐call interaction and the network of phone‐users’ movements, by considering the geographical context of mobile phone cells. We adopt an agglomerative clustering algorithm based on a Newman‐Girvan modularity metric and propose an alternative modularity function incorporating a gravity model to discover the clustering structures of spatial‐interaction communities using a mobile phone dataset from one week in a city in China. The results verify the distance decay effect and spatial continuity that control the process of partitioning phone‐call interaction, which indicates that people tend to communicate within a spatial‐proximity community. Furthermore, we discover that a high correlation exists between phone‐users’ movements in physical space and phone‐call interaction in cyberspace. Our approach presents a combined qualitative‐quantitative framework to identify clusters and interaction patterns, and explains how geographical context influences communities of callers and receivers. The findings of this empirical study are valuable for urban structure studies as well as for the detection of communities in spatial networks.

(2) Spatio-Temporal Analytics for Exploring Human Mobility Patterns and Urban Dynamics

In this research, we present a spatio-temporal analytical framework including spatiotemporal visualization (STV), space-time kernel density estimation (STKDE), and spatio-temporal-autocorrelation-analysis (STAA), to explore human mobility patterns and intra-urban communication dynamics. Experiments were conducted using large-scale detailed records of mobile phone calls in a city. The space-time path, time series graphs, vertical Bezier curves, STKDE, STAA, and related techniques in 3D GIS as well as statistical tests have been suggested for different spatio-temporal analysis tasks. We also investigated several statistical measures that extend the classic spatial association indices for spatio-temporal autocorrelation analysis. The spatial order of weighted matrix was found to have more significant effects than the temporal neighbors on influencing the autocorrelation strength of hourly phone calls.

(3) Spatio-Temporal-Network Visualization for Exploring Human Movements and Interactions in Physical and Virtual Spaces

Spatiotemporal visualization techniques are effective in detecting human activity patterns over space and time, while social network analysis is good for exploring graph structures and interactions among individual nodes and groups. Integrating these two types of methods can facilitate the exploration of complex social networks in space and time, and can help discover hidden spatiotemporal and social connections. In this research, we propose a novel conceptual framework for spatiotemporal and social network visualization in a three-dimensional context. Based on this framework, new spatio-temporal-network (STN) quantitative metrics (including STN-impact-extent, STN-impact-center, STN-distance, STN-efficiency, and STN-centrality) are introduced to measure the underlying dynamic interactions among entities. The proposed framework aims to help better understand spatiotemporal patterns of human dynamics and social interactions over both physical and virtual spaces simultaneously, as well as explore how emerging events trigger spatial-temporal-social interactions and information diffusion from a process perspective. As a proof of concept, we demonstrate the proposed framework with a case study using geotagged tweets and associated visualization in the ArcScene software. We hope that this research can stimulate new insights on integrating multidisciplinary knowledge to explore human dynamics in a broader way.

(4) Uncovering the digital divide and the physical divide using mobile phone data

In this research, we first aim at developing data analytics that can derive insights about how people from different regions communicate and connect via mobile phone calls and physical movements. We uncover the digital divide (geographical segregation of phone communication patterns) and the physical divide (geographical limits of human mobility) in a developing country. The research also demonstrates that the chosen spatial unit and temporal resolution can affect the community detection results of spatial interaction graphs when analyzing human mobility patterns and exploring urban dynamics in the mobile age. We find that the daily detection has generated a more stable partition structure than an hourly one, while monthly changes also exist over time. The presented framework can help identify patterns of spatial interaction in both cyberspace and physical space with phone call detailed records in some regions where census data acquisition is difficult, especially in some developing countries.

(5) Identifying Local Spatiotemporal Autocorrelation Patterns of Large-scale Taxi Pick-ups and Drop-offs

Analyzing spatiotemporal autocorrelation would be helpful to understand the underlying dynamic patterns in space and time simultaneously. In this work, we aim to extend the conventional spatial autocorrelation statistics to a more general framework considering both spatial and temporal dimensions. Specifically, we focus on the spatiotemporal version of Getis-Ord’s G*. The new indicator STG* can quantify the local association of adjacent features in space and time. As a proof of concept, the proposed method is applied in a large-scale GPS-enabled taxi dataset to identify local spatiotemporal autocorrelation patterns of taxi pick-ups and drop-offs in New York City.

(6) Extracting urban functional regions from points of interest and human activities on location‐based social networks

Data about points of interest (POI) have been widely used in studying urban land use types and for sensing human behavior. However, it is difficult to quantify the correct mix or the spatial relations among different POI types indicative of specific urban functions. In this research, we develop a statistical framework to help discover semantically meaningful topics and functional regions based on the co‐occurrence patterns of POI types. The framework applies the latent Dirichlet allocation (LDA) topic modeling technique and incorporates user check‐in activities on location‐based social networks. Using a large corpus of about 100,000 Foursquare venues and user check‐in behavior in the 10 most populated urban areas of the US, we demonstrate the effectiveness of our proposed methodology by identifying distinctive types of latent topics and, further, by extracting urban functional regions using K‐means clustering and Delaunay triangulation spatial constraints clustering. We show that a region can support multiple functions but with different probabilities, while the same type of functional region can span multiple geographically non‐adjacent locations. Since each region can be modeled as a vector consisting of multinomial topic distributions, similar regions with regard to their thematic topic signatures can be identified. Compared with remote sensing images which mainly uncover the physical landscape of urban environments, our popularity‐based POI topic modeling approach can be seen as a complementary social sensing view on urban space based on human activities.

(7) Detecting Origin-Destination Mobility Flows From Geotagged Tweets

Human origin-to-destination (OD) trip information is of major importance in urban transportation modelling and infrastructure planning in order to optimize the use of street networks. The increasing use of social media like Twitter offers unprecedented opportunities to study individual activities and movements, to know where users are at which time, and what they are talking about. In this work we study the reliability of detecting regional OD trips from individual geotagged tweets in comparison with survey data in a quantitative manner, and explore the spatiotemporal flow patterns extracted from social media. We investigate the research question of whether OD trips mined from social media yield comparable results to expensive and labour intensive large-scale studies. To do so, we derive large-scale OD trips from geotagged tweets, aggregate them, and compare the results by correlating them to the American Community Survey data.

(8) Exploring the uncertainty of activity zone detection from Geotagged Tweets with multi-scaled DBSCAN (M-DBSCAN)

While exploring human mobility patterns based on digital footprints captured from social media, the density-based spatial clustering of applications with noise (DBSCAN) method is often used to identify activity zones which an individual regularly visits. However, DBSCAN is sensitive to the two parameters, including the search radius of a cluster (eps), and the minimum number of points (minpts). This research first discusses the uncertainty while detecting an individual’s activity zones through digital footprints. An improved density-based clustering algorithm for mobility analysis known as Multi-Scaled DBSCAN (M-DBSCAN), is then presented to mitigate the detection uncertainty of clusters produced by DBSCAN at different scales of density and cluster size. Next, we demonstrate that M-DBSCAN iteratively calibrates suitable local eps and minpts values instead of using one global parameter setting as DBSCAN for detecting clusters of varying densities, and proves to be very effective for detecting potential activity zones (clusters) with the historic geo-tagged tweets of selected users. Besides, M-DBSCAN can significantly reduce the noise ratio (the proportion of trajectory points not included in any cluster) by identifying all points capturing the activities performed in each zone. Using the historic geo-tagged tweets of a large number of users in Madison, Wisconsin and Washington, D.C., the results of M-DBSCAN and DBSCAN with a minpts value of 4 and varying eps values reveal that: 1) M-DBSCAN can capture dispersed clusters with low density of points, and therefore detecting more activity zones for each user and resulting in a lower noise ratio; 2) A value of 40m or higher should be used for eps in order to reduce the possibility of collapsing distinctive activity zones, and ensure a relatively low noise ratio during the clustering process; and 3) A value between 200m to 300m is recommended for eps while using DBSCAN for detecting activity zones from geotagged tweets.

(9) Reconstruction of human movement trajectories from large-scale low-frequency mobile phone data

Understanding human mobility is significant in many fields, such as urban planning, transportation, and sociology. Due to the wide spatiotemporal coverage and low operational cost, mobile phone data have been recognized as a major resource for human mobility research. However, due to conflicts between the data sparsity problem of mobile phone data and the requirement of fine-scale solutions, trajectory reconstruction is of considerable importance. Although there have been initial studies on this problem, existing methods rarely consider the effect of similarities among individuals and the temporal patterns of missing data. To address this issue, we propose a novel multi-criteria data partitioning trajectory reconstruction (MDP-TR) method for large-scale mobile phone data. In this research, a multi-criteria data partitioning (MDP) technique is used to measure the similarity among individuals in near real-time and investigate the spatiotemporal patterns of missing data. With this technique, the trajectory reconstruction from mobile phone data is then conducted with classic machine learning models. We verified the method using a real mobile phone dataset in a large city. Results indicate that the MDP-TR method outperforms competing methods in both accuracy and robustness. We argue that the MDP-TR method can be effectively utilized for grasping highly dynamic human movement status and improving the spatiotemporal resolution of human mobility research.

(10) Understanding neighborhood isolation through spatial interaction network analysis using location big data

Hidden biases of racial and socioeconomic preferences shape residential neighborhoods throughout the USA. Thereby, these preferences shape neighborhoods composed predominantly of a particular race or income class. However, the assessment of spatial extent and the degree of isolation outside the residential neighborhoods at large scale is challenging, which requires further investigation to understand and identify the magnitude and underlying geospatial processes. With the ubiquitous availability of location-based services, large-scale individual-level location data have been widely collected using numerous mobile phone applications and enable the study of neighborhood isolation at large scale. In this research, we analyze large-scale anonymized smartphone users’ mobility data in Milwaukee, Wisconsin, to understand neighborhood-to-neighborhood spatial interaction patterns of different racial classes. Several isolated neighborhoods are successfully identified through the mobility-based spatial interaction network analysis.

References:

Gao, S., Liu, Y., Wang, Y., & Ma, X. (2013) Discovering Spatial Interaction Communities from Mobile Phone Data. Transactions in GIS. 17(3):463-481.

Gao, S. (2015). Spatio-temporal analytics for exploring human mobility patterns and urban dynamics in the mobile age. Spatial Cognition & Computation, 15(2), 86-114.

Gao, S., Janowicz, K., & Couclelis, H. (2017). Extracting urban functional regions from points of interest and human activities on location‐based social networks. Transactions in GIS, 21(3), 446-467.

Gao, S., Yan, B., Gong, L., Regalia, B., Ju, Y., & Hu, Y. (2017). Uncovering the digital divide and the physical divide in Senegal using mobile phone data. In Advances in Geocomputation (pp. 143-151). Springer, Cham.

Gao, S., Yang, J. A., Yan, B., Hu, Y., Janowicz, K., & McKenzie, G. (2014, September). Detecting origin-destination mobility flows from geotagged Tweets in greater Los Angeles area. In Eighth International Conference on Geographic Information Science (GIScience’14).

Gao, S., & Long, Y. (2015). Finding public transportation community structure based on large-scale smart card records in Beijing. In Long, Y., & Shen, Z. (Eds) Geospatial Analysis to Support Urban Planning in Beijing (pp. 155-167). Springer, Cham.

Gao, S., Zhu, R., & Mai, G. (2016, January). Identifying Local Spatiotemporal Autocorrelation Patterns of Taxi Pick-ups and Drop-offs. In International Conference on GIScience Short Paper Proceedings (Vol. 1, No. 1). (pp.109–113), Montreal, Canada, Sep.27-Sep.30, 2016. DOI:10.21433/B31104b2d8xp.

Gao, S., Chen, H., Luo, W., Hu, Y., & Ye, X. (2018) Spatio-Temporal-Network Visualization for Exploring Human Movements and Interactions in Physical and Virtual Spaces. In Shih-Lung Shaw and Daniel Sui (Eds): Human Dynamics Research in Smart and Connected Communities (Chapter 4). pp. 67-80, Springer.

Lee, J. H., Gao, S., & Goulias, K. G. (2015). Can Twitter data be used to validate travel demand models. In 14th International Conference on Travel Behaviour Research.

Liu, X.Y., Huang, Q.Y., & Gao, S. (2019). Exploring the uncertainty of activity zone detection using digital footprints with multi-scaled DBSCAN. International Journal of Geographical Information Science. DOI: 10.1080/13658816.2018.1563301

Li, M.X.,Gao, S., Lu, F., & Zhang, H.C. (2019). Reconstruction of human movement trajectories from large-scale low-frequency mobile phone data. Computers, Environment and Urban Systems. DOI: 10.1016/j.compenvurbsys.2019.101346

Prestby, T., App, J., Kang, Y., & Gao, S. (2019). Understanding Neighborhood Isolation through Spatial Interaction Network Analysis using Location Big Data. Environment and Planning A: Economy and Space. DOI: 10.1177/0308518X19891911

A street network is a system of interconnecting polylines and points (called edges and nodes in network science) that represent street segments/roads and intersections for a given area. It plays a very important role in transportation operation and management and many other fields. Below are some examples of research that we have been working on in this field.

(1) Street Centrality and Traffic Flow

The structural and morphological properties of a street network, represented in topological or geographic metric measurements, are considered to be the key factors that shape dynamic urban traffic flow. Urban traffic flow can be seen as individual trips aggregately distributed in street networks. Each trip is generated from an origin and destination (OD) pair or multiple destinations with a network path connecting them. Generally, urban planners and transportation engineers rely on household questionnaires or transportation surveys on job–housing places for traffic-demand forecasting. With the rapid development of information and communication technology (ICT), the availability of large amounts of GPS (Global Positioning System) data and mobile phone data over time and space has increased the capability for monitoring, visualizing, analyzing, and modeling urban dynamics. In this research we investigate the spatial distribution of urban traffic flow based on taxi trajectories in a city in China and compute the correlation between urban traffic fl ow and street betweenness centrality. The results confirm that purely betweenness centrality is not an ideal measure for predicting urban traffic flow. We analyze the characteristics of betweenness and point out the ‘gap’ between betweenness centrality and actual flow. The gap is filled by a framework taking into account the distance decay and the spatial heterogeneity of human activities.

(2) Ride-sharing and Street Networks

Given different types of constraints on human life, people must make decisions that satisfy social activity needs. Minimizing costs (i.e. distance, time, or money) associated with travel plays an important role in perceived and realized social quality of life. Identifying optimal interaction locations (e.g., for ride-sharing) along road networks when there are multiple moving objects (MMO) with space–time constraints remains a challenge. In this research, we formalize the problem of finding dynamic ideal interaction locations for MMO as a spatial optimization model and introduce a context-based geoprocessing heuristic framework to address this problem.

(3) Spatial Interactions along Street Networks

Researchers have proposed many methods to investigate the spatial interactions derived from human movements, such as the gravity model and the radiation model. However, most studies have mainly focused on the interactions among areal units at an aggregated level, neglecting that in most cases, human movements are carried by vehicles and constrained by the underlying road networks. To fill this gap, we propose a novel approach to identify spatial interaction patterns of vehicle movements along urban road networks.

Good characterization of traffic interactions among urban roads can facilitate traffic-related applications, such as traffic control and short-term forecasting. Most studies measure the traffic interaction between two roads by their topological distance or the correlation between their traffic variables. However, the distance-based methods neglect the spatial heterogeneity of roads’ traffic interactions, while the correlation-based methods cannot capture the non-linear dependency between two roads’ traffic variables. In this paper, we propose a novel approach called Road2Vec to quantify the implicit traffic interactions among roads based on large-scale taxi operating route data using a Word2Vec model from the natural language processing (NLP) domain. A case study on short-term traffic forecasting is conducted with artificial neural network (ANN) and support vector machine (SVM) algorithms to validate the advantages of the presented method. The results show that the forecasting achieves a higher accuracy with the support of the Road2Vec method than with the topological distance and traffic correlation based methods.

(4) Public Transportation Optimization

Public transportation systems, in particular, bus systems, play an essential role in the process of urbanization. Typically more bus stops enable more people to access the bus whereas lower the efficiency of bus system. We utilize spatial optimization techniques to address this issue.

In one of our studies, we use the Spatial Interaction Coverage (SIC) model to identify and remove redundant bus stops while maintain the overall success of the whole bus system. The SIC model aims to model the relationship between demand points and bus stops. It takes factors such as the distance and the attractiveness of each bus stop into consideration. By applying the SIC model to the iXpress 202 route in Kitchener-Waterloo region in Canada, we can effectively identify the number of stops to maintain and remove redundant stops. The bus operation efficiency can be increased by 7.28% after optimization. The relationships between bus ridership and the socioeconomic variables (population, income, and age) in the study area are also analyzed. We are expanding our research to multiple cities with the consideration of multi-route buses and multi-mode transportation.

(5) Regional Economy and Transportation Network Analytics

With the booming economy in China, many researches have pointed out that the improvement of regional transportation infrastructure among other factors had an important effect on economic growth. Utilizing a large-scale dataset which includes 3.5 billion entry and exit records of vehicles along highways generated from toll collection systems, we attempt to establish the relevance of mid-distance land transport patterns to regional economic status through transportation network analyses. We apply standard measurements of complex networks to analyze the highway transportation networks. A set of traffic flow features are computed and correlated to the regional economic development indicator. The multi-linear regression models explain about 89% to 96% of the variation of cities’ GDP across three provinces in China. We then fit gravity models using annual traffic volumes of cars, buses, and freight trucks between pairs of cities for each province separately as well as for the whole dataset. We find the temporal changes of distance-decay effects on spatial interactions between cities in transportation networks, which link to the economic development patterns of each province. We conclude that transportation big data reveal the status of regional economic development and contain valuable information of human mobility, production linkages, and logistics for regional management and planning. Our research offers insights into the investigation of regional economic development status using highway transportation big data.

References:

Gao, S., Wang, Y., Gao, Y., & Liu, Y. (2013). Understanding urban traffic-flow characteristics: a rethinking of betweenness centrality. Environment and Planning B: Planning and Design, 40(1), 135-153.

Gao, S., Yang, J. A., Yan, B., Hu, Y., Janowicz, K., & McKenzie, G. (2014, September). Detecting origin-destination mobility flows from geotagged Tweets in greater Los Angeles area. In Eighth International Conference on Geographic Information Science (GIScience’14).

Lee, J. H., Gao, S., & Goulias, K. G. (2015). Can Twitter data be used to validate travel demand models. In 14th International Conference on Travel Behaviour Research.

Liu, K., Gao, S., Qiu, P., Liu, X., Yan, B., & Lu, F. (2017). Road2Vec: Measuring Traffic Interactions in Urban Road System from Massive Travel Routes. ISPRS International Journal of Geo-Information, 6(11), 321.

Wang, S., Gao, S., Feng, X., Murray, A. T., & Zeng, Y. (2018). A context-based geoprocessing framework for optimizing meetup location of multiple moving objects along road networks. International Journal of Geographical Information Science, 32(7), 1368-1390.

Liang, Y., Gao, S., Wu, T., Wang, S., & Wu, Y. (2018, November). Optimizing Bus Stop Spacing Using the Simulated Annealing Algorithm with Spatial Interaction Coverage Model. In Proceedings of the 11th ACM SIGSPATIAL International Workshop on Computational Transportation Science (pp. 53-59). ACM.

Liu, K., Gao, S., Lu, F. (2019) Identifying spatial interaction patterns of vehicle movements on urban road networks by topic modelling. Computers, Environment and Urban Systems, 2019, 74, 50-61.

Yunlei Liang, Song Gao, Mingxiao Li, Yuhao Kang, and Jinmeng Rao (2019) Analyzing the Gap Between Ride-hailing Location and Pick-up Location with Geographical Contexts (Best Poster Award). In Proceedings of 1st ACM SIGSPATIAL International Workshop on Ride-hailing Algorithms, Applications, and Systems (RAAS’19)

Bin Li, Song Gao, Yunlei Liang, Yuhao Kang, Timothy Prestby, Yuqi Gao, and Runmou Xiao. (2020) “Estimation of Regional Economic Development Indicator from Transportation Network Analytics.”Scientific Reports, 10(2647), 1-15. DOI: https://doi.org/10.1038/s41598-020-59505-2