Understanding bike trip patterns leveraging bike sharing system open data

Bike sharing systems are booming globally as a green and flexible transportation mode, but the flexibility also brings difficulties in keeping the bike stations balanced with enough bikes and docks. Understanding the spatio-temporal bike trip patterns in a bike sharing system, such as the popular trip origins and destinations during rush hours, is important for researchers to design models for bike scheduling and sta- tion management. However, due to privacy and operational concerns, bike trip data are usually not publicly available in many cities. Instead, the station feeds about real-time bike and dock number in stations are usually public, which we refer to as bike sharing system open data. In this paper, we propose an approach to infer the spatio-temporal bike trip patterns from the public station feeds. Since the number of possible trips （i.e., origin-destination station pairs） is much larger than the number of stations, we define the trip infer- ence as an ill-posed inverse problem. To solve this problem, we identify the sparsity and locality properties of bike trip patterns, and propose a sparse and weighted regularization model to impose both properties in the solution. We evaluate our method using real-world data from Washington, D.C. and New York City. Results show that our method can effectively infer the spatio-temporal bike trip patterns and outperform the baselines in both cities.

Understanding urban structures and crowd dynamics leveraging large-scale vehicle mobility data

A comprehensive understanding of city structures and urban dynamics can greatly improve the efficiency and quality of urban planning and management,while the traditional approaches of which,such as manual surveys,usually incur substantial labor and time.In this paper,we propose a data-driven framework to sense urban structures and dynamics from large-scale vehicle mobility data.First,we divide the city into fine-grained grids,and cluster the grids with similar mobility features into structured urban areas with a proposed distance-constrained clustering algorithm(DCCA).Second,we detect irregular mobility traffic patterns in each area leveraging an ARIMA-based anomaly detection algorithm(ADAM),and correlate them to the urban social and emergency events.Finally,we build a visualization system to demonstrate the urban structures and crowd dynamics.We evaluate our framework using real-world datasets collected from Xiamen city,China,and the results show that the proposed framework can sense urban structures and crowd comprehensively and effectively.

Dynamic road crime risk prediction with urban open data

Crime risk prediction is helpful for urban safety and citizens’life quality.However,existing crime studies focused on coarse-grained prediction,and usually failed to capture the dynamics of urban crimes.The key challenge is data sparsity,since that 1)not all crimes have been recorded,and 2)crimes usually occur with low frequency.In this paper,we propose an effective framework to predict fine-grained and dynamic crime risks in each road using heterogeneous urban data.First,to address the issue of unreported crimes,we propose a cross-aggregation soft-impute(CASI)method to deal with possible unreported crimes.Then,we use a novel crime risk measurement to capture the crime dynamics from the perspective of influence propagation,taking into consideration of both time-varying and location-varying risk propagation.Based on the dynamically calculated crime risks,we design contextual features(i.e.,POI distributions,taxi mobility,demographic features)from various urban data sources,and propose a zero-inflated negative binomial regression(ZINBR)model to predict future crime risks in roads.The experiments using the real-world data from New York City show that our framework can accurately predict road crime risks,and outperform other baseline methods.

Route selection for opportunity-sensing and prediction of waterlogging

Accurate monitoring of urban waterlogging contributes to the city’s normal operation and the safety of residents’daily travel.However,due to feedback delays or high costs,existing methods make large-scale,fine-grained waterlogging monitoring impossible.A common method is to forecast the city’s global waterlogging status using its partial waterlogging data.This method has two challenges:first,existing predictive algorithms are either driven by knowledge or data alone;and second,the partial waterlogging data is not collected selectively,resulting in poor predictions.To overcome the aforementioned challenges,this paper proposes a framework for large-scale and fine-grained spatiotemporal waterlogging monitoring based on the opportunistic sensing of limited bus routes.This framework follows the Sparse Crowdsensing and mainly comprises a pair of iterative predictor and selector.The predictor uses the collected waterlogging status and the predicted status of the uncollected area to train the graph convolutional neural network.It combines both knowledge-driven and data-driven approaches and can be used to forecast waterlogging status in all regions for the upcoming term.The selector consists of a two-stage selection procedure that can select valuable bus routes while satisfying budget constraints.The experimental results on real waterlogging and bus routes in Shenzhen show that the proposed framework could easily perform urban waterlogging monitoring with low cost,high accuracy,wide coverage,and fine granularity.