A Participatory Urban Traffic Monitoring System: The Power of Bus Riders

Liu, Zhidan; Jiang, Shiqi; Zhou, Pengfei; Li, Mo

doi:10.1109/tits.2017.2650215

Cited by 64 publications

(24 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intuitively, traffic data of road segments in the same district would have spatial and temporal correlations [23], [56]. For example, Liu et al [27], [57] probed traffic conditions on different road segments with GPS data from bus riders. In our future work, we will further exploit the above multi-road and multiregion correlations to extend the coverage of BuildSenSys in traffic sensing and prediction.…”

Section: Discussionmentioning

confidence: 99%

BuildSenSys: Reusing Building Sensing Data for Traffic Prediction With Cross-Domain Learning

Fan

Xiang

Chen

et al. 2021

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

With the rapid development of smart cities, smart buildings are generating a massive amount of building sensing data by the equipped sensors. Indeed, building sensing data provides a promising way to enrich a series of data-demanding and cost-expensive urban mobile applications. In this paper, as a preliminary exploration, we study how to reuse building sensing data to predict traffic volume on nearby roads. Compared with existing studies, reusing building sensing data has considerable merits of cost-efficiency and high-reliability. Nevertheless, it is non-trivial to achieve accurate prediction on such cross-domain data with two major challenges. First, relationships between building sensing data and traffic data are not unknown as prior, and the spatio-temporal complexities impose more difficulties to uncover the underlying reasons behind the above relationships. Second, it is even more daunting to accurately predict traffic volume with dynamic building-traffic correlations, which are cross-domain, non-linear, and time-varying. To address the above challenges, we design and implement BuildSenSys, a first-of-its-kind system for nearby traffic volume prediction by reusing building sensing data. Our work consists of two parts, i.e., Correlation Analysis and Cross-domain Learning. First, we conduct a comprehensive building-traffic analysis based on multi-source datasets, disclosing how and why building sensing data is correlated with nearby traffic volume. Second, we propose a novel recurrent neural network for traffic volume prediction based on cross-domain learning with two attention mechanisms. Specifically, a cross-domain attention mechanism captures the building-traffic correlations and adaptively extracts the most relevant building sensing data at each predicting step. Then, a temporal attention mechanism is employed to model the temporal dependencies of data across historical time intervals. The extensive experimental studies demonstrate that BuildSenSys outperforms all baseline methods with up to 65.3% accuracy improvement (e.g., 2.2% MAPE) in predicting nearby traffic volume. We believe that this work can open a new gate of reusing building sensing data for urban traffic sensing, thus establishing connections between smart buildings and intelligent transportation.

show abstract

Section: Discussionmentioning

confidence: 99%

BuildSenSys: Reusing Building Sensing Data for Traffic Prediction With Cross-Domain Learning

Fan

Xiang

Chen

et al. 2021

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

show abstract

“…For example, the work in [29] proposed the use of smartphone-based crowdsensing to monitor traffic conditions, while the work in [30] exploited crowdsensed data to define traffic routes. From a similar perspective, the work in [31] also employed drivers' smartphones to collect data; however, its focus was on buses, indirectly measuring the traffic conditions of roads covered by bus routes.…”

Section: Related Workmentioning

confidence: 99%

CitySpeed: A Crowdsensing-Based Integrated Platform for General-Purpose Monitoring of Vehicular Speeds in Smart Cities

2019

View full text Add to dashboard Cite

The development of crowdsensing-based technologies has allowed for the use of smartphones in large-scale data collection for different scopes of applications, mostly in a transparent and ubiquitous way. When concerning urban areas and smart city initiatives, the collection and further analysis of information about the highest number of vehicles is of paramount importance, potentially supporting more efficient mobility planning and management actions in modern cities. In this context, this article proposes a public general-purpose platform for acquisition and visualization of vehicular speeds, which can then be exploited by any additional application. For that, a crowdsensing-based mobile software application was developed to collect instantaneous speeds provided by smartphone GPS, formatting and distributing this information to a database system. Such historical data can then be exported or visualized through a web-based comprehensive interface, which provides valuable data when planning traffic mobility in cities; for example, indicating areas with heavier traffic over a certain time period. Therefore, allowing the use of many different search filters and supporting data delivery in the JSON format, the CitySpeed platform can provide services not supported by popular applications, such as Waze and Google Maps, and potentially assist smart city initiatives in this area.

show abstract

“…In this project, we apply the idea of crowdsensing [65,121] and make use of the mobility data from a large number of local students to discover the uncharted walkways. Our study relies on an ongoing crowdsensing project -Singapore National Science Experiment (NSE) [69] -a city wide initiative that enrolls more than 250,000 local students carrying smart devices that sense their surrounding environment and track their mobility [103] on daily basis.…”

Section: Pedestrian Navigationmentioning

confidence: 99%

“…Researchers also leverage the power of crowdsensing to solve problems. In [65,121], authors leverage the crowdsensed data from the mobile phones of commuters on different buses to provide a service estimating the bus arrival time. The mobility measurement involving crowd-sensing is proposed in [40], where reposting, tagging and sharing public information are used in the FlierMeet project.…”

Section: Crowdsensingmentioning

confidence: 99%

See 1 more Smart Citation

Smart sensing and mobility analysis for improved transportation efficiency

Cao¹

View full text Add to dashboard Cite

Last but not least, I would like to thank my family for the support they give me and in particular, I must acknowledge my fiancee, Xiaoyu Miao. It is your love and support that make me get here. v Contents Statement of Originality i Supervisor Declaration Statement ii Authorship Attribution Statement iii Acknowledgement v List of Acronyms ix Lists of Figures xii Lists of Tables xiii Abstract xiv the Singapore National Science Experiment. As a result, 736 walkways (totaling 161 km in distance) are identified from the mobility dataset collected from 108,337 students in Singapore. We manually verify 224 walkways totaling 32.4 km over a 9 km 2 district through on-site inspection. The results suggest over 96% accuracy of VitalAlley in discovering the walkways.

show abstract

A Participatory Urban Traffic Monitoring System: The Power of Bus Riders

Cited by 64 publications

References 36 publications

BuildSenSys: Reusing Building Sensing Data for Traffic Prediction With Cross-Domain Learning

BuildSenSys: Reusing Building Sensing Data for Traffic Prediction With Cross-Domain Learning

CitySpeed: A Crowdsensing-Based Integrated Platform for General-Purpose Monitoring of Vehicular Speeds in Smart Cities

Smart sensing and mobility analysis for improved transportation efficiency

Contact Info

Product

Resources

About