Crowd flow forecasting plays an important role in risk assessment and public safety. It is a difficult task due to complex spatial-temporal dependencies as well as missing values in data. A number of models are proposed to predict crowd flow on city-scale, yet the missing pattern in city complex environment is seldomly considered. We propose a crowd flow forecasting model, Imputed Spatial-Temporal Convolution network(ISTC) to accurately predict the crowd flow in large complex buildings. ISTC uses convolution layers, whose structures are configured by graphs, to model the spatial-temporal correlations. Meanwhile ISTC adds imputation layers to handle the missing data. We demonstrate our model on several real data sets collected from sensors in a large six-floor commercial complex building. The results show that ISTC outperforms the baseline methods and is capable of handling data with as much as 40% missing data.

Forecasting the inflow and outflow of crowds at metro station, immediately controlling the number of people entering at some special times and places to avoid the occurrence of malignant events for public safety, is of great significance to subway stations management and very challenging as it is affected by many complex elements, such as inter region station flows, major events or activities, and weather. We propose a approach based on deep residual learning, called ST-DRN, to discern the pattern of spatial and temporal and integrally predict the inflow and outflow of crowds in each subway station of a city. We propose an end-to-end structure of ST-DRN based on distinct attributes of spatio-temporal data. More specifically, we apply the residual neural network framework to model the temporal nearby, day, and week properties of crowd in subway station. For each feature, we design a branch of residual convolutional units, each of which handles the spatial properties of subway crowd. ST-DRN learns to dynamically summation the output of the three residual neural networks, assigning different weights to each branch. The summation is also further combined with external elements, such as weather, holiday and workdays or weekends, to forecast the final traffic flow of crowds in each station. Evaluations on the automatic fare collection (AFC) system subway record data in Suzhou demonstrate that we proposed ST-DRN outperforms than three prominent baseline methods.

Due to the sparse distribution of road video surveillance cameras, precise trajectory tracking for vehicles remains a challenging task. To the best of our knowledge, none of the previous research considered using on-road taxicabs as mobile video surveillance cameras and road traffic flow patterns, therefore not suitable for recovering trajectories of vehicles. With this insight, we model the travel time-cost of a road segment during various time periods precisely with LNDs (Logarithmic Normal Distributions), then use LSNDs (Log Skew Normal Distributions) to approximate the time-cost of an urban trip during various time periods. We propose an approach to calculate possible location and time distribution of the vehicle, select the taxicab to verify the distribution by uploading and checking video clips of this taxicab, finally refine the restoring trajectory in a recursive manner. We evaluate our solution on real-world taxicab and road surveillance system datasets. Experimental results demonstrate that our approach outperforms alternative solutions in terms of accuracy ratio of vehicle tracking.

The research of electric vehicles (EVs) has gained more and more attention in recent years in both industry and academia, and new registrations of EVs increase rapidly, while the long delay at the convenient but crowded charging stations may discourage many drivers from switching to EVs. To address the problems, we propose a novel dynamic pricing policy that allows charging stations to adjust their service fees in real time based on the load at the stations. In our work, the selection of drivers is modeled by a new dissatisfaction function with multiple variables, which can be easily validated and improved by real applications, and our solution is evaluated from the real-world e-charge dataset. To the best of our knowledge, this is the first work that considers dynamic service fees among various charging stations for load balancing and reduction of queueing delay. This makes our work more realistic and beneficial.

Due to the sparse distribution of road video surveillance cameras, precise trajectory tracking for hit-and-run vehicles remains a challenging task. Previous research on vehicle trajectory recovery mostly focuses on recovering trajectory with low-sampling-rate GPS coordinates by retrieving road traffic flow patterns from collected GPS information. However, to the best of our knowledge, none of them considered using on-road taxicabs as mobile video surveillance cameras as well as the time-varying characteristics of vehicle traveling and road traffic flow patterns, therefore not suitable for recovering trajectories of hit-and-run vehicles. With this insight, we model the travel time-cost of a road segment during various time periods precisely with LNDs (Logarithmic Normal Distributions), then use LSNDs (Log Skew Normal Distributions) to approximate the time-cost of an urban trip during various time periods. We propose a novel approach to calculate possible location and time distribution of the hit-and-run vehicle in parallel, select the optimal taxicab to verify the distribution by uploading and checking video clips of this taxicab, finally refine the restoring trajectory in a parallel and recursive manner. We evaluate our solution on real-world taxicab and road surveillance system datasets. Experimental results demonstrate that our approach outperforms alternative solutions in terms of accuracy ratio of vehicle tracking.

This paper explores efficient 3G/4G budget utilization in mobile sensing applications. Distinct from previous research work that either relied on limited WiFi access points or assumed the availability of unlimited 3G/4G communication capability, we offer a more practical mobile sensing system that leverages potential 3G/4G budgets that participants contribute at will, and uses it efficiently customized for the needs of multiple mobile sensing applications with heterogeneous sensitivity to environmental changes. We address the challenge that the information of data generation and WiFi encounters is not a priori knowledge, and propose an online decision making algorithm that takes advantage of participants' historical data. Three typical mobile sensing applications, vehicular application, mobile health and video sharing application are explored. Experimental results demonstrate that our proposed algorithms lead to significantly better system performance compared to alternative solutions for both applications.

Due to high mobility and intermittent connections in vehicular networks, reliable and efficient vehicular communication is a challenging task. Previous research on Vehicle-to-Vehicle (V2V) communication mostly focuses on achieving reliable transmissions from a given source to a given destination by mining moving patterns of taxicabs. However, to the best of our knowledge, none of them considered the habit-driven regularities of individual taxicabs as well as the urban-layout-driven time-varying regularities of crowds of taxicabs synthetically. With this insight, we model both individual and holistic driving patterns by Markov Chain models, then devise a new method to predict possible driving routes for every single taxicab. In addition, we design a new method to evaluate the probability that a single taxicab retrieves information of a specific road segment while it drives through another road segment during a given time period, and also to quantify the expected probability that a single taxicab obtains the information of a given road segment in the near future. With such information, our solution enables the selection of the optimal data packet transmission scheme. We evaluate our solution on a real-world taxicab dataset. Experimental results demonstrate that our approach outperforms alternative solutions in terms of diffusion speed and success ratio of data retrieval.

Recent advances in vehicular networks, GPS and smartphone technologies have changed the paradigm of intelligent taxicab systems. Indeed, taxicab trajectories and online calling information have enabled us to provide more efficient and personalized services. However, existing approaches are not sufficient in exploiting cooperative scheduling techniques and utilizing real time calling information. To this end, in this paper, we model the time-varying regularities of traffic flows, activity ratios of passengers, and unoccupied taxicabs of road segments by mining statistical data on taxicab trajectories. Along this line, we propose a novel approach to calculate the expected revenue of possible routes for individual taxicabs while considering the influence of others, and at the same time, advance a dynamic taxicab scheduling mechanism with online taxicab calling information. Finally, we evaluate our algorithm on real-world taxicab data. Experimental results demonstrate that our approach outperforms existing alternative solutions in terms of average revenue of taxi drivers.

This paper explores direct phone-to-phone communication (via WiFi interface) among vehicles to support participatory sensing applications. Sensing data usually contains location, speed, and fuel consumption of the car, and has a long time delay between collected and transferred to the server. Direct communication among phones aboard is important in reducing data transfer delay time and sharing participatory sensing information in an inexpensive manner. We design a practical and optimized communication mechanism for direct phone-to-phone data transfer among phones aboard that strategically enables phone-to-phone and/or phone-to-WiFiAP communications by optimally toggling the phones between the normal client and the hotspot modes. We take advantage of the WiFi hotspot functionality on smartphones, and hence require neither involvement of participants nor changes to existing wireless infrastructure and protocols. An analytical model is established to optimize toggling between client and hotspot modes for optimal system efficiency. We fully implement this system on off-the-shelf Google Galaxy Nexus and Nexus S phones. Through a 35-vehicle two-month deployment study, as well as simulation experiments using the real-world T-drive 9,211-taxicab dataset, we show that our solution significantly reduces data transfer delay time and maintains over 80 percent system efficiency under varying system parameters.

Despite the clear benefits of electric vehicles (EVs) in terms of reducing greenhouse gas emissions and traditional energy consumptions, the popularization of EVs remains a challenge in the short run. When considering electric taxis, urban planners must face the additional issue of providing battery swapping services. While previous studies focused on planning battery swapping stations for private EVs, we investigate ways of supporting the upgrade of an entire urban taxi system, with demands differing both in scale and nature. With this insight, we analyze the historical sensing data of taxi routes, and evaluate the battery swapping demand profile, as well as the driving time between positions in the road network. Based on these inputs, we propose a method to calculate an optimized battery swapping station scheme. Our strategies are then evaluated via a real world 366-day, 3,976-taxi dataset. The results show that compared to uniform deployment, our planning scheme reduces the average time-cost by 67.2%.

Online shopping has been emerging in the past years and significantly affected conventional shopping styles, but many people still favor retail stores for reasons such as social lives and trying dresses. When they find interested goods, usually hope to obtain more information of them from online shopping for price comparison and so forth. However, state of the art solutions either have users frequently search them manually via smart phone apps, which results in a negative effect on shopping experience; or force users to delay the purchase after checking information late at home. In this demo, we present a novel system that can unobtrusively assist shopping in retail stores in a real time manner. It leverages the camera, voice control, and Internet capabilities on smart glasses, and allows users to conduct price match in real time to improve shopping experience. We describe the overall system design and demonstrate the system using Google Glass and Google Nexus 5 phone.

This paper explores direct phone-to-phone communication (via WiFi interface) among vehicles to support mobile sensing applications. Direct communication among drivers' phones is important in improving data collection efficiency and sharing participatory sensing information in an inexpensive manner. We design a practical and optimized communication mechanism for direct phone-to-phone data transfer among drivers' phones that strategically enables phone-to-phone and/or phone-to-WiFiAP communications by optimally toggles the phone between the normal client and the hotspot modes. We take advantage of the WiFi hotspot functionality on smartphones, and hence require neither involvement of participants nor changes to existing wireless infrastructure and protocols. An analytical model is established to optimize toggling between client and hotspot modes for optimal system efficiency. We fully implement this system on off-the-shelf Google Galaxy Nexus and Nexus S phones. Through a 35-vehicle 2-month deployment study, as well as simulation experiments using the real-world T-drive 9,211-taxicab dataset, we show that our solution significantly reduces data transfer delay time and maintains over 80% efficiency under varying system parameters. We even achieve 90% for parameter settings of the latest smartphones.

This paper explores efficient 3G budget utilization in mobile participatory sensing applications. 1 Distinct from previous research work that either rely on limited WiFi access points or assume the availability of unlimited 3G communication capability, we offer a more practical participatory sensing system that leverages potential 3G budgets that participants contribute at will, and uses it efficiently customized for the needs of multiple participatory sensing applications with heterogeneous sensitivity to environmental changes. We address the challenge that the information of data generation and WiFi encounters is not a priori knowledge, and propose an online decision making algorithm that takes advantage of participants' historical data. We also develop a heuristic algorithm to consume less energy and reduce the storage overhead while maintaining efficient 3G budget utilization. Experimental results from a 30-participant deployment demonstrate that, even when the budget is as small as 2.5% of a popular data plan, these two algorithms achieve higher utility of uploaded data compared to the baseline solution, especially, they increase the utility of received data by 151.4% and 137.8% for those sensitive applications.

In this demo, a learning system, called Metis, is presented that extrapolates missing pieces in participatory sensing data. The work addresses the challenge of incomplete coverage in participatory sensing applications, where lack of complete control over participant mobility and sensing patterns may create coverage gaps in space and in time. Metis learns the underlying spatiotemporal patterns of the measured phenomenon from available incomplete observations, and uses these patterns to infer missing data. We describe the overall system design and demonstrate the system using data collected during the New York City gas crisis in the aftermath of Hurricane Sandy.