Uncovering Online Sharing Vehicle Mobility Patterns from Massive GPS Trajectories

Sustainable development of transportation network companies: From the perspective of satisfaction across passengers with different travel distances

Intelligent transportation management requires not only statistical information on users' mobility patterns, but also knowledge of their corresponding transportation modes. While GPS trajectories can be readily obtained from GPS sensors found in modern smartphones and vehicles, these massive geospatial data are neither automatically annotated nor segmented by transportation mode, subsequently complicating transportation mode identification. In addition, predictive uncertainty caused by the learned model parameters or variable noise in GPS sensor readings typically remains unaccounted for. To jointly address the above issues, we propose a Bayesian deep learning framework for unsupervised GPS trajectory segmentation. After unlabeled GPS trajectories are preprocessed into sequences of motion features, they are used in unsupervised training of a channel-calibrated temporal convolutional neural network for timestep-level transportation mode identification. At test time, we approximate variational inference via Monte Carlo dropout sampling, leveraging the mean and variance of the predicted distributions to classify each input timestep and estimate its predictive uncertainty, respectively. The proposed approach outperforms both its non-Bayesian variant and established GPS trajectory segmentation baselines on Microsoft's Geolife dataset without using any labels.

Developed and developing countries have a lot of public transport networks and vehicles. This is the most important traffic key to consider. In particular, the restrictions imposed by the pandemic and the psychological factors left on people have made public transport even more important. In recent years, various micro-mobility applications have been seen in covering the last-mile distance in public transportation. Depending on the reason for the travel and the distance to be covered, the user can choose between scheduled and non-scheduled public transport services.The former are characterised by predefined timetables, routes and fares that cannot be changed either by the driver or at the request of the user. The latter are instead related to the square service or taxi service and garage service or Transportation Network Company (TNC) services .The development of electric vehicles (EV) is strongly influenced by consumer demand resulting from economic and environmental factors.The combination of EV and ridesharing also brings major benefits in terms of reduced traffic congestion, reduced environmental impact and in many cases also lower costs for the user. By incorporating e-buses into public transport fleets, a green public transport fleet can be achieved which can provide a step further towards sustainable transport system. In addition, in urban areas with low-speed limits, electric taxis can offer a faster, more efficient and cost-effective solution, as can small buses in the form of demand responsive transport (DRT) services. Unfortunately, there are still a number of problems limiting the development of all-electric transport services. This is the main reason for the spread of hybrid transport services rather than the experimentation of full electric vehicles (EVs) in the case of many non-scheduled services.Through a comparative overview of different case studies and strategies implemented by European and non-European countries, this research highlights the benefits and criticalities related to the integration of EVs and especially taxis in varying city sizes and lays the groundwork for future research steps.

During the COVID-19 pandemic, governments have attempted to control infections within their territories by implementing border controls and lockdowns. While large-scale quarantine has been the most successful short-term policy, the enormous costs exerted by lockdowns over long periods are unsustainable. As such, developing more flexible policies that limit transmission without requiring large-scale quarantine is an urgent priority. Here, the dynamics of dismantled community mobility structures within US society during the COVID-19 outbreak are analysed by applying the Louvain method with modularity optimization to weekly datasets of mobile device locations. Our networks are built based on individuals' movements from February to May 2020. In a multi-scale community detection process using the locations of confirmed cases, natural break points from mobility patterns as well as high risk areas for contagion are identified at three scales. Deviations from administrative boundaries were observed in detected communities, indicating that policies informed by assumptions of disease containment within administrative boundaries do not account for high risk patterns of movement across and through these boundaries. We have designed a multi-level quarantine process that takes these deviations into account based on the heterogeneity in mobility patterns. For communities with high numbers of confirmed cases, contact tracing and associated quarantine policies informed by underlying dismantled community mobility structures is of increasing importance.

Dynamic Estimation of Optimal Dispatching Locations for Taxi Services in Mega-Cities based on Detailed GPS Information

Bi-level decisions of vacant taxi drivers traveling towards taxi stands in customer-search: Modeling methodology and policy implications

In this paper, we propose a novel approach for mining lane-level road network information from low-precision vehicle GPS trajectories (MLIT), which includes the number and turn rules of traffic lanes based on naïve Bayesian classification. First, the proposed method (MLIT) uses an adaptive density optimization method to remove outliers from the raw GPS trajectories based on their space-time distribution and density clustering. Second, MLIT acquires the number of lanes in two steps. The first step establishes a naïve Bayesian classifier according to the trace features of the road plane and road profiles and the real number of lanes, as found in the training samples. The second step confirms the number of lanes using test samples in reference to the naïve Bayesian classifier using the known trace features of test sample. Third, MLIT infers the turn rules of each lane through tracking GPS trajectories. Experiments were conducted using the GPS trajectories of taxis in Wuhan, China. Compared with human-interpreted results, the automatically generated lane-level road network information was demonstrated to be of higher quality in terms of displaying detailed road networks with the number of lanes and turn rules of each lane.

Ridesplitting, a form of shared ridesourcing service, has the potential to significantly reduce emissions. However, its current adoption rate among users remains relatively low. Policies such as carbon credit schemes, which offer rewards for emission reduction, hold great promise in promoting ridesplitting. This study aimed to quantitatively analyze the choice behaviors for ridesplitting under a carbon credit scheme. First, both the socio-demographic and psychological factors that may influence the ridesplitting behavioral intention were identified based on the theory of planned behavior, technology acceptance model, and perceived risk theory. Then, a hybrid choice model of ridesplitting was established to model choice behaviors for ridesplitting under a carbon credit scheme by integrating both structural equation modeling and discrete choice modeling. Meanwhile, a stated preference survey was conducted to collect the socio-demographic and psychological information and ridesplitting behavioral intentions of transportation network company (TNC) users in 12 hypothetical scenarios with different travel distances and carbon credit prices. Finally, the model was evaluated based on the survey data. The results show that attitudes, subjective norms, perceived behavioral control, low-carbon values, and carbon credit prices have significant positive effects on the choice behavior for ridesplitting. Specifically, increasing the carbon credit price could raise the probability of travelers choosing ridesplitting. In addition, travelers with higher low-carbon values are usually more willing to choose ridesplitting and are less sensitive to carbon credit prices. The findings of this study indicate that a carbon credit scheme is an effective means to incentivize TNC users to choose ridesplitting.

Location-based check-in services enable individuals to share their activity-related choices and providing a new source of human activity data for researchers. In this paper urban human mobility and activity patterns are analyzed using location-based data collected from social media applications (e.g. Foursquare and Twitter). We first characterize aggregate activity patterns by finding the distributions of different activity categories over a city geography and thus determine the purpose-specific activity centers. We then characterize individual activity patterns by finding the timing distribution of visiting different places depending on activity category. We also explore the frequency of visiting a place with respect to the rank of the place in individual's visitation records and show interesting match with other results based on mobile phone mobility data. We finally propose a physics-based model of human mobility patterns that can explain the scaling laws observed in the data.

Raw GPS trajectory data are often very large and use up excessive storage space. The efficiency and accuracy of activity patterns analysis or individual–environment interaction modeling using such data may be compromised due to data size and computational needs. Line generalization algorithms may be used to simplify GPS trajectories. However, traditional algorithms focus on geometric characteristics of linear features. Trajectory data may record information beyond location. Examples include time and elevation, and inferred information such as speed, transportation mode, and activities. Effective trajectory simplification should preserve these characteristics in addition to location and orientation of spatial-temporal movement. This paper proposes an Enhanced Douglas–Peucker (EDP) algorithm that implements a set of Enhanced Spatial-Temporal Constraints (ESTC) when simplifying trajectory data. These constraints ensure that the essential properties of a trajectory be preserved through preserving critical points. Further, this study argues that speed profile can uniquely identify a trajectory and thus it can be used to evaluate the effectiveness of a trajectory simplification. The proposed ESTC-EDP simplification method is applied to two examples of GPS trajectory. The results of trajectory simplification are reported and compared with that from traditional DP algorithm. The effectiveness of simplification is evaluated.

Electric vehicles (EVs) currently face formidable challenges in promotion, i.e., short driving ranges, long charging times, and few charging stations, thereby limiting their acceptability to taxi drivers. Leveraging massive-scale taxi GPS trajectory data, we present a novel real-time route recommendation system for electric taxi (ET) drivers. Taxi travel knowledge, including the probability of picking up passengers and the distribution of destinations, is learned from the raw GPS trajectories. Considering the cascading effect of route decision making, consecutive ET actions are modeled with an action tree. The corresponding expected net revenue is estimated based on the learned knowledge. A prototype online system is developed for providing route recommendations, e.g., when to go to a charging station or cruise on certain roads. An experiment in Shenzhen demonstrates that the average daily net revenue of ET drivers is better than those of 76.2% of gasoline taxi drivers. The presented approach not only increases the revenue of ET drivers in the short term but also improves the viability of EVs in the long run.

Knowledge discovery from GPS trajectory data is an essential topic in several scientific areas, including data mining, human behavior analysis, and user modeling. This article proposes a task that assigns personalized visited points of interest (POIs). Its goal is to assign every fine-grain location (i.e., POIs) that a user actually visited, which we call visited-POI , to the corresponding span of his or her (personal) GPS trajectories. We also introduce a novel algorithm to solve this assignment task. First, we exhaustively extract stay-points as span candidates of visits using a variant of a conventional stay-point extraction method and then extract POIs that are located close to the extracted stay-points as visited-POI candidates. Then, we simultaneously predict which stay-points and POIs can be actual user visits by considering various aspects, which we formulate as integer linear programming. Experimental results conducted on a real user dataset show that our method achieves higher accuracy in the visited-POI assignment task than the various cascaded procedures of conventional methods.

Population mobility patterns are an important reflection of the future distribution of migrant populations and the evolution trends of urbanization patterns. However, although research based on statistical data can reveal the pattern of population flow, it also shows a time lag. Most of the population flow network research based on location services data has failed to fully discuss the symmetry of directional outflows and inflows in the same place and the two-way symmetrical connections between places. This paper creatively proposes and constructs the concept and analysis framework of population flow asymmetry. We used the Yangtze River Delta (YRD) as a typical case and the results of our analysis reveal the temporal and spatial asymmetry of the population flow using complex network analysis methods based on the Spring Festival (SF) population migration big data. We found that the timing asymmetry manifested in such a way that the closer it was to the festival, the greater the scale and intensity of the population movement. This is a feature of the lack of scale and regional differences within China. The spatial asymmetry was manifested in three aspects, network, node, and link, and the core cities with administrative and economic hierarchical advantages dominated the asymmetric pattern of regional population mobility. In addition, distance and administrative boundaries are factors that cannot be ignored in population movements, and they were implicated in the degree of asymmetry by distance enhancement and administrative boundary blocking. The conclusions of this study can not only provide policy decision-making guidelines for population management and resource allocation in the YRD, but they can also provide a reference value for achieving the goal of regional, high-quality, integrated development. Future research will further the discussion and management of socio-economic attributes in order to develop a more detailed and microscopic understanding of the mechanisms of population mobility patterns.

With the increasing availability of GPS-equipped mobile devices, location-based services have become an integral part of everyday life. Among one of the initial steps of positioning data management, map matching aims to reduce the uncertainty in a trajectory by matching the GPS points to the road network on a digital map. Most existing work has focused on estimating the likelihood of a candidate route based on the GPS observations, while neglecting to model the probability of a route choice from the perspective of drivers. In this work, we propose a novel feature-based map matching algorithm that estimates the cost of a candidate route based on both GPS observations and human factors. To take human factors into consideration is highly important, especially when dealing with low sampling rate data where most of the movement details are lost. Additionally, we simultaneously analyze a subsequence of coherent GPS points by utilizing a new segment-based probabilistic map matching strategy, which is less susceptible to the noisiness of the positioning data. We have evaluated both the offline and the online versions of our proposed approach on a public large-scale GPS dataset, which consists of 100 trajectories distributed all over the world. The experimental results show that our method is robust to sparse data with large sampling intervals (e.g., 60s ∼ 300s) and challenging track features (e.g., u-turns and loops). Measurements including map matching accuracy and system efficiency have been thoroughly evaluated and discussed. Compared with two state-of-the-art map matching algorithms, our method substantially reduces the route mismatch error by 6.4% ∼ 32.3% (either offline or online with the window size set to 360s), with a slight increase in terms of the processing time. The experimental results show that our proposed method obtains the state-of-the-art map matching results in all the different combinations of sampling rates and challenging features.

Location-based services (LBSs) typically crowdsource geo-tagged data from mobile users. Collecting more data will generally improve the utility for LBS providers; however, it also leads to more privacy exposure of users’ mobility patterns. Although the tension between data utility and user privacy has been recognized, there lacks a solution that determines how much data to collect—in both spatial and temporal domains—is the “best” for both mobile users and the service provider. This article proposes a strategy toward making an optimal tradeoff such that a user submits data only if her mobility privacy will not be compromised and the data utility of the LBS provider will be sufficiently improved. To this end, we first define and formulate a concept called privacy exposure , which incorporates both the spatial distribution and the temporal transition of a user’s activity points . Second, we define and quantify data utility in terms of spatial repetitions and temporal closeness among data based on an economic principle. Then, we propose a PRivacy-preserving and UTility-Enhancing Crowdsourcing (PRUTEC) algorithm to determine, on behalf of each mobile user, whether a newly sensed piece of data should be submitted to the LBS provider. Our simulation demonstrates that PRUTEC improves the data utility of the service provider with a much less amount of data to collect and reduces privacy exposure for mobile users while collecting useful data continuously.