Modeling human mobility and generating synthetic yet realistic location trajectories play a fundamental role in many (privacy-aware) analysis and design processes that operate on location data. In this paper, we propose a non-parametric generative model for location trajectories that can capture high-order geographic and semantic features of human mobility. We design a simple and intuitive yet effective embedding for locations traces, and use generative adversarial networks to produce data points in this space, which will finally be transformed back to a sequential location trajectory form. We evaluate our method on realistic location trajectories and compare our synthetic traces with multiple existing methods on how they preserve geographic and semantic features of real traces at both aggregated and individual levels. Our empirical results prove the capability of our generative model in preserving various useful properties of real data.

No abstract

Being able to obtain various environmental and driving data from vehicles is becoming more and more important for current and future intelligent transportation systems (ITSs) to operate efficiently and economically. However, the limitations of privacy protection and security of the current ITSs are hindering users and vehicles from providing data. In this paper, we propose a new ITS architecture by using blockchain technology solving the privacy protection and security problems, and promoting users and vehicles to provide data to ITSs. The proposed architecture uses blockchain as a trust infrastructure to protect users’ privacy and provide trustworthy services to users. It is also compatible with the legacy ITS infrastructure and services. In addition, the hierarchical organization of chains enables the scalability of the system, and the use of smart contracts provides a flexible way for introducing new services in the ITS. The proposed architecture is demonstrated by a proof of concept implementation based on Ethereum. The test results show that the proposed architecture is feasible.

Urban flow prediction benefits smart cities in many aspects, such as traffic management and risk assessment. However, a critical prerequisite for these benefits is having fine-grained knowledge of the city. Thus, unlike previous works that are limited to coarse-grained data, we extend the horizon of urban flow prediction to fine granularity which raises specific challenges: 1) the predominance of inter-grid transitions observed in fine-grained data makes it more complicated to capture the spatial dependencies among grid cells at a global scale; 2) it is very challenging to learn the impact of external factors (e.g., weather) on a large number of grid cells separately. To address these two challenges, we present a Spatio-Temporal Relation Network (STRN) to predict fine-grained urban flows. First, a backbone network is used to learn high-level representations for each cell. Second, we present a Global Relation Module (GloNet) that captures global spatial dependencies much more efficiently compared to existing methods. Third, we design a Meta Learner that takes external factors and land functions (e.g., POI density) as inputs to produce meta knowledge and boost model performances. We conduct extensive experiments on two real-world datasets. The results show that STRN reduces the errors by 7.1% to 11.5% compared to the state-of-the-art method while using much fewer parameters. Moreover, a cloud-based system called UrbanFlow 3.0 has been deployed to show the practicality of our approach.

No abstract