This demo presents GTI; a graph-based trajectory imputation framework that aims to impute sparse trajectory datasets to boost their accuracy. GTI can act as a pre-processing step to increase the accuracy of any trajectory data management system or trajectory-based application. Unlike the large majority of existing trajectory imputation frameworks, GTI assumes that the underlying road network is not available. Audience will be able to interact with GTI through different scenarios that show how GTI can be used and customized to improve the quality of trajectory data in their corresponding spatial and temporal aspects.

GPS-enabled devices, including vehicles, smartphones, wearable and tracking devices, as well as various check-in and social network data are continuously producing tremendous amounts of trajectory data, which are used consistently in many applications such as urban planning and map inference. Existing techniques for trajectory data imputation rely heavily on the existing maps to perform map-matching operations. However, modern applications such as map construction and map update assume no map exists. In this paper, we propose GTI - a scalable graph-based trajectory imputation approach for trajectory data completion. GTI relies on cross-trajectory imputation, as it exploits "mutual information" of the aggregated knowledge of all input sparse trajectories to impute the missing data for each single one of them. GTI can act as a pre-processing step for any trajectory data management system or trajectory-based application, as it takes raw sparse trajectory data as its input and outputs dense imputed trajectory data that significantly increase the accuracy of different systems that consume trajectory data. We evaluate GTI on junction-scale as well as city-scale real datasets. In addition, GTI is used as a pre-processing step in multiple trajectory-based applications and it boosts the accuracy across these applications compared with the state-of-the-art work.

The ability to collect large numbers of trajectory data through GPS-enabled devices have enabled a myriad of very important applications that are widely used on a daily basis. This includes urban computing, transportation, and map APIs for routing and navigation. Unfortunately, a major hinder for all these applications is the accuracy of collected trajectories. Due to low sampling rates, trajectories are usually sparse in terms of the large spatial and temporal distances between each two consecutive collected points. This paper presents TrImpute; a novel framework for trajectory imputation that inserts artificial GPS points between the real ones in a way that the imputed trajectories end up to be very similar to the case if such trajectories were collected with a much higher sampling rate. Unlike all prior trajectory imputation techniques, TrImpute does not assume the knowledge of the underlying road network. This makes it more practical when the underlying road network is not available or inaccurate. Experimental results on real datasets and a real deployment of TrImpute show that it is highly scalable, accurate, and can significantly boost the performance of trajectory applications by feeding them highly accurate trajectories.

This demo presents QARTA; an open-source full-fledged system for highly accurate and scalable map services. QARTA employs machine learning techniques to: (a) construct its own highly accurate map in terms of both map topology and edge weights, and (b) calibrate its query answers based on contextual information, including transportation modality, underlying algorithm, and time of day/week. The demo is based on actual deployment of QARTA in all Taxis in the State of Qatar and in the third-largest food delivery company in the country, and receiving hundreds of thousands of daily API calls with a real-time response time. Audience will be able to interact with the demo through various scenarios that show QARTA map and query accuracy as well as internals of QARTA.