An official website of the United States government
The availability of trajectory data combined with various real-life practical applications has sparked the interest of the research community to design a plethora of algorithms for various trajectory analysis techniques. However, there is an apparent lack of full-fledged systems that provide the infrastructure support for trajectory analysis techniques, which hinders the applicability of most of the designed algorithms. Inspired by the tremendous success of the Bidirectional Encoder Representations from Transformers (BERT) deep learning model in solving various Natural Language Processing tasks, our vision is to have a BERT-like system for trajectory analysis tasks. We envision that in a few years, we will have such system where no one needs to worry again about each specific trajectory analysis operation. Whether it is trajectory imputation, similarity, clustering, or whatever, it would be one system that researchers, developers, and practitioners can deploy to get high accuracy for their trajectory operations. Our vision stands on a solid ground that trajectories in a space are highly analogous to statements in a language. We outline the challenges and the road to our vision. Exploratory results confirm the promise and possibility of our vision.
more »
« less
Kamel: A Scalable BERT-Based System for Trajectory Imputation
Numerous important applications rely on detailed trajectory data. Yet, unfortunately, trajectory datasets are typically sparse with large spatial and temporal gaps between each two points, which is a major hurdle for their accuracy. This paper presents Kamel; a scalable trajectory imputation system that inserts additional realistic trajectory points, boosting the accuracy of trajectory applications. Kamel maps the trajectory imputation problem tofinding the missing wordproblem; a classical problem in the natural language processing (NLP) community. This allows employing the widely used BERT model for trajectory imputation. However, BERT, as is, does not lend itself to the special characteristics of trajectories. Hence, Kamel starts from BERT, but then adds spatial-awareness to its operations, adjusts trajectory data to be closer to the nature of language data, and adds multipoint imputation ability to it; all encapsulated in one system. Experimental results based on real datasets show that Kamel significantly outperforms its competitors and is applicable to city-scale trajectories, large gaps, and tight accuracy thresholds.
more »
« less
- Award ID(s):
- 2203553
- PAR ID:
- 10538601
- Publisher / Repository:
- PVLDB
- Date Published:
- Journal Name:
- Proceedings of the VLDB Endowment
- Volume:
- 17
- Issue:
- 3
- ISSN:
- 2150-8097
- Page Range / eLocation ID:
- 525 to 538
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Human mobility modeling from GPS-trajectories and synthetic trajectory generation are crucial for various applications, such as urban planning, disaster management and epidemiology. Both of these tasks often require filling gaps in a partially specified sequence of visits, – a new problem that we call “controlled” synthetic trajectory generation. Existing methods for next-location prediction or synthetic trajectory generation cannot solve this problem as they lack the mechanisms needed to constrain the generated sequences of visits. Moreover, existing approaches (1) frequently treat space and time as independent factors, an assumption that fails to hold true in real-world scenarios, and (2) suffer from challenges in accuracy of temporal prediction as they fail to deal with mixed distributions and the inter-relationships of different modes with latent variables (e.g., day-of-the-week). These limitations become even more pronounced when the task involves filling gaps within sequences instead of solely predicting the next visit. We introduce TrajGPT, a transformer-based, multi-task, joint spatiotemporal generative model to address these issues. Taking inspiration from large language models, TrajGPT poses the problem of controlled trajectory generation as that of text infilling in natural language. TrajGPT integrates the spatial and temporal models in a transformer architecture through a Bayesian probability model that ensures that the gaps in a visit sequence are filled in a spatiotemporally consistent manner. Our experiments on public and private datasets demonstrate that TrajGPT not only excels in controlled synthetic visit generation but also outperforms competing models in next-location prediction tasks–Relatively, TrajGPT achieves a 26-fold improvement in temporal accuracy while retaining more than 98% of spatial accuracy on average.more » « less
-
The prevalent issue in urban trajectory data usage, notably in low-sample rate datasets, revolves around the accuracy of travel time estimations, traffic flow predictions, and trajectory similarity measurements. Conventional methods, often relying on simplistic mixes of static road networks and raw GPS data, fail to adequately integrate both network and trajectory dimensions. Addressing this, the innovative GRFTrajRec framework offers a graph-based solution for trajectory recovery. Its key feature is a trajectory-aware graph representation, enhancing the understanding of trajectory-road network interactions and facilitating the extraction of detailed embedding features for road segments. Additionally, GRFTrajRec's trajectory representation acutely captures spatiotemporal attributes of trajectory points. Central to this framework is a novel spatiotemporal interval-informed seq2seq model, integrating an attention-enhanced transformer and a feature differences-aware decoder. This model specifically excels in handling spatiotemporal intervals, crucial for restoring missing GPS points in low-sample datasets. Validated through extensive experiments on two large real-life trajectory datasets, GRFTrajRec has proven its efficacy in significantly boosting prediction accuracy and spatial consistency.more » « less
-
A trajectory is a sequence of observations in time and space, for examples, the path formed by maritime vessels, orbital debris, or aircraft. It is important to track and reconstruct vessel trajectories using the Automated Identification System (AIS) data in real-world applications for maritime navigation safety. In this project, we use the National Science Foundation (NSF)'s Algorithms for Threat Detection program (ATD) 2019 Challenge AIS data to develop novel trajectory reconstruction method. Given a sequence ofNunlabeled timestamped observations, the goal is to track trajectories by clustering the AIS points with predicted positions using the information from the true trajectoriesΧ. It is a natural way to connect the observed pointxîwith the closest point that is estimated by using the location, time, speed, and angle information from a set of the points under considerationxi∀i∈ {1, 2, …,N}. The introduced method is an unsupervised clustering-based method that does not train a supervised model which may incur a significant computational cost, so it leads to a real-time, reliable, and accurate trajectory reconstruction method. Our experimental results show that the proposed method successfully clusters vessel trajectories.more » « less
-
Localizing video moments based on the movement patterns of objects is an important task in video analytics. Existing video analytics systems offer two types of querying interfaces based on natural language and SQL, respectively. However, both types of interfaces have major limitations. SQL-based systems require high query specification time, whereas natural language-based systems require large training datasets to achieve satisfactory retrieval accuracy. To address these limitations, we present SketchQL, a video database management system (VDBMS) for offline, exploratory video moment retrieval that is both easy to use and generalizes well across multiple video moment datasets. To improve ease-of-use, SketchQL features avisual query interfacethat enables users to sketch complex visual queries through intuitive drag-and-drop actions. To improve generalizability, SketchQL operates on object-tracking primitives that are reliably extracted across various datasets using pre-trained models. We present a learned similarity search algorithm for retrieving video moments closely matching the user's visual query based on object trajectories. SketchQL trains the model on a diverse dataset generated with a novel simulator, that enhances its accuracy across a wide array of datasets and queries. We evaluate SketchQL on four real-world datasets with nine queries, demonstrating its superior usability and retrieval accuracy over state-of-the-art VDBMSs.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.14778/3632093.3632113
