Let's speak trajectories
Let's speak trajectories
复制标题
DOI：
10.1145/3557915.3560972
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Mashaal Musleh;M. Mokbel;Sofiane Abbar
中科院分区：
文献类型：
--
作者：
Mashaal Musleh;M. Mokbel;Sofiane Abbar
在过去的十年里，随着用户生成的轨迹数据的大小不断增加，基于轨迹的应用程序得到了极大的关注。然而，由于缺乏统一的框架来解决潜在的轨迹分析挑战，构建基于轨迹的应用程序仍然很麻烦。受BERT深度学习模型在解决各种NLP任务方面的巨大成功的启发，我们的愿景是拥有一个类似BERT的系统，用于无数的轨迹分析操作。我们设想，在几年内，我们将拥有这样的系统，在这种系统中，没有人需要再次担心每一次具体的弹道分析操作。无论是弹道归因法、相似性、聚类法或其他任何方法，它都将是研究人员、开发人员和从业人员可以部署的一个系统，以便为他们的弹道操作获得高精度。
Trajectory-based applications have acquired significant attention over the past decade with the rising size of trajectory data generated by users. However, building trajectory-based applications is still cumbersome due to the lack of unified frameworks to tackle the underlying trajectory analysis challenges. Inspired by the tremendous success of the BERT deep learning model in solving various NLP tasks, our vision is to have a BERT-like system for a myriad of trajectory analysis operations. 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.