arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.00747cs.AI
收藏

基于贝叶斯过滤技术的RFID室内空间查询评估

RFID-Based Indoor Spatial Query Evaluation with Bayesian Filtering Techniques

Auburn University(奥本大学);TAMUCC(德州农工大学科珀斯克里斯蒂分校);National Central University(中央大学);Roskilde University(罗斯基勒大学)

Bo Hui, Wenlu Wang, Jiao Yu, Zhitao Gong, Wei-Shinn Ku, Min-Te Sun, Hua Lu

摘要:

人们在室内空间花费大量的时间(例如,办公楼、地铁系统等)在他们的日常生活中。因此,重要的是开发有效的室内空间查询算法,以支持各种基于位置的应用。然而,室内空间不同于室外空间,因为用户必须遵循室内平面图进行移动。此外,室内环境中的定位主要基于感测设备(例如,RFID阅读器)而不是GPS设备。因此,我们不能应用现有的空间查询评估技术设计的户外环境,这一新的挑战。由于贝叶斯过滤技术可以用来估计一个系统的状态,随着时间的推移,使用一系列的噪声测量系统上,在这项研究中,我们提出了贝叶斯过滤为基础的位置推断方法的基础上评估室内空间查询噪声RFID原始数据。此外,两个新的模型,室内行走图模型和锚点索引模型,在室内环境中的目标位置跟踪创建。基于推理方法和跟踪模型,我们开发了创新的室内范围和k近邻(kNN)查询算法。我们通过使用合成数据和真实数据来验证我们的解决方案。实验结果表明,该算法能够有效地评估室内空间查询。我们在https://github.com/DataScienceLab18/IndoorToolKit上开源了代码、数据和平面图。

英文摘要:

People spend a significant amount of time in indoor spaces (e.g., office buildings, subway systems, etc.) in their daily lives. Therefore, it is important to develop efficient indoor spatial query algorithms for supporting various location-based applications. However, indoor spaces differ from outdoor spaces because users have to follow the indoor floor plan for their movements. In addition, positioning in indoor environments is mainly based on sensing devices (e.g., RFID readers) rather than GPS devices. Consequently, we cannot apply existing spatial query evaluation techniques devised for outdoor environments for this new challenge. Because Bayesian filtering techniques can be employed to estimate the state of a system that changes over time using a sequence of noisy measurements made on the system, in this research, we propose the Bayesian filtering-based location inference methods as the basis for evaluating indoor spatial queries with noisy RFID raw data. Furthermore, two novel models, indoor walking graph model and anchor point indexing model, are created for tracking object locations in indoor environments. Based on the inference method and tracking models, we develop innovative indoor range and k nearest neighbor (kNN) query algorithms. We validate our solution through use of both synthetic data and real-world data. Our experimental results show that the proposed algorithms can evaluate indoor spatial queries effectively and efficiently. We open-source the code, data, and floor plan at https://github.com/DataScienceLab18/IndoorToolKit.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑