arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.09436eess.SYcs.LGcs.PFcs.SY
收藏

面向无处不在的室内定位:跨异构数据集的系统比较

Towards Ubiquitous Indoor Positioning: Comparing Systems across Heterogeneous Datasets

UBIK Geospatial Solutions S.L.(UBIK地理空间解决方案有限公司);University of Minho(米尼奥大学);Tampere University(坦佩雷大学);Universitat Jaume I(海梅一世大学);National Research Council(国家研究委员会)

Joaquín Torres-Sospedra, Ivo Silva, Lucie Klus, Darwin Quezada-Gaibor, Antonino Crivello, Paolo Barsocchi, Cristiano Pendão, Elena Simona Lohan, Jari Nurmi, Adriano Moreira

摘要:

室内定位系统(IPS)的评估主要依赖于研究人员或合作伙伴设施中的本地部署。准备综合实验、收集数据和考虑多种情景的复杂性通常限制了评估范围,因此也限制了对拟议系统的评估。由于不能保证使用相同的传感器或锚密度,因此无法概括受控实验的要求和特征。数据集的曙光正在将IPS评估推向与机器学习模型相似的水平,其中新的建议在许多异构数据集上进行评估。本文提出了一种在多个场景中评估IPS的方法,并通过三个用例进行了验证。结果证明,所提出的聚合的评价指标值是一个有用的工具,高层次的比较IPS。

英文摘要:

The evaluation of Indoor Positioning Systems (IPS) mostly relies on local deployments in the researchers' or partners' facilities. The complexity of preparing comprehensive experiments, collecting data, and considering multiple scenarios usually limits the evaluation area and, therefore, the assessment of the proposed systems. The requirements and features of controlled experiments cannot be generalized since the use of the same sensors or anchors density cannot be guaranteed. The dawn of datasets is pushing IPS evaluation to a similar level as machine-learning models, where new proposals are evaluated over many heterogeneous datasets. This paper proposes a way to evaluate IPSs in multiple scenarios, that is validated with three use cases. The results prove that the proposed aggregation of the evaluation metric values is a useful tool for high-level comparison of IPSs.

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。

↑