Ubiquitous presence of smart connected devices within the field of Internet of Things (IoT) have resulted in emergence of innovative ambience awareness concepts such as smart buildings and smart cities. In this context, Inertial Measurement Unit (IMU)-based localization is of particular interest as it provides a scalable solution independent of any proprietary sensors/modules. Existing IMU-based methodologies, however, are mainly developed based on statistical heading and step length estimation techniques that, typically, suffer from cumulative error issues and have extensive computational time requirements.To address the aforementioned issues, we propose the Online Dynamic Window (ODW)-assisted two-stage Long Short Term Memory (LSTM) localization framework. Three ODWs are proposed, where the first model uses a Natural Language Processing (NLP)-inspired Dynamic Window (DW) approach, which significantly reduces the localization computation time. The second framework is developed based on a Signal Processing Dynamic Windowing (SP-DW) approach to further reduce the required processing time. The third ODW, referred to as the SP-NLP, combines the first two windowing mechanisms to further improve the overall achieved accuracy. Compared to the traditional LSTM-based positioning approaches, the proposed ODW-assisted models can perform indoor localization in a near-real time fashion with high accuracy. Performances of the proposed ODW-assisted models are evaluated based on a real Pedestrian Dead Reckoning (PDR) dataset. The results illustrate potentials of the proposed ODW-assisted techniques in achieving high classification accuracy with significantly reduced computational time.

在物联网 (IoT) 领域中无处不在的智能连接设备导致了创新的环境感知概念的出现，例如智能建筑和智能城市。在这种情况下，基于惯性测量单元 (IMU) 的定位特别受关注，因为它提供了独立于任何专有传感器/模块的可扩展解决方案。然而，现有的基于 IMU 的方法主要是基于统计航向和步长估计技术开发的，这些技术通常会遇到累积误差问题并且需要大量计算时间。为了解决上述问题，我们提出了在线动态窗口（ODW ) 辅助的两阶段长短期记忆 (LSTM) 定位框架。提出了三个 ODW，其中第一个模型使用受自然语言处理 (NLP) 启发的动态窗口 (DW) 方法，这显着减少了定位计算时间。第二个框架是基于信号处理动态窗口 (SP-DW) 方法开发的，以进一步减少所需的处理时间。第三个 ODW，称为 SP-NLP，结合了前两个窗口机制，以进一步提高整体实现的准确性。与传统的基于 LSTM 的定位方法相比，所提出的 ODW 辅助模型可以以近实时的方式进行高精度的室内定位。所提出的 ODW 辅助模型的性能基于真实的行人航位推算 (PDR) 数据集进行评估。