| Paper ID | ASPS-3.3 |
| Paper Title |
Online Dynamic Window (ODW) Assisted 2-stage LSTM Indoor Localization for Smart Phones |
| Authors |
Mohammadamin Atashi, Arash Mohammadi, Concordia University, Canada |
| Session | ASPS-3: IoT |
| Location | Gather.Town |
| Session Time: | Thursday, 10 June, 13:00 - 13:45 |
| Presentation Time: | Thursday, 10 June, 13:00 - 13:45 |
| Presentation |
Poster
|
| Topic |
Applied Signal Processing Systems: Signal Processing over IoT [OTH-IoT] |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
There has been a recent surge of interest on smart phone-based indoor localization due to the urgent need for real-time, accurate, and scalable indoor positioning solutions independent of any proprietary sensors/modules. Existing Inertial Measurement Unit (IMU)-based approaches, typically, use statistical and error prone heading and step length estimation techniques rendering them impractical for robust, real-time and accurate indoor positioning. In this regard, the paper takes one step forward to transfer offline IMU-based models to online positioning frameworks. More specifically, inspired by prominent advances in sequential Signal Processing (SP) and Natural Language Processing (NLP) techniques, two near real-time dynamic windowing mechanisms are proposed based on a two stage Long Short-Term Memory (LSTM) localization architecture. The two underlying LSTM architectures are trained with 2100 Action Units (AU). Compared to the traditional LSTM-based positioning approaches suffering from either high tensor computation requirements or low accuracy preventing them for real-time deployment, the proposed Online Dynamic Windowing (ODW) assisted two stage LSTM model can perform localization in a real-time fashion. Performance evaluations based on a real Pedestrian Dead Reckoning (PDR) dataset shows that the proposed model can achieve exceptional classification accuracy of 97.9% and 95.5% for the two underlying LSTMs. |
