Multiscale Transformer and Attention Mechanism for Magnetic Spatiotemporal Sequence Localization
- 14 February 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (11) , 19454-19469
Abstract
Location-based service (LBS) is the core of Internet of Things (IoT), which serves tracking, navigation, and monitoring. The ubiquitous magnetic signals are temporally stable and spatially distinguishable and can achieve high-precision and ubiquitous positioning results without additional infrastructure, which is favored by researchers and has become a major research hotspot. Although there has been extensive research in the field of indoor magnetic positioning, there is still room for optimization in terms of positioning accuracy and robustness. Aiming at the problem that the magnetometer is offset and susceptible to environmental interference, we propose an online magnetometer calibration algorithm without user perception. Aiming at the inconsistency of magnetic data spatial scale problem caused by differences in device sampling frequency and user walking speed, we leverage different scales to segment the magnetic data, extract the magnetic sequence features of the corresponding scales through Transformer, utilize the attention mechanism to score the weights of the different scale features, and finally fuse the multiple scale features for positioning. We conduct extensive and well-designed experiments on public data sets and self-collected data sets. The experimental results indicate that the proposed method effectively solves the magnetic spatial scale problem and improves indoor magnetic positioning accuracy.Keywords
Funding Information
- National Key Research and Development Program of China (2020YFB1708800)
- China Postdoctoral Science Foundation (2021M700385)
- Basic and Applied Basic Research Foundation of Guangdong Province (2024A1515011866, 2021A1515110577)
- Central Guidance on Local Science and Technology Development Fund of Shanxi Province (YDZJSX2022B019, YDZJSX20231D005)
- National Natural Science Foundation of China (61872046, 62002026)
- Joint Research Fund for Beijing Natural Science Foundation and Haidian Original Innovation (L232001)
- University of Science and Technology Beijing Young Faculty International Exchange and Development Program (QNXM20230016)
- Fundamental Research Funds for Central Universities (FRF-MP-20-37)
This publication has 76 references indexed in Scilit:
- DarLoc: Deep learning and data-feature augmentation based robust magnetic indoor localizationExpert Systems with Applications, 2023
- Implementation and performance analysis of the PDR/GNSS integration on a smartphoneGPS Solutions, 2022
- Machine learning in indoor visible light positioning systems: A reviewNeurocomputing, 2022
- Accurate Indoor Localization Using Magnetic Sequence Fingerprints with Deep Learning2022
- A survey of step length estimation models based on inertial sensors for indoor navigation systemsInternational Journal of Communication Systems, 2021
- An enhanced foot-mounted PDR method with adaptive ZUPT and multi-sensors fusion for seamless pedestrian navigationGPS Solutions, 2021
- Indoor Localization Scheme Using Magnetic Map for SmartphonesWireless Personal Communications, 2021
- Real-time indoor localization using smartphone magnetic with LSTM networksNeural Computing and Applications, 2021
- A Comprehensive Analysis of Magnetic Field Based Indoor Positioning With Smartphones: Opportunities, Challenges and Practical LimitationsIEEE Access, 2020
- MINLOC:Magnetic Field Patterns-Based Indoor Localization Using Convolutional Neural NetworksIEEE Access, 2020