Deep-Learning Based High-Precision Localization with Massive MIMO
(2023) In IEEE Transactions on Machine Learning in Communications and Networking- Abstract
- High-precision localization and machine learning (ML) are envisioned to be key technologies in future wireless systems. This paper presents an ML pipeline to solve localization tasks. It consists of multiple parallel processing chains, each trained using a different fingerprint to estimate the position of the user equipment. In this way, ensemble learning can be utilized to fuse all chains to improve localization performance. Nevertheless, a common problem of ML-based techniques is that network training and fine-tuning can be challenging due to the increase in network sizes when applied to (massive) multiple-input multiple-output (MIMO) systems. To address this issue, we utilize a subarray-based approach. We divide the large antenna array... (More)
- High-precision localization and machine learning (ML) are envisioned to be key technologies in future wireless systems. This paper presents an ML pipeline to solve localization tasks. It consists of multiple parallel processing chains, each trained using a different fingerprint to estimate the position of the user equipment. In this way, ensemble learning can be utilized to fuse all chains to improve localization performance. Nevertheless, a common problem of ML-based techniques is that network training and fine-tuning can be challenging due to the increase in network sizes when applied to (massive) multiple-input multiple-output (MIMO) systems. To address this issue, we utilize a subarray-based approach. We divide the large antenna array into several subarrays, feeding the fingerprints of the subarrays into the pipeline. In our case, such an approach eases the training process while maintaining or even enhancing the performance. We also use the Nyquist sampling theorem to gain insight on how to appropriately sample and average training data. Finally, an indoor measurement campaign is conducted at 3.7 GHz using the Lund University massive MIMO testbed to evaluate the approaches. Localization accuracy at a centimeter level has been reached in this particular measurement campaign. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/759e2ecb-179a-4dec-84f6-7d1834d38707
- author
- Tian, Guoda LU ; Yaman, Ilayda LU ; Sandra, Michiel LU ; Cai, Xuesong LU ; Liu, Liang LU and Tufvesson, Fredrik LU
- organization
-
- Communications Engineering (research group)
- LU Profile Area: Natural and Artificial Cognition
- LTH Profile Area: AI and Digitalization
- ELLIIT: the Linköping-Lund initiative on IT and mobile communication
- LTH Profile Area: Nanoscience and Semiconductor Technology
- Embedded Electronics Engineering (M.Sc.)
- Integrated Electronic Systems (research group)
- publishing date
- 2023-11
- type
- Contribution to journal
- publication status
- in press
- subject
- in
- IEEE Transactions on Machine Learning in Communications and Networking
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- ISSN
- 2831-316X
- language
- English
- LU publication?
- yes
- id
- 759e2ecb-179a-4dec-84f6-7d1834d38707
- date added to LUP
- 2023-11-15 11:36:06
- date last changed
- 2023-11-16 16:50:27
@article{759e2ecb-179a-4dec-84f6-7d1834d38707, abstract = {{High-precision localization and machine learning (ML) are envisioned to be key technologies in future wireless systems. This paper presents an ML pipeline to solve localization tasks. It consists of multiple parallel processing chains, each trained using a different fingerprint to estimate the position of the user equipment. In this way, ensemble learning can be utilized to fuse all chains to improve localization performance. Nevertheless, a common problem of ML-based techniques is that network training and fine-tuning can be challenging due to the increase in network sizes when applied to (massive) multiple-input multiple-output (MIMO) systems. To address this issue, we utilize a subarray-based approach. We divide the large antenna array into several subarrays, feeding the fingerprints of the subarrays into the pipeline. In our case, such an approach eases the training process while maintaining or even enhancing the performance. We also use the Nyquist sampling theorem to gain insight on how to appropriately sample and average training data. Finally, an indoor measurement campaign is conducted at 3.7 GHz using the Lund University massive MIMO testbed to evaluate the approaches. Localization accuracy at a centimeter level has been reached in this particular measurement campaign.}}, author = {{Tian, Guoda and Yaman, Ilayda and Sandra, Michiel and Cai, Xuesong and Liu, Liang and Tufvesson, Fredrik}}, issn = {{2831-316X}}, language = {{eng}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, series = {{IEEE Transactions on Machine Learning in Communications and Networking}}, title = {{Deep-Learning Based High-Precision Localization with Massive MIMO}}, url = {{https://lup.lub.lu.se/search/files/165039395/TMLCN.pdf}}, year = {{2023}}, }