PMID- 36679782
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20230124
LR  - 20230201
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 23
IP  - 2
DP  - 2023 Jan 14
TI  - A Codeword-Independent Localization Technique for Reconfigurable Intelligent 
      Surface Enhanced Environments Using Adversarial Learning.
LID - 10.3390/s23020984 [doi]
LID - 984
AB  - Reconfigurable Intelligent Surfaces (RISs) not only enable software-defined radio 
      in modern wireless communication networks but also have the potential to be 
      utilized for localization. Most previous works used channel matrices to calculate 
      locations, requiring extensive field measurements, which leads to rapidly growing 
      complexity. Although a few studies have designed fingerprint-based systems, they 
      are only feasible under an unrealistic assumption that the RIS will be deployed 
      only for localization purposes. Additionally, all these methods utilize RIS 
      codewords for location inference, inducing considerable communication burdens. In 
      this paper, we propose a new localization technique for RIS-enhanced environments 
      that does not require RIS codewords for online location inference. Our proposed 
      approach extracts codeword-independent representations of fingerprints using a 
      domain adversarial neural network. We evaluated our solution using the DeepMIMO 
      dataset. Due to the lack of results from other studies, for fair comparisons, we 
      define oracle and baseline cases, which are the theoretical upper and lower 
      bounds of our system, respectively. In all experiments, our proposed solution 
      performed much more similarly to the oracle cases than the baseline cases, 
      demonstrating the effectiveness and robustness of our method.
FAU - Luo, Xuanshu
AU  - Luo X
AUID- ORCID: 0000-0002-6934-5854
AD  - Department of Mathematics and Computer Science, Eindhoven University of 
      Technology, 5600 MB Eindhoven, The Netherlands.
FAU - Meratnia, Nirvana
AU  - Meratnia N
AD  - Department of Mathematics and Computer Science, Eindhoven University of 
      Technology, 5600 MB Eindhoven, The Netherlands.
LA  - eng
GR  - 10100727/Key Digital Technologies Joint Undertaking (KDT JU)/
PT  - Journal Article
DEP - 20230114
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
SB  - IM
MH  - *Learning
MH  - *Intelligence
MH  - Neural Networks, Computer
MH  - Software
PMC - PMC9865069
OTO - NOTNLM
OT  - domain adversarial neural network (DANN)
OT  - domain generalization
OT  - localization
OT  - reconfigurable intelligent surface (RIS)
OT  - representation learning
COIS- The authors declare no conflict of interest.
EDAT- 2023/01/22 06:00
MHDA- 2023/01/25 06:00
PMCR- 2023/01/14
CRDT- 2023/01/21 01:56
PHST- 2022/12/07 00:00 [received]
PHST- 2023/01/01 00:00 [revised]
PHST- 2023/01/11 00:00 [accepted]
PHST- 2023/01/21 01:56 [entrez]
PHST- 2023/01/22 06:00 [pubmed]
PHST- 2023/01/25 06:00 [medline]
PHST- 2023/01/14 00:00 [pmc-release]
AID - s23020984 [pii]
AID - sensors-23-00984 [pii]
AID - 10.3390/s23020984 [doi]
PST - epublish
SO  - Sensors (Basel). 2023 Jan 14;23(2):984. doi: 10.3390/s23020984.