D-Fi: Domain adversarial neural network based CSI fingerprint indoor localization

Deep learning based channel state information (CSI) fingerprint indoor localization schemes need to collect massive labeled data samples for training, and the parameters of the deep neural network are used as the fingerprints. However, the indoor environment may change, and the previously constructe...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei Liu, Zhiqiang Dun
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2023-07-01
Series:Journal of Information and Intelligence
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2949715923000100
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849414941417668608
author Wei Liu
Zhiqiang Dun
author_facet Wei Liu
Zhiqiang Dun
author_sort Wei Liu
collection DOAJ
description Deep learning based channel state information (CSI) fingerprint indoor localization schemes need to collect massive labeled data samples for training, and the parameters of the deep neural network are used as the fingerprints. However, the indoor environment may change, and the previously constructed fingerprint may not be valid for the changed environment. In order to adapt to the changed environment, it requires to recollect massive amount of labeled data samples and perform the training again, which is labor-intensive and time-consuming. In order to overcome this drawback, in this paper, we propose one novel domain adversarial neural network (DANN) based CSI Fingerprint Indoor Localization (D-Fi) scheme, which only needs the unlabeled data samples from the changed environment to update the fingerprint to adapt to the changed environment. Specifically, the previous environment and changed environment are treated as the source domain and the target domain, respectively. The DANN consists of the classification path and the domain-adversarial path, which share the same feature extractor. In the offline phase, the labeled CSI samples are collected as source domain samples to train the neural network of the classification path, while in the online phase, for the changed environment, only the unlabeled CSI samples are collected as target domain samples to train the neural network of the domain-adversarial path to update parameters of the feature extractor. In this case, the feature extractor extracts the common features from both the source domain samples corresponding to the previous environment and the target domain samples corresponding to the changed environment. Experiment results show that for the changed localization environment, the proposed D-Fi scheme significantly outperforms the existing convolutional neural network (CNN) based scheme.
format Article
id doaj-art-7e9a607c29f144838212771ed2b56df7
institution Kabale University
issn 2949-7159
language English
publishDate 2023-07-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Journal of Information and Intelligence
spelling doaj-art-7e9a607c29f144838212771ed2b56df72025-08-20T03:33:39ZengKeAi Communications Co., Ltd.Journal of Information and Intelligence2949-71592023-07-011210411410.1016/j.jiixd.2023.04.002D-Fi: Domain adversarial neural network based CSI fingerprint indoor localizationWei Liu0Zhiqiang Dun1Corresponding author.; School of Telecommunications Engineering, Xidian University, Xi'an 710071, ChinaSchool of Telecommunications Engineering, Xidian University, Xi'an 710071, ChinaDeep learning based channel state information (CSI) fingerprint indoor localization schemes need to collect massive labeled data samples for training, and the parameters of the deep neural network are used as the fingerprints. However, the indoor environment may change, and the previously constructed fingerprint may not be valid for the changed environment. In order to adapt to the changed environment, it requires to recollect massive amount of labeled data samples and perform the training again, which is labor-intensive and time-consuming. In order to overcome this drawback, in this paper, we propose one novel domain adversarial neural network (DANN) based CSI Fingerprint Indoor Localization (D-Fi) scheme, which only needs the unlabeled data samples from the changed environment to update the fingerprint to adapt to the changed environment. Specifically, the previous environment and changed environment are treated as the source domain and the target domain, respectively. The DANN consists of the classification path and the domain-adversarial path, which share the same feature extractor. In the offline phase, the labeled CSI samples are collected as source domain samples to train the neural network of the classification path, while in the online phase, for the changed environment, only the unlabeled CSI samples are collected as target domain samples to train the neural network of the domain-adversarial path to update parameters of the feature extractor. In this case, the feature extractor extracts the common features from both the source domain samples corresponding to the previous environment and the target domain samples corresponding to the changed environment. Experiment results show that for the changed localization environment, the proposed D-Fi scheme significantly outperforms the existing convolutional neural network (CNN) based scheme.http://www.sciencedirect.com/science/article/pii/S2949715923000100Indoor localizationDomain adversarial neural networkCSIFingerprintDeep learning
spellingShingle Wei Liu
Zhiqiang Dun
D-Fi: Domain adversarial neural network based CSI fingerprint indoor localization
Journal of Information and Intelligence
Indoor localization
Domain adversarial neural network
CSI
Fingerprint
Deep learning
title D-Fi: Domain adversarial neural network based CSI fingerprint indoor localization
title_full D-Fi: Domain adversarial neural network based CSI fingerprint indoor localization
title_fullStr D-Fi: Domain adversarial neural network based CSI fingerprint indoor localization
title_full_unstemmed D-Fi: Domain adversarial neural network based CSI fingerprint indoor localization
title_short D-Fi: Domain adversarial neural network based CSI fingerprint indoor localization
title_sort d fi domain adversarial neural network based csi fingerprint indoor localization
topic Indoor localization
Domain adversarial neural network
CSI
Fingerprint
Deep learning
url http://www.sciencedirect.com/science/article/pii/S2949715923000100
work_keys_str_mv AT weiliu dfidomainadversarialneuralnetworkbasedcsifingerprintindoorlocalization
AT zhiqiangdun dfidomainadversarialneuralnetworkbasedcsifingerprintindoorlocalization