Channel state information–based multi-level fingerprinting for indoor localization with deep learning
With the rapid growth of indoor positioning requirements without equipment and the convenience of channel state information acquisition, the research on indoor fingerprint positioning based on channel state information is increasingly valued. In this article, a multi-level fingerprinting approach is...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-10-01
|
| Series: | International Journal of Distributed Sensor Networks |
| Online Access: | https://doi.org/10.1177/1550147718806719 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832553137679892480 |
|---|---|
| author | Tao Li Hai Wang Yuan Shao Qiang Niu |
| author_facet | Tao Li Hai Wang Yuan Shao Qiang Niu |
| author_sort | Tao Li |
| collection | DOAJ |
| description | With the rapid growth of indoor positioning requirements without equipment and the convenience of channel state information acquisition, the research on indoor fingerprint positioning based on channel state information is increasingly valued. In this article, a multi-level fingerprinting approach is proposed, which is composed of two-level methods: the first layer is achieved by deep learning and the second layer is implemented by the optimal subcarriers filtering method. This method using channel state information is termed multi-level fingerprinting with deep learning. Deep neural networks are applied in the deep learning of the first layer of multi-level fingerprinting with deep learning, which includes two phases: an offline training phase and an online localization phase. In the offline training phase, deep neural networks are used to train the optimal weights. In the online localization phase, the top five closest positions to the location position are obtained through forward propagation. The second layer optimizes the results of the first layer through the optimal subcarriers filtering method. Under the accuracy of 0.6 m, the positioning accuracy of two common environments has reached, respectively, 96% and 93.9%. The evaluation results show that the positioning accuracy of this method is better than the method based on received signal strength, and it is better than the support vector machine method, which is also slightly improved compared with the deep learning method. |
| format | Article |
| id | doaj-art-915c91631e1944a6b26d2fd3fdc74c26 |
| institution | Kabale University |
| issn | 1550-1477 |
| language | English |
| publishDate | 2018-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Distributed Sensor Networks |
| spelling | doaj-art-915c91631e1944a6b26d2fd3fdc74c262025-02-03T05:55:23ZengWileyInternational Journal of Distributed Sensor Networks1550-14772018-10-011410.1177/1550147718806719Channel state information–based multi-level fingerprinting for indoor localization with deep learningTao LiHai WangYuan ShaoQiang NiuWith the rapid growth of indoor positioning requirements without equipment and the convenience of channel state information acquisition, the research on indoor fingerprint positioning based on channel state information is increasingly valued. In this article, a multi-level fingerprinting approach is proposed, which is composed of two-level methods: the first layer is achieved by deep learning and the second layer is implemented by the optimal subcarriers filtering method. This method using channel state information is termed multi-level fingerprinting with deep learning. Deep neural networks are applied in the deep learning of the first layer of multi-level fingerprinting with deep learning, which includes two phases: an offline training phase and an online localization phase. In the offline training phase, deep neural networks are used to train the optimal weights. In the online localization phase, the top five closest positions to the location position are obtained through forward propagation. The second layer optimizes the results of the first layer through the optimal subcarriers filtering method. Under the accuracy of 0.6 m, the positioning accuracy of two common environments has reached, respectively, 96% and 93.9%. The evaluation results show that the positioning accuracy of this method is better than the method based on received signal strength, and it is better than the support vector machine method, which is also slightly improved compared with the deep learning method.https://doi.org/10.1177/1550147718806719 |
| spellingShingle | Tao Li Hai Wang Yuan Shao Qiang Niu Channel state information–based multi-level fingerprinting for indoor localization with deep learning International Journal of Distributed Sensor Networks |
| title | Channel state information–based multi-level fingerprinting for indoor localization with deep learning |
| title_full | Channel state information–based multi-level fingerprinting for indoor localization with deep learning |
| title_fullStr | Channel state information–based multi-level fingerprinting for indoor localization with deep learning |
| title_full_unstemmed | Channel state information–based multi-level fingerprinting for indoor localization with deep learning |
| title_short | Channel state information–based multi-level fingerprinting for indoor localization with deep learning |
| title_sort | channel state information based multi level fingerprinting for indoor localization with deep learning |
| url | https://doi.org/10.1177/1550147718806719 |
| work_keys_str_mv | AT taoli channelstateinformationbasedmultilevelfingerprintingforindoorlocalizationwithdeeplearning AT haiwang channelstateinformationbasedmultilevelfingerprintingforindoorlocalizationwithdeeplearning AT yuanshao channelstateinformationbasedmultilevelfingerprintingforindoorlocalizationwithdeeplearning AT qiangniu channelstateinformationbasedmultilevelfingerprintingforindoorlocalizationwithdeeplearning |