An Indoor Localization System Using Residual Learning with Channel State Information
With the increasing demand of location-based services, neural network (NN)-based intelligent indoor localization has attracted great interest due to its high localization accuracy. However, deep NNs are usually affected by degradation and gradient vanishing. To fill this gap, we propose a novel indo...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/23/5/574 |
| _version_ | 1827693219307061248 |
|---|---|
| author | Chendong Xu Weigang Wang Yunwei Zhang Jie Qin Shujuan Yu Yun Zhang |
| author_facet | Chendong Xu Weigang Wang Yunwei Zhang Jie Qin Shujuan Yu Yun Zhang |
| author_sort | Chendong Xu |
| collection | DOAJ |
| description | With the increasing demand of location-based services, neural network (NN)-based intelligent indoor localization has attracted great interest due to its high localization accuracy. However, deep NNs are usually affected by degradation and gradient vanishing. To fill this gap, we propose a novel indoor localization system, including denoising NN and residual network (ResNet), to predict the location of moving object by the channel state information (CSI). In the ResNet, to prevent overfitting, we replace all the residual blocks by the stochastic residual blocks. Specially, we explore the long-range stochastic shortcut connection (LRSSC) to solve the degradation problem and gradient vanishing. To obtain a large receptive field without losing information, we leverage the dilated convolution at the rear of the ResNet. Experimental results are presented to confirm that our system outperforms state-of-the-art methods in a representative indoor environment. |
| first_indexed | 2024-03-10T11:38:45Z |
| format | Article |
| id | doaj.art-96e84726ac5d4bffbd2237125ba999de |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-10T11:38:45Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-96e84726ac5d4bffbd2237125ba999de2023-11-21T18:40:39ZengMDPI AGEntropy1099-43002021-05-0123557410.3390/e23050574An Indoor Localization System Using Residual Learning with Channel State InformationChendong Xu0Weigang Wang1Yunwei Zhang2Jie Qin3Shujuan Yu4Yun Zhang5College of Electronic and Optical Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaCollege of Electronic and Optical Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaCollege of Electronic and Optical Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaCollege of Electronic and Optical Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaCollege of Electronic and Optical Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaCollege of Electronic and Optical Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaWith the increasing demand of location-based services, neural network (NN)-based intelligent indoor localization has attracted great interest due to its high localization accuracy. However, deep NNs are usually affected by degradation and gradient vanishing. To fill this gap, we propose a novel indoor localization system, including denoising NN and residual network (ResNet), to predict the location of moving object by the channel state information (CSI). In the ResNet, to prevent overfitting, we replace all the residual blocks by the stochastic residual blocks. Specially, we explore the long-range stochastic shortcut connection (LRSSC) to solve the degradation problem and gradient vanishing. To obtain a large receptive field without losing information, we leverage the dilated convolution at the rear of the ResNet. Experimental results are presented to confirm that our system outperforms state-of-the-art methods in a representative indoor environment.https://www.mdpi.com/1099-4300/23/5/574indoor localizationchannel state information (CSI)denoising neural network (NN)residual network (ResNet) |
| spellingShingle | Chendong Xu Weigang Wang Yunwei Zhang Jie Qin Shujuan Yu Yun Zhang An Indoor Localization System Using Residual Learning with Channel State Information Entropy indoor localization channel state information (CSI) denoising neural network (NN) residual network (ResNet) |
| title | An Indoor Localization System Using Residual Learning with Channel State Information |
| title_full | An Indoor Localization System Using Residual Learning with Channel State Information |
| title_fullStr | An Indoor Localization System Using Residual Learning with Channel State Information |
| title_full_unstemmed | An Indoor Localization System Using Residual Learning with Channel State Information |
| title_short | An Indoor Localization System Using Residual Learning with Channel State Information |
| title_sort | indoor localization system using residual learning with channel state information |
| topic | indoor localization channel state information (CSI) denoising neural network (NN) residual network (ResNet) |
| url | https://www.mdpi.com/1099-4300/23/5/574 |
| work_keys_str_mv | AT chendongxu anindoorlocalizationsystemusingresiduallearningwithchannelstateinformation AT weigangwang anindoorlocalizationsystemusingresiduallearningwithchannelstateinformation AT yunweizhang anindoorlocalizationsystemusingresiduallearningwithchannelstateinformation AT jieqin anindoorlocalizationsystemusingresiduallearningwithchannelstateinformation AT shujuanyu anindoorlocalizationsystemusingresiduallearningwithchannelstateinformation AT yunzhang anindoorlocalizationsystemusingresiduallearningwithchannelstateinformation AT chendongxu indoorlocalizationsystemusingresiduallearningwithchannelstateinformation AT weigangwang indoorlocalizationsystemusingresiduallearningwithchannelstateinformation AT yunweizhang indoorlocalizationsystemusingresiduallearningwithchannelstateinformation AT jieqin indoorlocalizationsystemusingresiduallearningwithchannelstateinformation AT shujuanyu indoorlocalizationsystemusingresiduallearningwithchannelstateinformation AT yunzhang indoorlocalizationsystemusingresiduallearningwithchannelstateinformation |