Deep Learning Based NLOS Identification With Commodity WLAN Devices
- Authors
- Choi, Jeong-Sik; Lee, Woong-Hee; Lee, Jae-Hyun; Lee, Jong-Ho; Kim, Seong-Cheol
- Issue Date
- Apr-2018
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Line-of-sight identification; indoor localization; channel state information; recurrent neural network; long short-term memory
- Citation
- IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, v.67, no.4, pp.3295 - 3303
- Journal Title
- IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
- Volume
- 67
- Number
- 4
- Start Page
- 3295
- End Page
- 3303
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/3934
- DOI
- 10.1109/TVT.2017.2780121
- ISSN
- 0018-9545
- Abstract
- Identifying line-of-sight (LOS) and non-LOS channel conditions can improve the performance of many wireless applications, such as signal strength-based localization algorithms. For this purpose, channel state information (CSI) obtained by commodity IEEE 802.11n devices can be used, because it contains information about channel impulse response (CIR). However, because of the limited sampling rate of the devices, a high-resolution CIR is not available, and it is difficult to detect the existence of an LOS path from a single CSI measurement, but it can be inferred from the variation pattern of CSI over time. To this end, we propose a recurrent neural network (RNN) model, which takes a series of CSI to identify the corresponding channel condition. We collect numerous measurement data under an indoor office environment, train the proposed RNN model, and compare the performance with those of existing schemes that use handcrafted features. The proposed method efficiently learns a nonlinear relationship between input and output, and thus, yields high accuracy even for data obtained in a very short period.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/3934)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.