Deep LSTM-Based Multimode Pedestrian Dead Reckoning System for Indoor Localization

Chaehun Im; Chahyeon Eom; Hyunwook Lee; Suhwan Jang; Chungyong Lee

doi:10.1109/ICEIC54506.2022.9748406

Deep LSTM-Based Multimode Pedestrian Dead Reckoning System for Indoor Localization

Chaehun Im, Chahyeon Eom, Hyunwook Lee, Suhwan Jang, Chungyong Lee

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

We propose a multimode pedestrian dead reckoning (PDR) system using a recurrent neural network. We adopt a long short-term memory (LSTM) layer to extract latent features from the sensor data. We then transform the extracted latent vector using conditional input of the pedestrian's mode to make the model operate in different contexts. Finally, the step length and heading angle are obtained through a multilayer neural network with the transformed sensor latent vector as input. The simulation results show that the proposed scheme can track pedestrians in the multimode situation using a single model.

Original language	English
Title of host publication	2022 International Conference on Electronics, Information, and Communication, ICEIC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665409346
DOIs	https://doi.org/10.1109/ICEIC54506.2022.9748406
Publication status	Published - 2022
Event	2022 International Conference on Electronics, Information, and Communication, ICEIC 2022 - Jeju, Korea, Republic of Duration: 2022 Feb 6 → 2022 Feb 9

Publication series

Name	2022 International Conference on Electronics, Information, and Communication, ICEIC 2022

Conference

Conference	2022 International Conference on Electronics, Information, and Communication, ICEIC 2022
Country/Territory	Korea, Republic of
City	Jeju
Period	22/2/6 → 22/2/9

Bibliographical note

Funding Information:
This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (NRF-2019R1A2C1010950).

Publisher Copyright:
© 2022 IEEE.

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Information Systems
Information Systems and Management
Energy Engineering and Power Technology
Electrical and Electronic Engineering

Access to Document

10.1109/ICEIC54506.2022.9748406

Cite this

Im, C., Eom, C., Lee, H., Jang, S., & Lee, C. (2022). Deep LSTM-Based Multimode Pedestrian Dead Reckoning System for Indoor Localization. In 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022 (2022 International Conference on Electronics, Information, and Communication, ICEIC 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICEIC54506.2022.9748406

Im, Chaehun ; Eom, Chahyeon ; Lee, Hyunwook et al. / Deep LSTM-Based Multimode Pedestrian Dead Reckoning System for Indoor Localization. 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 International Conference on Electronics, Information, and Communication, ICEIC 2022).

@inproceedings{1fb9bd7c28ba4752965a46ccdee16045,

title = "Deep LSTM-Based Multimode Pedestrian Dead Reckoning System for Indoor Localization",

abstract = "We propose a multimode pedestrian dead reckoning (PDR) system using a recurrent neural network. We adopt a long short-term memory (LSTM) layer to extract latent features from the sensor data. We then transform the extracted latent vector using conditional input of the pedestrian's mode to make the model operate in different contexts. Finally, the step length and heading angle are obtained through a multilayer neural network with the transformed sensor latent vector as input. The simulation results show that the proposed scheme can track pedestrians in the multimode situation using a single model.",

author = "Chaehun Im and Chahyeon Eom and Hyunwook Lee and Suhwan Jang and Chungyong Lee",

note = "Funding Information: This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (NRF-2019R1A2C1010950). Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022 ; Conference date: 06-02-2022 Through 09-02-2022",

year = "2022",

doi = "10.1109/ICEIC54506.2022.9748406",

language = "English",

series = "2022 International Conference on Electronics, Information, and Communication, ICEIC 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2022 International Conference on Electronics, Information, and Communication, ICEIC 2022",

address = "United States",

}

Im, C, Eom, C, Lee, H, Jang, S & Lee, C 2022, Deep LSTM-Based Multimode Pedestrian Dead Reckoning System for Indoor Localization. in 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022. 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022, Institute of Electrical and Electronics Engineers Inc., 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022, Jeju, Korea, Republic of, 22/2/6. https://doi.org/10.1109/ICEIC54506.2022.9748406

Deep LSTM-Based Multimode Pedestrian Dead Reckoning System for Indoor Localization. / Im, Chaehun; Eom, Chahyeon; Lee, Hyunwook et al.

2022 International Conference on Electronics, Information, and Communication, ICEIC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 International Conference on Electronics, Information, and Communication, ICEIC 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Deep LSTM-Based Multimode Pedestrian Dead Reckoning System for Indoor Localization

AU - Im, Chaehun

AU - Eom, Chahyeon

AU - Lee, Hyunwook

AU - Jang, Suhwan

AU - Lee, Chungyong

PY - 2022

Y1 - 2022

N2 - We propose a multimode pedestrian dead reckoning (PDR) system using a recurrent neural network. We adopt a long short-term memory (LSTM) layer to extract latent features from the sensor data. We then transform the extracted latent vector using conditional input of the pedestrian's mode to make the model operate in different contexts. Finally, the step length and heading angle are obtained through a multilayer neural network with the transformed sensor latent vector as input. The simulation results show that the proposed scheme can track pedestrians in the multimode situation using a single model.

AB - We propose a multimode pedestrian dead reckoning (PDR) system using a recurrent neural network. We adopt a long short-term memory (LSTM) layer to extract latent features from the sensor data. We then transform the extracted latent vector using conditional input of the pedestrian's mode to make the model operate in different contexts. Finally, the step length and heading angle are obtained through a multilayer neural network with the transformed sensor latent vector as input. The simulation results show that the proposed scheme can track pedestrians in the multimode situation using a single model.

UR - http://www.scopus.com/inward/record.url?scp=85128836929&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85128836929&partnerID=8YFLogxK

U2 - 10.1109/ICEIC54506.2022.9748406

DO - 10.1109/ICEIC54506.2022.9748406

M3 - Conference contribution

AN - SCOPUS:85128836929

T3 - 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022

BT - 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022

Y2 - 6 February 2022 through 9 February 2022

ER -

Im C, Eom C, Lee H, Jang S, Lee C. Deep LSTM-Based Multimode Pedestrian Dead Reckoning System for Indoor Localization. In 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (2022 International Conference on Electronics, Information, and Communication, ICEIC 2022). doi: 10.1109/ICEIC54506.2022.9748406

Deep LSTM-Based Multimode Pedestrian Dead Reckoning System for Indoor Localization

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this