Two-Way Long Short-Term Memory Architecture for Non-Contact Hand Gesture Identification

Arash Shokouhmand; Negar Tavassolian

doi:10.1109/AP-S/USNC-URSI47032.2022.9886404

Two-Way Long Short-Term Memory Architecture for Non-Contact Hand Gesture Identification

Arash Shokouhmand, Negar Tavassolian

Department of Electrical and Computer Engineering

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

Abstract

This study proposes a novel method for the classification of hand gestures using a frequency-modulated continuous-wave (FMCW) radar. A two-way long short-term memory (TW-LSTM) architecture is introduced to categorize the movements recorded by an FMCW radar into 12 standard types of hand gestures provided by IEEE DataPort. The TW-LSTM method initially segments the physical displacement features of 4,600 movements into smaller frames. It then applies intra-and inter-frame temporal operations on the data to identify the type of movement. Experiments on four different subjects report an F1 score and an average accuracy of 84.02% and 84.0% for the classification of hand gestures respectively. It is also demonstrated that the true positive rates for all subjects fall within the range of 71.0%-91.0%, showing excellent consistency between predicted and true labels of hand gestures.

Original language	English
Title of host publication	2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings
Pages	349-350
Number of pages	2
ISBN (Electronic)	9781665496582
DOIs	https://doi.org/10.1109/AP-S/USNC-URSI47032.2022.9886404
State	Published - 2022
Event	2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Denver, United States Duration: 10 Jul 2022 → 15 Jul 2022

Publication series

Name	2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings

Conference

Conference	2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022
Country/Territory	United States
City	Denver
Period	10/07/22 → 15/07/22

Keywords

Displacement Features
FMCW Radar
Hand Gestures
Long Short-Term Memory
Two-Way

Access to Document

10.1109/AP-S/USNC-URSI47032.2022.9886404

Cite this

Shokouhmand, A., & Tavassolian, N. (2022). Two-Way Long Short-Term Memory Architecture for Non-Contact Hand Gesture Identification. In 2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings (pp. 349-350). (2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings). https://doi.org/10.1109/AP-S/USNC-URSI47032.2022.9886404

Shokouhmand, Arash ; Tavassolian, Negar. / Two-Way Long Short-Term Memory Architecture for Non-Contact Hand Gesture Identification. 2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings. 2022. pp. 349-350 (2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings).

@inproceedings{3cc422fd0d6443d69afa237494d0fe6c,

title = "Two-Way Long Short-Term Memory Architecture for Non-Contact Hand Gesture Identification",

abstract = "This study proposes a novel method for the classification of hand gestures using a frequency-modulated continuous-wave (FMCW) radar. A two-way long short-term memory (TW-LSTM) architecture is introduced to categorize the movements recorded by an FMCW radar into 12 standard types of hand gestures provided by IEEE DataPort. The TW-LSTM method initially segments the physical displacement features of 4,600 movements into smaller frames. It then applies intra-and inter-frame temporal operations on the data to identify the type of movement. Experiments on four different subjects report an F1 score and an average accuracy of 84.02% and 84.0% for the classification of hand gestures respectively. It is also demonstrated that the true positive rates for all subjects fall within the range of 71.0%-91.0%, showing excellent consistency between predicted and true labels of hand gestures.",

keywords = "Displacement Features, FMCW Radar, Hand Gestures, Long Short-Term Memory, Two-Way",

author = "Arash Shokouhmand and Negar Tavassolian",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 ; Conference date: 10-07-2022 Through 15-07-2022",

year = "2022",

doi = "10.1109/AP-S/USNC-URSI47032.2022.9886404",

language = "English",

series = "2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings",

pages = "349--350",

booktitle = "2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings",

}

Shokouhmand, A & Tavassolian, N 2022, Two-Way Long Short-Term Memory Architecture for Non-Contact Hand Gesture Identification. in 2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings. 2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings, pp. 349-350, 2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022, Denver, United States, 10/07/22. https://doi.org/10.1109/AP-S/USNC-URSI47032.2022.9886404

Two-Way Long Short-Term Memory Architecture for Non-Contact Hand Gesture Identification. / Shokouhmand, Arash; Tavassolian, Negar.
2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings. 2022. p. 349-350 (2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings).

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

TY - GEN

T1 - Two-Way Long Short-Term Memory Architecture for Non-Contact Hand Gesture Identification

AU - Shokouhmand, Arash

AU - Tavassolian, Negar

PY - 2022

Y1 - 2022

N2 - This study proposes a novel method for the classification of hand gestures using a frequency-modulated continuous-wave (FMCW) radar. A two-way long short-term memory (TW-LSTM) architecture is introduced to categorize the movements recorded by an FMCW radar into 12 standard types of hand gestures provided by IEEE DataPort. The TW-LSTM method initially segments the physical displacement features of 4,600 movements into smaller frames. It then applies intra-and inter-frame temporal operations on the data to identify the type of movement. Experiments on four different subjects report an F1 score and an average accuracy of 84.02% and 84.0% for the classification of hand gestures respectively. It is also demonstrated that the true positive rates for all subjects fall within the range of 71.0%-91.0%, showing excellent consistency between predicted and true labels of hand gestures.

AB - This study proposes a novel method for the classification of hand gestures using a frequency-modulated continuous-wave (FMCW) radar. A two-way long short-term memory (TW-LSTM) architecture is introduced to categorize the movements recorded by an FMCW radar into 12 standard types of hand gestures provided by IEEE DataPort. The TW-LSTM method initially segments the physical displacement features of 4,600 movements into smaller frames. It then applies intra-and inter-frame temporal operations on the data to identify the type of movement. Experiments on four different subjects report an F1 score and an average accuracy of 84.02% and 84.0% for the classification of hand gestures respectively. It is also demonstrated that the true positive rates for all subjects fall within the range of 71.0%-91.0%, showing excellent consistency between predicted and true labels of hand gestures.

KW - Displacement Features

KW - FMCW Radar

KW - Hand Gestures

KW - Long Short-Term Memory

KW - Two-Way

UR - http://www.scopus.com/inward/record.url?scp=85139784870&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85139784870&partnerID=8YFLogxK

U2 - 10.1109/AP-S/USNC-URSI47032.2022.9886404

DO - 10.1109/AP-S/USNC-URSI47032.2022.9886404

M3 - Conference contribution

AN - SCOPUS:85139784870

T3 - 2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings

SP - 349

EP - 350

BT - 2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings

T2 - 2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022

Y2 - 10 July 2022 through 15 July 2022

ER -

Shokouhmand A, Tavassolian N. Two-Way Long Short-Term Memory Architecture for Non-Contact Hand Gesture Identification. In 2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings. 2022. p. 349-350. (2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022 - Proceedings). doi: 10.1109/AP-S/USNC-URSI47032.2022.9886404

Two-Way Long Short-Term Memory Architecture for Non-Contact Hand Gesture Identification

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this