An improved computer interface comprising a recurrent neural network and a natural user interface

Jiachen Yang, Ryota Horie

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

We developed an interface system by which a user can operate a computer with hand and finger movements. To implement the interface, we used a gesture sensor to acquire the movement-based data. A recurrent neural network (RNN) was included to discriminate types of gestures. Using the proposed interface, high recognition rates were obtained for simple gestures, while the recognition rates of complicated gestures were low. To improve the rate of accuracy in recognizing complicated gestures, we investigated the dependency of factors on the rate of recognition in the RNN learning process and identified settings to refine these factors.

Original languageEnglish
Title of host publicationProcedia Computer Science
PublisherElsevier
Pages1386-1395
Number of pages10
Volume60
Edition1
DOIs
Publication statusPublished - 2015
Event19th International Conference on Knowledge Based and Intelligent Information and Engineering Systems, KES 2015 - , Singapore
Duration: 2015 Sep 72015 Sep 9

Other

Other19th International Conference on Knowledge Based and Intelligent Information and Engineering Systems, KES 2015
CountrySingapore
Period15/9/715/9/9

Fingerprint

Recurrent neural networks
User interfaces
Interfaces (computer)
Computer systems
Sensors

Keywords

  • Back propagation through time
  • Computer interface
  • Leap motion
  • Natural user interface
  • Recurrent neural network

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

An improved computer interface comprising a recurrent neural network and a natural user interface. / Yang, Jiachen; Horie, Ryota.

Procedia Computer Science. Vol. 60 1. ed. Elsevier, 2015. p. 1386-1395.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yang, J & Horie, R 2015, An improved computer interface comprising a recurrent neural network and a natural user interface. in Procedia Computer Science. 1 edn, vol. 60, Elsevier, pp. 1386-1395, 19th International Conference on Knowledge Based and Intelligent Information and Engineering Systems, KES 2015, Singapore, 15/9/7. https://doi.org/10.1016/j.procs.2015.08.213
Yang, Jiachen ; Horie, Ryota. / An improved computer interface comprising a recurrent neural network and a natural user interface. Procedia Computer Science. Vol. 60 1. ed. Elsevier, 2015. pp. 1386-1395
@inproceedings{fb7bb7edfc3c404e832114917a38acf3,
title = "An improved computer interface comprising a recurrent neural network and a natural user interface",
abstract = "We developed an interface system by which a user can operate a computer with hand and finger movements. To implement the interface, we used a gesture sensor to acquire the movement-based data. A recurrent neural network (RNN) was included to discriminate types of gestures. Using the proposed interface, high recognition rates were obtained for simple gestures, while the recognition rates of complicated gestures were low. To improve the rate of accuracy in recognizing complicated gestures, we investigated the dependency of factors on the rate of recognition in the RNN learning process and identified settings to refine these factors.",
keywords = "Back propagation through time, Computer interface, Leap motion, Natural user interface, Recurrent neural network",
author = "Jiachen Yang and Ryota Horie",
year = "2015",
doi = "10.1016/j.procs.2015.08.213",
language = "English",
volume = "60",
pages = "1386--1395",
booktitle = "Procedia Computer Science",
publisher = "Elsevier",
edition = "1",

}

TY - GEN

T1 - An improved computer interface comprising a recurrent neural network and a natural user interface

AU - Yang, Jiachen

AU - Horie, Ryota

PY - 2015

Y1 - 2015

N2 - We developed an interface system by which a user can operate a computer with hand and finger movements. To implement the interface, we used a gesture sensor to acquire the movement-based data. A recurrent neural network (RNN) was included to discriminate types of gestures. Using the proposed interface, high recognition rates were obtained for simple gestures, while the recognition rates of complicated gestures were low. To improve the rate of accuracy in recognizing complicated gestures, we investigated the dependency of factors on the rate of recognition in the RNN learning process and identified settings to refine these factors.

AB - We developed an interface system by which a user can operate a computer with hand and finger movements. To implement the interface, we used a gesture sensor to acquire the movement-based data. A recurrent neural network (RNN) was included to discriminate types of gestures. Using the proposed interface, high recognition rates were obtained for simple gestures, while the recognition rates of complicated gestures were low. To improve the rate of accuracy in recognizing complicated gestures, we investigated the dependency of factors on the rate of recognition in the RNN learning process and identified settings to refine these factors.

KW - Back propagation through time

KW - Computer interface

KW - Leap motion

KW - Natural user interface

KW - Recurrent neural network

UR - http://www.scopus.com/inward/record.url?scp=84941069369&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84941069369&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2015.08.213

DO - 10.1016/j.procs.2015.08.213

M3 - Conference contribution

VL - 60

SP - 1386

EP - 1395

BT - Procedia Computer Science

PB - Elsevier

ER -