The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Este estudo desenvolveu um sistema que realiza comunicações de dados utilizando faixas de alta frequência de sinais sonoros. Ao contrário dos sistemas de comunicação por rádio que utilizam dispositivos sem fio avançados, ele requer apenas dispositivos legados, como microfones e alto-falantes, empregados em sistemas de comunicação telefônica comuns. Neste estudo, investigamos a possibilidade de uma abordagem de aprendizado de máquina para melhorar a precisão do reconhecimento identificando símbolos binários trocados através de mídia sonora. Este artigo descreve alguns resultados experimentais avaliando o desempenho da técnica proposta empregando uma rede neural como classificador de símbolos binários. Os resultados experimentais indicam que a técnica proposta pode ter certa adequação para projetar um classificador ideal para a tarefa de identificação de símbolos.
Kosei OZEKI
Hokkaido University
Naofumi AOKI
Hokkaido University
Saki ANAZAWA
Hokkaido University
Yoshinori DOBASHI
Hokkaido University
Kenichi IKEDA
Smart Solution Technology, Inc.
Hiroshi YASUDA
Smart Solution Technology, Inc.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Kosei OZEKI, Naofumi AOKI, Saki ANAZAWA, Yoshinori DOBASHI, Kenichi IKEDA, Hiroshi YASUDA, "Improving the Recognition Accuracy of a Sound Communication System Designed with a Neural Network" in IEICE TRANSACTIONS on Fundamentals,
vol. E104-A, no. 11, pp. 1577-1584, November 2021, doi: 10.1587/transfun.2020EAP1118.
Abstract: This study has developed a system that performs data communications using high frequency bands of sound signals. Unlike radio communication systems using advanced wireless devices, it only requires the legacy devices such as microphones and speakers employed in ordinary telephony communication systems. In this study, we have investigated the possibility of a machine learning approach to improve the recognition accuracy identifying binary symbols exchanged through sound media. This paper describes some experimental results evaluating the performance of our proposed technique employing a neural network as its classifier of binary symbols. The experimental results indicate that the proposed technique may have a certain appropriateness for designing an optimal classifier for the symbol identification task.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2020EAP1118/_p
Copiar
@ARTICLE{e104-a_11_1577,
author={Kosei OZEKI, Naofumi AOKI, Saki ANAZAWA, Yoshinori DOBASHI, Kenichi IKEDA, Hiroshi YASUDA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Improving the Recognition Accuracy of a Sound Communication System Designed with a Neural Network},
year={2021},
volume={E104-A},
number={11},
pages={1577-1584},
abstract={This study has developed a system that performs data communications using high frequency bands of sound signals. Unlike radio communication systems using advanced wireless devices, it only requires the legacy devices such as microphones and speakers employed in ordinary telephony communication systems. In this study, we have investigated the possibility of a machine learning approach to improve the recognition accuracy identifying binary symbols exchanged through sound media. This paper describes some experimental results evaluating the performance of our proposed technique employing a neural network as its classifier of binary symbols. The experimental results indicate that the proposed technique may have a certain appropriateness for designing an optimal classifier for the symbol identification task.},
keywords={},
doi={10.1587/transfun.2020EAP1118},
ISSN={1745-1337},
month={November},}
Copiar
TY - JOUR
TI - Improving the Recognition Accuracy of a Sound Communication System Designed with a Neural Network
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1577
EP - 1584
AU - Kosei OZEKI
AU - Naofumi AOKI
AU - Saki ANAZAWA
AU - Yoshinori DOBASHI
AU - Kenichi IKEDA
AU - Hiroshi YASUDA
PY - 2021
DO - 10.1587/transfun.2020EAP1118
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E104-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 2021
AB - This study has developed a system that performs data communications using high frequency bands of sound signals. Unlike radio communication systems using advanced wireless devices, it only requires the legacy devices such as microphones and speakers employed in ordinary telephony communication systems. In this study, we have investigated the possibility of a machine learning approach to improve the recognition accuracy identifying binary symbols exchanged through sound media. This paper describes some experimental results evaluating the performance of our proposed technique employing a neural network as its classifier of binary symbols. The experimental results indicate that the proposed technique may have a certain appropriateness for designing an optimal classifier for the symbol identification task.
ER -