Home // ALLSENSORS 2019, The Fourth International Conference on Advances in Sensors, Actuators, Metering and Sensing // View article

Frequency and Intensity Decision of Laser Microphone Using Deep Leaning

Authors:
Ryota Mori
Norio Tsuda
Jun Yamada

Keywords: Laser Microphone, self-coupling effect, deep learning

Abstract:
Laser Microphones do not use a diaphragm, and are hence able to detect sound waves over a wide frequency band, from low frequency waves to ultrasonic waves. They can also measure sound waves in fluids, such as under water, without contact. However, the output signal of the Laser Microphone has many superimposed noise components, digital filter processing may be necessary and there was a disadvantage that the amount of processing increased. Therefore, we verified whether the desired frequency and sound pressure intensity can be determined even in the presence of superimposed noise by learning the output signal in the non-processed state via Deep Learning. As a result, when the number of epochs corresponding to the learning amount is 500, frequency judgment was generally possible.

Pages: 35 to 36

Copyright: Copyright (c) IARIA, 2019

Publication date: February 24, 2019

Published in: conference

ISSN: 2519-836X

ISBN: 978-1-61208-691-0

Location: Athens, Greece

Dates: from February 24, 2019 to February 28, 2019