Presentation 2024-03-01
A study on analysis of rotation phenomena of MMF speckle patterns with deep learning
Ryusei Sato, Makoto Hasegawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) When laser light beams are allowed to propagate from one end of an optical fiber to the other end and further to be output onto a screen, irregular pattern called as speckle pattern can be observed in an output light spot. The authors previously reported the rotating phenomenon of speckle pattern when the optical fiber was placed onto a support plate in a loop-shape and the support plate was tilted. In this paper, we examined the method for estimating tilted angles to classify speckle pattern images by ResNet-18 trained using transfer learning. As a result, the network with a classification accuracy of approximately 95% in the measurement range of -10 to +10 degrees of tilt angle was realized.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Optical fiber / Speckle pattern / Laser light / Sensing / Deep learning / ResNet-18
Paper # EMD2023-41
Date of Issue 2024-02-23 (EMD)

Conference Information
Committee EMD
Conference Date 2024/3/1(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English) Short NOTE
Chair Takahiro Ueno(Nippon Inst. of Tech.)
Vice Chair
Secretary (NAIST)
Assistant Yoshiki Kayano(Univ. of Electro-Comm.) / Naoki Fukuda(Teikyo Univ.)

Paper Information
Registration To Technical Committee on Electromechanical Devices
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A study on analysis of rotation phenomena of MMF speckle patterns with deep learning
Sub Title (in English)
Keyword(1) Optical fiber
Keyword(2) Speckle pattern
Keyword(3) Laser light
Keyword(4) Sensing
Keyword(5) Deep learning
Keyword(6) ResNet-18
1st Author's Name Ryusei Sato
1st Author's Affiliation Chitose Institute of Science and Technology(Chitose Inst. of Science and Technology)
2nd Author's Name Makoto Hasegawa
2nd Author's Affiliation Chitose Institute of Science and Technology(Chitose Inst. of Science and Technology)
Date 2024-03-01
Paper # EMD2023-41
Volume (vol) vol.123
Number (no) EMD-404
Page pp.pp.13-18(EMD),
#Pages 6
Date of Issue 2024-02-23 (EMD)