[17p-K306-1~11] FS.1 Focused Session "AI Electronics"

3:45 PM - 4:00 PM JST(6:45 AM - 7:00 AM UTC)Presentation by Applicant for JSAP Young Scientists Presentation Award

[17p-K306-8] Reconstruction of Vibration Information Using FFNN with Laser Light

〇(B)Yuki Matsuda¹, Jisun Hong¹, Keito Ito¹, Satoshi Sunada¹, Takeo Maruyama¹ (1.Kanazawa Univ.)

Keywords:

reservoir computing,feedforward neural network

A new vibration detection method using optical remote sensing is proposed. This method focuses on the coherence of laser light and machine learning, utilizing a line-scan camera and a feedforward neural network to reconstruct vibration information from remote locations. In the experiment, an expanded HeNe laser was directed at a speaker, and the resulting interference fringe data were used to train the neural network through regression learning. The results confirmed the method's ability to reconstruct sinusoidal waves and audio signals, although challenges remain in high-frequency response and waveform accuracy.