Pre-Processing of Signals Observed from Laser Diode Self-mixing Intereferometries using Neural Networks

This paper presents a novel neural network signal interpolation technique in order to eliminate the noise and disturbance associated with the self-mixing signal observed from optical feedback self-mixing interferometry (OFSMI). The proposed technique aims to improve the accuracy for displacement and moving track measurement of a target. The performance of the proposed approach is evaluated by both simulation and experimentation, with simulation revealing a measuring accuracy of lambda/25 for weak feedback and lambda/20 for moderate feed back.