Neural processing-type displacement sensor employing multimode waveguide
- 1 April 1991
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Photonics Technology Letters
- Vol. 3 (4) , 394-396
- https://doi.org/10.1109/68.82123
Abstract
A novel neural processing-type displacement sensor, consisting of a multimode waveguide and a neural network, is demonstrated. This sensor detects displacement using changes in the interference output image of the waveguide. The interference image is directly processed by a three-layer perceptron neural network. Environmental change, such as the intensity fluctuation, and change of the temperature can be followed by training the neural network. Experimental results show that the sensor has a resolution of 1 mu m.Keywords
This publication has 7 references indexed in Scilit:
- A novel optical WDM demultiplexer consisting of a simple optical multimode guide and an electrical neural networkIEEE Photonics Technology Letters, 1990
- Two-mode fiber-optic resonant ring interferometer as a sensorOptics Letters, 1990
- Elliptical-core two mode optical-fiber sensor implementation methodsJournal of Lightwave Technology, 1990
- Integration of acoustic and visual speech signals using neural networksIEEE Communications Magazine, 1989
- Handwritten digit recognition: applications of neural network chips and automatic learningIEEE Communications Magazine, 1989
- Intermodal Pattern Modulation In Optical Fiber Modal Domain Sensor Systems: Experimental ResultsPublished by SPIE-Intl Soc Optical Eng ,1989
- An electrically trainable artificial neural network (ETANN) with 10240 'floating gate' synapsesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989