On the Capability of Artificial Neural Networks to Compensate Nonlinearities in Wavelength Sensing 英文参考文献.docVIP

Sensors 2009, 9, 2884-2894; doi:10.3390/OPEN ACCESS sensors ISSN 1424-8220 /journal/sensors Article On the Capability of Artificial Neural Networks to Compensate Nonlinearities in Wavelength Sensing ?Mohamed Lamine Hafiane *, Zohir Dibi and Otto Manck 1, 1 2 1 Laboratoire d’Electronique Avancée, Département d’Electronique, Université de Batna, 05 avenue Chahid Boukhlouf 05000 Batna, Algeria; E-Mail:zohirdibi@yahoo.fr (Z.D.) 2 Institut für Technische Informatik und Mikroelektronik, Technische Universit?t Berlin, Germany * Author to whom correspondence should be addressed; E-Mail: hafiane_lamine@yahoo.fr; Tel. +213 33 80 54 94; Fax: +213 33 80 54 94 Received: 6 April 2009; in revised form: 6 April 2009 / Accepted: 21 April 2009 / Published: 21 April 2009 Abstract: An intelligent sensor for light wavelength readout, suitable for visible range optical applications, has been developed. Using buried triple photo-junction as basic pixel sensing element in combination with artificial neural network (ANN), the wavelength readout with a full-scale error of less than 1.5% over the range of 400 to 780 nm can be achieved. Through this work, the applicability of the ANN approach in optical sensing is investigated and compared with conventional methods, and a good compromise between accuracy and the possibility for on-chip implementation was thus found. Indeed, this technique can serve different purposes and may replace conventional methods. Keywords: Buried photo PN junctions; Artificial Neural Network; wavelength measurement. 1. Introduction The use of wavelength measurement has a wide range of applications, varying from fiber-optic communication to biological purposes, such as DNA sequencing, including many engineering applications. This increase of applications has provided