Intelligent fiber optic statistical mode sensors using novel features and artificial neural networks

Hasan Seckin Efendioglu; Onur Toker; Tulay Yildirim; Kemal Fidanboylu

doi:10.1117/12.2009836

11 April 2013 Intelligent fiber optic statistical mode sensors using novel features and artificial neural networks

Hasan Seckin Efendioglu, Onur Toker, Tulay Yildirim, Kemal Fidanboylu

Proceedings Volume 8693, Smart Sensor Phenomena, Technology, Networks, and Systems Integration 2013; 86930B (2013) https://doi.org/10.1117/12.2009836
Event: SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring, 2013, San Diego, California, United States

Abstract

In this paper, intelligent statistical mode sensors are proposed and analyzed. Several statistical features are used in design of intelligent sensor systems. Force measurement experiments are conducted and experimental data is analyzed using newly proposed statistical features. After that, Artificial Neural Networks (ANNs) with sensor data fusion, which is an intelligent sensor architecture, was proposed to estimate the force values. Multilayer perceptron (MLP) with different algorithms are used in the ANN model, and all of them can predict the force values with acceptable error levels. Using sensor fusion with ANNs, statistical mode sensors can be calibrated and fault tolerance of the sensor can be decreased, hence more reliable intelligent sensors can be designed.

Citation Download Citation

Hasan Seckin Efendioglu, Onur Toker, Tulay Yildirim, and Kemal Fidanboylu "Intelligent fiber optic statistical mode sensors using novel features and artificial neural networks", Proc. SPIE 8693, Smart Sensor Phenomena, Technology, Networks, and Systems Integration 2013, 86930B (11 April 2013); https://doi.org/10.1117/12.2009836

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available