Advanced sensor data integration using neural networks

Using neural networks for sensor drift prediction is considered in this paper. There are described basis and advanced methods of "historical" data integration and appropriate models of single-layer and multi-layer perceptrons. Simulation modelling results show an improvement of the accuracy of sensor data processing of advanced method in 2-3 times in comparison with basis method.

[1]  Volodymyr Turchenko,et al.  Error compensation in an intelligent sensing instrumentation system , 2001, IMTC 2001. Proceedings of the 18th IEEE Instrumentation and Measurement Technology Conference. Rediscovering Measurement in the Age of Informatics (Cat. No.01CH 37188).

[2]  Lucio Grandinetti,et al.  Sensors signal processing using neural networks , 1999, 1999 IEEE Africon. 5th Africon Conference in Africa (Cat. No.99CH36342).

[3]  Volodymyr Turchenko,et al.  Sensor errors prediction using neural networks , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[4]  Lucio Grandinetti,et al.  Technique of learning rate estimation for efficient training of MLP , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[5]  Vincenzo Piuri,et al.  Artificial intelligence for instruments and measurement applications , 1998 .

[6]  C. Butler,et al.  Sensor signal processing using neural networks for a 3-D fibre-optic position sensor , 1994 .

[7]  J. E. Brignell,et al.  Digital compensation of sensors , 1987 .

[8]  Bernard Widrow,et al.  Adaptive switching circuits , 1988 .

[9]  Pasquale Daponte,et al.  Artificial neural networks in measurements , 1998 .