TY - GEN

T1 - Parallel algorithm of enhanced historical data integration using neural networks

AU - Turchenko, V.

AU - Triki, C.

AU - Grandinetti, L.

AU - Sachenko, A.

PY - 2005

Y1 - 2005

N2 - The main feature of neural network using for accuracy improvement of physical quantities (for example, temperature, humidity, pressure etc.) measurement by data acquisition systems is insufficient volume of input data for predicting neural network training at an initial exploitation period of sensors. The authors have proposed the technique of data volume increasing for predicting neural network training using integration of historical data method. In this paper we have proposed enhanced integration historical data method with its simulation results on mathematical models of sensor drift using single-layer and multi-layer perceptrons. We also considered a parallelization technique of enhanced integration historical data method in order to decrease its working time. A modified coarse-grain parallel algorithm with dynamic mapping on processors of parallel computing system using neural network training time as mapping criterion is considered. Fulfilled experiments have showed that modified parallel algorithm is more efficient than basic parallel algorithm with dynamic mapping, which does not use any mapping criterion.

AB - The main feature of neural network using for accuracy improvement of physical quantities (for example, temperature, humidity, pressure etc.) measurement by data acquisition systems is insufficient volume of input data for predicting neural network training at an initial exploitation period of sensors. The authors have proposed the technique of data volume increasing for predicting neural network training using integration of historical data method. In this paper we have proposed enhanced integration historical data method with its simulation results on mathematical models of sensor drift using single-layer and multi-layer perceptrons. We also considered a parallelization technique of enhanced integration historical data method in order to decrease its working time. A modified coarse-grain parallel algorithm with dynamic mapping on processors of parallel computing system using neural network training time as mapping criterion is considered. Fulfilled experiments have showed that modified parallel algorithm is more efficient than basic parallel algorithm with dynamic mapping, which does not use any mapping criterion.

KW - Coarse-grain parallel algorithm

KW - Computational grids

KW - Dynamic mapping

KW - Integration historical data

KW - Neural networks

KW - Sensor drift

UR - http://www.scopus.com/inward/record.url?scp=43549086684&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=43549086684&partnerID=8YFLogxK

U2 - 10.1109/IDAACS.2005.282943

DO - 10.1109/IDAACS.2005.282943

M3 - Conference contribution

AN - SCOPUS:43549086684

SN - 0780394461

SN - 9780780394469

T3 - Proceedings of the Third Workshop - 2005 IEEE Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, IDAACS 2005

SP - 66

EP - 73

BT - Proceedings of the Third Workshop - 2005 IEEE Intelligent Data Acquisition and Advanced Computing Systems

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd IEEE Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, IDAACS 2005

Y2 - 5 September 2005 through 7 September 2005

ER -