Defense Presentation

Michael McCarron

M.S. Final
March 06, 2009, 9:00am
LSC

Abstract:  An operationally adaptive (OA) system for prediction of acoustic transmission loss (TL) in the atmosphere is developed in this thesis. This system uses expert neural network predictors, each corresponding to a specific range of source elevation. The outputs of the expert predictors are combined using a weighting mechanism and a nonlinear fusion system. Using this prediction methodology the computational intractability of traditional acoustic propagation models is eliminated. In addition, new TL prediction frameworks for improving generalization of the expert neural network predictors are explored. The proposed OA system is tested on a synthetically generated acoustic data set for a wide range of geometric, source, and environmental conditions. The results show a significant improvement in both accuracy and reliability over a benchmark prediction system.

Adviser: Mahmood R. Azimi-Sadjadi
Co-adviser: NA
Non-ECE member: Tom Vonder Haar
Member3: Edwin K. Chong
Member4: NA
Additional member: NA

Publications to be Reviewed:
McCarron, M.; Azimi-Sadjadi, M.R.; Wichern, G.; Mungiole, M., "An Operationally Adaptive System for Rapid Acoustic Transmission Loss Prediction," Neural Networks, 2007. IJCNN 2007. International Joint Conference on , vol., no., pp.2262-2267, 12-17 Aug. 2007


Program of Study:
EE 513 EE 514 EE 520 EE 656 ECE 666 EE 752 ST 525