TY - GEN
T1 - Research on algorithms of neural network ensemble with multi-dsp mixture structure
AU - Xu, Tingfa
AU - Ni, Guoqiang
PY - 2007
Y1 - 2007
N2 - A neural network ensemble algorithm used in automatic target recognition (ATR) was designed based on multi-DSP mixture structure. It is formed a same type classifier under different size and initial condition by BP neural networks, and map every output of neural network into posteriori probability, then make weighted summation and judge. Real-time recognition was run by the neural networks ensemble system. The result showed that statistic recognition rate was up to 97 percent for 8 type object. The processing was finished in 30 ms. The recognition rate was better than single neural networks obviously.
AB - A neural network ensemble algorithm used in automatic target recognition (ATR) was designed based on multi-DSP mixture structure. It is formed a same type classifier under different size and initial condition by BP neural networks, and map every output of neural network into posteriori probability, then make weighted summation and judge. Real-time recognition was run by the neural networks ensemble system. The result showed that statistic recognition rate was up to 97 percent for 8 type object. The processing was finished in 30 ms. The recognition rate was better than single neural networks obviously.
UR - http://www.scopus.com/inward/record.url?scp=38049065433&partnerID=8YFLogxK
U2 - 10.1109/ICNC.2007.614
DO - 10.1109/ICNC.2007.614
M3 - Conference contribution
AN - SCOPUS:38049065433
SN - 0769528759
SN - 9780769528755
T3 - Proceedings - Third International Conference on Natural Computation, ICNC 2007
SP - 162
EP - 166
BT - Proceedings - Third International Conference on Natural Computation, ICNC 2007
T2 - 3rd International Conference on Natural Computation, ICNC 2007
Y2 - 24 August 2007 through 27 August 2007
ER -