The significant advantage of the complex resistivity method is to reflect the abnormal body through multi-parameters, but its inversion parameters are more than the resistivity tomography method. Therefore, how to eff...The significant advantage of the complex resistivity method is to reflect the abnormal body through multi-parameters, but its inversion parameters are more than the resistivity tomography method. Therefore, how to effectively invert these spectral parameters has become the focused area of the complex resistivity inversion. An optimized BP neural network (BPNN) approach based on Quantum Particle Swarm Optimization (QPSO) algorithm was presented, which was able to improve global search ability for complex resistivity multi-parameter nonlinear inversion. In the proposed method, the nonlinear weight adjustment strategy and mutation operator were used to enhance the optimization ability of QPSO algorithm. Implementation of proposed QPSO-BPNN was given, the network had 56 hidden neurons in two hidden layers (the first hidden layer has 46 neurons and the second hidden layer has 10 neurons) and it was trained on 48 datasets and tested on another 5 synthetic datasets. The training and test results show that BP neural network optimized by the QPSO algorithm performs better than the BP neural network without initial optimization on the inversion training and test models, and the mean square error distribution is better. At the same time, a double polarized anomalous bodies model was also used to verify the feasibility and effectiveness of the proposed method, the inversion results show that the QPSO-BP algorithm inversion clearly characterizes the anomalous boundaries and is closer to the values of the parameters.展开更多
为了提高太阳黑子数的预测精度，论文提出了一种基于量子粒子群神经网络预测太阳黑子数的模型（QPSO-BP 网络）。首先基于前18个太阳周（1755～1953）的年均值，利用量子粒子群算法优化 BP 神经网络的权值和阀值，完成网络训练训；然后...为了提高太阳黑子数的预测精度，论文提出了一种基于量子粒子群神经网络预测太阳黑子数的模型（QPSO-BP 网络）。首先基于前18个太阳周（1755～1953）的年均值，利用量子粒子群算法优化 BP 神经网络的权值和阀值，完成网络训练训；然后对第19太阳周（1954～2013）年均值进行预测，检验模型的预测能力。与普通 BP 神经网络预测的对比结果表明，该模型在逼近能力和预测精度两方面均有明显提高，从而表明基于量子粒子群优化的训练方法对于提高神经网络预测能力具有一定潜力。展开更多
In order to effectively predict occurrence quantity of Myzus persicae, BP neural network theory and method was used to establish prediction model for oc- currence quantity of M. persicae. Meanwhile, QPSO algorithm was...In order to effectively predict occurrence quantity of Myzus persicae, BP neural network theory and method was used to establish prediction model for oc- currence quantity of M. persicae. Meanwhile, QPSO algorithm was used to optimize connection weight and threshold value of BP neural network, so as to determine. the optimal connection weight and threshold value. The historical data of M. persica quantity in Hongta County, Yuxi City of Yunnan Province from 2003 to 2006 was adopted as training samples, and the occurrence quantities of M. persicae from 2007 to 2009 were predicted. The prediction accuracy was 99.35%, the mini- mum completion time was 30 s, the average completion time was 34.5 s, and the running times were 19. The prediction effect of the model was obviously superior to other prediction models. The experiment showed that this model was more effective and feasible, with faster convergence rate and stronger stability, and could solve the similar problems in prediction and clustering. The study provides a theoretical basis for comprehensive prevention and control against M. persicae.展开更多
文摘The significant advantage of the complex resistivity method is to reflect the abnormal body through multi-parameters, but its inversion parameters are more than the resistivity tomography method. Therefore, how to effectively invert these spectral parameters has become the focused area of the complex resistivity inversion. An optimized BP neural network (BPNN) approach based on Quantum Particle Swarm Optimization (QPSO) algorithm was presented, which was able to improve global search ability for complex resistivity multi-parameter nonlinear inversion. In the proposed method, the nonlinear weight adjustment strategy and mutation operator were used to enhance the optimization ability of QPSO algorithm. Implementation of proposed QPSO-BPNN was given, the network had 56 hidden neurons in two hidden layers (the first hidden layer has 46 neurons and the second hidden layer has 10 neurons) and it was trained on 48 datasets and tested on another 5 synthetic datasets. The training and test results show that BP neural network optimized by the QPSO algorithm performs better than the BP neural network without initial optimization on the inversion training and test models, and the mean square error distribution is better. At the same time, a double polarized anomalous bodies model was also used to verify the feasibility and effectiveness of the proposed method, the inversion results show that the QPSO-BP algorithm inversion clearly characterizes the anomalous boundaries and is closer to the values of the parameters.
文摘为了提高太阳黑子数的预测精度，论文提出了一种基于量子粒子群神经网络预测太阳黑子数的模型（QPSO-BP 网络）。首先基于前18个太阳周（1755～1953）的年均值，利用量子粒子群算法优化 BP 神经网络的权值和阀值，完成网络训练训；然后对第19太阳周（1954～2013）年均值进行预测，检验模型的预测能力。与普通 BP 神经网络预测的对比结果表明，该模型在逼近能力和预测精度两方面均有明显提高，从而表明基于量子粒子群优化的训练方法对于提高神经网络预测能力具有一定潜力。
基金Supported by Science and Technology Project of China National Tobacco Corporation(2009YN005&2010YN18&2010YN19)
文摘In order to effectively predict occurrence quantity of Myzus persicae, BP neural network theory and method was used to establish prediction model for oc- currence quantity of M. persicae. Meanwhile, QPSO algorithm was used to optimize connection weight and threshold value of BP neural network, so as to determine. the optimal connection weight and threshold value. The historical data of M. persica quantity in Hongta County, Yuxi City of Yunnan Province from 2003 to 2006 was adopted as training samples, and the occurrence quantities of M. persicae from 2007 to 2009 were predicted. The prediction accuracy was 99.35%, the mini- mum completion time was 30 s, the average completion time was 34.5 s, and the running times were 19. The prediction effect of the model was obviously superior to other prediction models. The experiment showed that this model was more effective and feasible, with faster convergence rate and stronger stability, and could solve the similar problems in prediction and clustering. The study provides a theoretical basis for comprehensive prevention and control against M. persicae.
