基于过程神经网络(procedure neural network,PNN)建立了具有高精确度的多步预测模型。针对PNN训练过程复杂的特点,提出了一种基于正交基函数展开和矢量矩免疫算法(vector distance based i mmunealgorithm,VD-IA)相结合的PNN训练方法...基于过程神经网络(procedure neural network,PNN)建立了具有高精确度的多步预测模型。针对PNN训练过程复杂的特点,提出了一种基于正交基函数展开和矢量矩免疫算法(vector distance based i mmunealgorithm,VD-IA)相结合的PNN训练方法。根据PNN在三角函数正交基展开形式下的数学模型,推导出适用于VD-IA的优化问题模型,采用一种自适应策略加快了VD-IA的收敛速度。基于Mackey-Glass混沌序列检验了该方法的有效性,将该方法与BP训练方法、改进粒子群优化(i mproved particle swarmopti mization,IPSO)算法进行了对比分析。仿真结果表明,基于VD-IA的PNN训练方法可以获得较优的结果,且获得泛化性能较好的PNN模型。展开更多
Independent component analysis (ICA) has demonstrated its power to extract mass spectra from over-lapping GC/MS signal. However, there is still a problem that mass spectra with negative peaks at some m/z will be obtai...Independent component analysis (ICA) has demonstrated its power to extract mass spectra from over-lapping GC/MS signal. However, there is still a problem that mass spectra with negative peaks at some m/z will be obtained in the resolved results when there are overlapping peaks in the mass spectra of a mixture. Based on a detail theoretical analysis of the preconditions for ICA and the non-negative property of GC/MS signals, a post-modification based on chemical knowledge (PMBK) strategy is pro-posed to solve this problem. By both simulated and experimental GC/MS signals, it was proved that the PMBK strategy can improve the resolution effectively.展开更多
基金Supported by the National Natural Science Foundation of China (Grant Nos. 20325517 and 20575031)the Teaching and Research Award Program for Out-standing Young Teachers in Higher Educations of MOE (TRAPOYT)
文摘Independent component analysis (ICA) has demonstrated its power to extract mass spectra from over-lapping GC/MS signal. However, there is still a problem that mass spectra with negative peaks at some m/z will be obtained in the resolved results when there are overlapping peaks in the mass spectra of a mixture. Based on a detail theoretical analysis of the preconditions for ICA and the non-negative property of GC/MS signals, a post-modification based on chemical knowledge (PMBK) strategy is pro-posed to solve this problem. By both simulated and experimental GC/MS signals, it was proved that the PMBK strategy can improve the resolution effectively.
