共查询到19条相似文献,搜索用时 156 毫秒
1.
2.
3.
神经网络Kalman滤波算法及多组分光度分析应用 总被引:4,自引:0,他引:4
前馈神经网络NN误差反向传播算法(BP)收敛速度较慢且常陷入局部极优值等,针对此种缺陷提出了一种基于扩展Kalman滤波的快速学习新算法(EF)。与BP相比,EF法不仅学习效率高收敛速度快,数值稳定性好,而且所需学习次数少,调节参数少,由非线性系统建模与辨识的模拟结果表明,EF是提高网络收敛速度改善神经学习性能的一种有效方法,谈谈用于多组分光谱分析,结果良好。 相似文献
4.
基于遗传算法的神经网络为苯乙酰胺类农药构效关系建模的研究 总被引:8,自引:0,他引:8
探讨用遗传算法训练神经网络,为苯乙酰胺类化合物的QSAR建模,效果良好,神经网络可以反映复杂的构效关系,而引入遗传算法又有助于多层前传网在训练过程中跳出局部最小点,使收敛速度大大提高,并在预报精度上有显著改善. 相似文献
5.
为提高溶解预测模型的效率和关联度, 建立基于混沌理论、自适应粒子群优化(PSO)算法和反向传播(BP)算法的混沌自适应PSO-BP神经网络模型, 并对二氧化碳(CO2)在聚苯乙烯(PS)和聚丙烯(PP)中、氮气(N2)在PS中的溶解度进行预测试验. 模型选用压力和温度作为输入参数, 使用试探法确定隐含层结点个数为8, 输出为预测的溶解度. 模型融合混沌理论、自适应PSO和BP算法各自的优势, 提高了训练速度和预测精度. 结果表明, 混沌自适应PSO-BP神经网络有很好的预测能力, 预测值与实验值相当吻合, 通过与传统BP神经网络和PSO-BP神经网络的比较可知, 其预测精度和相关性均明显较优, 预测平均绝对误差(AAD), 标准偏差(SD)和平方相关系数(R2)分别为0.0058, 0.0198和0.9914. 相似文献
6.
大鼠胰腺及癌组织红外光谱连续小波特征提取及径向基人工神经网络识别 总被引:1,自引:0,他引:1
采用水平衰减全反射(HATR)傅里叶变换红外光谱法(FTIR)测定了SD大鼠胰腺正常组织与非正常组织的谱图,提出了一种新的基于FTIR的连续小波特征提取与径向基人工神经网络分类方法以提高FTIR对早期SD大鼠胰腺癌的诊断准确率。利用连续小波多分辨率分析法提取FTIR特征量,对于提取的特征量采用径向基函数神经网络进行模式分类。对SD大鼠的胰腺正常组织、早期癌组织及进展期癌组织的FTIR,利用连续小波多分辨率分析法提取9个特征量,进行RBF神经网络分类判断。当目标误差为0.01,径向基函数的分布常数为5时,网络达到最优化,总的正确识别率为96.67%。并对影响分类结果的网络参数、目标误差和分布常数对分类样品的影响做了讨论。实验结果表明:此方法对早期胰腺癌具有较高的诊断率。 相似文献
7.
8.
9.
气化中煤灰熔点和黏度预测模型 总被引:1,自引:0,他引:1
气化中煤灰熔点和黏度预测模型 《燃料化学学报》2016,44(5):521-527
根据煤灰中硅铝含量及硅铝比对煤灰进行分类研究,构建了灰熔融点和黏度与组分关系的优化模型,并对宽组分范围的煤灰熔点、黏度关系进行探讨。获得了更加精确的灰熔点预测模型,全液相温度模型预测误差为±40℃,实验值和预测值的标准误差为25℃。采用修正的Urbain模型和Roscoe模型相结合,模型预测值和实验值吻合较好,低黏度下对数黏度的预测值和实验值误差为±0.1;高黏度下黏度的预测值和实验值误差为±0.2。结果表明,基于煤灰组分分类的拟合结果优于涵盖宽组分的模型。 相似文献
10.
反弹传播神经网络用于痕量铬的示波计时电位法测定 总被引:6,自引:0,他引:6
首次将反弹传播算法神经网络用于铜箔钝化液中痕量铬的示波计时电位法测定。探讨了网络层数、层结点数和结点转移函数等网络参数对预测结果的影响。实验结果表明 :Cr 浓度在 4.0× 10 -7~ 1.3× 10 -6mol/L范围内与示波计时电位曲线上的切口深度呈线性关系 ,检测下限可达 8× 10 -8mol/L ;与标准BP神经网络的训练和预测结果相比较 ,反弹传播神经网络用于示波测定时不仅具有较高的预测精度 ,而且大大提高了网络训练的收敛速度 相似文献
11.
A new approach named combinative neural network (CN) using partial least squares (PLS) analysis to modify the hidden layer in the multi-layered feed forward (MLFF) neural networks (NN) was proposed in this paper. The significant contributions of PLS in the proposed CN are to reorganize the outputs of hidden nodes such that the correlation of variables could be circumvented, to make the network meet the non-linear relationship best between the input and output data of the NN, and to eliminate the risk of over-fitting problem at the same time. The performance of the proposed approach was demonstrated through two examples, a well defined nonlinear approximation problem, and a practical nonlinear pattern classification problem with unknown relationship between the input and output data. The results were compared with those by conventional MLFF NNs. Good performance and time-saving implementation make the proposed method an attractive approach for non-linear mapping and classification. 相似文献
12.
Shen Q Jiang JH Jiao CX Lin WQ Shen GL Yu RQ 《Journal of computational chemistry》2004,25(14):1726-1735
The multilayer feed-forward ANN is an important modeling technique used in QSAR studying. The training of ANN is usually carried out only to optimize the weights of the neural network and without paying attention to the network topology. Some other strategies used to train ANN are, first, to discover an optimum structure of the network, and then to find weights for an already defined structure. These methods tend to converge to local optima, and may also lead to overfitting. In this article, a hybridized particle swarm optimization (PSO) approach was applied to the neural network structure training (HPSONN). The continuous version of PSO was used for the weight training of ANN, and the modified discrete PSO was applied to find appropriate the network architecture. The network structure and connectivity are trained simultaneously. The two versions of PSO can jointly search the global optimal ANN architecture and weights. A new objective function is formulated to determine the appropriate network architecture and optimum value of the weights. The proposed HPSONN algorithm was used to predict carcinogenic potency of aromatic amines and biological activity of a series of distamycin and distamycin-like derivatives. The results were compared to those obtained by PSO and GA training in which the network architecture was kept fixed. The comparison demonstrated that the HPSONN is a useful tool for training ANN, which converges quickly towards the optimal position, and can avoid overfitting in some extent. 相似文献
13.
14.
Accelerating the Construction of Neural Network Potential Energy Surfaces: A Fast Hybrid Training Algorithm 下载免费PDF全文
Machine learning approaches have been promising in constructing high-dimensional potential energy surfaces (PESs) for molecules and materials. Neural networks (NNs) are one of the most popular such tools because of its simplicity and efficiency. The training algorithm for NNs becomes essential to achieve a fast and accurate fit with numerous data. The Levenberg-Marquardt (LM) algorithm has been recognized as one of the fastest and robust algorithms to train medium sized NNs and widely applied in recent NN based high quality PESs. However, when the number of ab initio data becomes large, the efficiency of LM is limited, making the training time consuming. Extreme learning machine (ELM) is a recently proposed algorithm which determines the weights and biases of a single hidden layer NN by a linear solution and is thus extremely fast. It, however, does not produce sufficiently small fitting error because of its random nature. Taking advantages of both algorithms, we report a generalized hybrid algorithm in training multilayer NNs. Tests on H+H2 and CH4+Ni(111) systems demonstrate the much higher efficiency of this hybrid algorithm (ELM-LM) over the original LM. We expect that ELM-LM will find its widespread applications in building up high-dimensional NN based PESs. 相似文献
15.
16.
17.
Global optimization of binary Lennard-Jones clusters is a challenging problem in computational chemistry. The difficulty lies in not only that there are enormous local minima on the potential energy surface but also that we must determine both the coordinate position and the atom type for each atom and thus have to deal with both continuous and combinatorial optimization. This paper presents a heuristic algorithm (denoted by 3OP) which makes extensive use of three perturbation operators. With these operators, the proposed 3OP algorithm can efficiently move from a poor local minimum to another better local minimum and detect the global minimum through a sequence of local minima with decreasing energy. The proposed 3OP algorithm has been evaluated on a set of 96 × 6 instances with up to 100 atoms. We have found most putative global minima listed in the Cambridge Cluster Database as well as discovering 12 new global minima missed in previous research. 相似文献
18.
19.
Particle swarm optimization (PSO) combined with alternating least squares (ALS) is introduced to self-modeling curve resolution (SMCR) in this study for effective initial estimate. The proposed method aims to search concentration profiles or pure spectra which give the best resolution result by PSO. SMCR sometimes yields insufficient resolution results by getting trapped in a local minimum with poor initial estimates. The proposed method enables to reduce an undesirable effect of the local minimum in SMCR due to the advantages of PSO. Moreover, a new criterion based on global phase angle is also proposed for more effective performance of SMCR. It takes full advantage of data structure, that is to say, a sequential change with respect to a perturbation can be considered in SMCR with the criterion. To demonstrate its potential, SMCR by PSO is applied to concentration-dependent near-infrared (NIR) spectra of mixture solutions of oleic acid (OA) and ethanol. Its curve resolution performances are compared with SMCR with evolving factor analysis (EFA). The results show that SMCR by PSO yields significantly better curve resolution performances than those by EFA. It is revealed that SMCR by PSO is less sensitive to a local minimum in SMCR and it can be a new effective tool for curve resolution analysis. 相似文献