Combinative neural network and its applications

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.     

Recurrent neural network based hybrid model for reconstructing gene regulatory network

One of the exciting problems in systems biology research is to decipher how genome controls the development of complex biological system. The gene regulatory networks (GRNs) help in the identification of regulatory interactions between genes and offer fruitful information related to functional role of individual gene in a cellular system. Discovering GRNs lead to a wide range of applications, including identification of disease related pathways providing novel tentative drug targets, helps to predict disease response, and also assists in diagnosing various diseases including cancer. Reconstruction of GRNs from available biological data is still an open problem. This paper proposes a recurrent neural network (RNN) based model of GRN, hybridized with generalized extended Kalman filter for weight update in backpropagation through time training algorithm. The RNN is a complex neural network that gives a better settlement between biological closeness and mathematical flexibility to model GRN; and is also able to capture complex, non-linear and dynamic relationships among variables. Gene expression data are inherently noisy and Kalman filter performs well for estimation problem even in noisy data. Hence, we applied non-linear version of Kalman filter, known as generalized extended Kalman filter, for weight update during RNN training. The developed model has been tested on four benchmark networks such as DNA SOS repair network, IRMA network, and two synthetic networks from DREAM Challenge. We performed a comparison of our results with other state-of-the-art techniques which shows superiority of our proposed model. Further, 5% Gaussian noise has been induced in the dataset and result of the proposed model shows negligible effect of noise on results, demonstrating the noise tolerance capability of the model.     

Quantitative fuzzy neural network for analytical determination

A quantitative fuzzy neural network (Q-FNN) for pattern recognition in analytical determination is reported in this paper. The fuzzy neural network (FNN) combines a fuzzy logic system with an artificial neural network (ANN) so that it has both advantages of a high training speed and strong anti-interference. Importantly, the analytical concept of relative error (RE) in quantitative determination has been integrated into FNN so that the Q-FNN provides a very good quantitative capability in chemical analysis, and prevents the system from an over-fitting problem. The logarithm curve with noise in terms of analytical response versus concentration is calibrated by trained FNN and a close approximation to the ideal one without noise is obtained. The Q-FNN has been applied to the concentration determination of freon in the presence of interference gases. The prediction error for a test set in quantification is less than 10% while no qualitative mistake is observed, implying that the quantitative FNN has sustained the feature of pattern recognition. The results indicate that the Q-FNN has obvious advantages not only in converging speed, but also in the quantitative accuracy over the ANN.     

Multilayer neural network of adaptive bidirectional associative memories

The analysis of the functioning of the brain allows to propose a computational model of multilayer artificial neural network susceptible of associating some response to a particular input, so that when we present that input, we get the required output by the stability of its states and by minimizing the function of energy of the network. The problem of explosion in the number of interconnections has been solved by the introduction of a layer between the input and the output layer of the network. In this paper, we propose the adaptive bidirectional associative memory by conjugate gradient algorithm, so as to study the behavior and performances of the network on pairs of patterns through using the autoassociative or heteroassociative memories.     

Graph neural network based coarse-grained mapping prediction

The selection of coarse-grained (CG) mapping operators is a critical step for CG molecular dynamics (MD) simulation. It is still an open question about what is optimal for this choice and there is a need for theory. The current state-of-the art method is mapping operators manually selected by experts. In this work, we demonstrate an automated approach by viewing this problem as supervised learning where we seek to reproduce the mapping operators produced by experts. We present a graph neural network based CG mapping predictor called Deep Supervised Graph Partitioning Model (DSGPM) that treats mapping operators as a graph segmentation problem. DSGPM is trained on a novel dataset, Human-annotated Mappings (HAM), consisting of 1180 molecules with expert annotated mapping operators. HAM can be used to facilitate further research in this area. Our model uses a novel metric learning objective to produce high-quality atomic features that are used in spectral clustering. The results show that the DSGPM outperforms state-of-the-art methods in the field of graph segmentation. Finally, we find that predicted CG mapping operators indeed result in good CG MD models when used in simulation.

We propose a scalable graph neural network-based method for automating coarse-grained mapping prediction for molecules.     

Application of artificial neural network in food classification

Artificial neural network (ANN) classifiers have been successfully implemented for various quality inspection and grading tasks of diverse food products. ANN are very good pattern classifiers because of their ability to learn patterns that are not linearly separable and concepts dealing with uncertainty, noise and random events. In this research, the ANN was used to build the classification model based on the relevant features of beer. Samples of the same brand of beer but with varying manufacturing dates, originating from miscellaneous manufacturing lots, have been represented in the multidimensional space by data vectors, which was an assembly of 12 features (% of alcohol, pH, % of CO(2) etc.). The classification has been performed for two subsets, the first that included samples of good quality beer and the other containing samples of unsatisfactory quality. ANN techniques allowed the discrimination between qualities of beer samples with up to 100% of correct classifications.     

A neural network approach to infrared spectrum interpretation

The simple linear neural network model was investigated as a method for automated interpretation of infrared spectra. The model was trained using a database of infrared spectra of organic compounds of known structure. The model was able to learn, without any prior input of spectrum-structure correlations, to recognize and identify 76 functional groupings with accuracies ranging from fair to excellent. The effect of network input parameters and of training set composition were studied, and several sources of spurious correlations were identified and corrected.Dedicated to Professor W. Simon on the occasion of his 60th birthday     

Efficient chemical kinetic modeling through neural network maps

An approach to modeling nonlinear chemical kinetics using neural networks is introduced. It is found that neural networks based on a simple multivariate polynomial architecture are useful in approximating a wide variety of chemical kinetic systems. The accuracy and efficiency of these ridge polynomial networks (RPNs) are demonstrated by modeling the kinetics of H(2) bromination, formaldehyde oxidation, and H(2)+O(2) combustion. RPN kinetic modeling has a broad range of applications, including kinetic parameter inversion, simulation of reactor dynamics, and atmospheric modeling.     

色谱重叠峰分解的神经网络法

对于色谱图中两个相互重叠的峰, 本文提出了一种分解方法。首先在重叠峰的一阶导数曲线上取出五个无因次特征值, 然后用多层前传网来表达这五个特征值和重叠峰中子峰面积分率之间的关系。一系列实验的结果表明, 用神经网络方法所得子峰面积的准确度, 优于传统的垂线法及函数拟合法, 而且计算工作量较小, 可用于实时处理。     

级联神经网络用于单扫描示波极谱信号的测定

将改进小波神经网络与BP神经网络相结合,提出一种新的混级联神经网络结构,用于单扫描示波极谱信号的同时测定。通过对网络结构的优化和网络参数的调整,加快了训练速度,提高了预测的准确度。用该法对邻、间硝基氯苯混合样进行了预测,结果满意。对级联神经网络法与单一BP神经网络法的预测结果进行了比较,表明级联神经网络优于单一BP神经网络。     

人工神经网络法同时测定苯二酚异构体

研究了人工神经网络法与紫外分光光度分析相结合，用于邻苯二酚、间苯二酚、对苯二酚异构体的含量测定。本研究采用人工神经网络法，直接对苯二酚异构体混合液的紫外吸收光谱数据进行预测，不需预先分离，即可得到各异构体的浓度。     

Dynamic modelling of milk ultrafiltration by artificial neural network

Artificial neural networks (ANNs) have been used to dynamically model crossflow ultrafiltration of milk. It aims to predict permeate flux, total hydraulic resistance and the milk components rejection (protein, fat, lactose, ash and total solids) as a function of transmembrane pressure and processing time. Dynamic modelling of ultrafiltration performance of colloidal systems (such as milk) is very important for designing of a new process and better understanding of the present process. Such processes show complex non-linear behaviour due to unknown interactions between compounds of a colloidal system, thus the theoretical approaches were not being able to successfully model the process. In this work, emphasis has been focused on intelligent selection of training data, using few training data points and small network. Also it has been tried to test the ANN ability to predict new data that may not be originally available. Two neural network models were constructed to predict the flux/total resistance and rejection during ultrafiltration of milk. The results showed that there is an excellent agreement between the validation data (not used in training) and modelled data, with average errors less than 1%. Also the trained networks are able to accurately capture the non-linear dynamics of milk ultrafiltration even for a new condition that has not been used in the training process.     

Fine-tuning of a generative neural network for designing multi-target compounds

Journal of Computer-Aided Molecular Design - Exploring the origin of multi-target activity of small molecules and designing new multi-target compounds are highly topical issues in pharmaceutical...