A Quantitative Structure-Property Relationship Model Based on Chaos-Enhanced Accelerated Particle Swarm Optimization Algorithm and Back Propagation Artificial Neural Network

Abstract

Featured Application:The proposed hybrid intelligent model can be applied in engineering design, material performance prediction, numerical calculation, and the prediction of physical and chemical properties.Abstract: A quantitative structure-property relationship (QSPR) model is proposed to explore the relationship between the pKa of various compounds and their structures. Through QSPR studies, the relationship between the structure and properties can be obtained. In this study, a novel chaos-enhanced accelerated particle swarm algorithm (CAPSO) is adopted to screen molecular descriptors and optimize the weights of back propagation artificial neural network (BP ANN). Then, the QSPR model based on CAPSO and BP ANN is proposed and named the CAPSO BP ANN model. The prediction experiment showed that the CAPSO algorithm was a reliable method for screening molecular descriptors. The five molecular descriptors obtained by the CAPSO algorithm could well characterize the molecular structure of each compound in pKa prediction. The experimental results also showed that the CAPSO BP ANN model exhibited good performance in predicting the pKa values of various compounds. The absolute mean relative error, root mean square error, and square correlation coefficient are respectively 0.5364, 0.0632, and 0.9438, indicating the high prediction accuracy. The proposed hybrid intelligent model can be applied in engineering design and the prediction of physical and chemical properties.The establishment of the QSPR model mainly involves the following steps: acquisition of experimental data, construction and optimization of the molecular structure, calculation and screening of molecular descriptors, establishment and verification of the model, etc. First of all, the variable selection is important in many fields, such as spectroscopy [7,8], QSPR [9,10], and other fields [11,12]. The selection of molecular descriptors largely determines the quality of the QSPR model [13][14][15]. The step of molecular descriptor screening aims to reflect more structural information so that there is no noise in the descriptors. Many methods have been developed to screen molecular descriptors and can be mainly divided into two categories [16][17][18]. The first category includes the common methods, such as Akaike information criterion (AIC), Bayesian information criterion (BIC), and forward/backward/bi-directional stepwise multiple linear regression (MLR). The second includes the modern search algorithms, such as genetic algorithm (GA), simulated annealing algorithm (SA), ant colony algorithm (AC), particle swarm optimization (PSO), and other swarm intelligence algorithms [7,11,[19][20][21]. The common methods are the most simple and efficient, but their overall performances are low in complex nonlinear problems. The modern search algorithms based on the optimization strategy have obvious advantages and can search for optimal variables and deal with complex large data points. The model establishment is important in the QSPR study and commonly used QSPR model...

Emocolor: An assistant design method for emotional color matching based on semantics and images

“…The relationship between the emotional expression of a single color and the combination of two colors was also revealed. 25,26 Hanada used factor analysis, independent component analysis and correspondence analysis to explore the association between color and emotion. 9,10 Gong et al investigated the factors affecting color emotion and color preference as well as the relationship between color emotion and color preference based on a psychophysical experiment.…”

“…22 Pouli et al presented a histogram reshaping technique for determining the degree of color match between original and target images. 23 To build optimal color design models and obtain excellent color schemes that meet user needs, researchers have proposed many color design methods using intelligent algorithms, such as gray theory, 24 support vector machines (SVMs), 25,26 fuzzy theory, 27 artificial neural networks (ANNs), [28][29][30] the KE system and rough sets. 1,31 Moreover, semantic difference and other methods have been successfully used to evaluate the relationship between product color and user emotion, providing ideas and methods for product color emotional design.…”

“…Ou et al studied the association between color emotion and color preference. The relationship between the emotional expression of a single color and the combination of two colors was also revealed 25,26 . Hanada used factor analysis, independent component analysis and correspondence analysis to explore the association between color and emotion 9,10 .…”

Characterization of Short-Term Strength Properties of Fiber/Cement-Modified Slurry

“…Normalization was necessary for the input and output variables to guarantee the precision of fitting [25,26]. After fitting, the functions of stress (σ) and strain (ε) were stated as follows:…”

Prediction Model of Organic Molecular Absorption Energies based on Deep Learning trained by Chaos-enhanced Accelerated Evolutionary algorithm

“…The accurate prediction of absorption energies is an important direction in the field of computational chemistry with great research value and significance 1,2 . Many linear and nonlinear computational methods such as linear regression, density functional theory, support vector machine, and artificial neural network have been applied to examine the absorption energies of organic molecules 3–5 .…”