The pKa value of drugs is an important parameter in drug design and pharmacology. In this paper, improved particle swarm optimization (PSO) algorithm was proposed based on the population entropy diversity. algorithm, when higher than set maximum threshold, convergence strategy adopted; lower minimum threshold divergence between self-adaptive adjustment maintained. PSO applied training radial basis function artificial neural network (RBF ANN) model selection molecular descriptors. A...

Aqueous solubility is one of the most important physicochemical properties in drug discovery. At present, prediction aqueous compounds still a challenging problem. Machine learning has shown great potential prediction. Most machine models largely rely on setting hyperparameters, and their performance can be improved by hyperparameters better way. In this paper, we used MACCS fingerprints to represent structural features optimized light gradient boosting (LightGBM) with cuckoo search...

The swarm intelligence algorithm simulates the behavior of animal populations in nature and is a new type intelligent solution that different from traditional artificial intelligence. Feature selection very common data dimensionality reduction method, which requires us to select feature subset with best evaluation criteria original set. selection, as an effective processing has become hot research topic fields machine learning, pattern recognition, mining received extensive attention...

To overcome the shortcomings of traditional methods water quality evaluation, in this paper, a novel model combines particle swarm optimization (PSO), chaos theory, self-adaptive strategy and back propagation artificial neural network (BP ANN) that was proposed to evaluate Weihe River China. An improved PSO algorithm with inertia weight chaotic learning factor tuned by logistic function developed used optimize parameters BP ANN. The values average absolute deviation (AAD), root mean square...

A solubility prediction model based on a hybrid artificial intelligence method integrated with diffusion theory is proposed.

A quantitative structure-property relationship (QSPR) model is proposed to explore the between pKa of various compounds and their structures. Through QSPR studies, structure properties can be obtained. In this study, a novel chaos-enhanced accelerated particle swarm algorithm (CAPSO) adopted screen molecular descriptors optimize weights back propagation artificial neural network (BP ANN). Then, based on CAPSO BP ANN named model. The prediction experiment showed that was reliable method for...

Abstract Solubility is a significant physical and chemical property. The solubility of carbon dioxide(CO 2 ) in polymers an important application green chemistry. Aimed at the problem insufficient precision existing prediction model, model based on adaptive particle swarm optimization algorithm least‐squares support vector machine(APSO‐LSSVM) proposed. Different from traditional algorithm, APSO improves easily falling into local optimal solution. regularization parameters kernel function...

Abstract As an important physical property of molecules, absorption energy can characterize the electronic and structural information molecules. Moreover, accurate calculation molecular energies is highly valuable. Present linear nonlinear methods hold low accuracies due to great errors, especially irregular complicated systems for structures. Thus, developing a prediction model with enhanced accuracy, efficiency, stability beneficial. By combining deep learning intelligence algorithms, we...

Feature selection can classify the data with irrelevant features and improve accuracy of classification in pattern classification. At present, back propagation (BP) neural network particle swarm optimization algorithm be well combined feature selection. On this basis, paper adds interference factors to BP practicability This summarizes basic methods requirements for combines benefits global feedback mechanism networks based on backpropagation (BP-PSO). Firstly, a chaotic model is introduced...

To deal with the problems of premature convergence and tending to jump into local optimum in traditional particle swarm optimization, a novel improved optimization algorithm was proposed. The self-adaptive inertia weight factor used accelerate converging speed, chaotic sequences were tune acceleration coefficients for balance between exploration exploitation. performance proposed tested on four classical multi-objective functions by comparing non-dominated sorting genetic algorithm. results...

In order to improve some shortcomings of the standard particle swarm optimization algorithm, such as premature convergence and slow local search speed, a double population algorithm based on Lorenz equation dynamic self-adaptive strategy is proposed. Chaotic sequences produced by are used tune acceleration coefficients for balance between exploration exploitation, inertia weight factor accelerate converging purposes enhance accuracy. The experiment was carried out with four multi-objective...

We look at the network of mathematicians defined by hyperlinks between their biographies on Wikipedia. show how to extract this information using three snapshots Wikipedia data, taken in 2013, 2017 and 2018. illustrate such data can be used performing a centrality analysis. These measures that Hilbert Newton are most important mathematicians. use our example strengths weakness provide estimates robustness measurements. In part, we do comparison results from two other sources: an earlier...

Quantitative structure-activity relationship (QSAR) model is adopted to study the between chemical and physical properties of various substances structure. Through QSAR studies, internal invisible structure activity can be obtained. In this paper, a novel chaos-enhanced accelerate particle swarm algorithm (CAPSO) proposed, which used molecular descriptors screening optimization weights back propagation artificial neural network (BP ANN). Then, based on CAPSO BP ANN put forward, hereinafter...