Application of radial basis function neural network to predict soil sorption partition coefficient using topological descriptors

Thermodynamics-Based Model Construction for the Accurate Prediction of Molecular Properties From Partition Coefficients

Developing models for predicting molecular properties of organic compounds is imperative for drug development and environmental safety; however, development of such models that have high predictive power and are independent of the compounds used is challenging. To overcome the challenges, we used a thermodynamics-based theoretical derivation to construct models for accurately predicting molecular properties. The free energy change that determines a property equals the sum of the free energy changes (ΔG_Fs) caused by the factors affecting the property. By developing or selecting molecular descriptors that are directly proportional to ΔG_Fs, we built a general linear free energy relationship (LFER) for predicting the property with the molecular descriptors as predictive variables. The LFER can be used to construct models for predicting various specific properties from partition coefficients. Validations show that the models constructed according to the LFER have high predictive power and their performance is independent of the compounds used, including the models for the properties having little correlation with partition coefficients. The findings in this study are highly useful for applications in drug development and environmental safety.

Improved RBF neural network algorithm in financial time series prediction

The financial market is often unpredictable and extremely susceptible to political, economic and other factors. How to achieve accurate predictions of financial time series is very important for scientific research and financial enterprise management. Based on this, this article takes the application of the improved RBF neural network(NN) algorithm in financial time series forecasting as the research object, and explores how to use the improved RBF NN algorithm to predict the stock market price, with a view to reducing investment risks and increasing returns for the majority of stock investors to provide help. This article uses the stock market prices of three listed companies in May 2019 as the data samples for this survey, including 72 training sample data and 21 test sample data. These three stocks were predicted by using the improved RBF NN algorithm Experiments, the experimental results show that the prediction errors of the improved RBF NN algorithm for the three stocks are 2.14%, 0.69% and 1.47%, while the traditional RBF NN algorithm’s prediction errors for the stocks are 5.74%, 2.38% and 11.37%. This shows that the improved algorithm is significantly more accurate and more effective than traditional algorithms. Therefore, the application of the improved RBF NN algorithm in financial time series prediction will be more extensive in the future.

Prediction of daily suspended sediment load (SSL) using new optimization algorithms and soft computing models

Accurate modeling and prediction of suspended sediment load (SSL) in rivers have an important role in environmental science and design of engineering structures and are vital for watershed management. Since different parameters such as rainfall, temperature, and discharge with the different lag times have significant effects on the SSL, quantifying and understanding nonlinear interactions of the sediment dynamics has always been a challenge. In this study, three soft computing models (multilayer perceptron (MLP), adaptive neuro-fuzzy system (ANFIS), and radial basis function neural network (RBFNN)) were used to predict daily SSL. Four optimization algorithms (sine–cosine algorithm (SCA), particle swarm optimization (PSO), firefly algorithm (FFA), and bat algorithm (BA)) were used to improve the capability of SSL prediction of the models. Data from gauging stations at the mouth of the Kasilian and Talar rivers in northern Iran were used in the analysis. The selection of input combinations for the models was based on principal component analysis (PCA). Uncertainty in sequential uncertainty fitting (SUFI-2) and performance indicators were used to assess the potential of models. Taylor diagrams were used to visualize the match between model output and observed values. Assessment of daily SSL predictions for Talar station revealed that ANFIS-SCA yielded the best results (RMSE (root mean square error): 934.2 ton/day, MAE (mean absolute error): 912.2 ton/day, NSE (Nash–Sutcliffe efficiency): 0.93, PBIAS: 0.12). ANFIS-SCA also yielded the best results for Kasilian station (RMSE: 1412.10 ton/day, MAE: 1403.4 ton/day, NSE: 0.92, PBIAS: 0.14). The Taylor diagram confirmed that ANFIS-SCA achieved the best match between observed and predicted values for various hydraulic and hydrological parameters at both Talar and Kasilian stations. Further, the models were tested in Eagel Creek Basin, Indiana state, USA. The results indicated that the ANFIS-SCA model reduced RMSE by 15% and 21% compared to the MLP-SCA and RBFNN-SCA models in the training phase. Comparing models performance indicated that the ANFIS-SCA model could decrease MAE error compared to ANFIS-BA, ANFIS-PSO, ANFIS-FFA, and ANFIS models by 18%, 32%, 37%, and 49% in the training phase, respectively. The results indicated that the integration of optimization algorithms and soft computing models can improve the ability of models for predicting SSL. Additionally, the hybridization of soft computing models with optimization algorithms can decrease the uncertainty of models.

Predicting Aqueous Adsorption of Organic Compounds onto Biochars, Carbon Nanotubes, Granular Activated Carbons, and Resins with Machine Learning

Predictive models are useful tools for aqueous adsorption research; existing models such as multilinear regression (MLR), however, can only predict adsorption under specific equilibrium concentrations or for certain adsorption isotherm models. Also, few studies have discussed data processing beyond applying different modeling algorithms to improve the prediction accuracy. In this research, we employed a cosine similarity approach that focused on mining the available data before developing models; this approach can mine the most relevant data concerning the prediction target to build models and was found to considerably improve the prediction accuracy. We then built a machine-learning modeling process based on neural networks (NN), a group-selection data-splitting strategy for grouped adsorption data for adsorbent-adsorbate pairs under different equilibrium concentrations, and polyparameter linear free energy relationships (pp-LFERs) for aqueous adsorption of 165 organic compounds onto 50 biochars, 34 carbon nanotubes, 35 GACs, and 30 polymeric resins. The final NN-LFER models were successfully applied to various equilibrium concentrations regardless of the adsorption isotherm models and showed less prediction deviations than the published models with the root-mean-square errors 0.23-0.31 versus 0.23-0.97 log unit, and the predictions were improved by adding two key descriptors (BET surface area and pore volume) for the adsorbents. Finally, interpreting the NN-LFER models based on the Shapley values suggested that not considering equilibrium concentration and properties of the adsorbents in the existing MLR models is a possible reason for their higher prediction deviations.

Application of Hyperspectral Imaging to Detect Sclerotinia sclerotiorum on Oilseed Rape Stems

Hyperspectral imaging covering the spectral range of 384-1034 nm combined with chemometric methods was used to detect Sclerotinia sclerotiorum (SS) on oilseed rape stems by two sample sets (60 healthy and 60 infected stems for each set). Second derivative spectra and PCA loadings were used to select the optimal wavelengths. Discriminant models were built and compared to detect SS on oilseed rape stems, including partial least squares-discriminant analysis, radial basis function neural network, support vector machine and extreme learning machine. The discriminant models using full spectra and optimal wavelengths showed good performance with classification accuracies of over 80% for the calibration and prediction set. Comparing all developed models, the optimal classification accuracies of the calibration and prediction set were over 90%. The similarity of selected optimal wavelengths also indicated the feasibility of using hyperspectral imaging to detect SS on oilseed rape stems. The results indicated that hyperspectral imaging could be used as a fast, non-destructive and reliable technique to detect plant diseases on stems.