Selective ensemble modeling based on nonlinear frequency spectral feature extraction for predicting load parameter in ball mills

Strong mechanical vibration and acoustical signals of grinding process contain useful information related to load parameters in ball mills. It is a challenge to extract latent features and construct soft sensor model with high dimensional frequency spectra of these signals. This paper aims to develop a selective ensemble modeling approach based on nonlinear latent frequency spectral feature extraction for accurate measurement of material to ball volume ratio. Latent features are first extracted from different vibrations and acoustic spectral segments by kernel partial least squares. Algorithms of bootstrap and least squares support vector machines are employed to produce candidate sub-models using these latent features as inputs. Ensemble sub-models are selected based on genetic algorithm optimization toolbox. Partial least squares regression is used to combine these sub-models to eliminate collinearity among their prediction outputs. Results indicate that the proposed modeling approach has better prediction performance than previous ones.

Autonomous Kernel Based Models for Short-Term Load Forecasting

The application of support vector machines to forecasting problems is becoming popular, lately. Several comparisons between neural networks trained with error backpropagation and support vector machines have shown advantage for the latter in different domains of application. However, some difficulties still deteriorate the performance of the support vector machines. The main one is related to the setting of the hyperparameters involved in their training. Techniques based on meta-heuristics have been employed to determine appropriate values for those hyperparameters. However, because of the high noneonvexity of this estimation problem, which makes the search for a good solution very hard, an approach based on Bayesian inference, called relevance vector machine, has been proposed more recently. The present paper aims at investigating the suitability of this new approach to the short-term load forecasting problem.

GIS-based evaluation of landslide susceptibility using a novel hybrid computational intelligence model on different mapping units

Landslide susceptibility mapping is significant for landslide prevention.Many approaches have been used for landslide susceptibility prediction,however,their performances are unstable.This study constructed a hybrid model,namely box counting dimension-based kernel logistic regression model,which uses fractal dimension calculated by box counting method as input data based on grid cells mapping unit and terrain mapping unit.The performance of this model was evaluated in the application in Zhidan County,Shaanxi Province,China.Firstly,a total of 221 landslides were identified and mapped,and 11 landslide predisposing factors were considered.Secondly,the landslide susceptibility maps(LSMs) of the study area were obtained by constructing the model on two different mapping units.Finally,the results were evaluated with five statistical indexes,sensitivity,specificity,positive predictive value(PPV),negative predictive value(NPV) and Accuracy.The statistical indexes of the model obtained on the terrain mapping unit were larger than those based on grid cells mapping unit.For training and validation datasets,the area under the receiver operating characteristic curve(AUC) of the model based on terrain mapping unit were 0.9374 and 0.9527,respectively,indicating that establishing this model on the terrain mapping unit was advantageous in the study area.The results show that the fractal dimension improves the prediction ability of the kernel logistic model.In addition,the terrain mapping unit is a more promising mapping unit in Loess areas.

Static Frame Model Validation with Small Samples Solution Using Improved Kernel Density Estimation and Confidence Level Method

An improved method using kernel density estimation （KDE） and confidence level is presented for model validation with small samples. Decision making is a challenging problem because of input uncertainty and only small samples can be used due to the high costs of experimental measurements. However, model validation provides more confidence for decision makers when improving prediction accuracy at the same time. The confidence level method is introduced and the optimum sample variance is determined using a new method in kernel density estimation to increase the credibility of model validation. As a numerical example, the static frame model validation challenge problem presented by Sandia National Laboratories has been chosen. The optimum bandwidth is selected in kernel density estimation in order to build the probability model based on the calibration data. The model assessment is achieved using validation and accreditation experimental data respectively based on the probability model. Finally, the target structure prediction is performed using validated model, which are consistent with the results obtained by other researchers. The results demonstrate that the method using the improved confidence level and kernel density estimation is an effective approach to solve the model validation problem with small samples.

Over-Smoothing Algorithm and Its Application to GCN Semi-supervised Classification

The feature information of the local graph structure and the nodes may be over-smoothing due to the large number of encodings,which causes the node characterization to converge to one or several values.In other words,nodes from different clusters become difficult to distinguish,as two different classes of nodes with closer topological distance are more likely to belong to the same class and vice versa.To alleviate this problem,an over-smoothing algorithm is proposed,and a method of reweighted mechanism is applied to make the tradeoff of the information representation of nodes and neighborhoods more reasonable.By improving several propagation models,including Chebyshev polynomial kernel model and Laplace linear 1st Chebyshev kernel model,a new model named RWGCN based on different propagation kernels was proposed logically.The experiments show that satisfactory results are achieved on the semi-supervised classification task of graph type data.