scholarly journals Improved Predictive Ability of KPLS Regression with Memetic Algorithms

Mathematics ◽  
2021 ◽  
Vol 9 (5) ◽  
pp. 506
Author(s):  
Jorge Daniel Mello-Román ◽  
Adolfo Hernández ◽  
Julio César Mello-Román
Keyword(s):  
Kernel Function ◽  
Linear Method ◽  
Predictive Ability ◽  
Feature Space ◽  
Memetic Algorithms ◽  
Least Squares Regression ◽  
Optimal Parameters ◽  
Number Of Components ◽  
Kernel Partial Least Squares ◽  
Dependent Variables

Kernel partial least squares regression (KPLS) is a non-linear method for predicting one or more dependent variables from a set of predictors, which transforms the original datasets into a feature space where it is possible to generate a linear model and extract orthogonal factors also called components. A difficulty in implementing KPLS regression is determining the number of components and the kernel function parameters that maximize its performance. In this work, a method is proposed to improve the predictive ability of the KPLS regression by means of memetic algorithms. A metaheuristic tuning procedure is carried out to select the number of components and the kernel function parameters that maximize the cumulative predictive squared correlation coefficient, an overall indicator of the predictive ability of KPLS. The proposed methodology led to estimate optimal parameters of the KPLS regression for the improvement of its predictive ability.

Financial Distress Prediction Based on Support Vector Machine with a Modified Kernel Function

2016 ◽  
Vol 25 (3) ◽  
pp. 417-429
Author(s):  
Chong Wu ◽  
Lu Wang ◽  
Zhe Shi
Keyword(s):  
Support Vector Machine ◽  
Kernel Function ◽  
Financial Distress ◽  
Classification Accuracy ◽  
Feature Space ◽  
Support Vector ◽  
Input Space ◽  
Financial Distress Prediction ◽  
Support Vectors ◽  
Distress Prediction

AbstractFor the financial distress prediction model based on support vector machine, there are no theories concerning how to choose a proper kernel function in a data-dependent way. This paper proposes a method of modified kernel function that can availably enhance classification accuracy. We apply an information-geometric method to modifying a kernel that is based on the structure of the Riemannian geometry induced in the input space by the kernel. A conformal transformation of a kernel from input space to higher-dimensional feature space enlarges volume elements locally near support vectors that are situated around the classification boundary and reduce the number of support vectors. This paper takes the Gaussian radial basis function as the internal kernel. Additionally, this paper combines the above method with the theories of standard regularization and non-dimensionalization to construct the new model. In the empirical analysis section, the paper adopts the financial data of Chinese listed companies. It uses five groups of experiments with different parameters to compare the classification accuracy. We can make the conclusion that the model of modified kernel function can effectively reduce the number of support vectors, and improve the classification accuracy.

scholarly journals Forecasting of Steam Coal Price Based on Robust Regularized Kernel Regression and Empirical Mode Decomposition

2021 ◽  
Vol 9 ◽  
Author(s):  
Xiangwan Fu ◽  
Mingzhu Tang ◽  
Dongqun Xu ◽  
Jun Yang ◽  
Donglin Chen ◽  
...  
Keyword(s):  
Empirical Mode Decomposition ◽  
Kernel Function ◽  
Dimensional Space ◽  
Kernel Regression ◽  
Model Performance ◽  
Feature Space ◽  
Evaluation Index ◽  
High Dimensional ◽  
Polynomial Kernel ◽  
Mode Decomposition

Aiming at the problem of difficulties in modeling the nonlinear relation in the steam coal dataset, this article proposes a forecasting method for the price of steam coal based on robust regularized kernel regression and empirical mode decomposition. By selecting the polynomial kernel function, the robust loss function and L2 regular term to construct a robust regularized kernel regression model are used. The polynomial kernel function does not depend on the kernel parameters and can mine the global rules in the dataset so that improves the forecasting stability of the kernel model. This method maps the features to the high-dimensional space by using the polynomial kernel function to transform the nonlinear law in the original feature space into linear law in the high-dimensional space and helps learn the linear law in the high-dimensional feature space by using the linear model. The Huber loss function is selected to reduce the influence of abnormal noise in the dataset on the model performance, and the L2 regular term is used to reduce the risk of model overfitting. We use the combined model based on empirical mode decomposition (EMD) and auto regressive integrated moving average (ARIMA) model to compensate for the error of robust regularized kernel regression model, thus making up for the limitations of the single forecasting model. Finally, we use the steam coal dataset to verify the proposed model and such model has an optimal evaluation index value compared to other contrast models after the model performance is evaluated as per the evaluation index such as RMSE, MAE, and mean absolute percentage error.

Prediction of diet quality for sheep from faecal characteristics: comparison of near-infrared spectroscopy and conventional chemistry predictive models

2015 ◽  
Vol 55 (1) ◽  
pp. 1 ◽  
Author(s):  
D. G. Kneebone ◽  
G. McL. Dryden
Keyword(s):  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Predictive Ability ◽  
Validation Dataset ◽  
Least Squares Regression ◽  
Prediction Equations ◽  
Faecal Excretion ◽  
Excretion Rates

This study evaluated the ability of equations developed from the analysis of faecal material by conventional chemistry (F.CHEM), and by near-infrared spectroscopy (F.NIRS), to predict intake and digestibility of forages fed with or without supplements. In vivo datasets were obtained using 30 sheep and 25 diets to provide 124 diet–faecal pairs, with each sheep fed four or five of the diets. The diets were five forages fed alone or with urea, molasses, cottonseed meal or sorghum grain supplements. Ninety-nine diet–faecal pairs were selected at random, but ensuring that all diets were represented and both the F.CHEM and F.NIRS prediction equations were developed from this dataset. The remaining 25 diet–faecal pairs were used as a validation dataset. Regressions for F.CHEM were developed by stepwise regression, and F.NIRS prediction equations were developed by partial least-squares regression. Prediction equations based solely on faecal analyte concentrations (F.CHEMc) had poor predictive ability, and models incorporating faecal constituent excretion rates (F.CHEMe) were the best at predicting feed constituent intakes. These models had slightly lower standard errors of prediction (SEP) for organic matter (OM) intake and digestible OM intake compared with the F.NIRS models that did not include faecal excretion rates. However, F.NIRS models had lower SEP for protein intake and OM digestibility. Good agreement between the F.CHEMe and F.NIRS methods was evident (according to the 95% limits-of-agreement test), and both predicted the reference values precisely and with small bias. Equations derived from a dataset that included representatives of all diets used in the experiment gave much better prediction of diet characteristics than those developed from a dataset constructed entirely at random. Equations for F.NIRS developed in this way successfully predicted the characteristics of diets that included forages fed alone and with the type of supplements used in tropical Australia.

Effort-Reward Imbalance, Overcommitment, and Psychological Distress in Canadian Police Officers

2007 ◽  
Vol 100 (2) ◽  
pp. 525-530 ◽  
Author(s):  
B. L. Janzen ◽  
Nazeem Muhajarine ◽  
Tong Zhu ◽  
I. W. Kelly
Keyword(s):  
Psychological Distress ◽  
Sex Education ◽  
Police Officers ◽  
Ordinary Least Squares ◽  
Occupational Group ◽  
Least Squares Regression ◽  
Dependent Variables ◽  
Effort Reward Imbalance ◽  
Reward Imbalance ◽  
The Relationship

The purpose of the present study was to examine the relationship among Effort, Reward, and Overcommitment dimensions of Siegrist's Effort-Reward Imbalance Model and Psychological Distress in a sample of 78 Canadian police officers. Ages of respondents ranged between 24 and 56 years ( M = 36.1, SD=8.0). 30% of respondents had been in policing for 16 years or more, 24% between 6 and 15 years, and 44% for 5 years or less. Ordinary least-squares regression was used to evaluate the relationship between the independent and dependent variables. After adjusting for age, sex, education, and marital status, higher levels of Effort-Reward Imbalance and Overcommitment were associated with greater Psychological Distress. Present findings support the utility of the model in this particular occupational group and add to the increasing literature suggesting association of Effort-Reward Imbalance, Overcommitment, and reduced mental health.

Sign in / Sign up

Export Citation Format

Share Document