Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation

Wong, Tzu-Tsung

doi:10.1016/j.patcog.2015.03.009

Cited by 1,081 publications

(563 citation statements)

References 2 publications

Supporting

Mentioning

530

Contrasting

Unclassified

Order By: Relevance

“…LOOCV could be carried out in two manners: global and local LOOCV. In both frameworks, each known miRNA-disease association was left in turn as a test sample and other known miRNA-disease associations were regarded as training samples[37]. The only difference between global LOOCV and local LOOCV was that whether all the diseases were investigated simultaneously.…”

Section: Resultsmentioning

confidence: 99%

GLNMDA: a novel method for miRNA-disease association prediction based on global linear neighborhoods

Liang

Xiao

et al. 2018

RNA Biology

View full text Add to dashboard Cite

Recently, increasing studies have shown that miRNAs are involved in the development and progression of various complex diseases. Consequently, predicting potential miRNA-disease associations makes an important contribution to understanding the pathogenesis of diseases, developing new drugs as well as designing individualized diagnostic and therapeutic approaches for different human diseases. Nonetheless, the inherent noise and incompleteness in the existing biological datasets have limited the prediction accuracy of current computational models. To solve this issue, in this paper, we propose a novel method for miRNA-disease association prediction based on global linear neighborhoods (GLNMDA). Specifically, our method obtains a new miRNA/disease similarity matrix by linearly reconstructing each miRNA/disease according to the known experimentally verified miRNA-disease associations. We then adopt label propagation to infer the potential associations between miRNAs and diseases. As a result, GLNMDA achieved reliable performance in the frameworks of both local and global LOOCV (AUCs of 0.867 and 0.929, respectively) and 5-fold cross validation (average AUC of 0.926). Case studies on five common human diseases further confirmed the utility of our method in discovering latent miRNA-disease pairs. Taken together, GLNMDA could serve as a reliable computational tool for miRNA-disease association prediction.

show abstract

Section: Resultsmentioning

confidence: 99%

GLNMDA: a novel method for miRNA-disease association prediction based on global linear neighborhoods

Liang

Xiao

et al. 2018

RNA Biology

View full text Add to dashboard Cite

show abstract

“…Each original dataset was divided into test and validation sets in proportion 9:1 with 10-fold cross-validation, which is widely accepted in data mining and machine learning community and serves as a standard procedure of validation [15]- [17].…”

Section: Methodsmentioning

confidence: 99%

Preprocessing compensation techniques for improved classification of imbalanced medical datasets

Wosiak

Karbowiak

2017

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Abstract-The paper describes the study on the problem of applying classification techniques in medical datasets with a class imbalance. The aim of the research is to identify factors that negatively affect classification results and propose actions that may be taken to improve the performance. To alleviate the impact of uneven and complex class distribution, methods of balancing the datasets are proposed and compared. The experiments were conducted on five datasets -three binary and two multiclass. They comprise several data preprocessing methods applied on data and the classification with different techniques. The study shows that for some datasets there exists a combination of a certain preprocessing method and a classification technique which outperforms other approaches. For datasets with complex distribution or too many features the ratio of correctly predicted labels may be low regardless what resampling method and classification technique has been applied.

show abstract

“…For the remaining point data, a different interpolation method is used to compute the simulation value by combining the calculating error of the observed value [25][26][27].…”

Section: Cross Validationmentioning

confidence: 99%

Cooperation of the Spatial Interpolation Algorithm for the Contour Map of the Shockwave Overpressure Field

Yong-li¹,

Han²,

Liu³

et al. 2017

JESTR

View full text Add to dashboard Cite

Traditionally, the peak overpressures of multi-point shockwave are obtained through the sensor array by using the electrometric method, and then the surface interpolation is carried out by the mathematical model to draw the contour lines of the shockwave overpressure field. The cross-validation method of the mean absolute error (MAE), mean relative error (MRE), and root mean square error (RMSE) was proposed in this study to achieve high precision and effective interpolation of the contour lines. The quantitative test of Kinney-Graham Formula was verified, and the peak overpressures of the multi-point shockwave of a 7.62-mm caliber gun and a naval gun were obtained through the sensor array based on polar coordinate. Then, the shockwave overpressure field was interpolated by the inverse distance weighted (IDW) interpolation, the ordinary kriging interpolation(OK), the radial basis function (RBF) interpolation, and the cubic spline (CS) function interpolation, Finally, cross-validation analysis was performed on MAE, MRE, and RMSE. Results demonstrate that the MAE of the RBF interpolation is 0.038, and the MRE is 0.001. The error is smallest, the accuracy is highest, and the interpolation effect is closest to the shockwave field model. The OK interpolation is close to the RBF interpolation. The MRE of the CS interpolation is 0.254, which is relatively large. The RMSE of the IDW interpolation is 14.268, which is abnormal. The RBF interpolation is the optimal interpolation algorithm for the shockwave overpressure field, which provides a reference for the contour drawing of the shockwave overpressure field.

show abstract

Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation

Cited by 1,081 publications

References 2 publications

GLNMDA: a novel method for miRNA-disease association prediction based on global linear neighborhoods

GLNMDA: a novel method for miRNA-disease association prediction based on global linear neighborhoods

Preprocessing compensation techniques for improved classification of imbalanced medical datasets

Cooperation of the Spatial Interpolation Algorithm for the Contour Map of the Shockwave Overpressure Field

Contact Info

Product

Resources

About