Sensitivity Analysis of k-Fold Cross Validation in Prediction Error Estimation

By Juan Diego Rodríguez, Aritz Pérez Martínez, José Antonio Lozano. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010

1,635 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

View Paper: https://www.semanticscholar.org/paper/da048cdf883f2ac0551162cb1abd7e6d09e8e86a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

The Future of Sensitivity Analysis: An essential discipline for systems modeling and policy support (2020, neutral): “Such mathematical models can be data-driven (also called statistical), directly mapping inputs to outputs (Engelbrecht et al., 1995; Rodriguez et al., 2010), or mechanistic (also called process-based), solving a set of differential or other mathematical equations governing the (possibly)…”
Machine Learning Based Intrusion Detection Systems for IoT Applications (2019, background): “As suggested in [53], the repeated version stabilizes the error estimation and minimizes the variance of the validation approach.”
Feature dimensionality reduction: a review (2022, methodology): “K -fold cross-validation method [117] is applied to select the parameters to select a reasonable parameter.”
Researcher Bias: The Use of Machine Learning in Software Defect Prediction (2014, background): “dency (see [10] for a more detailed discussion).”
Satellite Based Mapping of Ground PM2.5 Concentration Using Generalized Additive Modeling (2016, methodology): “Furthermore, we used a 10-fold cross-validation (10-CV) [42] to test the potential overfitting of the established GAM models.”
HAST-IDS: Learning Hierarchical Spatial-Temporal Features Using Deep Neural Networks to Improve Intrusion Detection (2018, methodology): “In our experiments, k was set to 10 because of the resulting low bias, low variance, low overfitting and good error estimate [18].”
Optimized neural network using beetle antennae search for predicting the unconfined compressive strength of jet grouting coalcretes (2019, methodology): “According to recommendations and the number of the dataset, the determination value of k was set to be 10 in this paper.(44,45) In this study, mean squared error (MSE) and correlation coefficient (R) were used as the performance measures for validating hyperparameter tuning and model evaluation.”
Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation (2015, background): “The bias of accuracy estimate will be smaller when the number of folds is either five or ten [4].”
Estimating Ground‐Level PM2.5 by Fusing Satellite and Station Observations: A Geo‐Intelligent Deep Learning Approach (2017, methodology): “Furthermore, to evaluate the model performance, a 10-fold cross-validation technique [Rodriguez et al., 2010] was applied to test the model overfitting and predictive power.”
Point-surface fusion of station measurements and satellite observations for mapping PM 2.5 distribution in China: Methods and assessment (2016, methodology): “Furthermore, a 10-fold cross-validation method (Rodriguez et al., 2010) was applied to test the model overfitting and predictive power.”
Recent Trends in the Use of Statistical Tests for Comparing Swarm and Evolutionary Computing Algorithms: Practical Guidelines and a Critical Review (2020, methodology): “[33] Frequentist - Classification Decomposition of the variance of the k-fold CV for prediction error estimation.”