Two new undersampling methods improve classification accuracy for imbalanced datasets.
problem Class imbalance and distributional differences in large datasets lead to biased models and poor predictive performance.
method Mutual information-based stratified simple random sampling and support points optimization.
result Empirical results show higher balanced classification accuracy compared to traditional techniques.
Proposes a new undersampling method for imbalanced data classification.
problem Challenges of oversampling and undersampling in imbalanced data.
method Bilevel optimization framework for identifying optimal subset of majority training data.
result Improves F1 scores by up to 10% compared to state-of-the-art methods.
Approach predicts extubation readiness with high accuracy.
problem High reintubation rates due to inconsistent extubation readiness prediction.
method Random Forest classifiers trained on undersampled cardiorespiratory variability data.
result 71% of infants who failed extubation were correctly identified.
Optimal model improves AUC, recall, and F1 score for class-imbalanced business risk.
problem Improving prediction of class-imbalanced business risk.
method Resampling, regularization, and model ensembling techniques.
result Boosting on DT with SMOTE oversampling achieves AUC, recall, and F1 score of 0.8633, 0.9260, and 0.8907, respectively.
Better signal detection in undersampled data using joint and cross covariances.
problem Detecting shared signals in high-dimensional data with limited samples.
method Analysis of three covariance matrices: individual, cross, and joint.
result Joint and cross covariance matrices detect signals earlier than individual covariances.
The paper examines how data preparation affects fairness in machine learning models.
problem The impact of data preparation on fairness in machine learning models.
method The study evaluated the effect of removing sensitive attributes, encoding categorical attributes, and instance selection methods on fairness and predictive performance using the Adult Income and German Credit datasets.
result Data preparation significantly affects fairness in machine learning models, and removing the sensitive attribute is not sufficient to eliminate unfairness.
This paper proposes neural network-based undersampling techniques to improve model performance on class-imbalanced datasets.
problem Class imbalance problem in machine learning models leads to biased predictions and lower performance metrics.
method Neural network-based undersampling techniques applied to class-imbalanced datasets.
result Neural network-based undersampling outperforms other resampling techniques in terms of AUC, F1, and G-mean scores.
DeepCodec learns to take undersampled measurements and recover signals using deep neural networks.
problem Signal recovery from undersampled data.
method Adaptive deep convolutional neural networks for sensing and recovery.
result DeepCodec outperforms traditional ℓ1-minimization in signal recovery. Undersampling often outperforms other methods in nonparametric classification.
problem Distribution shift challenges in nonparametric binary classification.
method Proved undersampling is minimax optimal in worst-case scenarios.
result Undersampling is a robustness intervention with theoretical guarantees.
This chapter tackles class imbalance in datasets to promote data democracy.
problem Class imbalance in datasets leading to biased decisions and policies.
method Statistical measures and data-level methods (oversampling, undersampling, etc.) applied to a real dataset.
result Popular data-level methods improve performance in handling class imbalance.
A new deep learning model speeds up MRI by reconstructing from undersampled data.
problem Slow MRI due to undersampling in k-space.
method Unrolling primal-dual hybrid gradient algorithm into a deep network, gradually relaxing constraints.
result Superior MR reconstructions from highly undersampled data.
Proposes a new technique for handling imbalanced data.
problem Data imbalance in classification tasks.
method Combines oversampling and undersampling techniques.
result CSMOUTE shows promise for handling imbalanced datasets.
Enhances ECC for multi-label learning under class imbalance.
problem Class imbalance in multi-label datasets.
method Coupling ECC with random undersampling, and extending ECC with varying binary models per label and chains of different sizes.
result Improves ECC's performance on multi-label datasets using various evaluation metrics.
New undersampling method reduces computational complexity for imbalanced datasets.
problem Data imbalance in machine learning datasets.
method Radial-Based Undersampling (RBO) using mutual class potential.
result Significantly reduced time complexity of the proposed algorithm.
Subspace learning and matrix factorization problems have great many applications in science and engineering, and efficient algorithms are critical as dataset sizes continue to grow. Many relevant problem formulations are non-convex, and in a variety of contexts it has been observed that solving the non-convex problem d…
Jointly correct bias fields and reconstruct undersampled MRI images.
problem Recovering fully sampled MRI images from undersampled data while accounting for bias field differences.
method An unsupervised learning-based reconstruction algorithm combined with a N4-based bias field estimation method in a joint optimization scheme.
result The proposed method improves reconstruction quality, both visually and in terms of RMSE.
BCD-Net uses identical CNN structures for image recovery in undersampled imaging.
problem Challenges in obtaining accurate images from undersampled or noisy measurements.
method Incorporates image mapping CNN into BCD signal recovery method using alternating direction method of multipliers.
result Significantly more accurate image recovery compared to existing methods.
A novel two-stage resampling method improves CNN training on imbalanced colorectal cancer image data.
problem Data imbalance in medical image datasets, especially in histopathological images.
method Two-stage resampling: first oversampling in image space, then undersampling in feature space.
result The proposed method enhances CNN training on imbalanced colorectal cancer image datasets.
A new method flips class values to address class and treatment imbalance in uplift modeling and HTE.
problem Class and treatment imbalance in imbalanced RCT data.
method Class flipping approach to address imbalance without distorting predictions.
result The method does not distort predicted effects and does not require calibration.
This study proposes a method to predict ICU infections from imbalanced data using clustering-based undersampling and ensemble classifiers.
problem Predicting healthcare-associated infections in ICU patients from imbalanced data.
method Clustering-based undersampling strategy combined with ensemble classifiers.
result The proposed method outperforms other resampling techniques in predicting ICU infections.
Study examines fraud detection methods for credit cards with limited data.
problem Data imbalance in credit card fraud detection.
method Assesses different sampling methods and machine learning algorithms.
result Monte Carlo analysis shows random undersampling outperforms SMOTE in fraud cost reduction.
PC-RNN reconstructs MRI images from undersampled data with more details.
problem Recovering fine details from undersampled MRI data.
method Pyramid Convolutional RNN (PC-RNN) with three ConvRNN modules for multi-scale reconstruction.
result PC-RNN outperforms other methods in recovering more details from MRI images.
Gaussian process regression improves diffusion MRI data accuracy and efficiency.
problem Improving accuracy and efficiency of diffusion MRI data, especially for non-uniform and undersampled data.
method Gaussian process regression to estimate diffusion MRI signals at arbitrary locations.
result The method outperforms linear interpolation and allows significant undersampling.
New method estimates intrinsic dimensionality in undersampled data.
problem Challenges in estimating intrinsic dimensionality in high-dimensional, undersampled data.
method Uses tangent space properties and full correlation integral for accurate estimation.
result Capable of estimating ID in extremely undersampled regimes and curved manifolds.
We introduce a two step algorithm with theoretical guarantees to recover a jointly sparse and low-rank matrix from undersampled measurements of its columns. The algorithm first estimates the row subspace of the matrix using a set of common measurements of the columns. In the second step, the subspace aware recovery of …
In many applications one may acquire a composition of several signals that may be corrupted by noise, and it is a challenging problem to reliably separate the components from one another without sacrificing significant details. Adding to the challenge, in a compressive sensing framework, one is given only an undersampl…
Stochastic Gradient Descent finds wide but shallow minima due to undersampling, akin to energy-entropy competition.
problem The empirical effectiveness of Stochastic Gradient Descent in machine learning.
method Deriving a correspondence between parameter inference and free energy minimisation in statistical physics, where the degree of undersampling plays the role of temperature.
result Stochasticity in Stochastic Gradient Descent biases it towards wide minima, explaining its empirical effectiveness.
LIUBoost improves classification on imbalanced datasets by balancing and weighting instances.
problem Class imbalance and overlapping classes in imbalanced datasets.
method LIUBoost uses under-sampling and a cost term for balancing and weighting instances.
result LIUBoost significantly outperforms RUSBoost on 18 imbalanced datasets.
Proposes a new method for MR image reconstruction using unsupervised deep learning.
problem Compensating for missing k-space data in MR images.
method Learns the probability distribution of fully sampled MR images using VAE and uses it as an explicit prior term in reconstruction.
result Produces high-quality reconstructions with low RMSE values, outperforming other methods.
This paper surveys various data balancing methods for imbalanced datasets.
problem Imbalanced datasets bias predictions and degrade classifier performance.
method Extensive review of oversampling, undersampling, adaptive, generative, combination, and ensemble methods.
result No single method universally outperforms others; selection depends on dataset characteristics.
Generative adversarial networks reconstruct MRI images without full data.
problem Lack of fully-sampled ground truth data for supervised MRI reconstruction.
method Generative adversarial networks for unsupervised MRI reconstruction.
result Reconstructed images show more anatomical structure than conventional methods.
Natural signals and images are well-known to be approximately sparse in transform domains such as Wavelets and DCT. This property has been heavily exploited in various applications in image processing and medical imaging. Compressed sensing exploits the sparsity of images or image patches in a transform domain or synth…
Framework uses DL and STORM priors for FBU cardiac MRI reconstruction.
problem Reconstructing FBU cardiac MRI from undersampled data.
method Model-based reconstruction with DL and STORM priors.
result Demonstrates potential for accelerating FBU cardiac MRI.
Subspace clustering refers to the problem of clustering unlabeled high-dimensional data points into a union of low-dimensional linear subspaces, assumed unknown. In practice one may have access to dimensionality-reduced observations of the data only, resulting, e.g., from "undersampling" due to complexity and speed con…
Tree-based models biased when trained on imbalanced data, requiring new calibration methods.
problem Bias in tree-based models trained on imbalanced datasets.
method Analytical calibration of random forest models, demonstrating bias in decision trees.
result Calibrating tree-based models on imbalanced data negatively impacts predictions, especially for the minority class.
Study proposes new methods to calculate probabilistic benchmarks in noisy data.
problem Identifying opportunities for improvement in comparable units with noisy data.
method 2-step methodology involving undersampling and relevance vector machine.
result Higher discrimination power achieved with macro-economic environment variables.
Study investigates class imbalance in CNNs and compares methods to address it.
problem Class imbalance in convolutional neural networks (CNNs).
method Three benchmark datasets (MNIST, CIFAR-10, ImageNet) and comparison of oversampling, undersampling, two-phase training, and thresholding.
result Oversampling is the dominant method for addressing class imbalance in CNNs.
Deep learning speeds MRI by using less data, achieving high-quality images.
problem MRI reconstruction with full k-space data is time-consuming and resource-intensive.
method Sub-Nyquist sampling, image-folding correction, and deep learning.
result Deep learning can reconstruct high-quality MRI images with only 29% of k-space data.
HardVis helps visually manage imbalanced data by sampling hard instances.
problem Managing unsafe or noisy instances in imbalanced classification.
method Visual analytics system using undersampling and oversampling techniques.
result Boosts predictive power of ML models by balancing data sets.
Study uses 1D-CNNs to forecast mortality in ELSA survey.
problem Forecasting mortality in the middle-aged and older population.
method 1D-CNNs applied to longitudinal data with various over/undersampling and activation functions.
result Swish nonlinearity outperforms other functions in forecasting mortality.
This paper explores deep learning for improving X-ray CT image reconstruction from undersampled data.
problem Improving image reconstruction from undersampled X-ray CT data.
method Analysis of classical and deep learning methods for solving inverse problems.
result Deep learning methods show promise in improving image quality from undersampled data.
Proposes a Monte-Carlo method for sparse signal reconstruction.
problem Reconstructing sparse signals in high-dimensional settings.
method Greedy Monte-Carlo (GMC) search algorithm.
result GMC can achieve perfect reconstruction in undersampling situations.
Improved 2D cardiac MRI with less data using deep learning.
problem Reducing artefacts in undersampled 2D radial cine MRI.
method Modified U-net trained on spatio-temporal slices.
result Outperforms existing methods in image quality and training efficiency.
This paper concerns the performance of the LASSO (also knows as basis pursuit denoising) for recovering sparse signals from undersampled, randomized, noisy measurements. We consider the recovery of the signal xo∈RN from n random and noisy linear observations y=Axo+w, where A is the measuremen…
Develops a method for identifying structured dynamical systems from data.
problem Identifying structured dynamical systems from undersampled and noisy data.
method Sparse least-squares fitting via ℓ1−ℓ2 optimization with the alternating direction method of multipliers. result The method is stable and successful under certain conditions, as shown by theoretical guarantees and computational results.
Machine learning models predict bluebottles' presence on beaches, addressing class imbalance and unreliable absence data.
problem Predicting bluebottles' presence on beaches with machine learning, tackling class imbalance and unreliable absence data.
method Used Multilayer Perceptron, Random Forest, and XGBoost models; employed data augmentation techniques like SMOTE, Random Undersampling, and Synthetic Negative Approach.
result Random Forests combined with Synthetic Negative Approach provided the best predictive model, identifying wind direction as a key factor.
Unified framework for imbalanced data resampling improves classification performance.
problem Data imbalance negatively impacts machine learning performance.
method Unified framework combining over- and undersampling with radial basis functions optimization.
result Potential Anchoring outperforms state-of-the-art resampling algorithms.
Deep model learns coupled representations from side information for sparse signal recovery.
problem Recovering signals from undersampled, incomplete or noisy linear measurements.
method Deep unfolding model incorporating side information from different modalities.
result Superior performance compared to single-modal and multimodal methods.