Results 51 to 60 of about 38,801 (275)

Predictive Modeling of ICU Healthcare-Associated Infections from Imbalanced Data. Using Ensembles and a Clustering-Based Undersampling Approach

, 2019
Early detection of patients vulnerable to infections acquired in the hospital environment is a challenge in current health systems given the impact that such infections have on patient mortality and healthcare costs.
Ballesteros-Herráez, Juan Carlos, Kraiem, Mohamed S., Moreno-García, María N., Sánchez-Barba, Mercedes, Sánchez-Hernández, Fernando   +4 more
core   +1 more source

3D Large‐Scale Subwavelength‐Resolution Sound Sheet Tomography Based on an Active and Programmable Circular Meta‐Array

Advanced Science, EarlyView.
A programmable 2048‐element circular ultrasound array combined with a compact acoustic lens produces a thin “sound sheet” over a large field of view, and records echoes with wide angular diversity across the ring aperture. Coherence‐enhanced beamforming converts full‐matrix data into high‐contrast tomographic slices, delivering near‐diffraction‐limited
Qiu‐De Zhang, Zi‐Bin Lin, Zhuo Chen, Zhao‐Hui Liu, Jin‐Lian He, Jun‐Jie Song, Long‐Sheng Zeng, Liang Zhou, Ming‐Yue Ding, Yu‐Gui Peng, Ming Yuchi, Xue‐Feng Zhu   +11 more
wiley   +1 more source

Zero-Inflated Text Data Analysis Using Imbalanced Data Sampling and Statistical Models

Computers
Text data often exhibits high sparsity and zero inflation, where a substantial proportion of entries in the document–keyword matrix are zeros. This characteristic presents challenges to traditional count-based models, which may suffer from reduced ...
Sunghae Jun
doaj   +1 more source

Undersampling bankruptcy prediction: Taiwan bankruptcy data.

PLoS ONE, 2021
Machine learning models have increasingly been used in bankruptcy prediction. However, the observed historical data of bankrupt companies are often affected by data imbalance, which causes incorrect prediction, resulting in substantial economic losses ...
Haoming Wang, Xiangdong Liu
doaj   +1 more source

ML Workflows for Screening Degradation‐Relevant Properties of Forever Chemicals

Advanced Science, EarlyView.
The environmental persistence of per‐ and polyfluoroalkyl substances (PFAS) necessitates efficient remediation strategies. This study presents physics‐informed machine learning workflows that accurately predict critical degradation properties, including bond dissociation energies and polarizability.
Pranoy Ray, Andrew R. Castillo, Manoj Kolel‐Veetil, Surya R. Kalidindi   +3 more
wiley   +1 more source

Orchid Species Classification Using the DenseNet121 Deep Learning Model with a Data Imbalance Handling Approach

Journal of Applied Informatics and Computing
For conservation, commercial cultivation, and scientific research, accurate identification of orchid species often requires specialized expertise.
Fadhilah Aditya Akbar, Christy Atika Sari   +1 more
doaj   +1 more source

On Generalized Schürmann Entropy Estimators

Entropy, 2022
We present a new class of estimators of Shannon entropy for severely undersampled discrete distributions. It is based on a generalization of an estimator proposed by T.
Peter Grassberger
doaj   +1 more source

MR image reconstruction using deep density priors

, 2018
Algorithms for Magnetic Resonance (MR) image reconstruction from undersampled measurements exploit prior information to compensate for missing k-space data.
Baumgartner, Christian F., Konukoglu, Ender, Luechinger, Roger, Pruessmann, Klaas P., Tezcan, Kerem C.   +4 more
core   +1 more source

Random Walk-steered Majority Undersampling

2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2022
In this work, we propose Random Walk-steered Majority Undersampling (RWMaU), which undersamples the majority points of a class imbalanced dataset, in order to balance the classes. Rather than marking the majority points which belong to the neighborhood of a few minority points, we are interested to perceive the closeness of the majority points to the ...
Payel Sadhukhan, Arjun Pakrashi, Brian Mac Namee   +2 more
openaire   +2 more sources

Hadamard Matrix Slicing Single‐Pixel Imaging: Establishing a Linear‐Array‐Inspired Paradigm for N‐fold Acceleration Single‐Pixel Imaging

Advanced Science, EarlyView.
To overcome two‐dimensional modulation bottlenecks, Hadamard Matrix Slicing Single‐Pixel Imaging (HMS‐SPI) establishes an efficient one‐dimensional imaging paradigm. By slicing the traditional Hadamard matrix into one‐dimensional encoding vectors and spatially expanding them, the required measurement patterns decrease by a factor of N.
Xiaoxue Li, Jieting Hou, Qizheng Zhao, Yiqi Jia, Xiang Zhong, Mengchao Ma, Huaxia Deng, Xinglong Gong, Ziwei Wang   +8 more
wiley   +1 more source