Results 21 to 30 of about 207,018 (117)

Gaussian noise up-sampling is better suited than SMOTE and ADASYN for clinical decision making

BioData Mining, 2021
Clinical data sets have very special properties and suffer from many caveats in machine learning. They typically show a high-class imbalance, have a small number of samples and a large number of parameters, and have missing values.
Jacqueline Beinecke, Dominik Heider
doaj   +1 more source

Text Data Augmentation for the Korean Language

Applied Sciences, 2022
Data augmentation (DA) is a universal technique to reduce overfitting and improve the robustness of machine learning models by increasing the quantity and variety of the training dataset.
Dang Thanh Vu, Gwanghyun Yu, Chilwoo Lee, Jinyoung Kim   +3 more
doaj   +1 more source

Data-Driven RANS Modeling With Data Augmentation

气体物理
Guo et al.[1] proposed using implicit treatment with asynchronous iterations in Reynolds-averaged Navier-Stokes （RANS） simulations for training cases[2].
Chun BAO, Zhenhua XIA, Yipeng SHI
doaj   +1 more source

An adaptive fusion-based data augmentation method for abstract dialogue summarization [PDF]

PeerJ Computer Science
The dialogue summarization is necessary for information retrieval, and the training of abstract dialogue summarization models heavily rely on large amounts of labeled data.
Weihao Li, Dan Jiang, Han Zhang, Kejing Xiao, Shaozhong Cao   +4 more
doaj   +2 more sources

Implicit Semantic Data Augmentation for Hand Pose Estimation

IEEE Access, 2022
Data augmentation is a well-known technique used for improving the generalization performance of modern neural networks. After the success of several traditional random data augmentation for images (including flipping, translation, or rotation), a recent
Kyeongeun Seo, Hyeonjoong Cho, Daewoong Choi, Ju-Derk Park   +3 more
doaj   +1 more source

Empirical copula-based data augmentation for mixed-type datasets: a robust approach for synthetic data generation [PDF]

PeerJ Computer Science
Data augmentation is a critical technique for enhancing model performance in scenarios with limited, sparse, or imbalanced datasets. While existing methods often focus on homogeneous data types (e.g., continuous-only or categorical-only), real-world ...
Mohsen Ben Hassine, Lamine Mili
doaj   +2 more sources

A New Multispectral Data Augmentation Technique Based on Data Imputation

Remote Sensing, 2021
Deep Learning (DL) has been recently introduced into the hyperspectral and multispectral image classification landscape. Despite the success of DL in the remote sensing field, DL models are computationally intensive due to the large number of parameters ...
Álvaro Acción, Francisco Argüello, Dora B. Heras   +2 more
doaj   +1 more source

Data Augmentation using Counterfactuals: Proximity vs Diversity

Proceedings of the International Florida Artificial Intelligence Research Society Conference, 2022
Counterfactual explanations are gaining in popularity as a way of explaining machine learning models. Counterfactual examples are generally created to help interpret the decision of a model.
Md Golam Moula Mehedi Hasan, Douglas Talbert   +1 more
doaj   +1 more source

LLM-Based Persona-Driven Text Data Augmentation

IEEE Access
Illicit online communication, such as drug-dealing dialogues, is increasingly conducted through covert, context dependent language patterns that evade traditional detection techniques in South Korea.
Hyeon Seong Jeong, Han Kyeong Ko, Soo Yong Park, Taehoon Kim   +3 more
doaj   +1 more source

Spectral image data aggregation for multisource data augmentation

European Journal of Remote Sensing
Multispectral and hyperspectral images are increasingly popular in different research fields, such as remote sensing, astronomical imaging, or precision agriculture.
R. I. Luca, A. Baicoianu, I. C. Plajer
doaj   +1 more source