Results 71 to 80 of about 116,076 (264)
Targeting Precision with Data Augmented Samples in Deep Learning [PDF]
, 2019 In the last five years, deep learning (DL) has become the state-of-the-art tool for solving various tasks in medical image analysis. Among the different methods that have been proposed to improve the performance of Convolutional Neural Networks (CNNs), one typical approach is the augmentation of the training data set through various transformations of ...
Pietro Nardelli +1 more
openaire +2 more sources
PAITS: Pretraining and Augmentation for Irregularly-Sampled Time Series
CoRR, 2023 Code: \url{https://github.com/google-research/google-research/tree/master/irregular_timeseries_pretraining}
Nicasia Beebe-Wang +4 more
openaire +2 more sources
Molecular Oncology, EarlyView.The novel styrylquinazolinone‐based molecule W1B effectively suppresses glioblastoma by inhibiting IGF1R and EGFR. In high‐glucose microenvironments driving tumor resistance, W1B acts synergistically with the EGFR inhibitor dacomitinib. This combination safely blocks compensatory survival signaling in zebrafish xenograft models. Showcasing promising in
Patryk Rurka +9 more
wiley +1 more source
IEEE AccessIn the context of the low-carbon transition of energy systems, power system operating conditions exhibit strong stochasticity, making rapid and accurate characterization of the steady-state security region boundary essential for online security ...
Hongyin Liu +6 more
doaj +1 more source
Data Augmentation by Pairing Samples for Images Classification
CoRR, 2018 Data augmentation is a widely used technique in many machine learning tasks, such as image classification, to virtually enlarge the training dataset size and avoid overfitting. Traditional data augmentation techniques for image classification tasks create new samples from the original training data by, for example, flipping, distorting, adding a small ...
openaire +2 more sources
Molecular Oncology, EarlyView.Single‐cell multi‐omics reveals epigenetic heterogeneity across therapy‐adaptive tumor states, including quiescent/dormant, drug‐tolerant persister, and EMT‐like phenotypes. By linking regulatory features with state‐associated biomarkers, these approaches inform biomarker‐guided therapeutic strategies for evolving tumors.
Hee Jung Kim +3 more
wiley +1 more source
Enhanced mixup for improved time series analysis
IJAIN (International Journal of Advances in Intelligent Informatics)Time series data analysis is crucial for real-world applications. While deep learning has advanced in this field, it still faces challenges, such as limited or poor-quality data.
Khoa Tho Anh Nguyen +4 more
doaj +1 more source
GAN-Based Image Augmentation for Finger-Vein Biometric Recognition
IEEE Access, 2019 Deep learning methods, and especially convolutional neural networks (CNNs), have made a considerable breakthrough in various fields of machine vision, basically by employing large-scale labeled databases.
Jianfeng Zhang +3 more
doaj +1 more source
FEBS Open Bio, EarlyView.In this study, we developed a deep learning method for mitotic figure counting in H&E‐stained whole‐slide images and evaluated its prognostic impact in 13 external validation cohorts from seven different cancer types. Patients with more mitotic figures per mm2 had significantly worse patient outcome in all the studied cancer types except colorectal ...
Joakim Kalsnes +32 more
wiley +1 more source
Synthetic Data Generation for Augmenting Small Samples
CoRRSmall datasets are common in health research. However, the generalization performance of machine learning models is suboptimal when the training datasets are small. To address this, data augmentation is one solution. Augmentation increases sample size and is seen as a form of regularization that increases the diversity of small datasets, leading them ...
Dan Liu +8 more
openaire +2 more sources