Results 91 to 100 of about 9,759,453 (201)

A just-in-time software defect prediction method based on data augmentation

Nantong Daxue xuebao. Ziran kexue ban
Just-in-time (JIT) software defect prediction aims to predict whether code commits during project development and maintenance will introduce defects.In the field of JIT software defect prediction research,model training relies on high-quality datasets ...
YANG Fan; XIA Hongling
doaj   +1 more source

Lung Segmentation from Chest X-rays using Variational Data Imputation

, 2020
Pulmonary opacification is the inflammation in the lungs caused by many respiratory ailments, including the novel corona virus disease 2019 (COVID-19).
Dam, Erik B., Detlefsen, Nicki S., Nielsen, Mads, Pai, Akshay, Rischel, Sofus, Selvan, Raghavendra, Sheng, Kaining   +6 more
core  

Specific emitter identification under extremely small sample conditions via chaotic integration

Electronics Letters
As a potential solution to improve wireless security, specific emitter identification is a lightweight access authentication technology. However, the existed deep learning‐based specific emitter identification methods are highly dependent on the training
Haotian Zhang, Yuan Jiang, Lei Zhao, Bo Peng   +3 more
doaj   +1 more source

Sample and feature augmentation strategies for calibration updating

Journal of Chemometrics, 2018
AbstractCalibration updating—transfer and/or maintenance—has historically been implemented using a simple but effective technique: in addition to primary samples, include a small number of secondary samples and weight them. It would be beneficial if these classical weighting techniques could be enhanced. Moreover, it would be ideal if we could only use
Erik Andries, John H. Kalivas, Anit Gurung   +2 more
openaire   +2 more sources

Landslide recognition with sample augmentation based on a joint DCGAN and Pix2Pix

Geomatics, Natural Hazards & Risk
Landslides are among the most frequent and destructive geological hazards in mountainous regions; however, the ability to automatically identify landslides is often constrained by limited amounts of labelled samples, modest gains derived from traditional
Peihui Li, Shaojin Huang, Ping Duan, Kang Zhao, Jia Li   +4 more
doaj   +1 more source

Augmented Feature Diffusion on Sparsely Sampled Subgraph

Electronics
Link prediction is a fundamental problem in graphs. Currently, SubGraph Representation Learning (SGRL) methods provide state-of-the-art solutions for link prediction by transforming the task into a graph classification problem. However, existing SGRL solutions suffer from high computational costs and lack scalability.
Xinyue Wu, Huilin Chen
openaire   +1 more source

Multi-hop Federated Private Data Augmentation with Sample Compression

, 2019
On-device machine learning (ML) has brought about the accessibility to a tremendous amount of data from the users while keeping their local data private instead of storing it in a central entity. However, for privacy guarantee, it is inevitable at each device to compensate for the quality of data or learning performance, especially when it has a non ...
Jeong, E. (Eunjeong), Oh, S. (Seungeun), Park, J. (Jihong), Kim, H. (Hyesung), Bennis, M. (Mehdi), Kim, S.-L. (Seong-Lyun)   +5 more
openaire   +3 more sources

Multi-Aligned and Multi-Scale Augmentation for Occluded Person Re-Identification

Sensors
Occluded person re-identification (Re-ID) faces significant challenges, mainly due to the interference of occlusion noise and the scarcity of realistic occluded training data.
Xuan Jiang, Xin Yuan, Xiaolan Yang
doaj   +1 more source

The Augmented SOLOW Model And The OECD Sample

International Business & Economics Research Journal (IBER), 2011
In their influential work on the augmented Solow model, Mankiw, Romer and Weil (1992) showed that cross-section evidence was reasonably consistent with the Solow growth model augmented to include human capital for a wide range of countries. However, for the sample of OECD countries, they found that the model had low explanatory power and underestimated
Giorgio Canarella, Stephen K. Pollard
openaire   +2 more sources

Star Generative Adversarial VGG Network-Based Sample Augmentation for Insulator Defect Detection

International Journal of Computational Intelligence Systems
Deep learning-based automated detection of insulator defects in electric power systems is a critical technological challenge, pivotal for ensuring reliability and efficiency in the global energy infrastructure.
Linghao Zhang, Luqing Wang, Zhijie Yan, Zhentang Jia, Hongjun Wang, Xinyu Tang   +5 more
doaj   +1 more source