A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications

Journal Of Big Data, Год журнала: 2023, Номер 10(1)

Опубликована: Апрель 14, 2023

Abstract Data scarcity is a major challenge when training deep learning (DL) models. DL demands large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate train frameworks. Usually, manual labeling needed provide labeled data, which typically involves human annotators with vast background knowledge. This annotation process costly, time-consuming, and error-prone. every framework fed by significant automatically learn representations. Ultimately, larger would generate better model its performance also application dependent. issue the main barrier for dismissing use DL. Having sufficient first step toward any successful trustworthy application. paper presents holistic survey on state-of-the-art techniques deal models overcome three challenges including small, imbalanced datasets, lack generalization. starts listing techniques. Next, types architectures are introduced. After that, solutions address listed, such as Transfer Learning (TL), Self-Supervised (SSL), Generative Adversarial Networks (GANs), Model Architecture (MA), Physics-Informed Neural Network (PINN), Deep Synthetic Minority Oversampling Technique (DeepSMOTE). Then, these were followed some related tips about acquisition prior purposes, well recommendations ensuring trustworthiness dataset. The ends list that suffer from scarcity, several alternatives proposed in order more each Electromagnetic Imaging (EMI), Civil Structural Health Monitoring, Medical imaging, Meteorology, Wireless Communications, Fluid Mechanics, Microelectromechanical system, Cybersecurity. To best authors’ knowledge, this review offers comprehensive overview strategies tackle

Язык: Английский

---

Motivation and Continuance Intention towards Online Instruction among Teachers during the COVID-19 Pandemic: The Mediating Effect of Burnout and Technostress

International Journal of Environmental Research and Public Health, Год журнала: 2020, Номер 17(21), С. 8002 - 8002

Опубликована: Окт. 30, 2020

In-service teachers have various emotional and motivational experiences that can influence their continuance intention towards online-only instruction during the COVID-19 pandemic, as a significant stress factor for workplace. Derived from Self-Determination Theory (SDT), Job Demands–Resources Model (JD–R), Technology Acceptance (TAM), present research model includes technological pedagogical knowledge (TPK) self-efficacy (SE), intrinsic (IM) extrinsic (EM) work motivation, occupational (OS) (i.e., burnout technostress which been examined in tandem) key dimensions to explain better among in-service use (CI). Data were collected 980 outbreak between April May 2020. Overall, structural explained 70% of variance teachers’ CI. Motivational practices directly indirectly linked through OS with The findings showed IM has most effect on CI, followed by TPK-SE, significant, but lower predictors. was positively associated TPK-SE negatively EM. results offered valuable insights into how motivation constructs related understanding online an unstable context, order support coping working remotely.

Язык: Английский

---

Machine Learning, Deep Learning and Statistical Analysis for forecasting building energy consumption — A systematic review

Engineering Applications of Artificial Intelligence, Год журнала: 2022, Номер 115, С. 105287 - 105287

Опубликована: Авг. 12, 2022

Язык: Английский

---

Advances in Computational Intelligence of Polymer Composite Materials: Machine Learning Assisted Modeling, Analysis and Design

Archives of Computational Methods in Engineering, Год журнала: 2022, Номер 29(5), С. 3341 - 3385

Опубликована: Янв. 31, 2022

Язык: Английский

---

SPlit: An Optimal Method for Data Splitting

Technometrics, Год журнала: 2021, Номер 64(2), С. 166 - 176

Опубликована: Апрель 28, 2021

In this article, we propose an optimal method referred to as SPlit for splitting a dataset into training and testing sets. is based on the of support points (SP), which was initially developed finding representative continuous distribution. We adapt SP subsampling from using sequential nearest neighbor algorithm. also extend deal with categorical variables so that can be applied both regression classification problems. The implementation real datasets shows substantial improvement in worst-case performance several modeling methods compared commonly used random procedure.

Язык: Английский

---

A Novel Approach to Uncertainty Quantification in Groundwater Table Modeling by Automated Predictive Deep Learning

Natural Resources Research, Год журнала: 2022, Номер 31(3), С. 1351 - 1373

Опубликована: Апрель 12, 2022

Abstract Uncertainty quantification ( UQ ) is an important benchmark to assess the performance of artificial intelligence AI and particularly deep learning ensembled-based models. However, ability for using current -based methods not only limited in terms computational resources but it also requires changes topology optimization processes, as well multiple performances monitor model instabilities. From both geo-engineering societal perspectives, a predictive groundwater table GWT presents challenge, where lack limits validity findings may undermine science-based decisions. To overcome address these limitations, novel ensemble, automated random deactivating connective weights approach ARDCW ), presented applied retrieved geographical locations data from project Stockholm, Sweden. In this approach, was achieved via combination several derived ensembles fixed optimum subjected randomly switched off weights, which allow predictability with one forward pass. The process developed programmed provide trackable specific task access wide variety different internal characteristics libraries. A comparison Monte Carlo dropout quantile regression computer vision control metrics showed significant progress . This does require can be already trained topologies way that outperforms other

Язык: Английский

---

Can artificial intelligence and data-driven machine learning models match or even replace process-driven hydrologic models for streamflow simulation?: A case study of four watersheds with different hydro-climatic regions across the CONUS

Journal of Hydrology, Год журнала: 2021, Номер 598, С. 126423 - 126423

Опубликована: Май 7, 2021

Язык: Английский

---

Machine learning applications in power system fault diagnosis: Research advancements and perspectives

Engineering Applications of Artificial Intelligence, Год журнала: 2021, Номер 106, С. 104504 - 104504

Опубликована: Окт. 19, 2021

Язык: Английский

---

An integrated 3D CNN-GRU deep learning method for short-term prediction of PM2.5 concentration in urban environment

The Science of The Total Environment, Год журнала: 2022, Номер 834, С. 155324 - 155324

Опубликована: Апрель 19, 2022

Язык: Английский

---

Bayesian-based optimized deep learning model to detect COVID-19 patients using chest X-ray image data

Computers in Biology and Medicine, Год журнала: 2022, Номер 142, С. 105213 - 105213

Опубликована: Янв. 5, 2022

Язык: Английский

---