Data scarcity is a major challenge when training deep learning (DL) models. DL demands a large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate data to train DL frameworks. Usually, manual labeling is needed to provide labeled data, which typically involves human annotators with a vast background of knowledge. This annotation process is costly, time-consuming, and error-prone. Usually, every DL framework is fed by a significant amount of labeled data to automatically learn representations. Ultimately, a larger amount of data would generate a better DL model and its performance is also application dependent. This issue is the main barrier for many applications dismissing the use of DL. Having sufficient data is the first step toward any successful and trustworthy DL application. This paper presents a holistic survey on state-of-the-art techniques to deal with training DL models to overcome three challenges including small, imbalanced datasets, and lack of generalization. This survey starts by listing the learning techniques. Next, the types of DL architectures are introduced. After that, state-of-the-art solutions to address the issue of lack of training data are listed, such as Transfer Learning (TL), Self-Supervised Learning (SSL), Generative Adversarial Networks (GANs), Model Architecture (MA), Physics-Informed Neural Network (PINN), and Deep Synthetic Minority Oversampling Technique (DeepSMOTE). Then, these solutions were followed by some related tips about data acquisition needed prior to training purposes, as well as recommendations for ensuring the trustworthiness of the training dataset. The survey ends with a list of applications that suffer from data scarcity, several alternatives are proposed in order to generate more data in each application including Electromagnetic Imaging (EMI), Civil Structural Health Monitoring, Medical imaging, Meteorology, Wireless Communications, Fluid Mechanics, Microelectromechanical system, and Cybersecurity. To the best of the authors’ knowledge, this is the first review that offers a comprehensive overview on strategies to tackle data scarcity in DL.
Since the COVID-19 pandemic began, there have been concerns related to the preparedness of healthcare workers (HCWs). This study aimed to describe the level of awareness and preparedness of hospital HCWs at the time of the first wave.
This multinational, multicenter, cross-sectional survey was conducted among hospital HCWs from February to May 2020. We used a hierarchical logistic regression multivariate analysis to adjust the influence of variables based on awareness and preparedness. We then used association rule mining to identify relationships between HCW confidence in handling suspected
The research aims to reach a set of objectives concerning creation a clear vision about conceptual, philosophical and practical dimension of relations, and effects between knowledge management, costumer orientation and competitiveness to construct a framework of a pragmatic model as a solution to research problem and its questions which the main one is about the role of knowledge management and costumer orientation in competitiveness of business organizations. To achieving this goal, it was necessary to make, in priory, a review and discussion to the theoretical dimension of research variables to have a clear vision about constructing hypostatical research model implying a set of hypotheses which, by proving them in companies studied, repr
... Show MoreThe study aimed to determine the effect of the flipped learning model in improving the acquisition of the overhand serve skill in volleyball among second-year students at the College of Physical Education and Sport Sciences, University of Baghdad, for the academic year 2024/2025. The study used an experimental design with a control group and pre-post testing, on a purposive sample consisting of 12 students. The model relied on watching short videos before class via the SGS application, and practical application in class at a rate of three sessions per week. The results showed a significant improvement in performance, as the calculated value (t = 5.356) exceeded the tabulated value (2.042) at a significance level of 0.05. The percentage of s
... Show MoreThe study aims at studying and analyzing the subject of marketing vigilance as it is one of the modern approaches in the marketing field that can be used to face changes in the competitive and strategic environment and that represents quick reactions on the part of the institution to ensure its survival and distinctiveness other aims are: Consolidating the strength of the marketing organization and its success continuously, represented by changes in the market share, awareness of the institution's position in the market and its relations with competing tourism companies, diversification of tourism services, as well as an analysis of the competitive strategic position of tourism institutions for the purpose of conducting a r
... Show MoreSoils that cause effective damages to engineer structures (such as pavement and foundation) are called problematic or difficult soils (include collapsible soil, expansive soil, etc.). These damages occur due to poor or unfavorited engineering properties, such as low shear strength, high compressibility, high volume changes, etc. In the case of expansive soil, the problem of the shrink-swell phenomenon, when the soil reacts with water, is more pronounced. To overcome such problems, soils can be treated or stabilized with many stabilization ways (mechanical, chemical, etc.). Such ways can amend the unfavorited soil properties. In this review, the pozzolanic materials have been selected to be presented and discussed as chem
... Show MoreSorting and grading agricultural crops using manual sorting is a cumbersome and arduous process, in addition to the high costs and increased labor, as well as the low quality of sorting and grading compared to automatic sorting. the importance of deep learning, which includes the artificial neural network in prediction, also shows the importance of automated sorting in terms of efficiency, quality, and accuracy of sorting and grading. artificial neural network in predicting values and choosing what is good and suitable for agricultural crops, especially local lemons.