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.
Abstract
The aim of the present research is to identify the test wisdom and the preoccupation with learning and psychological tension among postgraduate students at the University of Samarra according to the variables of the department, gender, age, and employee or non-employee, and revealing the relationship between the test wisdom and the preoccupation with learning and psychological tension. The research sample consisted of (75) students randomly selected from postgraduate students at the college of Education. The researcher applies test –wisdom of (Mellman & Ebel) and measurement of preoccupation with learning prepared by (Al-zaabi 2013) also, the researcher used the scale of t
... Show More
Journal of Theoretical and Applied Information Technology is a peer-reviewed electronic research papers & review papers journal with aim of promoting and publishing original high quality research dealing with theoretical and scientific aspects in all disciplines of IT (Informaiton Technology
This study aims at identifying the role played by Public Relations in the field of security awareness of the dangers of terrorism. The research is directed to the employees at the Directorate General of Public Relations and Media at the Ministry of Interior. And that on the basis that those who play an important role in the security awareness are the security institutions, primarily the Ministry of Interior, since this Directorate is responsible for all subjects related to the public security using public relations science. It aims at identifying the functions, methods and communication tools used by the Directorate to raise awareness about the dangers of terrorism. In order to achieve the research objectives, the researcher uses the sur
... Show More