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.
— In light of the pandemic that has swept the world, the use of e-learning in educational institutions has become an urgent necessity for continued knowledge communication with students. Educational institutions can benefit from the free tools that Google provide and from these applications, Google classroom which is characterized by ease of use, but the efficiency of using Google classroom is affected by several variables not studied in previous studies Clearly, this study aimed to identify the use of Google classroom as a system for managing e-learning and the factors affecting the performance of students and lecturer. The data of this study were collected from 219 members of the faculty and students at the College of Administra
... Show MoreIn this study, SnO2 nanoparticles were prepared from cost-low tin chloride (SnCl2.2H2O) and ethanol by adding ammonia solution by the sol-gel method, which is one of the lowest-cost and simplest techniques. The SnO2 nanoparticles were dried in a drying oven at a temperature of 70°C for 7 hours. After that, it burned in an oven at a temperature of 200°C for 24 hours. The structure, material, morphological, and optical properties of the synthesized SnO2 in nanoparticle sizes are studied utilizing X-ray diffraction. The Scherrer expression was used to compute nanoparticle sizes according to X-ray diffraction, and the results needed to be scrutinized more closely. The micro-strain indicates the broadening of diffraction peaks for nano
... Show MoreCarbonate reservoirs are an essential source of hydrocarbons worldwide, and their petrophysical properties play a crucial role in hydrocarbon production. Carbonate reservoirs' most critical petrophysical properties are porosity, permeability, and water saturation. A tight reservoir refers to a reservoir with low porosity and permeability, which means it is difficult for fluids to move from one side to another. This study's primary goal is to evaluate reservoir properties and lithological identification of the SADI Formation in the Halfaya oil field. It is considered one of Iraq's most significant oilfields, 35 km south of Amarah. The Sadi formation consists of four units: A, B1, B2, and B3. Sadi A was excluded as it was not filled with h
... Show MoreUnconfined compressive strength (UCS) of rock is the most critical geomechanical property widely used as input parameters for designing fractures, analyzing wellbore stability, drilling programming and carrying out various petroleum engineering projects. The USC regulates rock deformation by measuring its strength and load-bearing capacity. The determination of UCS in the laboratory is a time-consuming and costly process. The current study aims to develop empirical equations to predict UCS using regression analysis by JMP software for the Khasib Formation in the Buzurgan oil fields, in southeastern Iraq using well-log data. The proposed equation accuracy was tested using the coefficient of determination (R²), the average absolute
... Show MoreIn this paper, we used four classification methods to classify objects and compareamong these methods, these are K Nearest Neighbor's (KNN), Stochastic Gradient Descentlearning (SGD), Logistic Regression Algorithm(LR), and Multi-Layer Perceptron (MLP). Weused MCOCO dataset for classification and detection the objects, these dataset image wererandomly divided into training and testing datasets at a ratio of 7:3, respectively. In randomlyselect training and testing dataset images, converted the color images to the gray level, thenenhancement these gray images using the histogram equalization method, resize (20 x 20) fordataset image. Principal component analysis (PCA) was used for feature extraction, andfinally apply four classification metho
... Show MoreThe current study aims to examine the level of problems faced by university students in distance learning, in addition to identify the differences in these problems in terms of the availability of internet services, gender, college, GPA, interactions, academic cohort, and family economic status. The study sample consisted of (3172) students (57.3% females). The researchers developed a questionnaire with (32) items to measure distance learning problems in four areas: Psychological (9 items), academic (10 items), technological (7 items), and study environment (6 items). The responses are scored on a (5) point Likert Scale ranging from 1 (strongly disagree) to 5 (strongly agree). Means, standard deviations, and Multivariate Analysis of Vari
... Show MoreOnline learning is not a new concept in education, but it has been used extensively since the Covid-19 pandemic and is still in use now. Every student in the world has gone through this learning process from the primary to the college levels, with both teachers and students conducting instruction online (at home). The goal of the current study is to investigate college students’ attitudes towards online learning. To accomplish the goal of the current study, a questionnaire is developed and adjusted before being administered to a sample of 155 students. Additionally, validity and reliability are attained. Some conclusions, recommendations, and suggestions are offered in the end.
Television white spaces (TVWSs) refer to the unused part of the spectrum under the very high frequency (VHF) and ultra-high frequency (UHF) bands. TVWS are frequencies under licenced primary users (PUs) that are not being used and are available for secondary users (SUs). There are several ways of implementing TVWS in communications, one of which is the use of TVWS database (TVWSDB). The primary purpose of TVWSDB is to protect PUs from interference with SUs. There are several geolocation databases available for this purpose. However, it is unclear if those databases have the prediction feature that gives TVWSDB the capability of decreasing the number of inquiries from SUs. With this in mind, the authors present a reinforcement learning-ba
... Show MoreSocial Networking has dominated the whole world by providing a platform of information dissemination. Usually people share information without knowing its truthfulness. Nowadays Social Networks are used for gaining influence in many fields like in elections, advertisements etc. It is not surprising that social media has become a weapon for manipulating sentiments by spreading disinformation. Propaganda is one of the systematic and deliberate attempts used for influencing people for the political, religious gains. In this research paper, efforts were made to classify Propagandist text from Non-Propagandist text using supervised machine learning algorithms. Data was collected from the news sources from July 2018-August 2018. After annota
... Show More