In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used ...computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.
Evaluating immune responses following COVID-19 vaccination is paramount to understanding vaccine effectiveness and optimizing public health interventions. This study seeks to elucidate individuals' ...immune status after administering a second dose of diverse COVID-19 vaccines. By analyzing immune responses through serological markers, we aim to contribute valuable insights into the uniformity of vaccine performance.
A total of 80 participants were enrolled in this study, with demographic and COVID-19 infection-related data collected for categorization. Serum samples were acquired within a specified timeframe, and SARS-CoV-2 IgM/IgG rapid tests were conducted. Moreover, CTLA-4 levels were measured through ELISA assays, allowing us to assess the immune responses comprehensively. The participants were divided into eight groups based on various factors, facilitating a multifaceted analysis.
The outcomes of our investigation demonstrated consistent immune responses across the diverse types of COVID-19 vaccines administered in Iraq. Statistical analysis revealed no significant distinctions among the vaccine categories. In contrast, significant differences were observed in CTLA-4 among the control group (non-infected/non-vaccinated, infected/non-vaccinated) and infected/Pfizer, non-infected/Pfizer, and infected/Sinopharm, non-infected/sinopharm (P = 0.001, < 0.001, 0.023, respectively). This suggests that these vaccines exhibit comparable effectiveness in eliciting an immune response among the study participants.
In conclusion, our study's results underscore the lack of discriminatory variations between different COVID-19 vaccine types utilized in Iraq. The uniform immune responses observed signify the equitable efficacy and performance of these vaccines. Despite minor quantitative discrepancies, these variations do not hold statistical significance, reaffirming the notion that the various vaccines serve a similar purpose in conferring protection against COVID-19.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
In persons who had received the BNT162b2 vaccine in Qatar, the incidence of infection with the omicron variant after 35 days of observation was 2.4% among those who had received three doses and 4.5% ...among those who were vaccinated but not boosted; among those who had received the mRNA-1273 vaccine, the incidence was 1.0% with a boost and 1.9% without.
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 a test-negative, case–control study involving more than 900,000 participants in Qatar, vaccine effectiveness peaked at 77.5% in the first month after the second dose. The effectiveness fell ...thereafter to as low as 20% in months 5 through 7 after vaccination, but protection against serious Covid-19 remained greater than 90% for at least 6 months.
A study in Qatar assessed the effectiveness of previous infection, vaccination, and both against symptomatic SARS-CoV-2 caused by omicron BA.1 and BA.2 and against severe, critical, or fatal Covid-19.
Using a national Covid-19 database in Qatar, investigators found that previous SARS-CoV-2 infection provided protection against subsequent reinfection that ranged from 85% to 92% for the alpha, beta, ...and delta strains and was approximately 60% protective against the omicron variant. Previous infection also appeared to protect against severe disease, hospitalization, and death.
With the global expansion of the highly transmissible SARS-CoV-2 Delta (B.1.617.2) variant, we conducted a matched test-negative case-control study to assess the real-world effectiveness of COVID-19 ...messenger RNA vaccines against infection with Delta in Qatar's population. BNT162b2 effectiveness against any, symptomatic or asymptomatic, Delta infection was 45.3% (95% CI, 22.0-61.6%) ≥14 d after the first vaccine dose, but only 51.9% (95% CI, 47.0-56.4%) ≥14 d after the second dose, with 50% of fully vaccinated individuals receiving their second dose before 11 May 2021. Corresponding mRNA-1273 effectiveness ≥14 d after the first or second dose was 73.7% (95% CI, 58.1-83.5%) and 73.1% (95% CI, 67.5-77.8%), respectively. Notably, effectiveness against Delta-induced severe, critical or fatal disease was 93.4% (95% CI, 85.4-97.0%) for BNT162b2 and 96.1% (95% CI, 71.6-99.5%) for mRNA-1273 ≥ 14 d after the second dose. Our findings show robust effectiveness for both BNT162b2 and mRNA-1273 in preventing Delta hospitalization and death in Qatar's population, despite lower effectiveness in preventing infection, particularly for the BNT162b2 vaccine.
The burgeoning epidemic of diabetes mellitus (DM) is one of the major global health challenges. We systematically reviewed the published literature to provide a summary estimate of the association ...between DM and active tuberculosis (TB). We searched Medline and EMBASE databases for studies reporting adjusted estimates on the TB-DM association published before December 22, 2015, with no restrictions on region and language. In the meta-analysis, adjusted estimates were pooled using a DerSimonian-Laird random-effects model, according to study design. Risk of bias assessment and sensitivity analyses were conducted. 44 eligible studies were included, which consisted of 58,468,404 subjects from 16 countries. Compared with non-DM patients, DM patients had 3.59-fold (95% confidence interval (CI) 2.25-5.73), 1.55-fold (95% CI 1.39-1.72), and 2.09-fold (95% CI 1.71-2.55) increased risk of active TB in four prospective, 16 retrospective, and 17 case-control studies, respectively. Country income level (3.16-fold in low/middle-vs. 1.73-fold in high-income countries), background TB incidence (2.05-fold in countries with >50 vs. 1.89-fold in countries with ≤50 TB cases per 100,000 person-year), and geographical region (2.44-fold in Asia vs. 1.71-fold in Europe and 1.73-fold in USA/Canada) affected appreciably the estimated association, but potential risk of bias, type of population (general versus clinical), and potential for duplicate data, did not. Microbiological ascertainment for TB (3.03-fold) and/or blood testing for DM (3.10-fold), as well as uncontrolled DM (3.30-fold), resulted in stronger estimated association. DM is associated with a two- to four-fold increased risk of active TB. The association was stronger when ascertainment was based on biological testing rather than medical records or self-report. The burgeoning DM epidemic could impact upon the achievements of the WHO "End TB Strategy" for reducing TB incidence.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK