A Survey on Applications of Artificial Intelligence in Fighting Against COVID-19

ACM Computing Surveys, Journal Year: 2021, Volume and Issue: 54(8), P. 1 - 32

Published: Oct. 4, 2021

The COVID-19 pandemic caused by the SARS-CoV-2 virus has spread rapidly worldwide, leading to a global outbreak. Most governments, enterprises, and scientific research institutions are participating in struggle curb of pandemic. As powerful tool against COVID-19, artificial intelligence (AI) technologies widely used combating this In survey, we investigate main scope contributions AI from aspects disease detection diagnosis, virology pathogenesis, drug vaccine development, epidemic transmission prediction. addition, summarize available data resources that can be for AI-based research. Finally, challenges potential directions fighting discussed. Currently, mainly focuses on medical image inspection, genomics, prediction, thus still great field. This survey presents researchers with comprehensive view existing applications technology goal inspiring continue maximize advantages big fight COVID-19.

Language: Английский

---

Deep features to detect pulmonary abnormalities in chest X-rays due to infectious diseaseX: Covid-19, pneumonia, and tuberculosis

Information Sciences, Journal Year: 2022, Volume and Issue: 592, P. 389 - 401

Published: Feb. 4, 2022

Language: Английский

---

Analysis and Prediction of COVID-19 Using SIR, SEIQR, and Machine Learning Models: Australia, Italy, and UK Cases

Information, Journal Year: 2021, Volume and Issue: 12(3), P. 109 - 109

Published: March 3, 2021

The novel coronavirus disease, also known as COVID-19, is a disease outbreak that was first identified in Wuhan, Central Chinese city. In this report, short analysis focusing on Australia, Italy, and UK conducted. includes confirmed recovered cases deaths, the growth rate Australia compared with Italy UK, trend of different Australian regions. Mathematical approaches based susceptible, infected, (SIR) exposed, quarantined, (SEIQR) models are proposed to predict epidemiology above-mentioned countries. Since performance classic forms SIR SEIQR depends parameter settings, some optimization algorithms, namely Broyden–Fletcher–Goldfarb–Shanno (BFGS), conjugate gradients (CG), limited memory bound constrained BFGS (L-BFGS-B), Nelder–Mead, optimize parameters predictive capabilities models. results optimized were those two well-known machine learning i.e., Prophet algorithm logistic function. demonstrate behaviors these algorithms countries well better improved Moreover, found provide prediction than function, for cases. Therefore, it seems suitable data an increasing context pandemic. Optimization model yielded significant improvement accuracy Despite availability several predictions pandemic, there no single would be optimal all

Language: Английский

---

Automatic Lung Health Screening Using Respiratory Sounds

Journal of Medical Systems, Journal Year: 2021, Volume and Issue: 45(2)

Published: Jan. 11, 2021

Language: Английский

---

Covid-19 Imaging Tools: How Big Data is Big?

Journal of Medical Systems, Journal Year: 2021, Volume and Issue: 45(7)

Published: June 3, 2021

Language: Английский

---

Model-based assessment of COVID-19 epidemic dynamics by wastewater analysis

The Science of The Total Environment, Journal Year: 2022, Volume and Issue: 827, P. 154235 - 154235

Published: March 1, 2022

Continuous surveillance of COVID-19 diffusion remains crucial to control its and anticipate infection waves. Detecting viral RNA load in wastewater samples has been suggested as an effective approach for epidemic monitoring the development warning system. However, quantitative link status stages outbreak is still elusive. Modelling thus address these challenges. In this study, we present a novel mechanistic model-based reconstruct complete dynamics from SARS-CoV-2 wastewater. Our integrates noisy data daily case numbers into dynamical epidemiological model. As demonstrated various regions sampling protocols, it quantifies numbers, provides indicators accurately infers future trends. Following analysis, also provide recommendations standards their use against new situations reduced testing capacity, our modelling can enhance early prediction robust cost-effective real-time local dynamics.

Language: Английский

---

Incremental learning-based cascaded model for detection and localization of tuberculosis from chest x-ray images

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 238, P. 122129 - 122129

Published: Oct. 14, 2023

Language: Английский

---

Federated Learning Approach for Early Detection of Chest Lesion Caused by COVID-19 Infection Using Particle Swarm Optimization

Electronics, Journal Year: 2023, Volume and Issue: 12(3), P. 710 - 710

Published: Jan. 31, 2023

The chest lesion caused by COVID-19 infection pandemic is threatening the lives and well-being of people all over world. Artificial intelligence (AI)-based strategies are efficient methods for helping radiologists assessing vast number X-ray images, which may play a significant role in simplifying improving diagnosis infection. Machine learning (ML) deep (DL) such AI that have helped researchers predict cases. But ML DL face challenges like transmission delays, lack computing power, communication privacy concerns. Federated Learning (FL) new development makes it easier to collect, process, analyze large amounts multidimensional data. This could help solve been identified DL. However, FL algorithms send receive weights from client-side trained models, resulting overhead. To address this problem, we offer unified framework combining particle swarm optimization algorithm (PSO) speed up government’s response time outbreaks. Particle Swarm Optimization approach tested on image dataset (pneumonia) Kaggle’s repository. Our research shows proposed model works better when there an uneven amount data, has lower costs, therefore more network’s point view. results were validated; 96.15% prediction accuracy was achieved lesions dataset, 96.55% dataset. These can be used develop progressive early detection

Language: Английский

---

Influenza-type epidemic risks by spatio-temporal Gaidai-Yakimov method

Dialogues in Health, Journal Year: 2023, Volume and Issue: 3, P. 100157 - 100157

Published: Oct. 27, 2023

Global public health was recently hampered by reported widespread spread of new coronavirus illness, although morbidity and fatality rates were low. Future infection may be accurately predicted over a long-time horizon, using novel bio-reliability approach, being especially well suitable for environmental multi-regional biological systems. The high regional dimensionality along with cross-correlations between various datasets challenging conventional statistical tools to manage. To assess future risks epidemiological outbreak in any province interest, spatio-temporal technique has been proposed. In multicenter, population-based environment, raw clinical data state-of-the-art, cutting-edge methodologies. Authors have developed reliable long-term risk assessment methodology outbreaks. Based on national patient monitoring dataset, it is concluded that underlying set quality questionable, the proposed method still applied.

Language: Английский

---

Robust Medical Diagnosis: A Novel Two-Phase Deep Learning Framework for Adversarial Proof Disease Detection in Radiology Images

Deleted Journal, Journal Year: 2024, Volume and Issue: 37(1), P. 308 - 338

Published: Jan. 10, 2024

In the realm of medical diagnostics, utilization deep learning techniques, notably in context radiology images, has emerged as a transformative force. The significance artificial intelligence (AI), specifically machine (ML) and (DL), lies their capacity to rapidly accurately diagnose diseases from images. This capability been particularly vital during COVID-19 pandemic, where rapid precise diagnosis played pivotal role managing spread virus. DL models, trained on vast datasets have showcased remarkable proficiency distinguishing between normal COVID-19-affected cases, offering ray hope amidst crisis. However, with any technological advancement, vulnerabilities emerge. Deep learning-based diagnostic although proficient, are not immune adversarial attacks. These attacks, characterized by carefully crafted perturbations input data, can potentially disrupt models' decision-making processes. context, such could dire consequences, leading misdiagnoses compromised patient care. To address this, we propose two-phase defense framework that combines advanced image filtering techniques. We use modified algorithm enhance model's resilience against examples training phase. During inference phase, apply JPEG compression mitigate cause misclassification. evaluate our approach three models based ResNet-50, VGG-16, Inception-V3. perform exceptionally classifying images (X-ray CT) lung regions into normal, pneumonia, pneumonia categories. then assess vulnerability these targeted attacks: fast gradient sign method (FGSM), projected descent (PGD), basic iterative (BIM). results show significant drop model performance after greatly improves resistance maintaining high accuracy examples. Importantly, ensures reliability diagnosing clean

Language: Английский

---