Automated detection and forecasting of COVID-19 using deep learning techniques: A review

Neurocomputing, Journal Year: 2024, Volume and Issue: 577, P. 127317 - 127317

Published: Jan. 26, 2024

Language: Английский

---

An Ensemble Approach to Predict a Sustainable Energy Plan for London Households

Sustainability, Journal Year: 2025, Volume and Issue: 17(2), P. 500 - 500

Published: Jan. 10, 2025

The energy sector plays a vital role in driving environmental and social advancements. Accurately predicting demand across various time frames offers numerous benefits, such as facilitating sustainable transition planning of resources. This research focuses on consumption using three individual models: Prophet, eXtreme Gradient Boosting (XGBoost), long short-term memory (LSTM). Additionally, it proposes an ensemble model that combines the predictions from all to enhance overall accuracy. approach aims leverage strengths each for better prediction performance. We examine accuracy Mean Absolute Error (MAE), Percentage (MAPE), Root Square (RMSE) through means resource allocation. investigates use real data smart meters gathered 5567 London residences part UK Power Networks-led Low Carbon project Datastore. performance was recorded follows: 62.96% Prophet model, 70.37% LSTM, 66.66% XGBoost. In contrast, proposed which XGBoost, achieved impressive 81.48%, surpassing models. findings this study indicate enhances efficiency supports towards future. Consequently, can accurately forecast maximum loads distribution networks households. addition, work contributes improvement load forecasting networks, guide higher authorities developing plans.

Language: Английский

---

Artificial intelligence-driven prediction of COVID-19-related hospitalization and death: a systematic review

Frontiers in Public Health, Journal Year: 2023, Volume and Issue: 11

Published: June 20, 2023

Aim To perform a systematic review on the use of Artificial Intelligence (AI) techniques for predicting COVID-19 hospitalization and mortality using primary secondary data sources. Study eligibility criteria Cohort, clinical trials, meta-analyses, observational studies investigating or artificial intelligence were eligible. Articles without full text available in English language excluded. Data sources recorded Ovid MEDLINE from 01/01/2019 to 22/08/2022 screened. extraction We extracted information sources, AI models, epidemiological aspects retrieved studies. Bias assessment A bias models was done PROBAST. Participants Patients tested positive COVID-19. Results included 39 related AI-based prediction death The articles published period 2019-2022, mostly used Random Forest as model with best performance. trained cohorts individuals sampled populations European non-European countries, cohort sample size <5,000. collection generally demographics, records, laboratory results, pharmacological treatments (i.e., high-dimensional datasets). In most studies, internally validated cross-validation, but majority lacked external validation calibration. Covariates not prioritized ensemble approaches however, still showed moderately good performances Area under Receiver operating characteristic Curve (AUC) values >0.7. According PROBAST, all had high risk and/or concern regarding applicability. Conclusions broad range have been predict mortality. reported performance applicability detected.

Language: Английский

---

Technological Advancements and Elucidation Gadgets for Healthcare Applications: An Exhaustive Methodological Review-Part-I (AI, Big Data, Block Chain, Open-Source Technologies, and Cloud Computing)

Electronics, Journal Year: 2023, Volume and Issue: 12(3), P. 750 - 750

Published: Feb. 2, 2023

In the realm of emergence and spread infectious diseases with pandemic potential throughout history, plenty pandemics (and epidemics), from plague to AIDS (1981) SARS (in 2003) bunch COVID variants, have tormented mankind. Though technological innovations are overwhelmingly progressing curb them—a significant number such astounded world, impacting billions lives posing uncovered challenges healthcare organizations clinical pathologists globally. view addressing these limitations, a critically exhaustive review is performed signify prospective role advancements highlight implicit problems associated rendering best quality lifesaving treatments patient community. The proposed work conducted in two parts. Part 1 essentially focused upon discussion advanced technologies akin artificial intelligence, Big Data, block chain technology, open-source cloud computing, etc. Research works governing applicability solving many issues prominently faced by doctors surgeons fields cardiology, medicine, neurology, orthopaedics, paediatrics, gynaecology, psychiatry, plastic surgery, etc., as well their curtailing numerous infectious, pathological, neurotic maladies thrown light off. Boundary conditions implicitly substantiated remedies coupled future directions presented at end.

Language: Английский

---

A Comparative Study of COVID-19 Dynamics in Major Turkish Cities Using Fractional Advection–Diffusion–Reaction Equations

Fractal and Fractional, Journal Year: 2025, Volume and Issue: 9(4), P. 201 - 201

Published: March 25, 2025

Robust epidemiological models are essential for managing COVID-19, especially in diverse urban settings. In this study, we present a fractional advection–diffusion–reaction model to analyze COVID-19 spread three major Turkish cities: Ankara, Istanbul, and Izmir. The employs Caputo-type time-fractional derivative, with its order dynamically determined by the Hurst exponent, capturing memory effects of disease transmission. A nonlinear reaction term self-reinforcing viral spread, while Gaussian forcing simulates public health interventions adjustable spatial temporal parameters. We solve resulting PDE using an implicit finite difference scheme that ensures numerical stability. Calibration weekly case data from February 2021 March 2022 reveals Ankara has exponent 0.4222, Istanbul 0.1932, Izmir 0.6085, indicating varied persistence characteristics. Distribution fitting shows Weibull best represents whereas two-component normal mixture suits Sensitivity analysis confirms key parameters, including duration, critically influence outcomes. These findings provide valuable insights policy planning, offering tailored forecasting tool epidemic management.

Language: Английский

---

Mathematical Contact Tracing Models for the COVID-19 Pandemic: A Systematic Review of the Literature

Healthcare, Journal Year: 2025, Volume and Issue: 13(8), P. 935 - 935

Published: April 18, 2025

Background: Contact tracing (CT) is a primary means of controlling infectious diseases, such as coronavirus disease 2019 (COVID-19), especially in the early months pandemic. Objectives: This work systematic review mathematical models used during COVID-19 pandemic that explicitly parameterise CT potential mitigator effects Methods: registered PROSPERO. A comprehensive literature search was conducted using PubMed, EMBASE, Cochrane Library, CINAHL, and Scopus databases. Two reviewers independently selected title/abstract, full text, data extraction, risk bias. Disagreements were resolved through discussion. The characteristics studies collected from each study. Results: total 53 articles out 2101 included. modelling main objective 23 studies, while remaining evaluated forecast transmission COVID-19. Most compartmental to simulate (26, 49.1%), others agent-based (16, 34%), branching processes (5, 9.4%), or other (6). applying consider separate compartment. Quarantine basic reproduction numbers also considered models. quality assessment scores ranged 13 26 28. Conclusions: Despite significant heterogeneity assumptions on relevant model parameters, this provides overview proposed evaluate pandemic, including non-pharmaceutical public health interventions CT. Prospero Registration: CRD42022359060.

Language: Английский

---

Ensemble machine learning framework for predicting maternal health risk during pregnancy

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Sept. 14, 2024

Language: Английский

---

Deep Learning in COVID-19 Diagnosis, Prognosis and Treatment Selection

Mathematics, Journal Year: 2023, Volume and Issue: 11(6), P. 1279 - 1279

Published: March 7, 2023

Deep learning is a sub-discipline of artificial intelligence that uses neural networks, machine technique, to extract patterns and make predictions from large datasets. In recent years, it has achieved rapid development widely used in numerous disciplines with fruitful results. Learning valuable information complex, high-dimensional, heterogeneous biomedical data key challenge transforming healthcare. this review, we provide an overview emerging deep-learning techniques, COVID-19 research involving deep learning, concrete examples methods diagnosis, prognosis, treatment management. can process medical imaging data, laboratory test results, other relevant diagnose diseases judge disease progression even recommend plans drug-use strategies accelerate drug improve quality. Furthermore, help governments develop proper prevention control measures. We also assess the current limitations challenges therapy precision for COVID-19, including lack phenotypically abundant need more interpretable models. Finally, discuss how barriers be overcome enable future clinical applications learning.

Language: Английский

---

StatModPredict: A User-Friendly R-Shiny Interface for Fitting and Forecasting with Statistical Models

Published: Jan. 1, 2024

Many fields, such as public health, employ statistical time series models for real-time and retrospective forecasting efforts. However, their successful implementation often requires extensive programming knowledge. This paper presents StatModPredict, a user-friendly R-Shiny interface fitting, forecasting, evaluating, comparing the results from ARIMA, GLM, GAM, Facebook's Prophet models. Utilizing any data, users can customize model parameters to obtain fits, forecasts, evaluation statistics compare "outside" Therefore, StatModPredict facilitates by removing all requirements, facilitating timely efficient decisions obtained through

Language: Английский

---

Comparison of Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) for Estimating the Susceptible-Exposed-Infected-Recovered (SEIR) Model Parameter Values

Journal of Information Systems Engineering and Business Intelligence, Journal Year: 2024, Volume and Issue: 10(2), P. 290 - 301

Published: June 28, 2024

Background: The most commonly used mathematical model for analyzing disease spread is the Susceptible-Exposed-Infected-Recovered (SEIR) model. Moreover, dynamics of SEIR depend on several factors, such as parameter values. Objective: This study aimed to compare two optimization methods, namely genetic algorithm (GA) and particle swarm (PSO), in estimating values, infection, transition, recovery, death rates. Methods: GA PSO algorithms were compared estimate values fitness value was calculated from error between actual data cumulative positive COVID-19 cases numerical solution Furthermore, using fourth-order Runge-Kutta (RK-4), while obtained dataset province Jakarta, Indonesia. Two datasets then success each algorithm, namely, Dataset 1, representing initial interval COVID-19, 2, an where there a high increase cases. Results: Four parameters estimated, infection rate, transition recovery due disease. In smallest method, 8.9%, occurred when , 7.5%. 31.21%, 3.46%. Conclusion: Based estimation results Datasets 1 had better fitting than GA. showed more robust provided could adapt trends epidemic. Keywords: Genetic Particle optimization, model, Parameter estimation.

Language: Английский

---