A Dual Long Short-Term Memory Model in Forecasting the Number of COVID-19 Infections DOI Open Access
Jung-Pin Lai, Ping‐Feng Pai

Electronics, Год журнала: 2023, Номер 12(3), С. 759 - 759

Опубликована: Фев. 2, 2023

Since the outbreak of Coronavirus Disease 2019 (COVID-19), spread epidemic has been a major international public health issue. Hence, various forecasting models have used to predict infectious disease. In general, problems often involve prediction accuracy decreasing as horizon increases. Thus, extend without performance or prediction, this study developed Dual Long Short-Term Memory (LSTM) with Genetic Algorithms (DULSTMGA) model. The model employed predicted values generated by LSTM in short-forecasting horizons inputs for long-term rolling manner. algorithms were applied determine parameters models, allowing increase long short-term was accurate. addition, compartment utilized simulate state COVID-19 and generate numbers cases. Infectious cases three countries examine feasibility proposed DULSTMGA Numerical results indicated that could obtain satisfactory superior many previous studies terms mean absolute percentage error. Therefore, designed is feasible promising alternative number

Язык: Английский

Air quality index forecast in Beijing based on CNN-LSTM multi-model DOI
Jiaxuan Zhang,

Shunyong Li

Chemosphere, Год журнала: 2022, Номер 308, С. 136180 - 136180

Опубликована: Сен. 1, 2022

Язык: Английский

Процитировано

121
Machine Learning-Based Research for COVID-19 Detection, Diagnosis, and Prediction: A Survey DOI Open Access
Yassine Meraihi, Asma Benmessaoud Gabis, Seyedali Mirjalili

и другие.

SN Computer Science, Год журнала: 2022, Номер 3(4)

Опубликована: Май 12, 2022

Язык: Английский

Процитировано

51
Deep learning for Covid-19 forecasting: State-of-the-art review. DOI
Firuz Kamalov, Khairan Rajab, Aswani Kumar Cherukuri

и другие.

Neurocomputing, Год журнала: 2022, Номер 511, С. 142 - 154

Опубликована: Сен. 8, 2022

Язык: Английский

Процитировано

38
Machine Learning, Deep Learning, and Mathematical Models to Analyze Forecasting and Epidemiology of COVID-19: A Systematic Literature Review DOI Open Access
Farrukh Saleem, Abdullah Alghamdi, Madini O. Alassafi

и другие.

International Journal of Environmental Research and Public Health, Год журнала: 2022, Номер 19(9), С. 5099 - 5099

Опубликована: Апрель 22, 2022

COVID-19 is a disease caused by SARS-CoV-2 and has been declared worldwide pandemic the World Health Organization due to its rapid spread. Since first case was identified in Wuhan, China, battle against this deadly started disrupted almost every field of life. Medical staff laboratories are leading from front, but researchers various fields governmental agencies have also proposed healthy ideas protect each other. In article, Systematic Literature Review (SLR) presented highlight latest developments analyzing data using machine learning deep algorithms. The number studies related Machine Learning (ML), Deep (DL), mathematical models discussed research shown significant impact on forecasting spread COVID-19. results discussion study based PRISMA (Preferred Reporting Items for Reviews Meta-Analyses) guidelines. Out 218 articles selected at stage, 57 met criteria were included review process. findings therefore associated with those studies, which recorded that CNN (DL) SVM (ML) most used algorithms forecasting, classification, automatic detection. importance compartmental useful measuring epidemiological features Current suggest it will take around 1.7 140 days epidemic double size studies. 12 estimates basic reproduction range 0 7.1. main purpose illustrate use ML, DL, can be helpful generate valuable solutions higher authorities healthcare industry reduce epidemic.

Язык: Английский

Процитировано

34
Higher Order Dynamic Mode Decomposition-Based Timeseries Forecasting for Covid-19 DOI

A. Aadharsh Aadhithya,

Vishnu Radhakrishnan,

Jayanth Mohan

и другие.

Springer series in reliability engineering, Год журнала: 2025, Номер unknown, С. 283 - 305

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
An ensemble n-sub-epidemic modeling framework for short-term forecasting epidemic trajectories: Application to the COVID-19 pandemic in the USA DOI Creative Commons
Gerardo Chowell, Sushma Dahal, Amna Tariq

и другие.

PLoS Computational Biology, Год журнала: 2022, Номер 18(10), С. e1010602 - e1010602

Опубликована: Окт. 6, 2022

We analyze an ensemble of n -sub-epidemic modeling for forecasting the trajectory epidemics and pandemics. These approaches, models that integrate sub-epidemics to capture complex temporal dynamics, have demonstrated powerful capability. This framework can characterize epidemic patterns, including plateaus, resurgences, waves characterized by multiple peaks different sizes. systematically assess their calibration short-term performance in forecasts COVID-19 pandemic USA from late April 2020 February 2022. compare with two commonly used statistical ARIMA models. The best fit sub-epidemic model three constructed using top-ranking consistently outperformed terms weighted interval score (WIS) coverage 95% prediction across 10-, 20-, 30-day forecasts. In our forecasts, average WIS ranged 377.6 421.3 models, whereas it 439.29 767.05 Across 98 incorporating top four ranking (Ensemble(4)) (log) 66.3% time, model, 69.4% time ahead WIS. Ensemble(4) yielded metrics account uncertainty predictions. be readily applied investigate spread pandemics beyond COVID-19, as well other dynamic growth processes found nature society would benefit

Язык: Английский

Процитировано

18
Prediction and Comparison of In-Vehicle CO2 Concentration Based on ARIMA and LSTM Models DOI Creative Commons
Jie Han,

Han Lin,

Zhenkai Qin

и другие.

Applied Sciences, Год журнала: 2023, Номер 13(19), С. 10858 - 10858

Опубликована: Сен. 29, 2023

An increase in the carbon dioxide (CO2) concentration within a vehicle can lead to decrease air quality, resulting numerous adverse effects on human body. Therefore, it is very important know in-vehicle CO2 level and accurately predict change. The purpose of this research investigate levels CO2, comparing accuracy an autoregressive integrated moving average (ARIMA) model long short-term memory (LSTM) predicting change concentration. We conducted field test obtain original data while driving, establishing prediction with ARIMA LSTM. selected mean absolute percentage error (MAPE) root squared (RMSE) as evaluation indicators. findings indicate following: (1) With windows closed recirculation ventilation mode activated, increases rapidly. During testing, accumulation rates were measured at 1.43 ppm/s for one occupant 3.52 three occupants 20 min driving period. Average concentrations exceeded 1000 ppm, so recommended improve promptly driving. (2) MAPE LSTM results are 0.46% 0.56%, respectively. RMSE 19.62 ppm 22.76 demonstrate that both models effectively forecast changes vehicle’s interior environment but better than provide theoretical guidance traffic safety managers selecting suitable establish effective warning control system.

Язык: Английский

Процитировано

9
Analysis and Forecasting of Area Under Cultivation of Rice in India: Univariate Time Series Approach DOI Open Access
Niveditha Annamalai,

Amala Johnson

SN Computer Science, Год журнала: 2023, Номер 4(2)

Опубликована: Фев. 3, 2023

Язык: Английский

Процитировано

8
Applications of time series analysis in epidemiology: Literature review and our experience during COVID-19 pandemic DOI Open Access
L Tomov, Lyubomir Chervenkov, Dimitrina Miteva

и другие.

World Journal of Clinical Cases, Год журнала: 2023, Номер 11(29), С. 6974 - 6983

Опубликована: Окт. 13, 2023

Time series analysis is a valuable tool in epidemiology that complements the classical epidemiological models two different ways: Prediction and forecast. related to explaining past current data based on various internal external influences may or not have causative role. Forecasting an exploration of possible future values predictive ability model hypothesized and/or influences. The time approach has advantage being easier use (in cases more straightforward linear such as Auto-Regressive Integrated Moving Average). Still, it limited forecasting time, unlike Susceptible-Exposed-Infectious-Removed. Its applicability comes from its better accuracy for short-term prediction. In basic form, does assume much theoretical knowledge mechanisms spreading mutating pathogens reaction people regulatory structures (governments, companies, etc. ). Instead, estimates directly. allows testing hypotheses factors positively negatively contribute pandemic spread; be school closures, emerging variants, It can used mortality hospital risk estimation new cases, seroprevalence studies, assessing properties estimating excess relationship with pandemic.

Язык: Английский

Процитировано

8
Development of a novel dynamic nosocomial infection risk management method for COVID-19 in outpatient settings DOI Creative Commons

Yuncong Wang,

Lihong Wang, Wenhui Ma

и другие.

BMC Infectious Diseases, Год журнала: 2024, Номер 24(1)

Опубликована: Фев. 19, 2024

Abstract Background Application of accumulated experience and management measures in the prevention control coronavirus disease 2019 (COVID-19) has generally depended on subjective judgment epidemic intensity, with quality being uneven. The present study was designed to develop a novel risk system for COVID-19 infection outpatients, ability provide accurate hierarchical based estimated infection. Methods Infection using an auto regressive integrated moving average model (ARIMA). Weekly surveillance data influenza-like-illness (ILI) among outpatients at Xuanwu Hospital Capital Medical University Baidu search downloaded from Index 2021 22 were used fit ARIMA model. this estimate evaluated by determining mean absolute percentage error (MAPE), Delphi process build consensus measures. selected reviewing published regulations, papers guidelines. Recommendations surface sterilization personal protection determined low high periods, these recommendations implemented predicted results. Results produced exact estimates both ILI engine data. MAPEs 20-week rolling forecasts datasets 13.65% 8.04%, respectively. Based two levels, methods provided guidelines disinfection. Criteria also established upgrading or downgrading strategies Conclusion These innovative methods, along model, showed efficient healthcare workers close contact infected patients, saving nearly 41% cost maintaining high-level enhancing respiratory infections.

Язык: Английский

Процитировано

3