FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367670335> ?p ?o ?g. }

• W4367670335 abstract "Abstract Background Influenza virus is responsible for a yearly epidemic in much of the world. To better predict short-term, seasonal variations in flu infection rates and possible mechanisms of yearly infection variation, we trained a Long Short-Term Memory (LSTM)-based deep neural network on historical Influenza-Like-Illness (ILI), climate, and population data. Methods Data were collected from the Centers for Disease Control and Prevention (CDC), the National Center for Environmental Information (NCEI), and the United States Census Bureau. The model was initially build in Python using the Keras API and tuned manually. We explored the roles of temperature, precipitation, local wind speed, population size, vaccination rate and vaccination efficacy. The model was validated using K-fold cross validation as well as forward chaining cross validation and compared to several standard algorithms. Finally, simulation data was generated in R and used for further exploration of the model. Results We found that temperature is the strongest predictor of ILI rates, but also found that precipitation increased the predictive power of the network. The model was able to outperform comparison models at several prediction points. Additionally, the model accurately predicted simulation data. To test the role of temperature in the network, we phase-shifted temperature in time and found a predictable reduction in prediction accuracy. Conclusions The results of this study confirm that flu forecasting may be effectively accomplished using architectures traditionally reserved for time series analysis, specifically LSTM-based neural networks. Additionally, this model provided insight into the week-to-week effects of climatic and biotic factors and revealed potential patterns in data series. Specifically, we found that temperature is the strongest predictor of seasonal flu infection rates. This information may prove to be especially important for flu forecasting given the uncertain long-term impact of the SARS-CoV-2 pandemic on seasonal influenza." @default.
• W4367670335 created "2023-05-03" @default.
• W4367670335 creator A5012684235 @default.
• W4367670335 creator A5046627918 @default.
• W4367670335 creator A5069108498 @default.
• W4367670335 creator A5088209745 @default.
• W4367670335 date "2023-05-02" @default.
• W4367670335 modified "2023-09-27" @default.
• W4367670335 title "LSTM-Based Recurrent Neural Network Provides Effective Short Term Flu Forecasting" @default.
• W4367670335 doi "https://doi.org/10.21203/rs.3.rs-2818892/v1" @default.
• W4367670335 hasPublicationYear "2023" @default.
• W4367670335 type Work @default.
• W4367670335 citedByCount "0" @default.
• W4367670335 crossrefType "posted-content" @default.
• W4367670335 hasAuthorship W4367670335A5012684235 @default.
• W4367670335 hasAuthorship W4367670335A5046627918 @default.
• W4367670335 hasAuthorship W4367670335A5069108498 @default.
• W4367670335 hasAuthorship W4367670335A5088209745 @default.
• W4367670335 hasBestOaLocation W43676703351 @default.
• W4367670335 hasConcept C111472728 @default.
• W4367670335 hasConcept C111919701 @default.
• W4367670335 hasConcept C119857082 @default.
• W4367670335 hasConcept C138885662 @default.
• W4367670335 hasConcept C144024400 @default.
• W4367670335 hasConcept C147168706 @default.
• W4367670335 hasConcept C149923435 @default.
• W4367670335 hasConcept C154945302 @default.
• W4367670335 hasConcept C2778136018 @default.
• W4367670335 hasConcept C2908647359 @default.
• W4367670335 hasConcept C41008148 @default.
• W4367670335 hasConcept C50644808 @default.
• W4367670335 hasConcept C519991488 @default.
• W4367670335 hasConceptScore W4367670335C111472728 @default.
• W4367670335 hasConceptScore W4367670335C111919701 @default.
• W4367670335 hasConceptScore W4367670335C119857082 @default.
• W4367670335 hasConceptScore W4367670335C138885662 @default.
• W4367670335 hasConceptScore W4367670335C144024400 @default.
• W4367670335 hasConceptScore W4367670335C147168706 @default.
• W4367670335 hasConceptScore W4367670335C149923435 @default.
• W4367670335 hasConceptScore W4367670335C154945302 @default.
• W4367670335 hasConceptScore W4367670335C2778136018 @default.
• W4367670335 hasConceptScore W4367670335C2908647359 @default.
• W4367670335 hasConceptScore W4367670335C41008148 @default.
• W4367670335 hasConceptScore W4367670335C50644808 @default.
• W4367670335 hasConceptScore W4367670335C519991488 @default.
• W4367670335 hasLocation W43676703351 @default.
• W4367670335 hasOpenAccess W4367670335 @default.
• W4367670335 hasPrimaryLocation W43676703351 @default.
• W4367670335 hasRelatedWork W2327204559 @default.
• W4367670335 hasRelatedWork W2587671147 @default.
• W4367670335 hasRelatedWork W2902723393 @default.
• W4367670335 hasRelatedWork W2961085424 @default.
• W4367670335 hasRelatedWork W3129254793 @default.
• W4367670335 hasRelatedWork W4281386417 @default.
• W4367670335 hasRelatedWork W4286629047 @default.
• W4367670335 hasRelatedWork W4306674287 @default.
• W4367670335 hasRelatedWork W4327831767 @default.
• W4367670335 hasRelatedWork W4224009465 @default.
• W4367670335 isParatext "false" @default.
• W4367670335 isRetracted "false" @default.
• W4367670335 workType "article" @default.