Filters








163 Hits in 14.6 sec

Forecasting a Moving Target: Ensemble Models for ILI Case Count Predictions [chapter]

Prithwish Chakraborty, Pejman Khadivi, Bryan Lewis, Aravindan Mahendiran, Jiangzhuo Chen, Patrick Butler, Elaine O. Nsoesie, Sumiko R. Mekaru, John S. Brownstein, Madhav V. Marathe, Naren Ramakrishnan
2014 Proceedings of the 2014 SIAM International Conference on Data Mining  
Finally, we present a novel matrix factorization approach using neighborhood embedding to predict flu case counts.  ...  For a realtime prediction system, we posit that one of the key challenges is to effectively handle the uncertainty associated with reports of flu activity.  ...  Advanced Research Projects Activity (IARPA) via Department of Interior National Business Center (DoI/NBC) contract number D12PC000337, the US Government is authorized to reproduce and distribute reprints for  ... 
doi:10.1137/1.9781611973440.30 dblp:conf/sdm/ChakrabortyKLMCBNMBMR14 fatcat:lun3c6gsyzao3fpoorbxygh2ea

Moving beyond the cost-loss ratio: Economic assessment of streamflow forecasts for a risk-averse decision maker

Simon Matte, Marie-Amélie Boucher, Vincent Boucher, Thomas-Charles Fortier Filion
2016 Hydrology and Earth System Sciences Discussions  
It is found that the economic value of a forecast for a risk-averse decision maker is closely linked to the forecast reliability in predicting the upper tail of the streamflow distribution.  ...  Another approach is the use of ensemble meteorological forecasts for precipitation and temperature, which are then provided as inputs to one or many hydrological model(s).  ...  The authors also thank the ECMWF for the development and maintenance of the TIGGE data portal allowing free access to meteorological ensemble forecasts for research purposes.  ... 
doi:10.5194/hess-2016-495 fatcat:ismtral55rbnzijaornautyqti

Moving beyond the cost–loss ratio: economic assessment of streamflow forecasts for a risk-averse decision maker

Simon Matte, Marie-Amélie Boucher, Vincent Boucher, Thomas-Charles Fortier Filion
2017 Hydrology and Earth System Sciences  
It is found that the economic value of a forecast for a risk-averse decision maker is closely linked to the forecast reliability in predicting the upper tail of the streamflow distribution.  ...  Another approach is the use of ensemble meteorological forecasts for precipitation and temperature, which are then provided as inputs to one or many hydrological model(s).  ...  The authors also thank the ECMWF for the development and maintenance of the TIGGE data portal allowing free access to meteorological ensemble forecasts for research purposes.  ... 
doi:10.5194/hess-21-2967-2017 fatcat:lijv3bwxqnganf42nety6ihxsq

A stacked ensemble method for forecasting influenza-like illness visit volumes at emergency departments

Arthur Novaes de Amorim, Rob Deardon, Vineet Saini, Shinya Tsuzuki
2021 PLoS ONE  
In this paper, we developed a stacked ensemble model that averages the predictions from various competing methodologies in the current frontier for ILI-related forecasts.  ...  We also constructed a back-of-the-envelope prediction interval for the stacked ensemble, which provides a conservative characterization of the uncertainty in the stacked ensemble predictions.  ...  Hussain Usman, Adrienne Macdonald and Jason Cabaj provided helpful input and feedback during the model development stage.  ... 
doi:10.1371/journal.pone.0241725 pmid:33750974 fatcat:jx2pidi37nd5lpamjxq6igbcoq

A Stacked ensemble method for forecasting influenza-like illness visit volumes at emergency departments [article]

Arthur Novaes de Amorim, Vineet Saini, Rob Deardon
2020 bioRxiv   pre-print
In this paper, we developed a stacked ensemble model that averages the predictions from various competing methodologies in the current frontier for ILI-related forecasts.  ...  We also constructed a back-of-the-envelope prediction interval for the stacked ensemble, which provides a conservative characterization of the uncertainty in the stacked ensemble predictions.  ...  Hussain Usman and Adrienne Macdonald provided helpful input and feedback 277 during the model development stage. We also thank Sherry Trithart and Shaun Malo 278 for data provision from ARTSSN.  ... 
doi:10.1101/2020.10.21.348417 fatcat:vpfqt2outvevrnidfnt54gqrq4

Forecasting Influenza Outbreaks in Boroughs and Neighborhoods of New York City

Wan Yang, Donald R. Olson, Jeffrey Shaman, Justin Lessler
2016 PLoS Computational Biology  
These forecasts are compared to an alternate system that predicts influenza for each borough or neighborhood in isolation.  ...  By identifying the optimal granularity for a given disease and host population, and matching surveillance and prediction efforts to this scale, response to emergent and recurrent outbreaks can be improved  ...  Acknowledgments We thank Robert Mathes and Ramona Lall of the Syndromic Surveillance Unit of the Bureau of Communicable Disease, New York City Department of Health and Mental Hygiene for preparing the  ... 
doi:10.1371/journal.pcbi.1005201 pmid:27855155 pmcid:PMC5113861 fatcat:u5okuoaspbhefea4pz6mn6yfhi

Using electronic health records and Internet search information for accurate influenza forecasting

Shihao Yang, Mauricio Santillana, John S. Brownstein, Josh Gray, Stewart Richardson, S. C. Kou
2017 BMC Infectious Diseases  
Our regularized multivariate regression model dynamically selects the most appropriate variables for flu prediction every week.  ...  We present a method that combines the information from these two data sources with historical flu activity to produce national flu forecasts for the United States up to 4 weeks ahead of the publication  ...  Acknowledgements The authors would like to thank David Harrington and Anna Zink for their helpful comments.  ... 
doi:10.1186/s12879-017-2424-7 pmid:28482810 pmcid:PMC5423019 fatcat:7yzhdmfgyfg7dp2brdfgyycs4y

Examining Deep Learning Models with Multiple Data Sources for COVID-19 Forecasting [article]

Lijing Wang, Aniruddha Adiga, Srinivasan Venkatramanan, Jiangzhuo Chen, Bryan Lewis, Madhav Marathe
2020 arXiv   pre-print
In order to incorporate the effects of multiple factors in COVID-19 spread, we consider multiple sources such as COVID-19 confirmed and death case count data and testing data for better predictions.  ...  Deep learning-based time series models for forecasting have recently gained popularity and have been successfully used for epidemic forecasting.  ...  suggestions related to epidemic modeling and response support.  ... 
arXiv:2010.14491v2 fatcat:axkpnt2yq5grbppj7cojk4fbqe

Forecasting national and regional influenza-like illness for the USA

Michal Ben-Nun, Pete Riley, James Turtle, David P. Bacon, Steven Riley, Gerardo Chowell
2019 PLoS Computational Biology  
Also, we tested a simple ensemble model for the 2016-17 season and found that it underperformed our subjective choice for all forecast targets.  ...  Here, we describe our participation in a weekly prospective ILI forecasting challenge for the United States for the 2016-17 season and subsequent evaluation of our performance.  ...  Acknowledgments We thank the organizers and participants of the CDC influenza challenge for helpful discussions. Author Contributions  ... 
doi:10.1371/journal.pcbi.1007013 pmid:31120881 pmcid:PMC6557527 fatcat:m36kbloav5eo5ddkyr5bywid5a

A systematic review of studies on forecasting the dynamics of influenza outbreaks

Elaine O. Nsoesie, John S. Brownstein, Naren Ramakrishnan, Madhav V. Marathe
2013 Influenza and Other Respiratory Viruses  
"A systematic review of studies on forecasting the dynamics of influenza outbreaks." Influenza and Other Respiratory Viruses 8 (3): 309-316.  ...  Research Projects Activity (IARPA) via Department of Interior National Business Center (DoI/NBC) contract number D12PC000337, and the US Government is authorized to reproduce and distribute reprints for  ...  Ong et al. 4 2010 ILI Weekly 2009 Singapore SEIR model with particle filtering Weekly case counts, peak timing, and duration Error Chao et al. 2 2010 CDC influenza case estimates  ... 
doi:10.1111/irv.12226 pmid:24373466 pmcid:PMC4181479 fatcat:dmqavzp6kbcd7b6pewoxcl6vmq

Chimeric forecasting: combining probabilistic predictions from computational models and human judgment [article]

Thomas McAndrew, Allison Codi, Juan Cambeiro, Tamay Besiroglu, David Braun, Eva Chen, Luis Enrique Urtubey de Cesaris, Damon Luk
2022 arXiv   pre-print
We find a chimeric ensemble compared to an ensemble including only computational models improves predictions of incident cases and shows similar performance for predictions of incident deaths.  ...  A traditional approach to forecasting fits a computational model to structured data and generates a predictive distribution.  ...  If a model missed a forecast in the past they are still included. If a model missed a forecast for the present survey for either cases or deaths than they are removed from the ensemble.  ... 
arXiv:2202.09820v1 fatcat:ohprj4cgtjfyzoo2l7ydfdlxse

Addressing delayed case reporting in infectious disease forecast modeling [article]

Lauren J Beesley and Dave Osthus and Sara Y Del Valle
2021 arXiv   pre-print
Due to delays in case reporting, however, forecasting models may often underestimate the current and future disease burden.  ...  This work provides intuition and guidance for handling delay in disease case reporting and may serve as a useful resource to inform practical infectious disease forecasting efforts.  ...  This work is approved for distribution under LA-UR-21-30640.  ... 
arXiv:2110.14533v1 fatcat:y6byurt53zey7oynswqguvikxa

COVID-19 and Influenza Joint Forecasts Using Internet Search Information in the United States [article]

Simin Ma, Shaoyang Ning, Shihao Yang
2022 arXiv   pre-print
Inspired by the inner-connection between influenza and COVID-19 activities, we propose ARGOX-Joint-Ensemble which allows us to combine historical influenza and COVID-19 disease forecasting models to a  ...  Moreover, our experiments demonstrate that our approach is successful in adapting past influenza forecasting models to the current pandemic, while improving upon previous COVID-19 forecasting models, by  ...  Ref [35] uses incidence patterns from past influenza seasons, COVID-19 time series information, and demographic covariates in a Generalized Linear Model to forecast next week's country-level case counts  ... 
arXiv:2202.02621v1 fatcat:ywxd3mebpzbvdk6n6qmeekkjdy

Forecasting influenza activity using self-adaptive AI model and multi-source data in Chongqing, China

Kun Su, Liang Xu, Guanqiao Li, Xiaowen Ruan, Xian Li, Pan Deng, Xinmi Li, Qin Li, Xianxian Chen, Yu Xiong, Shaofeng Lu, Li Qi (+14 others)
2019 EBioMedicine  
an innovative Self-adaptive AI Model (SAAIM), which was constructed by integrating Seasonal Autoregressive Integrated Moving Average model and XGBoost model using a self-adaptive weight adjustment mechanism  ...  SAAIM was applied to ILI% forecast in Chongqing from 2017 to 2018, of which the performance was compared with three previously available models on forecasting.  ...  allow for the recent historical performance of the ensemble model.  ... 
doi:10.1016/j.ebiom.2019.08.024 pmid:31477561 pmcid:PMC6796527 fatcat:mnmeo6biqvbm3k62lt7uu7qsqy

Improved forecasts of influenza-associated hospitalization rates with Google Search Trends

Sasikiran Kandula, Sen Pei, Jeffrey Shaman
2019 Journal of the Royal Society Interface  
In this paper, we describe a method to forecast hospitalization rates using a population level transmission model in combination with a data assimilation technique.  ...  These results suggest that the model-inference framework can provide reasonably accurate real-time forecasts of influenza hospitalizations; backcasts and nowcasts offer a way to improve system tolerance  ...  In effect, the lowest possible score for a forecast is 26.9. Endnote  ... 
doi:10.1098/rsif.2019.0080 pmid:31185818 pmcid:PMC6597779 fatcat:rlytrvtmtzgtpiq2fk43dwffiq
« Previous Showing results 1 — 15 out of 163 results