Epicasting: An Ensemble Wavelet Neural Network (EWNet) for Forecasting Epidemics

  title={Epicasting: An Ensemble Wavelet Neural Network (EWNet) for Forecasting Epidemics},
  author={Madhurima Panja and Tanujit Chakraborty and Uttam Kumar and Nan Liu},
—Infectious diseases remain among the top contribu-tors to human illness and death worldwide, among which many diseases produce epidemic waves of infection. The unavailability of specific drugs and ready-to-use vaccines to prevent most of these epidemics makes the situation worse. These force public health officials and policymakers to rely on early warning systems generated by reliable and accurate forecasts of epidemics. Accurate forecasts of epidemics can assist stakeholders in tailoring… 
3 Citations

Figures and Tables from this paper

Knowledge-based Deep Learning for Modeling Chaotic Systems

This paper considers extreme events and their dynamics and proposes elegant models based on deep neural networks, called knowledge-based deep learning (KDL), which can learn the complex patterns governing chaotic systems by jointly training on real and simulated data directly from the dynamics and their differential equations.

W-Transformers : A Wavelet-based Transformer Framework for Univariate Time Series Forecasting

A novel framework for univariate time series representation learning based on the wavelet-based transformer encoder architecture and call it W-Transformer, which demonstrates that it performs, on average, better than the baseline forecasters for short-term and long-term forecasting, even for datasets that consist of only a few hundred training samples.

A Comparative Analysis of the Choice of Mother Wavelet Functions Affecting the Accuracy of Forecasts of Daily Balances in the Treasury Single Account

Improving the accuracy of cash flow forecasting in the TSA is key to fulfilling government payment obligations, minimizing the cost of maintaining the cash reserve, providing the absence of



DEFSI: Deep Learning Based Epidemic Forecasting with Synthetic Information

This work proposes DEFSI (Deep Learning Based Epidemic Forecasting with Synthetic Information), an epidemic forecasting framework that integrates the strengths of artificial neural networks and causal methods that significantly outperforms the other methods for short-term ILI forecasting at the state level.

Phenomenological forecasting of disease incidence using heteroskedastic Gaussian processes: a dengue case study

This paper shows that the GP approach generally outperforms a more classical generalized linear (autoregressive) model (GLM) that was developed to utilize abundant covariate information and illustrates variations of the method(s) on the two benchmark locales.

An open challenge to advance probabilistic forecasting for dengue epidemics

An open collaborative forecasting challenge to assess probabilistic forecasts for seasonal epidemics of dengue, a major global public health problem, revealed that average forecast skill was lower for models including biologically meaningful data and mechanisms and that both multimodel and multiteam ensemble forecasts consistently outperformed individual model forecasts.

Forecasting dengue epidemics using a hybrid methodology

The results of this study indicate that dengue cases can be accurately forecasted over a sufficient time period using the proposed hybrid methodology.

An Interpretable Probabilistic Autoregressive Neural Network Model for Time Series Forecasting

This work introduces an interpretable probabilistic autoregressive neural network model for an explainable, scalable, and “white box-like” framework that can handle a wide variety of irregular time series data (e.g., nonlinearity and nonstationarity).

Detection, forecasting and control of infectious disease epidemics: modelling outbreaks in humans, animals and plants

The questions pertinent to, and approaches used by, epidemiological modellers of human, animal and plant pathogens are compared, and it is argued that more inter-disciplinary collaboration would enhance each of the related disciplines.

Parameter identification for a stochastic SEIRS epidemic model: case study influenza

The local lagged adapted generalized method of moments is used to identify the time-dependent disease transmission rate and time- dependent noise for the stochastic susceptible, exposed, infectious, temporarily immune, susceptible disease model (SEIRS) with vital rates.

Improving probabilistic infectious disease forecasting through coherence

A novel algorithm is proposed that transforms a set of independent forecast distributions to obey the geographical constraint that respects the correlation structure between geographical units, and shows consistent improvement across 90% of models and that held when stratified by targets and test seasons.

Nowcasting of COVID-19 Confirmed Cases: Foundations, Trends, and Challenges

Evidence is provided to show that there is no universal method available that can accurately forecast pandemic data and forecasters' predictions are useful for the effective allocation of healthcare resources and will act as an early-warning system for government policymakers.