Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Multilateral Attention-enhanced Deep Neural Network for Disease Outbreak Forecasting: A Case Study on COVID-19

Ashutosh Anshul, Jhalak Gupta, Mohammad Zia Ur Rehman, Nagendra Kumar

TL;DR

The paper tackles the challenge of forecasting pandemic spread by leveraging multi-source data (news, Google Trends, and statistics) through a transformer-based multi-head attention layer followed by GRU temporal modeling. The authors introduce MAG, a multilateral attention-enhanced GRU that fuses diverse inputs and yields superior COVID-19 case forecasts three days ahead, demonstrated on an India-focused dataset with RMSE/MAE improvements over several baselines. They also curate a comprehensive multi-source dataset and perform extensive ablation analyses to quantify the contribution of each data stream and the attention mechanism. The approach shows practical potential for proactive resource planning and policy-making by providing more accurate short-horizon outbreak predictions. The work highlights the value of integrating non-traditional signals with traditional epidemiological data in time-series forecasting.

Abstract

The worldwide impact of the recent COVID-19 pandemic has been substantial, necessitating the development of accurate forecasting models to predict the spread and course of a pandemic. Previous methods for outbreak forecasting have faced limitations by not utilizing multiple sources of input and yielding suboptimal performance due to the limited availability of data. In this study, we propose a novel approach to address the challenges of infectious disease forecasting. We introduce a Multilateral Attention-enhanced GRU model that leverages information from multiple sources, thus enabling a comprehensive analysis of factors influencing the spread of a pandemic. By incorporating attention mechanisms within a GRU framework, our model can effectively capture complex relationships and temporal dependencies in the data, leading to improved forecasting performance. Further, we have curated a well-structured multi-source dataset for the recent COVID-19 pandemic that the research community can utilize as a great resource to conduct experiments and analysis on time-series forecasting. We evaluated the proposed model on our COVID-19 dataset and reported the output in terms of RMSE and MAE. The experimental results provide evidence that our proposed model surpasses existing techniques in terms of performance. We also performed performance gain and qualitative analysis on our dataset to evaluate the impact of the attention mechanism and show that the proposed model closely follows the trajectory of the pandemic.

A Multilateral Attention-enhanced Deep Neural Network for Disease Outbreak Forecasting: A Case Study on COVID-19

TL;DR

The paper tackles the challenge of forecasting pandemic spread by leveraging multi-source data (news, Google Trends, and statistics) through a transformer-based multi-head attention layer followed by GRU temporal modeling. The authors introduce MAG, a multilateral attention-enhanced GRU that fuses diverse inputs and yields superior COVID-19 case forecasts three days ahead, demonstrated on an India-focused dataset with RMSE/MAE improvements over several baselines. They also curate a comprehensive multi-source dataset and perform extensive ablation analyses to quantify the contribution of each data stream and the attention mechanism. The approach shows practical potential for proactive resource planning and policy-making by providing more accurate short-horizon outbreak predictions. The work highlights the value of integrating non-traditional signals with traditional epidemiological data in time-series forecasting.

Abstract

The worldwide impact of the recent COVID-19 pandemic has been substantial, necessitating the development of accurate forecasting models to predict the spread and course of a pandemic. Previous methods for outbreak forecasting have faced limitations by not utilizing multiple sources of input and yielding suboptimal performance due to the limited availability of data. In this study, we propose a novel approach to address the challenges of infectious disease forecasting. We introduce a Multilateral Attention-enhanced GRU model that leverages information from multiple sources, thus enabling a comprehensive analysis of factors influencing the spread of a pandemic. By incorporating attention mechanisms within a GRU framework, our model can effectively capture complex relationships and temporal dependencies in the data, leading to improved forecasting performance. Further, we have curated a well-structured multi-source dataset for the recent COVID-19 pandemic that the research community can utilize as a great resource to conduct experiments and analysis on time-series forecasting. We evaluated the proposed model on our COVID-19 dataset and reported the output in terms of RMSE and MAE. The experimental results provide evidence that our proposed model surpasses existing techniques in terms of performance. We also performed performance gain and qualitative analysis on our dataset to evaluate the impact of the attention mechanism and show that the proposed model closely follows the trajectory of the pandemic.
Paper Structure (24 sections, 7 equations, 4 figures, 2 tables, 1 algorithm)

This paper contains 24 sections, 7 equations, 4 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Works
  3. Rule-based Time Series Forecasting
  4. Machine Learning-based Time Series Forecasting
  5. Deep Learning-based Time Series Forecasting
  6. COVID-19 Cases Prediction using Time Series Analysis
  7. Proposed Methodology
  8. News Encoding Generation
  9. Google Trends Data Extraction
  10. Statistical Feature Extraction
  11. Covid Case Prediction - MAG Model
  12. Transformer Encoder based Attention Layer
  13. GRU Layer
  14. Experimental Evaluations
  15. Experimental Setup
  16. ...and 9 more sections

Figures (4)

  • Figure 1: System architecture of the proposed model
  • Figure 2: Architecture of the MAG model
  • Figure 3: Graph showing actual data vs predicted data
  • Figure 4: Performance comparison graph over test data