Real-Time Disease Outbreak Prediction Using GPU-Accelerated ML Models

EasyChair Preprint 13833

Abstract

The rapid detection and prediction of disease outbreaks are critical for effective public health responses and mitigating the impact of epidemics. This study explores the implementation of GPU-accelerated machine learning (ML) models to enhance real-time disease outbreak prediction. Leveraging the parallel processing capabilities of Graphics Processing Units (GPUs), we develop and optimize advanced ML algorithms capable of analyzing vast and complex epidemiological data at unprecedented speeds. Our approach integrates diverse data sources, including social media trends, environmental factors, and healthcare reports, to construct a robust predictive framework. By employing deep learning techniques and ensemble methods, our models achieve high accuracy in forecasting outbreaks and identifying potential hotspots. The results demonstrate significant improvements in processing times and predictive performance compared to traditional CPU-based models. This research highlights the potential of GPU-accelerated ML models in transforming epidemiological surveillance and public health decision-making, ultimately contributing to more timely and effective interventions during disease outbreaks.

Keyphrases: Accelerated sequence analysis, Bioinformatic algorithms, Computational Proteomics, Computational genomics, Deep learning in bioinformatics, GPU-accelerated machine learning, GPU-based bioinformatics, Genomic data processing, High Performance Computing, Machine learning in computational biology

@booklet{EasyChair:13833,
  author    = {Abey Litty},
  title     = {Real-Time Disease Outbreak Prediction Using GPU-Accelerated ML Models},
  howpublished = {EasyChair Preprint 13833},
  year      = {EasyChair, 2024}}