Real-Time Pathogen Detection Using GPU-Accelerated Machine Learning

EasyChair Preprint 14036

Abstract

Recent advancements in machine learning (ML) and GPU-accelerated computing have revolutionized real-time pathogen detection, offering rapid and accurate identification of microbial threats. This paper explores the integration of GPU-accelerated ML models to enhance the efficiency and speed of pathogen detection processes. By leveraging GPU capabilities, complex genomic data analysis can be streamlined, enabling timely identification of pathogens from diverse biological samples. Key techniques such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are implemented to analyze genomic sequences, improving both sensitivity and specificity in detection. Case studies highlight the application of GPU-accelerated ML in various domains, illustrating its potential to transform infectious disease management and public health surveillance. This research underscores the pivotal role of GPU-accelerated machine learning in advancing real-time pathogen detection capabilities, contributing to enhanced preparedness and response strategies against emerging infectious diseases.

Keyphrases: Convolutional Neural Networks (CNNs), Machine Learning (ML), Recurrent Neural Networks (RNNs)

@booklet{EasyChair:14036,
  author    = {Abi Cit},
  title     = {Real-Time Pathogen Detection Using GPU-Accelerated Machine Learning},
  howpublished = {EasyChair Preprint 14036},
  year      = {EasyChair, 2024}}