Home // IARIA Congress 2024, The 2024 IARIA Annual Congress on Frontiers in Science, Technology, Services, and Applications // View article

A Comparative Analysis of CPU and GPU-Based Cloud Platforms for CNN Binary Classification

Authors:
Taieba Tasnim
Mohammad Rahman
Fan Wu

Keywords: CNN; CPU; GPU; Cloud.

Abstract:
This study explores how Convolutional Neural Network (CNN) model performs in binary classification tasks, particularly on a cloud platform configured with Central Processing Unit (CPU) and Graphics Processing Unit (GPU) resources. We conducted simulations of the CNN model for binary classification with different parameters to compare the CPU and GPU performances. We analyzed evaluation matrices, emphasizing both binary classification accuracy and training time. This analysis aims to facilitate the selection of a computational platform by considering both budgetary constraints and specific requirements.

Pages: 198 to 201

Copyright: Copyright (c) IARIA, 2024

Publication date: June 30, 2024

Published in: conference

ISBN: 978-1-68558-180-0

Location: Porto, Portugal

Dates: from June 30, 2024 to July 4, 2024