Autism Disease Detection Using Transfer Learning Techniques: Performance Comparison Between Central Processing Unit vs Graphics Processing Unit Functions for Neural Networks

TL;DR

This study compares CPU and GPU performance in neural network-based autism detection from facial images, demonstrating GPU's superior speed and accuracy across multiple models and evaluation metrics.

Contribution

It introduces a comprehensive comparison of CPU versus GPU processing for neural network models in autism detection using facial images.

Findings

GPU outperforms CPU in all tests

Neural network accuracy improves on GPU

Execution time is significantly reduced on GPU

Abstract

Neural network approaches are machine learning methods that are widely used in various domains, such as healthcare and cybersecurity. Neural networks are especially renowned for their ability to deal with image datasets. During the training process with images, various fundamental mathematical operations are performed in the neural network. These operations include several algebraic and mathematical functions, such as derivatives, convolutions, and matrix inversions and transpositions. Such operations demand higher processing power than what is typically required for regular computer usage. Since CPUs are built with serial processing, they are not appropriate for handling large image datasets. On the other hand, GPUs have parallel processing capabilities and can provide higher speed. This paper utilizes advanced neural network techniques, such as VGG16, Resnet50, Densenet, Inceptionv3, Xception, Mobilenet, XGBOOST VGG16, and our proposed models, to compare CPU and GPU resources. We implemented a system for classifying Autism disease using face images of autistic and non-autistic children to compare performance during testing. We used evaluation matrices such as Accuracy, F1 score, Precision, Recall, and Execution time. It was observed that GPU outperformed CPU in all tests conducted. Moreover, the performance of the neural network models in terms of accuracy increased on GPU compared to CPU.