Optimization and Implementation of a Collaborative Learning Algorithm for an AI-Enabled Real-time Biomedical System

Sinchhean Phea,Jiangkun Wang,Zhishang Wang,Abderazek Ben Abdallah,D Roy,G Fragulis,H.A Cantu Campos

doi:10.1051/shsconf/202110204017

Abstract

Recent years have witnessed a rapid growth of Artificial Intelligence (AI) in biomedical fields. However, an accurate and secure system for pneumonia detection and diagnosis is urgently needed. We present the optimization and implementation of a collaborative learning algorithm for an AI-Enabled Real-time Biomedical System (AIRBiS), where a convolution neural network is deployed for pneumonia (i.e., COVID-19) image classification. With augmentation optimization, the federated learning (FL) approach achieves a high accuracy of 95.66%, which outperforms the conventional learning approach with an accuracy of 94.08%. Using multiple edge devices also reduces overall training time.

Highlights

Efficient and accurate diagnosis of biomedical signals and images plays a significant role in health care systems [1, 2]
As Convolution neural networks (CNNs) show promising performance in feature extraction and representation, they have become a favourable choice in current biomedical area [10, 11]
We propose to deploy collaborative learning algorithm for Artificial Intelligence (AI) Enabled Real-Time Biomedical System (AIRBiS) [12]

Summary

Introduction

Efficient and accurate diagnosis of biomedical signals and images plays a significant role in health care systems [1, 2]. In the conventional medical system, diagnosis is managed by doctors or experts. Such procedures usually take long time, and when there is rapid increase in the number of patients, the human experts face a big challenge of working effectively while avoiding medical errors [3, 4]. Convolution neural networks (CNNs) have been widely used in many studies, e.g., speech recognition and image classification [7,8,9]. As CNNs show promising performance in feature extraction and representation, they have become a favourable choice in current biomedical area [10, 11]

Results

Discussion

Conclusion