From Mushroom-Peaches to Disease Prediction: Deep Learning Approaches

Loukil, Zainab and Ali Mirza, Qublai Khan ORCID: 0000-0003-3403-2935 (2022) From Mushroom-Peaches to Disease Prediction: Deep Learning Approaches. In: 2022 9th International Conference on Future Internet of Things and Cloud (FiCloud). IEEE, pp. 119-133. ISBN 9781665493512

Text (Peer Reviewed Version) 11657 Loukil and Ali Mirza ( 2022) From_Mushroom-Peaches_to_Disease_Prediction_Deep_Learning_Approaches.pdf - Accepted Version Restricted to Repository staff only Available under License All Rights Reserved. Download (681kB)

Abstract

Recent years have seen a noticeable shift towards the use of automated mechanisms by medical professionals for disease identification with an aim to also eventually predict life threatening diseases. The use of Artificial Intelligence is at the centre of such automated approaches, generally powered by the magnitude of rich datasets of medical imaging. Current approaches involving Machine Learning and other associated technologies have shown promising results in this domain with somewhat accurate detection of certain diseases. However, there are limitations with respect to resource consumption and accurate detection and a significant lack of accurate prediction models. This paper presents a thorough analysis to understand the origins of disease detection through object localisation. Discussion in this paper is based on the identification of certain fruits and vegetables that have complicated visual attributes from machine’s perspective. This analogy is then used to enhance the understanding of disease detection that can lead to accurate prediction.

Item Type:	Book Section
Article Type:	Article
Uncontrolled Keywords:	Deep Learning; Object Detection; Autonomous Systems; Medical Imaging; Disease Prediction
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Schools and Research Institutes > School of Business, Computing and Social Sciences
Research Priority Areas:	Applied Business & Technology
Depositing User:	Kate Greenaway
Date Deposited:	21 Oct 2022 14:28
Last Modified:	31 Oct 2023 13:04
URI:	https://eprints.glos.ac.uk/id/eprint/11657

University Staff: Request a correction | Repository Editors: Update this record