Covid-19 detection via deep neural network and occlusion sensitivity maps | Zendy

Muhammad Aminu | Zendy; Noor Atinah Ahmad | Zendy; Mohd Halim Mohd Noor | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Covid-19 detection via deep neural network and occlusion sensitivity maps

Author(s) -

Muhammad Aminu,

Noor Atinah Ahmad,

Mohd Halim Mohd Noor

Publication year - 2021

Publication title -

alexandria engineering journal

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.584

H-Index - 58

eISSN - 2090-2670

pISSN - 1110-0168

DOI - 10.1016/j.aej.2021.03.052

Subject(s) - grayscale , deep learning , artificial intelligence , covid-19 , transfer of learning , computer science , pattern recognition (psychology) , sensitivity (control systems) , deep neural networks , artificial neural network , machine learning , computer vision , image (mathematics) , engineering , medicine , disease , pathology , virology , electronic engineering , outbreak , infectious disease (medical specialty) , biology

Deep learning approaches have attracted a lot of attention in the automatic detection of Covid-19 and transfer learning is the most common approach. However, majority of the pre-trained models are trained on color images, which can cause inefficiencies when fine-tuning the models on Covid-19 images which are often grayscale. To address this issue, we propose a deep learning architecture called CovidNet which requires a relatively smaller number of parameters. CovidNet accepts grayscale images as inputs and is suitable for training with limited training dataset. Experimental results show that CovidNet outperforms other state-of-the-art deep learning models for Covid-19 detection.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research