Guha, S and Kodipalli, A and Rao, T (2023) Computational Deep Learning Models for Detection of COVID-19 Using Chest X-Ray Images. In: Lecture Notes in Electrical Engineering, 25- 26 February 2022, Bengaluru, pp. 291-306.
Full text not available from this repository.Abstract
Traditional deep learning architectures after the AlexNet have added more layers to achieve higher accuracy. However, with increasing number of layers, we are likely to encounter vanishing/exploding gradient problems in these architectures which significantly impact the training performance. This was solved by the introduction of residual networks which make use of “skip connections” by adding the output from the previous layer to the layer ahead. ResNets are often combined with the Inception v4 model and was first used by Google researchers as Inception-ResNet. Inception v4 aimed to reduce the complexity of Inception v3 model which gave the state-of-the-art accuracy on ILSVRC 2015 challenge. The initial set of layers before the Inception block in Inception v4, referred to as “stem of the architecture,” was modified to make it more uniform. This model can be trained without partition of replicas unlike the previous versions of inceptions which required different replica in order to fit in memory. This architecture uses memory optimization on back propagation to reduce the memory requirement. In this paper, we propose two approaches for detection of COVID-19 using chest X-ray images by implementing ResNet16 and Inception v4 and providing a comparison of their performances.
| Item Type: | Conference Paper |
|---|---|
| Publication: | Lecture Notes in Electrical Engineering |
| Publisher: | Springer Science and Business Media Deutschland GmbH |
| Additional Information: | The copyright for this article belongs to Springer Science and Business Media Deutschland GmbH. |
| Keywords: | Backpropagation; Deep learning; Learning systems; Memory architecture; Network architecture, Chest X-ray image; COVID-19 detection; Deep learning architecture; High-accuracy; Inception v4; Learning architectures; Learning models; Number of layers; Performance; Resnet 16, COVID-19 |
| Department/Centre: | Division of Interdisciplinary Sciences > Computational and Data Sciences Others |
| Date Deposited: | 27 Jan 2023 08:49 |
| Last Modified: | 27 Jan 2023 08:49 |
| URI: | https://eprints.iisc.ac.in/id/eprint/79536 |
Actions (login required)
 |
View Item |
