A Power Efficient Solution to Determine Red Blood Cell Deformation Type Using Binarized DenseNet
Paper
Reza, Md Tanzim, Dipto, Shakib Mahmud, Parvez, Mohammad Zavid, Barua, Prabal Datta and Chakraborty, Subrata. 2023. "A Power Efficient Solution to Determine Red Blood Cell Deformation Type Using Binarized DenseNet." 2023 International Conference on Advances in Computing Research (ACR’23). Orlando, United States 08 - 10 May 2023 Switzerland. https://doi.org/10.1007/978-3-031-33743-7_21
| Paper/Presentation Title | A Power Efficient Solution to Determine Red Blood Cell Deformation Type Using Binarized DenseNet |
|---|---|
| Presentation Type | Paper |
| Authors | Reza, Md Tanzim, Dipto, Shakib Mahmud, Parvez, Mohammad Zavid, Barua, Prabal Datta and Chakraborty, Subrata |
| Journal or Proceedings Title | Proceedings of the 2023 International Conference on Advances in Computing Research (ACR’23) |
| Journal Citation | 700, pp. 246-256 |
| Number of Pages | 8 |
| Year | 2023 |
| Place of Publication | Switzerland |
| ISBN | 9783031337420 |
| Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-031-33743-7_21 |
| Web Address (URL) of Paper | https://link.springer.com/chapter/10.1007/978-3-031-33743-7_21 |
| Web Address (URL) of Conference Proceedings | https://link.springer.com/book/10.1007/978-3-031-33743-7 |
| Conference/Event | 2023 International Conference on Advances in Computing Research (ACR’23) |
| Event Details | 2023 International Conference on Advances in Computing Research (ACR’23) Delivery In person Event Date 08 to end of 10 May 2023 Event Location Orlando, United States |
| Abstract | Red Blood Cells (RBCs) play an important role in the welfare of human being as it helps to transport oxygen throughout the body. Different RBC-related diseases, for example, variants of anemias, can disrupt regular functionality and become life-threatening. Classification systems leveraging CNNs can be useful for automated diagnosis of RBC deformation, but the system can be quite resource-intensive in case the CNN architecture is large. The proposed approach provides an empirical analysis of the application of 28 and 45-layer Binarized DenseNet for identifying RBC deformations. According to our investigation, the accuracy of the 45-layer binarized variant can reach 93–94%, which is on par with the results of the conventional variant, which also achieves 93–94% accuracy. The 23-layer binarized variant, while not on par with the regular variant, also gets very close in terms of accuracy. Meanwhile, the 45-layer and 28-layer binarized variant only requires 9% and 11% storage space respectively to that of regular DenseNet, with potentially faster inference time. This optimized model can be useful since it can be easily deployed in resource-constrained devices, such as mobile phones and cheap embedded systems. |
| Keywords | Anemia; Binarized Neural Network; Larq; Red Blood Cell; Erythrocyte; DenseNet; Convolutional Neural Network |
| ANZSRC Field of Research 2020 | 461299. Software engineering not elsewhere classified |
| Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
| Series | Lecture Notes in Networks and Systems |
| Byline Affiliations | BRAC University, Bangladesh |
| Asia Pacific International College (APIC), Australia | |
| Torrens University | |
| Australian Catholic University | |
| Charles Sturt University | |
| School of Business | |
| Cogninet Australia, Australia | |
| University of New England |
Permalink -
https://research.usq.edu.au/item/z276w/a-power-efficient-solution-to-determine-red-blood-cell-deformation-type-using-binarized-densenet
Download files
Submitted Version
40
total views10
total downloads0
views this month0
downloads this month