| Issue |
E3S Web Conf.
Volume 399, 2023
International Conference on Newer Engineering Concepts and Technology (ICONNECT-2023)
|
|
|---|---|---|
| Article Number | 09002 | |
| Number of page(s) | 9 | |
| Section | Life Science | |
| DOI | https://doi.org/10.1051/e3sconf/202339909002 | |
| Published online | 12 July 2023 | |
Comparison of Dense Net and over Logistic Regression in Predicting Leukemia Classification with Improved Accuracy
1 Research Scholar, Department of Medical Instrumentation, Saveetha School of Engineering, saveetha Institute of Medical and Technical Sciences, Saveetha University, Chennai, Tamilnadu, India
2 Project guide, Department of Medical Instrumentation, Saveetha School of Engineering, saveetha Institute of Medical and Technical Sciences, Saveetha University, Chennai, Tamilnadu, India
* Corresponding author: bitmist2017@gmail.com
This study compares the performance of densenet and support vector machines (SVMs) in the diagnosis of leukemia disease, with the aim of improving the accuracy of the classification results. Materials and Method The Kaggle website is where the dataset was found. The dataset consists of 20 samples per group in JPG files with a resolution of 96 dpi and 512×512 pixel size.The sample size is determined using a pretest power of 80%, a threshold of 0.05, and a confidence interval of 95%. Results: For leukemia, dense net is 96.5%, whereas logistic regression is 89%. The significance levels for Densenet and logistic regression are data with p=.000 (p<0.05) statistical significance difference respectively. Conclusion: Based on the findings, I believe that densenet performs superior to logistic regression.
Key words: Novel-Accuracy / Dense Net / Disease / Leukemia / Logistic Regression / Machine Learning / Red Blood Cells / White Blood Cells
© The Authors, published by EDP Sciences, 2023
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.