Research Article
Covid-19 Detection by Wavelet Entropy and Artificial Bee Colony
@INPROCEEDINGS{10.1007/978-3-031-18123-8_50, author={Jia-Ji Wang and Yangrong Pei and Liam O’Donnell and Dimas Lima}, title={Covid-19 Detection by Wavelet Entropy and Artificial Bee Colony}, proceedings={Multimedia Technology and Enhanced Learning. 4th EAI International Conference, ICMTEL 2022, Virtual Event, April 15-16, 2022, Proceedings}, proceedings_a={ICMTEL}, year={2022}, month={10}, keywords={Covid-19 detection Wavelet entropy Artificial bee colony}, doi={10.1007/978-3-031-18123-8_50} }- Jia-Ji Wang
Yangrong Pei
Liam O’Donnell
Dimas Lima
Year: 2022
Covid-19 Detection by Wavelet Entropy and Artificial Bee Colony
ICMTEL
Springer
DOI: 10.1007/978-3-031-18123-8_50
Abstract
Computer analysis of patients’ lung CT images has become a popular and effective way to diagnose COVID-19 patients amid repeated and evolving outbreaks. In this paper, wavelet entropy is used to extract features from CT images and integrate the information of various scales, including the characteristic signals of signals with transient components. Combined with the artificial bee colony optimization algorithm, we used the advantages of fewer parameters and simpler calculation to find the optimal solution and confirm COVID-19 positive. The use of K-fold cross validation allows the data set to avoid overfitting and unbalanced data set partition in small cases. The experimental results were compared with those of WE + BBO, GLCM-SVM, GLCM-ELM and WE-Jaya. Experimental data show that this method achieves our initial expectation.
