Enhancing Pneumonia Segmentation in Lung Radiographs: A Jellyfish Search Optimizer Approach

Mathematics, Journal Year: 2023, Volume and Issue: 11(20), P. 4363 - 4363

Published: Oct. 20, 2023

Segmentation of pneumonia on lung radiographs is vital for the precise diagnosis and monitoring disease. It enables healthcare professionals to locate quantify extent infection, guide treatment decisions, improve patient care. One most-employed approaches effectively segment in treat it as an optimization task. By formulating problem this manner, possible use interesting capabilities metaheuristic methods determine optimal segmentation solution. Although these produce results, they frequently suboptimal solutions owing lack exploration search space. In paper, a new method segmenting introduced. The algorithm based jellyfish optimizer (JSO), which characterized by its excellent global capability robustness. This uses energy curve cross-entropy cost function that penalizes misclassified pixels more heavily, leading sharper focus regions where errors occur. particularly important because allows accurate delineation objects or interest. To validate our proposed approach, we conducted extensive testing most widely available datasets. results were compared with those obtained using other established techniques. evaluation demonstrate approach consistently outperforms at levels 8, 16, 32, difference than 10%.

Language: Английский

Malaria cell identification using improved machine learning and modified deep learning architecture

Indonesian Journal of Electrical Engineering and Computer Science, Journal Year: 2024, Volume and Issue: 34(3), P. 2078 - 2078

Published: April 5, 2024

Malaria continues to be a serious problem for public health because of its occurrence in tropical and subtropical areas with inadequate healthcare systems few resources. For prompt intervention treatment malaria, effective precise diagnosis is essential. Professional pathologists examine blood smear films by hand get microscopic another way they will do rapid antigen malaria test which produces the result 50% accuracy. Convolutional neural network (CNN) type deep learning (DL) model that has been effectively used variety image recognition applications. Our suggested approach uses, improved machine (IML) methods like support vector (SVM)+principal component analysis (PCA) fit, SVM+t-distributed stochastic neighbor embedding (t-SNE) CNN architecture an accuracy 86.23%, 88.27%, 97.16% respectively, combine feature extraction, data augmentation, modify layers including SVM algorithm final layer architecture. The proposed method significantly reduce pathologists' burden automating identification improving resourceconstrained contexts

Language: Английский

Development of an Optimized Pneumonia Classification Model from Chest X-ray Images

Published: Dec. 6, 2024

Language: Английский