A novel lightweight deep learning model based on SqueezeNet architecture for viral lung disease classification in X-ray and CT images

International Journal of Computational and Experimental Science and Engineering, Год журнала: 2024, Номер 10(4)

Опубликована: Окт. 8, 2024

COVID-19 has affected hundreds of millions individuals, seriously harming the global population’s health, welfare, and economy. Furthermore, health facilities are severely overburdened due to record number cases, which makes prompt accurate diagnosis difficult. Automatically identifying infected individuals promptly placing them under special care is a critical step in reducing burden such issues. Convolutional Neural Networks (CNN) other machine learning techniques can be utilized address this demand. Many existing Deep models, albeit producing intended outcomes, were developed using parameters, making unsuitable for use on devices with constrained resources. Motivated by fact, novel lightweight deep model based Efficient Channel Attention (ECA) module SqueezeNet architecture, work identify patients from chest X-ray CT images initial phases disease. After proposed was tested different datasets two, three four classes, results show its better performance over models. The outcomes shown that, comparison current heavyweight our models reduced cost memory requirements computing resources dramatically, while still achieving comparable performance. These support notion that help diagnose Covid-19 being easily implemented low-resource low-processing devices.

Язык: Английский

---

Interpretable COVID-19 chest X-ray detection based on handcrafted feature analysis and sequential neural network

Computers in Biology and Medicine, Год журнала: 2025, Номер 186, С. 109659 - 109659

Опубликована: Янв. 22, 2025

Язык: Английский

---

Attention induced multi-head convolutional neural network organization with MobileNetv1 transfer learning and COVID-19 diagnosis using jellyfish search optimization process on chest X-ray images

Biomedical Signal Processing and Control, Год журнала: 2024, Номер 93, С. 106133 - 106133

Опубликована: Март 2, 2024

Язык: Английский

---

TfrAdmCov: a robust transformer encoder based model with Adam optimizer algorithm for COVID-19 mutation prediction

Connection Science, Год журнала: 2024, Номер 36(1)

Опубликована: Июнь 12, 2024

The development of vaccines and drugs is very important in combating the coronavirus disease 2019 (COVID-19) virus. effectiveness these developed has decreased as a result mutation COVID-19 Therefore, it to combat mutations. majority studies published literature are other than prediction. We focused on this gap study. This study proposes robust transformer encoder based model with Adam optimizer algorithm called TfrAdmCov for Our main motivation predict mutations occurring virus using proposed model. experimental results have shown that outperforms both baseline models several state-of-the-art models. reached accuracy 99.93%, precision 100.00%, recall 97.38%, f1-score 98.67% MCC 98.65% testing dataset. Moreover, evaluate performance model, we carried out prediction influenza A/H3N2 HA obtained promising drugs.

Язык: Английский

---

A novel soft computing based efficient feature selection approach for timely identification of COVID-19 infection using chest computed tomography images: a human centered intelligent clinical decision support system

Multimedia Tools and Applications, Год журнала: 2024, Номер unknown

Опубликована: Июнь 12, 2024

Язык: Английский

---

IncV3-BLSTM: a multi-label inceptionV3-BLSTM model for predicting potential side effects of COVID-19 drugs

Annals of Mathematics and Artificial Intelligence, Год журнала: 2025, Номер unknown

Опубликована: Март 31, 2025

Язык: Английский

---

Computer Vision and Transfer Learning for Grading of Egyptian Cotton Fibres

AgriEngineering, Год журнала: 2025, Номер 7(5), С. 127 - 127

Опубликована: Апрель 22, 2025

Egyptian cotton fibres have worldwide recognition due to their distinct quality and luxurious textile products known by the “Egyptian Cotton“ label. However, fibre trading in Egypt still depends on human grading of quality, which is resource-intensive faces challenges terms subjectivity expertise requirements. This study investigates colour vision transfer learning classify grade five long (Giza 86, Giza 90, 94) extra-long 87 96) staple cultivars. Five Convolutional Neural networks (CNNs)—AlexNet, GoogleNet, SqueezeNet, VGG16, VGG19—were fine-tuned, optimised, tested independent datasets. The highest classifications were 75.7%, 85.0%, 80.0%, 77.1%, 90.0% for 87, 94, 96, respectively, with F1-Scores ranging from 51.9–100%, 66.7–100%, 42.9–100%, 40.0–100%, 80.0–100%. Among CNNs, AlexNet, VGG19 outperformed others. Fused CNN models further improved classification accuracy up 7.2% all cultivars except 87. These results demonstrate feasibility developing a fast, low-cost, low-skilled system that overcomes inconsistencies limitations manual early stages Egypt.

Язык: Английский

---

Metaheuristic optimizers integrated with vision transformer model for severity detection and classification via multimodal COVID-19 images

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 22, 2025

Язык: Английский

---

The Role of Advanced Machine Learning in COVID-19 Medical Imaging: A Technical Review

Results in Engineering, Год журнала: 2025, Номер unknown, С. 105154 - 105154

Опубликована: Май 1, 2025

Язык: Английский

---

Rapid and accurate classification of Covid-19 severity in CT scans using DRIEN model and advanced feature selection

Biomedical Signal Processing and Control, Год журнала: 2025, Номер 109, С. 108052 - 108052

Опубликована: Май 8, 2025

Язык: Английский

---