COVID-19 image classification using deep features and fractional-order marine predators algorithm; Scientific Reports; Vol. 10, iss. 1

Dades bibliogràfiques
Parent link:Scientific Reports
Vol. 10, iss. 1.— 2020.— [15364, 10 p.]
Autor corporatiu: Национальный исследовательский Томский политехнический университет Инженерная школа информационных технологий и робототехники
Altres autors: Sahlol A. T. Ahmed, Yousri D. Dalia, Ewees A. A. Ahmed, Al-qaness M. A. A. Mohammed, Damasevicius R. Robertas, Mokhamed Elsaed (Mohamed Abd Elaziz) A. M. Akhmed Mokhamed
Sumari:Title screen
Currently, we witness the severe spread of the pandemic of the new Corona virus, COVID-19, which causes dangerous symptoms to humans and animals, its complications may lead to death. Although convolutional neural networks (CNNs) is considered the current state-of-the-art image classification technique, it needs massive computational cost for deployment and training. In this paper, we propose an improved hybrid classification approach for COVID-19 images by combining the strengths of CNNs (using a powerful architecture called Inception) to extract features and a swarm-based feature selection algorithm (Marine Predators Algorithm) to select the most relevant features. A combination of fractional-order and marine predators algorithm (FO-MPA) is considered an integration among a robust tool in mathematics named fractional-order calculus (FO). The proposed approach was evaluated on two public COVID-19 X-ray datasets which achieves both high performance and reduction of computational complexity. The two datasets consist of X-ray COVID-19 images by international Cardiothoracic radiologist, researchers and others published on Kaggle. The proposed approach selected successfully 130 and 86 out of 51 K features extracted by inception from dataset 1 and dataset 2, while improving classification accuracy at the same time. The results are the best achieved on these datasets when compared to a set of recent feature selection algorithms. By achieving 98.7%, 98.2% and 99.6%, 99% of classification accuracy and F-Score for dataset 1 and dataset 2, respectively, the proposed approach outperforms several CNNs and all recent works on COVID-19 images.
Idioma:anglès
Publicat: 2020
Matèries:
Accés en línia:https://doi.org/10.1038/s41598-020-71294-2
Format: Electrònic Capítol de llibre
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=668323

MARC

LEADER 00000naa0a2200000 4500
001 668323
005 20260807071632.0
035 |a (RuTPU)RU\TPU\network\39548 
035 |a RU\TPU\network\39380 
090 |a 668323 
100 |a 20221004d2020 k||y0rusy50 ba 
101 0 |a eng 
135 |a drcn ---uucaa 
181 0 |a i  
182 0 |a b 
200 1 |a COVID-19 image classification using deep features and fractional-order marine predators algorithm  |f A. T. Sahlol, D. Yousri, A. A. Ewees [et al.] 
203 |a Text  |c electronic 
300 |a Title screen 
320 |a [References: 59 tit.] 
330 |a Currently, we witness the severe spread of the pandemic of the new Corona virus, COVID-19, which causes dangerous symptoms to humans and animals, its complications may lead to death. Although convolutional neural networks (CNNs) is considered the current state-of-the-art image classification technique, it needs massive computational cost for deployment and training. In this paper, we propose an improved hybrid classification approach for COVID-19 images by combining the strengths of CNNs (using a powerful architecture called Inception) to extract features and a swarm-based feature selection algorithm (Marine Predators Algorithm) to select the most relevant features. A combination of fractional-order and marine predators algorithm (FO-MPA) is considered an integration among a robust tool in mathematics named fractional-order calculus (FO). The proposed approach was evaluated on two public COVID-19 X-ray datasets which achieves both high performance and reduction of computational complexity. The two datasets consist of X-ray COVID-19 images by international Cardiothoracic radiologist, researchers and others published on Kaggle. The proposed approach selected successfully 130 and 86 out of 51 K features extracted by inception from dataset 1 and dataset 2, while improving classification accuracy at the same time. The results are the best achieved on these datasets when compared to a set of recent feature selection algorithms. By achieving 98.7%, 98.2% and 99.6%, 99% of classification accuracy and F-Score for dataset 1 and dataset 2, respectively, the proposed approach outperforms several CNNs and all recent works on COVID-19 images. 
461 |t Scientific Reports 
463 |t Vol. 10, iss. 1  |v [15364, 10 p.]  |d 2020 
610 1 |a электронный ресурс 
610 1 |a труды учёных ТПУ 
610 1 |a computational models 
610 1 |a image processing 
610 1 |a machine learning 
610 1 |a вычислительные модели 
610 1 |a обработка изображений 
610 1 |a машинное обучение 
701 1 |a Sahlol  |b A. T.  |g Ahmed 
701 1 |a Yousri  |b D.  |g Dalia 
701 1 |a Ewees  |b A. A.  |g Ahmed 
701 1 |a Al-qaness  |b M. A. A.  |g Mohammed 
701 1 |a Damasevicius  |b R.  |g Robertas 
701 1 |a Mokhamed Elsaed (Mohamed Abd Elaziz)  |b A. M.  |c Specialist in the field of informatics and computer technology  |c Professor of Tomsk Polytechnic University  |f 1987-  |g Akhmed Mokhamed  |3 (RuTPU)RU\TPU\pers\46943 
712 0 2 |a Национальный исследовательский Томский политехнический университет  |b Инженерная школа информационных технологий и робототехники  |c 2017-  |x TPU  |7 ca  |8 rus  |9 28330 
801 0 |a RU  |b 63413507  |c 20221004  |g RCR 
856 4 |u https://doi.org/10.1038/s41598-020-71294-2 
942 |c CF