Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283709675> ?p ?o ?g. }
- W4283709675 endingPage "24" @default.
- W4283709675 startingPage "1" @default.
- W4283709675 abstract "Deep learning artificial intelligent (AI) methods have potential to help improve diagnostic efficiency and accuracy for reading portable CXRs. Public datasets taken from SIRM and Kaggle repositories comprised of COVID-19 (N = 130, 975), normal (N = 138, 1525), bacterial pneumonia (N = 145, 2521), non-COVID-19 viral pneumonia (N = 145, 1342) respectively CXRs were analyzed. On the first dataset, we first extracted 2048 features from last pooling layer of Residual Network 101 (ResNet101) which were fed into selected classifiers. The three-class (Covid-19, normal, viral) yielded highest accuracy of 97.30% using support vector machine linear (SVM-L). This accuracy was further improved to 98.20% by applying the chi-square feature selection method. The four-class using original ResNet101 features yielded highest accuracy of 85.06% which was further improved to 87.01% using chi-square and recursive feature elimination (RFE) feature selection methods. Moreover, using the second dataset, we utilized and optimized robust deep learning methods including densenet201, inception-V3, ResNet101, GoogleNet and VGG-19 using transfer learning approach. The densenet201 yielded the highest performance for three-class (Covid-19, normal, pneumonia) to detect Covid-19 with accuracy (99.92%).The results revealed that feature selection methods improved multiclass classification as dynamic deep feature may contains redundant information. Thus, proposed methods have the potential to improve diagnostic efficiency and accuracy for portable CXRs." @default.
- W4283709675 created "2022-06-30" @default.
- W4283709675 creator A5004775175 @default.
- W4283709675 creator A5011639304 @default.
- W4283709675 creator A5043871968 @default.
- W4283709675 creator A5063442798 @default.
- W4283709675 creator A5063580605 @default.
- W4283709675 creator A5064562623 @default.
- W4283709675 creator A5083737327 @default.
- W4283709675 creator A5085467807 @default.
- W4283709675 date "2022-06-28" @default.
- W4283709675 modified "2023-10-16" @default.
- W4283709675 title "COVID-19 lung infection detection using deep learning with transfer learning and ResNet101 features extraction and selection" @default.
- W4283709675 cites W1692174238 @default.
- W4283709675 cites W2017337590 @default.
- W4283709675 cites W2028551759 @default.
- W4283709675 cites W2091151456 @default.
- W4283709675 cites W2097117768 @default.
- W4283709675 cites W2108598243 @default.
- W4283709675 cites W2158933803 @default.
- W4283709675 cites W2163070219 @default.
- W4283709675 cites W2167533099 @default.
- W4283709675 cites W2169618946 @default.
- W4283709675 cites W2194775991 @default.
- W4283709675 cites W2293009534 @default.
- W4283709675 cites W2523168882 @default.
- W4283709675 cites W2551940739 @default.
- W4283709675 cites W2556605533 @default.
- W4283709675 cites W2575615142 @default.
- W4283709675 cites W2577696039 @default.
- W4283709675 cites W2592929672 @default.
- W4283709675 cites W2620760558 @default.
- W4283709675 cites W2740520864 @default.
- W4283709675 cites W2789255992 @default.
- W4283709675 cites W2802612595 @default.
- W4283709675 cites W2911925130 @default.
- W4283709675 cites W2919115771 @default.
- W4283709675 cites W2949535518 @default.
- W4283709675 cites W2963556638 @default.
- W4283709675 cites W2964278775 @default.
- W4283709675 cites W2968171911 @default.
- W4283709675 cites W2997781171 @default.
- W4283709675 cites W3011149445 @default.
- W4283709675 cites W3011414569 @default.
- W4283709675 cites W3015292413 @default.
- W4283709675 cites W3017117984 @default.
- W4283709675 cites W3024740627 @default.
- W4283709675 cites W3026350508 @default.
- W4283709675 cites W3030621456 @default.
- W4283709675 cites W3033616466 @default.
- W4283709675 cites W3037538421 @default.
- W4283709675 cites W3040660552 @default.
- W4283709675 cites W3047941401 @default.
- W4283709675 cites W3048828727 @default.
- W4283709675 cites W3108203735 @default.
- W4283709675 cites W3110920910 @default.
- W4283709675 cites W3126674636 @default.
- W4283709675 cites W3133191822 @default.
- W4283709675 cites W3135243128 @default.
- W4283709675 cites W3136753563 @default.
- W4283709675 cites W3142371777 @default.
- W4283709675 cites W3145352525 @default.
- W4283709675 cites W3162351260 @default.
- W4283709675 cites W3163405749 @default.
- W4283709675 cites W3176429669 @default.
- W4283709675 cites W3187766292 @default.
- W4283709675 cites W3190831142 @default.
- W4283709675 cites W3197184862 @default.
- W4283709675 cites W4200551431 @default.
- W4283709675 doi "https://doi.org/10.1080/17455030.2022.2091807" @default.
- W4283709675 hasPublicationYear "2022" @default.
- W4283709675 type Work @default.
- W4283709675 citedByCount "1" @default.
- W4283709675 countsByYear W42837096752023 @default.
- W4283709675 crossrefType "journal-article" @default.
- W4283709675 hasAuthorship W4283709675A5004775175 @default.
- W4283709675 hasAuthorship W4283709675A5011639304 @default.
- W4283709675 hasAuthorship W4283709675A5043871968 @default.
- W4283709675 hasAuthorship W4283709675A5063442798 @default.
- W4283709675 hasAuthorship W4283709675A5063580605 @default.
- W4283709675 hasAuthorship W4283709675A5064562623 @default.
- W4283709675 hasAuthorship W4283709675A5083737327 @default.
- W4283709675 hasAuthorship W4283709675A5085467807 @default.
- W4283709675 hasConcept C108583219 @default.
- W4283709675 hasConcept C119857082 @default.
- W4283709675 hasConcept C12267149 @default.
- W4283709675 hasConcept C138885662 @default.
- W4283709675 hasConcept C142724271 @default.
- W4283709675 hasConcept C148483581 @default.
- W4283709675 hasConcept C150899416 @default.
- W4283709675 hasConcept C153180895 @default.
- W4283709675 hasConcept C154945302 @default.
- W4283709675 hasConcept C2776401178 @default.
- W4283709675 hasConcept C2779134260 @default.
- W4283709675 hasConcept C3008058167 @default.
- W4283709675 hasConcept C41008148 @default.
- W4283709675 hasConcept C41895202 @default.
- W4283709675 hasConcept C50644808 @default.