Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387445099> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4387445099 abstract "Crop diseases diagnosis using image processing is considering a key element in precision agriculture. Nowadays, automatic recognition and classification of plant diseases is a great challenge. Our study focuses on this purpose by developing an automatic method for diagnosing and recognizing two diseases in potato tubers, Black Scarf and Green Tuber. This work proposes two different models for detecting diseases of potato tubers based on Traditional Machine Learning (ML) and Deep Learning (DL). A comparative study between four traditional machine learning classifiers (Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Decision Tree) is done in order to determine the best accuracy for potato tubers disease classification. Moreover, three deep learning models (DenseNet201, VGG19 and MobileNetV2) were applied on the same training dataset to compare their performance in tubers disease recognition. The used images dataset contains 78 raw real potato tubers images, taken from the potato field for three different classes; two diseases and one normal (healthy) class. Results showed that the highest accuracy achieved in traditional ML is 80% using SVM technique. But DL highest accuracy is 99% using DenseNet201 technique." @default.
- W4387445099 created "2023-10-10" @default.
- W4387445099 creator A5051004884 @default.
- W4387445099 creator A5075274872 @default.
- W4387445099 creator A5076782872 @default.
- W4387445099 creator A5093026268 @default.
- W4387445099 date "2023-09-03" @default.
- W4387445099 modified "2023-10-11" @default.
- W4387445099 title "Detection of Potato Tuber Diseases Using Machine Learning Models" @default.
- W4387445099 cites W1968378357 @default.
- W4387445099 cites W1973574038 @default.
- W4387445099 cites W2057106128 @default.
- W4387445099 cites W2168736308 @default.
- W4387445099 cites W2504081689 @default.
- W4387445099 cites W2795016359 @default.
- W4387445099 cites W2958796117 @default.
- W4387445099 cites W2966160658 @default.
- W4387445099 cites W2981854649 @default.
- W4387445099 cites W2996062047 @default.
- W4387445099 cites W3003289562 @default.
- W4387445099 cites W3005071760 @default.
- W4387445099 cites W3025223191 @default.
- W4387445099 cites W3131259093 @default.
- W4387445099 cites W3138118097 @default.
- W4387445099 cites W3138644757 @default.
- W4387445099 cites W3151832061 @default.
- W4387445099 cites W3175335170 @default.
- W4387445099 cites W3193830270 @default.
- W4387445099 cites W3197135690 @default.
- W4387445099 cites W4200466187 @default.
- W4387445099 cites W4224331011 @default.
- W4387445099 cites W4312989667 @default.
- W4387445099 cites W4378895574 @default.
- W4387445099 doi "https://doi.org/10.1109/caisais59399.2023.10269994" @default.
- W4387445099 hasPublicationYear "2023" @default.
- W4387445099 type Work @default.
- W4387445099 citedByCount "0" @default.
- W4387445099 crossrefType "proceedings-article" @default.
- W4387445099 hasAuthorship W4387445099A5051004884 @default.
- W4387445099 hasAuthorship W4387445099A5075274872 @default.
- W4387445099 hasAuthorship W4387445099A5076782872 @default.
- W4387445099 hasAuthorship W4387445099A5093026268 @default.
- W4387445099 hasConcept C108583219 @default.
- W4387445099 hasConcept C119857082 @default.
- W4387445099 hasConcept C12267149 @default.
- W4387445099 hasConcept C151956035 @default.
- W4387445099 hasConcept C153180895 @default.
- W4387445099 hasConcept C154945302 @default.
- W4387445099 hasConcept C202444582 @default.
- W4387445099 hasConcept C33923547 @default.
- W4387445099 hasConcept C41008148 @default.
- W4387445099 hasConcept C84525736 @default.
- W4387445099 hasConcept C9652623 @default.
- W4387445099 hasConceptScore W4387445099C108583219 @default.
- W4387445099 hasConceptScore W4387445099C119857082 @default.
- W4387445099 hasConceptScore W4387445099C12267149 @default.
- W4387445099 hasConceptScore W4387445099C151956035 @default.
- W4387445099 hasConceptScore W4387445099C153180895 @default.
- W4387445099 hasConceptScore W4387445099C154945302 @default.
- W4387445099 hasConceptScore W4387445099C202444582 @default.
- W4387445099 hasConceptScore W4387445099C33923547 @default.
- W4387445099 hasConceptScore W4387445099C41008148 @default.
- W4387445099 hasConceptScore W4387445099C84525736 @default.
- W4387445099 hasConceptScore W4387445099C9652623 @default.
- W4387445099 hasLocation W43874450991 @default.
- W4387445099 hasOpenAccess W4387445099 @default.
- W4387445099 hasPrimaryLocation W43874450991 @default.
- W4387445099 hasRelatedWork W148178222 @default.
- W4387445099 hasRelatedWork W2090763504 @default.
- W4387445099 hasRelatedWork W3036095178 @default.
- W4387445099 hasRelatedWork W3134840015 @default.
- W4387445099 hasRelatedWork W4224922629 @default.
- W4387445099 hasRelatedWork W4366979180 @default.
- W4387445099 hasRelatedWork W4367335967 @default.
- W4387445099 hasRelatedWork W4375867731 @default.
- W4387445099 hasRelatedWork W4380075502 @default.
- W4387445099 hasRelatedWork W4384470695 @default.
- W4387445099 isParatext "false" @default.
- W4387445099 isRetracted "false" @default.
- W4387445099 workType "article" @default.