Soft Computing Approaches for Accurate Prediction of Potato Leaf Diseases

dc.contributor.guideClara Kanmani A
dc.coverage.spatial
dc.creator.researcherRapaka, Anuj
dc.date.accessioned2023-07-20T09:32:38Z
dc.date.available2023-07-20T09:32:38Z
dc.date.awarded2023
dc.date.completed2023
dc.date.registered2018
dc.description.abstractThe potato holds significant global importance as a major food crop, serving as a vital component in the nutrition of a substantial portion of the population on a global scale. Potato is considered one among the most significant food crops globally, ranking fourth in importance after wheat, maize, and rice. Among root crops, it holds a prominent position as the foremost crop. In terms of overall production for human consumption, potatoes hold the fourth position among major food crops, following wheat, rice, and maize. newlinePotato tubers yield exceptionally high quantities per acre, surpassing the yields of any grain crop by a considerable margin. Potatoes find application in a diverse range of table and processed products, serving various industrial purposes as well. newlineThe nutritional value of potatoes is of utmost significance, offering important vitamins and minerals, such as a high concentration of vitamin C and iron. Potatoes also offer a substantial amount of proteins, making them a prominent source of carbohydrates. newlineImage processing is an intriguing idea employed in numerous computerized applications for precise feature recognition. In the agricultural domain, this methodology is primarily utilized for identifying diseases affecting plants and leaves. However, the complexity of images often hampers the accuracy of classification and segmentation. In the current study, the focus is on normal and diseased images of potato leaves. Therefore, a novel approach called ALHTCNA (Ant Lion-based Hyper-Parameter tuned Convolution Neural Approach) was devised, incorporating the necessary parameters to maximize accuracy. The preprocessing function ensures error-free data, which is then processed through the classification framework, involving feature extraction, segmentation, along with disease classification. The disease types focused on in this study are Late Blight (LB) and Early Blight (EB). Leaves that do not show symptoms of these diseases are categorized as healthy.
dc.description.note
dc.format.accompanyingmaterialDVD
dc.format.dimensions
dc.format.extent
dc.identifier.urihttp://hdl.handle.net/10603/500578
dc.languageEnglish
dc.publisher.institutionSchool of Engineering
dc.publisher.placeIttagalpura
dc.publisher.universityPresidency University, Karnataka
dc.relation
dc.rightsuniversity
dc.source.universityUniversity
dc.subject.keywordComputer Science
dc.subject.keywordComputer Science Interdisciplinary Applications
dc.subject.keywordEngineering and Technology
dc.subject.keywordPotato Leaf Diseases
dc.subject.keywordSoft Computing
dc.titleSoft Computing Approaches for Accurate Prediction of Potato Leaf Diseases
dc.title.alternativeAn Exploration in Disease Detection and Classification
dc.type.degreePh.D.

Files

Original bundle

Now showing 1 - 5 of 12
Loading...
Thumbnail Image
Name:
01_title.pdf
Size:
57.3 KB
Format:
Adobe Portable Document Format
Description:
Attached File
Loading...
Thumbnail Image
Name:
02_prelim pages.pdf
Size:
3.03 MB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
03_content.pdf
Size:
88.04 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
04_abstract.pdf
Size:
54.92 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
05_chapter 1.pdf
Size:
344.39 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.79 KB
Format:
Plain Text
Description: