Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/451031
Full metadata record
DC FieldValueLanguage
dc.coverage.spatialMachine Learning, Regression, Linear Discriminant Analyses
dc.date.accessioned2023-01-20T10:27:40Z-
dc.date.available2023-01-20T10:27:40Z-
dc.identifier.urihttp://hdl.handle.net/10603/451031-
dc.description.abstractAgriculture plays a significant role in the financial system worldwide, demand in the agricultural system will rise with the ongoing growth of the human population. Agriculture -technology and precision farming, now also termed digital agriculture, have arisen as a novel technical field that use data centric approaches to have better yield. The data created in current agricultural operations given by a variety of sensors that allow a superior understanding of the operational environment (an interaction of dynamic soil, crop, and weather circumstances) and the operation itself (machinery data), leading to extra precise and quicker decision making. This research primarily aims to enhance agriculture technology. The research methodology is categorized into four phases, viz soil profile prediction, crop yield production forecasting, crop disease detection, groundwater and dam reservoir level forecasting. The experimental result shows that the proposed Modified Regression, Fuzzy C Means, Linear Discriminant Analysis and Artificial Neural Network model gives superior performance than the existing models. In this thesis, the first phase has taken up the issue of predicting the yield level by analyzing the soil characteristics for the particular soil. As gathering the information from the enormous volume of data is practically a complicated task in the recent circumstances. This phase has concentrated only Trichy district, and the soil data samples have been collected. A preprocessing element was premeditated to construct training and testing sets to use among the proposed and compared classifiers. The classifiers like Linear Regression, Simple Linear Regression, Additive Regression, and Regression by Discretization used for training and testing of the data sets. This phase has modified the Regression by Discretization classifier and applied. newlineThe second contribution of the work is Crop Yield Prediction Forecasting in Trichy District using Fuzzy C Means Algorithm and Multilayer Perceptron.
dc.format.extent152 p.
dc.languageEnglish
dc.relation
dc.rightsuniversity
dc.titleA Novel Framework for Smart Agriculture Prediction using Machine Learning Techniques
dc.title.alternative
dc.creator.researcherGeetha M C S
dc.subject.keywordEngineering and Technology
dc.subject.keywordComputer Science
dc.subject.keywordComputer Science Artificial Intelligence
dc.description.note
dc.contributor.guideElizabeth Shanthi I
dc.publisher.placeCoimbatore
dc.publisher.universityAvinashilingam Institute for Home Science and Higher Education for Women
dc.publisher.institutionDepartment of Computer Science
dc.date.registered2015
dc.date.completed2022
dc.date.awarded2023
dc.format.dimensions210 mm X 290 mm
dc.format.accompanyingmaterialDVD
dc.source.universityUniversity
dc.type.degreePh.D.
Appears in Departments:Department of Computer Science

Files in This Item:
File Description SizeFormat 
01_title.pdfAttached File4.25 kBAdobe PDFView/Open
02_prelimpages.pdf2.41 MBAdobe PDFView/Open
03_contents.pdf17.87 kBAdobe PDFView/Open
04_abstract.pdf10.2 kBAdobe PDFView/Open
05_chapter 1.pdf581.26 kBAdobe PDFView/Open
06_chapter 2.pdf644.9 kBAdobe PDFView/Open
07_chapter 3.pdf993.74 kBAdobe PDFView/Open
08_chapter 4.pdf1.07 MBAdobe PDFView/Open
09_chapter 5.pdf921.12 kBAdobe PDFView/Open
10_chapter 6.pdf921.65 kBAdobe PDFView/Open
11_chapter 7.pdf496.93 kBAdobe PDFView/Open
12_annexures.pdf6.27 MBAdobe PDFView/Open
80_recommendation.pdf23.56 kBAdobe PDFView/Open


Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).

Altmetric Badge: