Please use this identifier to cite or link to this item: http://repository.kln.ac.lk/handle/123456789/25361
Title: Deep learning-based pesticides prescription system for leaf diseases of home garden crops in Sri Lanka
Authors: Sangeevan, Siventhirarajah
Keywords: convolutional neural network, leaf diseases, Machine Learning, pesticides
Issue Date: 2021
Publisher: Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka
Citation: Sangeevan Siventhirarajah (2021), Deep learning-based pesticides prescription system for leaf diseases of home garden crops in Sri Lanka, International Research Conference on Smart Computing and Systems Engineering (SCSE 2021), Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka. 94-98.
Abstract: The study proposes a deep learning-based pesticides prescription system for leaf diseases of home garden crops in Sri Lanka. It is an intelligent system to get suitable pesticides prescriptions for plant leaf diseases. Home gardening has become popular and is rapid because of the current pandemic situation. However, plant diseases are a major problem in gardening activities, even in a home garden or in a commercial garden. Identifying and finding a solution for the plant disease is a big challenge for home gardeners rather than commercial farmers. The proposed system of deep learning-based pesticides prescription system for leaf diseases of home garden crops in Sri Lanka will be the best solution for identifying and finding a solution to the plant diseases. The system is using a trained model for prescribing pesticides. The model was built using the deep learning method and trained in the supervised learning process. The convolutional neural network algorithm was used in the model. Transfer learning with AlexNet pre-trained model was used to increase the performance in the proposed solution and the best accuracy of 88.64% was achieved in the experiments.
URI: http://repository.kln.ac.lk/handle/123456789/25361
Appears in Collections:Smart Computing and Systems Engineering - 2021 (SCSE 2021)

Files in This Item:
File Description SizeFormat 
SCSE 2021 15.pdf464.44 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.