Pest detection system using machine learning techniques

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022

Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριοι συγγραφείς:	Prithvi, Protyusha Barua, Zahin, Fabliha, Anny, Sanjida Sultana
Άλλοι συγγραφείς:	Chakrabarty, Amitabha
Μορφή:	Thesis
Γλώσσα:	English
Έκδοση:	Brac University 2022
Θέματα:	Deep learning Transfer learning Pest detection Data augmentation Loss function Hyperparameter tuning Support Vector Machine (SVM) Inceptionv3 Xception You Only Look Once version 5 (YOLOv5) Convolutional Neural Network (CNN) Machine learning Cognitive learning theory (Deep learning) Neural networks (Computer science)
Διαθέσιμο Online:	http://hdl.handle.net/10361/17127

id	10361-17127
record_format	dspace
spelling	10361-171272022-08-28T21:01:36Z Pest detection system using machine learning techniques Prithvi, Protyusha Barua Zahin, Fabliha Anny, Sanjida Sultana Chakrabarty, Amitabha Department of Computer Science and Engineering, Brac University Deep learning Transfer learning Pest detection Data augmentation Loss function Hyperparameter tuning Support Vector Machine (SVM) Inceptionv3 Xception You Only Look Once version 5 (YOLOv5) Convolutional Neural Network (CNN) Machine learning Cognitive learning theory (Deep learning) Neural networks (Computer science) This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022 Cataloged from PDF version of thesis. Includes bibliographical references (pages 28-30). Countries like Bangladesh yield a significant portion of their economy from their agricultural sector. Agricultural pests, on the other hand, have a significant impact on both agricultural production and crop storage. The pest category must be precisely identified, and specific management actions must be adopted as a prevention technique against these pests. As a result, a computer vision-based agricultural pest recognition system must be developed. The implications of certain prospective machine learning algorithms, like Support Vector Machine, Inceptionv3, and Xception, are discussed in this research to achieve insect detection with the complicated agriculture setting. In this study, the dataset used are images of mainly 5 common pests found in a paddy field in Bangladesh. The results achieved from the models were studied based on their accuracy and loss percentage to determine the better approach for such detection to take necessary actions. In this research, SVM outperformed both InceptionV3 and Xception with an accuracy of about 72.5%. Protyusha Barua Prithvi Fabliha Zahin Sanjida Sultana Anny B. Computer Science 2022-08-28T09:47:45Z 2022-08-28T09:47:45Z 2022 2022-01 Thesis ID 21241069 ID 21241068 ID 18101131 http://hdl.handle.net/10361/17127 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 30 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Deep learning Transfer learning Pest detection Data augmentation Loss function Hyperparameter tuning Support Vector Machine (SVM) Inceptionv3 Xception You Only Look Once version 5 (YOLOv5) Convolutional Neural Network (CNN) Machine learning Cognitive learning theory (Deep learning) Neural networks (Computer science)
spellingShingle	Deep learning Transfer learning Pest detection Data augmentation Loss function Hyperparameter tuning Support Vector Machine (SVM) Inceptionv3 Xception You Only Look Once version 5 (YOLOv5) Convolutional Neural Network (CNN) Machine learning Cognitive learning theory (Deep learning) Neural networks (Computer science) Prithvi, Protyusha Barua Zahin, Fabliha Anny, Sanjida Sultana Pest detection system using machine learning techniques
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022
author2	Chakrabarty, Amitabha
author_facet	Chakrabarty, Amitabha Prithvi, Protyusha Barua Zahin, Fabliha Anny, Sanjida Sultana
format	Thesis
author	Prithvi, Protyusha Barua Zahin, Fabliha Anny, Sanjida Sultana
author_sort	Prithvi, Protyusha Barua
title	Pest detection system using machine learning techniques
title_short	Pest detection system using machine learning techniques
title_full	Pest detection system using machine learning techniques
title_fullStr	Pest detection system using machine learning techniques
title_full_unstemmed	Pest detection system using machine learning techniques
title_sort	pest detection system using machine learning techniques
publisher	Brac University
publishDate	2022
url	http://hdl.handle.net/10361/17127
work_keys_str_mv	AT prithviprotyushabarua pestdetectionsystemusingmachinelearningtechniques AT zahinfabliha pestdetectionsystemusingmachinelearningtechniques AT annysanjidasultana pestdetectionsystemusingmachinelearningtechniques
_version_	1814309644425756672

Pest detection system using machine learning techniques

Παρόμοια τεκμήρια