Reza, Md TanzimGhosh, PialAlin, Istiak AhmedChowdhury, Hasan Al Mahmud2025-01-212025-01-21©20242024-10ID 19201069ID 19201087ID 23141069http://hdl.handle.net/10361/25241Cataloged from PDF version of thesis.Includes bibliographical references (pages 33-34).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024.One of the most vital aspects of a human’s existence is food. Each food contains several nutrients which help in growth and development of the human body. It also prevents our body from various diseases. Most of the food we consume comes from crops, trees and plants. Pests infestation is the biggest threat for the agriculture sector.It can cause various types of diseases in crops and reduce crop production. As a result, it is necessary to detect pests early and take necessary steps to stop the infestation. For decades, humans used traditional manual techniques to detect pests. However, this technique is very time consuming, laborious and less accurate. With the development of deep learning , pest detection has become easier than the traditional techniques.The aim of this study is to propose a novel model named VGG19-KAN for crop pest detection and compare it with the State-of-the-arts model like Mobilenetv2 and VGG19. We used the IP102 dataset to train the model. We divided the pest images of IP102 into 8 crop types: rice, corn, wheat, beet, alfalfa, vitis, citrus, and mango. This paper highlights the potential of the VGG19-KAN model. For example, we trained VGG19-KAN along with Mobilenetv2 and VGG19 and found that VGG19-KAN performed much better than Mobilenetv2 and VGG19 in Mango class.The training accuracy of VGG19-KAN was 98.07%.38 pagesenBRAC 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.Crop productionPests infestationPests detectionDeep learningImage data analysisImage processing--Digital techniques.Machine learning--Industrial applications.Agriculture--Data processing.Agricultural pests--Detection.Insect pests--Control--Technological innovations.Precision farming.Agricultural innovations.Photographic interpretation.Thesis