Indonesian Journal of Electrical Engineering and Computer Science Vol. 29, No. 1, January 2023, pp. 365~374 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v29.i1.pp365-374  365 Journal homepage: http://ijeecs.iaescore.com Convolutional neural network-based crop disease detection model using transfer learning approach Segun Adebayo 1 , Halleluyah Oluwatobi Aworinde 2 , Akinwale O. Akinwunmi 2 , Adebamiji Ayandiji 3 , Awoniran Olalekan Monsir 2 1 Mechatronics Programme, College of Agricultural, Engineering and Science, Bowen University, Iwo, Nigeria 2 Computer Science Programme, College of Computing and Communication Studies, Bowen University, Iwo, Nigeria 3 Agriculture Programme, College of Agriculture, Engineering and Science, Bowen University, Iwo, Nigeria Article Info ABSTRACT Article history: Received Dec 6, 2021 Revised Sep 26, 2022 Accepted Oct 13, 2022 Crop diseases disrupt the crop's physiological constitution by affecting the crop's natural state. The physical recognition of the symptoms of the various diseases has largely been used to diagnose cassava infections. Every disease has a distinct set of symptoms that can be used to identify it. Early detection through physical identification, however, is quite difficult for a vast crop field. The use of electronic tools for illness identification then becomes necessary to promote early disease detection and control. Convolutional neural networks (CNN) were investigated in this study for the electronic identification and categorization of photographs of cassava leaves. For feature extraction and classification, the study used databases of cassava images and a deep convolutional neural network model. The methodology of this study retrained the models' current weights for visual geometry group (VGG-16), VGG-19, SqueezeNet, and MobileNet. Accuracy, loss, model complexity, and training time were all taken into consideration when evaluating how well the final layer of CNN models performed when trained on the new cassava image datasets. Keywords: Convolutional neural network Crop disease detection Deep learning Pattern recognition Transfer learning This is an open access article under the CC BY-SA license. Corresponding Author: Halleluyah Oluwatobi Aworinde Computer Science Programme, College of Computing and Communication Studies, Bowen University Iwo, Osun State, Nigeria Email: aworinde.halleluyah@bowen.edu.ng 1. INTRODUCTION Crop diseases affect the physiological makeup of the crop while impairing its natural state [1]. Plant infections that afflict the host plants and make them sick are to blame for these deficiencies. These diseases, which can harm any component of a plant above or below the earth, can be bacterial, viral, fungal, or parasitic nematodes [2]. These illnesses can alter the physical, chemical, and biological makeup of agricultural crops, which in turn alters how the affected plant component’s function [3]. As a result, the changed physiology of the farm plants lowers the production of the crops [4]. Some of the elements that affect disease occurrences and their dissemination in farm crops include seasonal variations, environmental circumstances, the presence of specific pathogens, and crop variety features [5]-[7]. This makes it difficult to predict and identify potential disease attacks on agricultural crops. Cassava (Manihot esculenta Crantz) is an agricultural crop that is very susceptible to many different forms of illnesses [8], [9]. One of the most significant staple foods farmed in Africa is cassava, which is also an essential raw material for industries in Latin America and Asia [9]. Cassava is vegetatively propagated by stem cuttings, which has many benefits but also means that the crop's diseases can readily and quickly be spread from one generation of the crop to another, endangering the crop's ability to