Web-based CNN Application for Arabica Coffee Leaf Disease Prediction in Smart Agriculture

Abstract

In the agriculture industry, plant diseases provide difficulty, particularly for Arabica coffee production. A first step in eliminating and treating infections to avoid crop damage is recognizing ailments on Arabica coffee leaves. Convolutional neural networks (CNN) are rapidly advancing, making it possible to diagnose Arabica coffee leaf damage without a specialist's help. CNN is aimed to find features adaptively through backpropagation by adding layers including convolutional layers and pooling layers. This study aims to optimize and increase the accuracy of Arabica coffee leaf disease classification utilizing the neural network architectures: ResNet50, InceptionResNetV4, MobileNetV2, and DensNet169. Additionally, this research presents an interactive web platform integrated with the Arabica coffee leaf disease prediction system. Inside this research, 5000 image data points will be divided into five classes—Phoma, Rust, Cescospora, healthy, and Miner—to assess the efficacy of CNN architecture in classifying images of Arabica coffee leaf disease. 80:10:10 is the ratio between training data, validation, and testing. In the testing findings, the InceptionResnetV2 and DensNet169 designs had the highest accuracy, at 100%, followed by the MobileNetV2 architecture at 99% and the ResNet50 architecture at 59%. Even though MobileNetV2 is not more accurate than InceptionResnetV2 and DensNet169, MobileNetV2 is the smallest of the three models. The MobileNetV2 paradigm was chosen for web application development. The system accurately identified and advised treatment for Arabica coffee leaf diseases, as shown by the system's implementation outcomes.

Coffee Plant Leaf Disease Detection for Digital Agriculture

“…Hence, all the CNNs assessed, with the exception of Mo-bileNetV2, demonstrate comparable performance in this specific task. In comparison to the results obtained by Aufar et al [2023], equivalent performance was achieved, but with smaller architectures. The InceptionV3 and ShuffleNet models, for example, have 57.24 % and 97.54 % fewer parameters, respectively, than InceptionResNetV2.…”

“…This observation holds particular practical significance, as the former heavily relies on human intervention and expertise for feature extraction and architecture design. When examining the results obtained with the contemporary approach, it is first noteworthy to highlight the performance degradation of MobileNetV2 when compared to the results reported in the work by Aufar et al [2023]. These results are indicative of underfitting for this model with respect to the learning task.…”

“…Although the experimental results obtained on a diverse and realistic dataset labeled by experts have exhibited promising metrics that endorse the adoption of CNNs for the detection of coffee leaf diseases, it is imperative to acknowledge potential threats to the validity of these findings. A comparative analysis between the proposed solution, utilizing ShuffleNet and having experimental accuracy of 99.93±0.03 %, and the work of Aufar et al [2023], which reports a experimental accuracy of 100 % using Inception-ResNetV2, reveals a compelling performance by both approaches in addressing a real-world Computer Vision task. A visual inspection of dataset samples, as depicted in Figures 6-8, provides preliminary insights into this matter.…”

“…The study by Aufar et al [2023] utilized JMuBEN and JMuBEN2 datasets which contains 58 550 samples from four diseases and also from healthy leaves [Jepkoech et al, 2021]. The authors approached the problem as a multi-class classification task, partitioning the dataset into 10 subsets and conducting a holdout cross-validation on each subset, with 80 % of the data for training, 10 % for training validation, and 10 % for testing purposes.…”

Development of Smart Agriculture to detect the Arabica Coffee Leaf Disease using IAFSA based MSAB with Channel and Spatial Attention Network

“…Utilising the ResNet50, MobileNetV2, InceptionResNetV4, and DensNet169 neural network architectures, Aufar et al's [18] objective is to enhance and increase the precision of the categorization of Arabica coffee leaf diseases. Additionally, this study shows off an interactive website connected to the Arabica coffee plant leaf disease forecasting system.…”