TinyML for smart agriculture: Comparative analysis of TinyML platforms and practical deployment for maize leaf disease identification

BackgroundBanana (Musa spp.) is the most popular marketable fruit crop grown all over the world, and a dominant staple food in many developing countries. Worldwide, banana production is affected by numerous diseases and pests. Novel and rapid methods for the timely detection of pests and diseases will allow to surveil and develop control measures with greater efficiency. As deep convolutional neural networks (DCNN) and transfer learning has been successfully applied in various fields, it has freshly moved in the domain of just-in-time crop disease detection. The aim of this research is to develop an AI-based banana disease and pest detection system using a DCNN to support banana farmers.ResultsLarge datasets of expert pre-screened banana disease and pest symptom/damage images were collected from various hotspots in Africa and Southern India. To build a detection model, we retrained three different convolutional neural network (CNN) architectures using a transfer learning approach. A total of six different models were developed from 18 different classes (disease by plant parts) using images collected from different parts of the banana plant. Our studies revealed ResNet50 and InceptionV2 based models performed better compared to MobileNetV1. These architectures represent the state-of-the-art results of banana diseases and pest detection with an accuracy of more than 90% in most of the models tested. These experimental results were comparable with other state-of-the-art models found in the literature. With a future view to run these detection capabilities on a mobile device, we evaluated the performance of SSD (single shot detector) MobileNetV1. Performance and validation metrics were also computed to measure the accuracy of different models in automated disease detection methods.ConclusionOur results showed that the DCNN was a robust and easily deployable strategy for digital banana disease and pest detection. Using a pre-trained disease recognition model, we were able to perform deep transfer learning (DTL) to produce a network that can make accurate predictions. This significant high success rate makes the model a useful early disease and pest detection tool, and this research could be further extended to develop a fully automated mobile app to help millions of banana farmers in developing countries.

Maize leaf disease recognition based on improved MSRCR and OSCRNet

Disease detection in agricultural crops, such as Solanum tuberosum L. (potato), is of utmost importance to ensure crop health and maximize yield. Traditional methods for disease detection in potatoes rely on manual inspection, which can be time-consuming and prone to human error. Image processing and machine learning techniques have shown promise in automating disease detection processes. This study proposes a novel approach for disease detection in Solanum tuberosum L. by leveraging image fusion techniques. The proposed method involves the fusion of multiple images of potato plants, acquired using different sensors or imaging modalities, to create a comprehensive and informative representation of the crop. Image fusion methods, such as discrete wavelet transform and continuous wavelet transform, are employed to combine the spectral and spatial information from the images effectively. The different image fusion rule is applied to the input images and resultant fused images, where relevant features are extracted to distinguish between healthy and diseased potato plants. The training dataset comprises diverse samples of both healthy and diseased potato plants, captured under various environmental conditions and disease stages. The performance of the proposed disease detection system is evaluated using standard metrics such as entropy. The results demonstrate the effectiveness of the image fusion approach in accurately identifying diseased potato plants, achieving high detection accuracy and generalization capabilities. The potential benefits of this paper include providing farmers and agricultural experts with an efficient and reliable tool for early disease detection in potato crops. Early detection can lead to timely intervention, minimizing crop losses and optimizing agricultural practices. The proposed methodology also lays the groundwork for future research in using advanced image processing techniques and machine learning algorithms for disease detection in other agricultural crops, contributing to the overall improvement of crop management and food security.

Detecting pests and diseases on maize leaves is challenging. This is especially true under complex conditions, such as variable lighting and occlusion. Current methods suffer from low detection accuracy. They also lack sufficient real-time performance. Hence, this study introduces the lightweight detection method YOLOv11-RCDWD based on an improved YOLOv11 model. The proposed approach enhances the YOLOv11 model by incorporating the RepLKNet module as the backbone, which significantly enhances the model’s capacity to capture characteristics of maize leaf pests and diseases. Additionally, the CBAM is embedded within the neck feature extraction network to further refine the feature representation to augment the model’s capability to identify and select essential features by introducing attention mechanisms in both the channel and spatial dimensions, thereby improving the accuracy of feature expression. We have also improved the model by incorporating the DynamicHead module, WIoU loss function, and DynamicATSS label assignment strategy, which collectively enhance detection accuracy, efficiency, and robustness through optimized attention mechanisms, better handling of low-quality samples, and dynamic sample selection during training. The experimental findings indicate that the improved YOLOv11-RCDWD model effectively detected pests and diseases on maize leaves. The precision reached 92.6%, while the recall was 85.4%. The F1 score was 88.9%, and the mAP@0.5 and mAP@0.5~0.95 demonstrated an improvement of 4.9% and 9.0% over the baseline YOLOv11s. Notably, the YOLOv11-RCDWD model significantly outperformed other architectures such as Faster R-CNN, SSD, and various models within the YOLO series, demonstrating superior capabilities in terms of detection speed, parameter count, computational efficiency, and memory utilization. This model achieves an optimal balance between detection performance and resource efficiency. Overall, the improved YOLOv11-RCDWD model significantly reduces detection time and memory usage while maintaining high detection accuracy, supporting the automated detection of maize pests and diseases, and offering a robust solution for intelligent monitoring of agricultural pests.

There are thousands of grains and fruits grown on this planet every day. In order to cope with the needs of the people, new farming practices are constantly being invented. In addition, the discovery and use of new technologies, which can easily and quickly detect plant diseases. In this research, we tried to detect the diseases and provided their remedies through the images of the infected leaf of a grain "Corn" along with a fruit "Peach" with the help of computer science by using Artificial Intelligence. Since corn is a very popular crop and food, it is cultivated throughout the world. In particular, the demand and popularity of corn in Bangladesh is a skyscraper. Even though peach is not as much popular as corn in Bangladesh but in recent time it is gaining attraction of people in the fruit market. But due to timely consultation and availability of available technology, maize farmers and the farmers who are interested in cultivating peach professionally, often face the attack of insects and diseases. As soon as the crop gets destroyed, the farmers' dividends also get spoiled which is a huge loss for all. So, this research will predict the diseases of corn leaf as well as peach plant leaf and pass down their remedy soon after the affected leaf's picture is given as an input. In this research we have used image processing, convolutional neural network (CNN) algorithm to train our dataset. In the end, our system successfully achieved validation accuracy of over 99.28%. This research is going to help numerous farmers all over the world especially the farmers of our country Bangladesh to increase the production rate of corn and the popularity rate of peach by reducing the attack of insects and diseases in time.

Crops play a vital role in the global food supply. Various environmental factors can cause crop diseases and insect pests, resulting in severe production losses. However, manual detection of crop diseases and insect pests is a time-consuming and error-prone process, which often fails to identify and prevent the spread of plant diseases in a timely and effective manner. To overcome these challenges, machine learning (ML) and deep learning (DL) technologies have been introduced in recent years to improve early identification and effective response to plant pests and diseases. In this article, the principles of convolutional neural network (CNN), recurrent neural network (RNN) and adversarial generative neural network (GAN) are explained, as well as the latest progress in the improvement and application of the three algorithms in plant disease detection and detection. By applying DL technology, efficient and accurate detection of pests and diseases can be achieved, thereby providing reliable support for agricultural production. It is hoped that this work will become a valuable resource for researchers studying plant pest and disease detection and provide guidance to further advance research and practice in this field. At the same time, some current challenges and issues that need to be solved are also discussed, such as data quality, target occlusion, model generalization ability, and adaptability in practical applications. Deep learning holds great promise in revolutionizing precision agriculture by providing efficient and accurate solutions for pest and disease management.

In agricultural research, effective and efficient disease detection in crops is crucial for enhancing yield and sustainability. This study presents a novel approach to improving YOLOv8, a state-of-the-art object detection model, by integrating the Ghost model with three advanced attention mechanisms: Convolutional Block Attention Module (CBAM), Triplet Attention, and Efficiency Multi-Scale Attention (EMA). The Ghost model optimizes feature extraction by reducing computational complexity, while the attention modules enable the model to focus on relevant regions, improving detection performance. The resulting Ghost-Attention-YOLOv8 model was evaluated on the Rice Leaf Disease dataset to assess its efficacy in identifying and classifying various diseases. The experimental results demonstrate significant improvements in accuracy, precision, and recall compared to the baseline YOLOv8 model. The proposed Ghost YOLOv8s with Efficiency Multi-Scale Attention model achieves a parameter count of 5.5 M, a reduction of 4.3 million compared to the original YOLOv8s model, while the accuracy is improved: the mAP@50 metric reaches 95.4%, a 2.3% increase; and mAP@50–95 improves to 62.4%, an increase of 3.7% over the original YOLOv8s. This research offers a practical solution to the challenges of computational efficiency and accuracy in agricultural monitoring, contributing to the development of robust AI tools for disease detection in crops.

Maize leaf disease detection is an essential project in the maize planting stage. This paper proposes the convolutional neural network optimized by a Multi-Activation Function (MAF) module to detect maize leaf disease, aiming to increase the accuracy of traditional artificial intelligence methods. Since the disease dataset was insufficient, this paper adopts image pre-processing methods to extend and augment the disease samples. This paper uses transfer learning and warm-up method to accelerate the training. As a result, three kinds of maize diseases, including maculopathy, rust, and blight, could be detected efficiently and accurately. The accuracy of the proposed method in the validation set reached 97.41%. This paper carried out a baseline test to verify the effectiveness of the proposed method. First, three groups of CNNs with the best performance were selected. Then, ablation experiments were conducted on five CNNs. The results indicated that the performances of CNNs have been improved by adding the MAF module. In addition, the combination of Sigmoid, ReLU, and Mish showed the best performance on ResNet50. The accuracy can be improved by 2.33%, proving that the model proposed in this paper can be well applied to agricultural production.

This paper proposed an intelligent plant disease detection system that uses the modified Alexnet. As a convolutional neural network (CNN), Alexnet is good at objection detection from images. However, plant disease detection by the leaf image is a difficult task compared to traditional object detection. Therefore, Alexnet is modified for the different size images and angles to fit the requirement of a practical scenario. A training corpus gathered from the internet and with human leveling is used to train the detection models. According to the experimental results, the proposed approach achieves a good performance.

Agriculture is one of the keys to the significant growth of human civilization. In this progressive world, Automation has begun its supremacy in every field of work. But Automation in the field of agriculture is not as advanced comparatively. Thus, the requirement of developing an Automation system in the field of agriculture is imminent. One of the biggest challenges faced by farmers is the detection of diseases in crops during the early stages of growth. Where it is obliged to take care of the crops and also prevent them from acquiring any serious diseases, our project tends to create an autonomous drone for the detection of diseases at the early stages of crop growth. This project succeeds in detecting the diseases, which in turn helps the farmers to detect the crop diseases at their early stages. We use the image processing method to detect and identify these diseases and highlight the infected crop area using coordinates from the GPS module attached within the drone.

Precisely discerning disease types and vulnerable areas is crucial in implementing effective monitoring of crop production. This forms the basis for generating targeted plant protection recommendations and automatic, precise applications. In this study, we constructed a dataset comprising six types of field maize leaf images and developed a framework for classifying and localizing maize leaf diseases. Our approach involved integrating lightweight convolutional neural networks with interpretable AI algorithms, which resulted in high classification accuracy and fast detection speeds. To evaluate the performance of our framework, we tested the mean Intersection over Union (mIoU) of localized disease spot coverage and actual disease spot coverage when relying solely on image-level annotations. The results showed that our framework achieved a mIoU of up to 55.302%, indicating the feasibility of using weakly supervised semantic segmentation based on class activation mapping techniques for identifying disease spots in crop disease detection. This approach, which combines deep learning models with visualization techniques, improves the interpretability of the deep learning models and achieves successful localization of infected areas of maize leaves through weakly supervised learning. The framework allows for smart monitoring of crop diseases and plant protection operations using mobile phones, smart farm machines, and other devices. Furthermore, it offers a reference for deep learning research on crop diseases.

Identification of the crop diseases is the key to prevent the losses in the yield and quantity of the agricultural production.The study of the crop diseases detection mean the studing of visually observable patterns seen on the crop.Health monitoring and disease detection on crop is very critical for sustainable agriculture.It is very difficult to monitor the crop diseases manually.It requires tremendous amount of work, expertise in the crop diseases, and also require the excessive processing time.Hence, image processing is used for the detection of crop diseases by capturing the images of the leaves and comparing it with the data sets.The data set consist of different images of diseased leaves of the crop. The proposed (Convolutional Neural Networks) CNN-based model utilizes deep learning to automatically extract features from crop images for disease detection.A diverse dataset of healthy and diseased crops enhances generalization.The CNN architecture captures intricate patterns, while transfer learning improves efficiency and accuracy.Experimental results confirm the model's effectiveness, outperforming traditional methods and demonstrating robustness across various diseases and soil recommendation.Additionally, the model's real-time applicability highlights its potential for on-site disease detection.

Comparative study of IoT- and AI-based computing disease detection approaches

Crop diagnostic system: A robust disease detection and management system for leafy green crops grown in an aquaponics facility

Improving cotton yield greatly depends on the early and accurate detection of diseases affecting cotton leaves. In recent years, deep learning has gained momentum in agricultural research, offering promising solutions across various applications. One major area of interest is the real-time diagnosis of cotton leaf diseases. Despite the significant advances made using Convolutional Neural Networks (CNNs) for plant disease classification, there remains a considerable gap in delivering accessible and effective tools for farmers and agricultural experts.Manual disease detection in crops is not only time-consuming and labor-intensive but also prone to human error, which can lead to misdiagnosis, ineffective treatment strategies, and financial losses. To address these challenges, this work proposes leveraging a Faster R-CNN model trained on a cotton leaf image dataset for precise disease identification and classification. The Plant Village dataset is used as a standard reference to evaluate different feature extraction networks such as VGG-16, InceptionV1, and InceptionV2 for performance comparison.Given the critical role agriculture plays in India’s economy, modernizing disease detection methods is essential. As climate change and environmental variability continue to impact crop health, it is crucial to replace traditional, manual inspection methods with automated, intelligent solutions that can support sustainable farming and food security.