A novel PCA–whale optimization-based deep neural network model for classification of tomato plant diseases using GPU

The wide scale prevalence of diseases in agricultural crops affects both the production quality and quantity of agricultural products at local to regional scale. More often than not, the diseases remain unidentified causing huge distress to the farmers while threatening national food security. In order to circumvent this problem, early diagnosis of diseases using a fast and reliable method is beneficial. Plant disease identification from images captured by digital cameras is an area of active research. Use of various machine learning algorithms for plant disease classification and the evolution of deep convolutional neural network (CNN) based architectures have further enhanced the plant disease classification accuracy. In this context, an automated computer vision-based plant disease detection and classification scheme from plant and leaf’s photographs will be highly desirable. Although, there exist a few techniques currently used in an adhoc fashion for plant disease detection and/or classification, a systematic study to evaluate their usage and efficacy on actual plant data has largely remained unexplored.The aim of this paper is to evaluate various CNN based state-of-the-art transfer learning architectures like GoogLeNet, AlexNet, VGG16 and ResNet50V2 models for plant disease detection and classification. The models were tested on popular publicly available three plant disease benchmark database such as PlantVillage Dataset, New Plant Disease Dataset and Plant Pathology Dataset. Various validation metrics such as Precision, Recall, F1 score and overall accuracy were used to evaluate the final results of the experiments, which revealed that VGG16 rendered highest accuracy of 96.6%, 98.5% and 89% on the three dataset respectively, outperforming all other state-of-the-art models.

With the rapid development of precision agriculture and smart agriculture, the need to build an automatic identification and detection system for diseases and insect pests is increasing. Using computers to correctly label plant diseases and insect pests is an important prerequisite for achieving accurate classification of plant diseases and insect pests and ensuring system performance. In order to improve the accuracy of computer classification of plant pests and diseases, this paper proposes an automatic pest identification method based on the Vision Transformer (ViT). In order to avoid training overfitting, the plant diseases and insect pests data sets are enhanced by methods such as Histogram Equalization, Laplacian, Gamma Transformation, CLAHE, Retinex-SSR, and Retinex-MSR. Then use the enhanced data set to train the constructed ViT neural network, so as to realize the automatic classification of plant diseases and insect pests. The simulation results show that the constructed ViT network has a test recognition accuracy rate of 96.71% on the plant disease and insect pest public data set Plant_Village, which is about 1.00% higher than the Plant disease and pest identification method based on traditional convolutional neural networks such as GoogleNet and EfficentNetV2.

Early detection of infestation by mustard aphid, vegetable thrips and two-spotted spider mite in bok choy with deep neural network (DNN) classification model using hyperspectral imaging data

Subsistence farmers and global food security depend on sufficient food production, which aligns with the UN's “Zero Hunger,” “Climate Action,” and “Responsible Consumption and Production” sustainable development goals. In addition to already available methods for early disease detection and classification facing overfitting and fine feature extraction complexities during the training process, how early signs of green attacks can be identified or classified remains uncertain. Most pests and disease symptoms are seen in plant leaves and fruits, yet their diagnosis by experts in the laboratory is expensive, tedious, labor-intensive, and time-consuming. Notably, how plant pests and diseases can be appropriately detected and timely prevented is a hotspot paradigm in smart, sustainable agriculture remains unknown. In recent years, deep transfer learning has demonstrated tremendous advances in the recognition accuracy of object detection and image classification systems since these frameworks utilize previously acquired knowledge to solve similar problems more effectively and quickly. Therefore, in this research, we introduce two plant disease detection (PDDNet) models of early fusion (AE) and the lead voting ensemble (LVE) integrated with nine pre-trained convolutional neural networks (CNNs) and fine-tuned by deep feature extraction for efficient plant disease identification and classification. The experiments were carried out on 15 classes of the popular PlantVillage dataset, which has 54,305 image samples of different plant disease species in 38 categories. Hyperparameter fine-tuning was done with popular pre-trained models, including DenseNet201, ResNet101, ResNet50, GoogleNet, AlexNet, ResNet18, EfficientNetB7, NASNetMobile, and ConvNeXtSmall. We test these CNNs on the stated plant disease detection and classification problem, both independently and as part of an ensemble. In the final phase, a logistic regression (LR) classifier is utilized to determine the performance of various CNN model combinations. A comparative analysis was also performed on classifiers, deep learning, the proposed model, and similar state-of-the-art studies. The experiments demonstrated that PDDNet-AE and PDDNet-LVE achieved 96.74% and 97.79%, respectively, compared to current CNNs when tested on several plant diseases, depicting its exceptional robustness and generalization capabilities and mitigating current concerns in plant disease detection and classification.

Our project presents an innovative approach to address the crucial issue of plant disease identification through the utilization of deep learning techniques. Agricultural productivity is significantly affected by plant diseases, leading to economic losses and food security concerns. In this research, a comprehensive dataset comprising images of healthy and diseased plants is collected and pre-processed for training deep convolutional neural networks (CNNs). The proposed system harnesses the power of deep learning to automatically learn intricate patterns and features from plant images, enabling accurate classification between healthy and diseased states. The trained model is evaluated on an independent dataset to assess its classification performance. Various deep learning architectures, such as VGG, ResNet, and Inception, are experimented with to identify the most suitable architecture for achieving high accuracy and robustness. To enhance the model's generalization capability, data augmentation techniques are employed during training. Transfer learning is also explored, allowing the pre-trained models to be fine-tuned for the specific task of plant disease classification. The performance metrics, including accuracy, precision, recall, and F1-score, are thoroughly evaluated to quantify the model's effectiveness. The proposed deep learning-based plant disease classification system holds great promise for real-world agricultural applications. Its automated and accurate nature has the potential to revolutionize plant disease management by enabling early detection and timely intervention. As a result, this research contributes to the advancement of precision agriculture practices, helping to mitigate the adverse impacts of plant diseases and promote sustainable agricultural production.

Timely and accurate identification of plant diseases plays a crucial role in maintaining crop health and improving agricultural productivity. Traditional machine learning and deep learning methods have shown promise in plant disease classification, but challenges remain in feature selection and hyperparameter tuning. This paper proposes a methodology utilizing the Dragonfly Optimization Algorithm (DOA) to enhance both feature selection and the hyperparameter tuning of a Convolutional Neural Network (CNN) model. The optimized framework was evaluated using the several plant disease dataset. Experimental results demonstrate that the proposed DOA- based approach significantly improves classification accuracy, reaching up to 97.85%, and accelerates convergence, outperforming traditional methods such as Genetic Algorithms, Particle Swarm Optimization, and baseline CNNs. The model’s efficiency and high accuracy make it suitable for real-time deployment in agricultural decision-support systems.

A review of imaging techniques for plant disease detection

Accurately recognising and forecasting plant disease plays a significant role in the agricultural sector at an earlier stage. Thus, it enables timely intervention to avoid the propagation of disease, reduce crop losses and enhance productivity. Several deep learning techniques have emerged for segmenting and classifying plant diseases. However, the presence of noise in the images is highly affecting the image quality, leading to poor outcomes. To address these challenges, a deep learning-aided plant disease classification method is introduced. The key objective of the work is to classify the disease and reduce damage caused by plant diseases. In the initial phase, the images are garnered from the standard sources and provided to the segmentation phase. Here, the affected regions of the images are segmented through Optimised K-Means Clustering (OKMC). Here, the segmentation process can effectively handle a large number of datasets and also it can segment the Region Of Interest (ROI) from the complex background. During this phase, the parameters of the OKMC are optimally tuned using an Iterative-based Upgrading in Pine Cone Optimisation (IUPCO). IUPCO can effectively solve complex optimisation problems and help the developed technique achieve better performance in the classification stage. In this stage, the classification is carried out using an Attention-based Multi-Dilated DenseNet (AMD-DNet). This model aims to achieve precise disease classification outcomes. The attention mechanism in the proposed approach aids in focusing on the relevant features in the images. Further, the multiscale operation can capture the features at different scales and make the classification process more robust. Evaluation is conducted on the developed approach to validate its effectiveness in plant disease classification. The outcomes showcase the developed approach’s potential as a robust result in the field.

<span id="docs-internal-guid-01580d49-7fff-6f2a-70d1-7893ec0a6e14"><span>Plant diseases are a major cause of destruction and death of most plants and especially trees. However, with the help of early detection, this issue can be solved and treated appropriately. A timely and accurate diagnosis is critical in maintaining the quality of crops. Recent innovations in the field of deep learning (DL), especially in convolutional neural networks (CNNs) have achieved great breakthroughs across different applications such as the classification of plant diseases. This study aims to evaluate scratch and pre-trained CNNs in the classification of tomato plant diseases by comparing some of the state-of-the-art architectures including densely connected convolutional network (Densenet) 120, residual network (ResNet) 101, ResNet 50, ReseNet 30, ResNet 18, squeezenet and Vgg.net. The comparison was then evaluated using a multiclass statistical analysis based on the F-Score, specificity, sensitivity, precision, and accuracy. The dataset used for the experiments was drawn from 9 classes of tomato diseases and a healthy class from PlantVillage. The findings show that the pretrained Densenet-120 performed excellently with 99.68% precision, 99.84% F-1 score, and 99.81% accuracy, which is higher compared to its non-trained based model showing the effectiveness of using a combination of a CNN model with fine-tuning adjustment in classifying crop diseases.</span></span>

Global food security is facing numerous severe challenges. Population growth, climate change, and irrational agricultural inputs have led to a reduction in available arable land, a decline in soil fertility, and difficulties in increasing crop yields. As a result, the supply of food and agricultural products is under serious threat. Against this backdrop, the development of new technologies to increase the production of food and agricultural products and ensure their supply is extremely urgent. Agricultural nanotechnology, as an emerging technology, mainly utilizes the characteristics of nanomaterials such as small size, large specific surface area, and surface effects. It plays a role in gene delivery, regulating crop growth, adsorbing environmental pollutants, detecting the quality of agricultural products, and preserving fruits and vegetables, providing important technical support for ensuring the global supply of food and agricultural products. Currently, the research focus of agricultural nanotechnology is concentrated on the design and preparation of nanomaterials, the regulation of their properties, and the optimization of their application effects in the agricultural field. In terms of the research status, certain progress has been made in the research of nano-fertilizers, nano-pesticides, nano-sensors, nano-preservation materials, and nano-gene delivery vectors. However, it also faces problems such as complex processes and incomplete safety evaluations. This review focuses on the horticultural industry, comprehensively expounding the research status and application progress of agricultural nanotechnology in aspects such as the growth regulation of horticultural crops and the quality detection and preservation of horticultural products. It also deeply analyzes the opportunities and challenges faced by the application of nanomaterials in the horticultural field. The aim is to provide a reference for the further development of agricultural nanotechnology in the horticultural industry, promote its broader and more efficient application, contribute to solving the global food security problem, and achieve sustainable agricultural development.

Early plant diseases and pests identification reduces social, economic, and environmental deficiencies entailing toxic chemical utilization on agricultural farms, thus posing a threat to global food security. An enhanced convolutional neural network (CNN) along with long short-term memory (LSTM) using a majority voting ensemble classifier has been proposed to tackle plant pest and disease identification and classification. Within pre-trained models, deep feature extractions have been obtained from connected layers. Deep features have been extracted and are sent to the LSTM layer to build a robust, enhanced LSTM-CNN model for detecting plant pests and diseases. Experiments were carried out using a Turkey dataset, with 4447 apple pests and diseases categorized into 15 different classes. The study was evaluated in different CNNs using logistic regression (LR), LSTM, and extreme learning machine (ELM), focusing on plant disease detection problems. The ensemble majority voting classifier was used at the LSTM layer to detect and classify plant disease labels. Furthermore, an autonomous selection of the optimal LSTM layer network parameters was applied. Finally, the performance was validated based on sensitivity, F1 score, accuracy, and specificity using LSTM, ELM, and LR classifiers. The presented model attained 99.2% accuracy compared to the cutting-edge models on different classifiers such as LSTM, LR, and ELM, and performed better compared to transfer learning. Pre-trained models, such as VGG19, VGG18, and AlexNet, demonstrated better accuracy when the fc6 layer was compared with other layers. © 2023 Society of Chemical Industry.

Under the requirements for high-quality development, the coordinated promotion of agricultural carbon emission reduction and agricultural product supply guarantee in China is crucial to hold the bottom line of national food security as well as promote agricultural green transformation and development. Based on such situation, from the perspective of decoupling effect, driving factors and the prediction, this paper uses panel data of 30 provinces in China from 2011 to 2020, takes the carbon emission formula, the “two-stage rolling” Tapio decoupling elasticity coefficient method, the spatial Durbin model and the Grey model optimized by the Simpson formula background value to quantify the relationship between agricultural carbon emission and agricultural product supply, analyze the driving effects of agricultural carbon emission reduction and agricultural product increase, and predict the decoupling state of agricultural carbon emission and agricultural product supply between 2021 and 2025, so as to draw a scientific basis that is conducive to the coordinated promotion of agricultural carbon emission reduction and agricultural product supply guarantee in China. The result shows that: (1) The decoupling state of agricultural carbon emission and agricultural product supply shows generally “the eastern and central regions are better than the western regions” in China, and the decoupling state has improved significantly year by year. Green technology innovation (GTI), agricultural carbon emission and agricultural product supply in China have significant spatial differences and spatial auto-correlation, which shows the spatial factors cannot be ignored; (2) Green technology innovation and agricultural carbon emission in local and adjacent provinces are both in an inverted “U-shaped” relationship, meaning that high level green technology innovation is an effective way to reduce carbon emission. Though green technology innovation and agricultural product supply in local and adjacent provinces are both in a positive “U-shaped” relationship, but the minimum value of lnGTI is greater than 0, which indicates that current level of green technology has been raised to a certain level, effectively improving the output of agricultural products; (3) Compared with those in 2016–2020 in China, it is projected that in 2021–2025 the decoupling state of agricultural carbon emission and agricultural product supply will be improved significantly, and the provinces below the optimal state will leave the extremely unreasonable strong negative decoupling state, mainly show recessionary decoupling and recessionary connection. Our findings provide Chinese decision-makers with corresponding references to formulate accountable and scientific regional policies in order to achieve high-quality development of agriculture and realize “Double carbon” target in China.

DFN-PSAN: Multi-level deep information feature fusion extraction network for interpretable plant disease classification

The detection and classification of plant diseases are crucial to ensuring food security and maximizing agricultural productivity. Traditional methods of plant disease identification are time-consuming and labor-intensive, necessitating the adoption of more efficient and accurate techniques. In recent years, advancements in machine learning have led to the development of robust methods for automated plant disease detection. This research paper presents a novel approach for plantdisease detection using Convolutional Neural Networks (CNNs). CNNs have demonstrated exceptional performance in image recognition tasks, making them a promising choice for detecting diseases in plant images. The proposed system utilizes a pre- processed dataset of plant images, comprising both healthy and diseased samples, to train the CNN model. Keywords—Plant disease and detection, convolutional neural networks, deep learning architectures, feature extraction, classifier methods

Plant diseases are the primary issue that reduces agricultural yield and production, causing significant economic losses and instability in the food supply. In plants, citrus is a fruit crop of great economic importance, produced and typically grown in about 140 countries. However, citrus cultivation is widely affected by various factors, including pests and diseases, resulted in significant yield and quality losses. In recent years, computer vision and machine learning have been widely used in plant disease detection and classification, which present opportunities for early disease detection and bring improvements in the field of agriculture. Early and accurate detection of plant diseases is crucial to reducing the disease’s spread and damage to the crop. Therefore, this paper employs a two-stage deep CNN model for plant disease detection and citrus diseases classification using leaf images. The proposed model consists of two main stages; (a) proposing the potential target diseased areas using a region proposal network; (b) classification of the most likely target area to the corresponding disease class using a classifier. The proposed model delivers 94.37% accuracy in detection and an average precision of 95.8%. The findings demonstrate that the proposed model identifies and distinguishes between the three different citrus diseases, namely citrus black spot, citrus bacterial canker and Huanglongbing. The proposed model serves as a useful decision support tool for growers and farmers to recognize and classify citrus diseases.