Figure - available from: Journal of Food Quality
This content is subject to copyright. Terms and conditions apply.
![Typical deep convolutional neural network architecture [6].](publication/358524767/figure/fig2/AS:1122296504811665@1644587746753/Typical-deep-convolutional-neural-network-architecture-6.jpg)
Source publication
![Typical deep convolutional neural network architecture [6].](publication/358524767/figure/fig2/AS:1122296504811665@1644587746753/Typical-deep-convolutional-neural-network-architecture-6_Q320.jpg)
![2D convolution level function of a CNN [26].](publication/358524767/figure/fig3/AS:1122296504811670@1644587746780/2D-convolution-level-function-of-a-CNN-26_Q320.jpg)
![Cooccurrence matrices [35].](publication/358524767/figure/fig5/AS:1122296509005831@1644587747237/Cooccurrence-matrices-35_Q320.jpg)
Plant diseases are unfavourable factors that cause a significant decrease in the quality and quantity of crops. Experienced biologists or farmers often observe plants with the naked eye for disease, but this method is often imprecise and can take a long time. In this study, we use artificial intelligence and computer vision techniques to achieve th...
Similar publications
The timely and accurate identification of stripe rust and leaf rust is essential in effective disease control and the safe production of wheat worldwide. To investigate methods for identifying the two diseases on different wheat varieties based on image processing technology, single-leaf images of the diseases on different wheat varieties, acquired...
Citations
... Ferentinos et al. 33 introduced a CNN model to diagnose and detect plant diseases by utilizing images of both diseased plants and healthy leaves. Singth et al. 34 developed a hybrid feature-based method for disease detection in plant leaves. This method combines color, texture, and deep features to form hybrid features, which are then classified using a random forest algorithm after data augmentation and Bayesian optimized support vector classifier. ...
Deep learning has emerged as a highly effective and precise method for classifying images. The presence of plant diseases poses a significant threat to food security. However, accurately identifying these diseases in plants is challenging due to limited infrastructure and techniques. Fortunately, the recent advancements in deep learning within the field of computer vision have opened up new possibilities for diagnosing plant pathology. Detecting plant diseases at an early stage is crucial, and this research paper proposes a deep convolutional neural network model that can rapidly and accurately identify plant diseases. Given the minimal variation in image texture and color, deep learning techniques are essential for robust recognition. In this study, we introduce a deep, explainable neural architecture specifically designed for recognizing plant diseases. Fine-tuned deep convolutional neural network is designed by freezing the layers and adjusting the weights of learnable layers. By extracting deep features from a down sampled feature map of a fine-tuned neural network, we are able to classify these features using a customized K-Nearest Neighbors Algorithm. To train and validate our model, we utilize the largest standard plant village dataset, which consists of 38 classes. To evaluate the performance of our proposed system, we estimate specificity, sensitivity, accuracy, and AUC. The results demonstrate that our system achieves an impressive maximum validation accuracy of 99.95% and an AUC of 1, making it the most ideal and highest-performing approach compared to current state-of-the-art deep learning methods for automatically identifying plant diseases.
... RF classifier is a supervised ensemble learning algorithm that combines numerous decision trees and makes predictions based on their combined results to enhance model performance. 42 It has several advantages, including built-in feature selection, robustness to overfitting, 43 accuracy, flexibility of variables, scalability, and interpretability. Some of its key hyperparameters are the number and depth of trees in the forest, the minimum number of samples required to split an internal node, and the maximum number of features considered per split. ...
As one of the fastest‐growing neurological disorders, Parkinson's disease is a neurodegenerative, cardinally motor ailment. Associated with the late onset of symptoms and often misdiagnosed, it inflicts massive life handicaps. To aid in its early detection, the research community is seeking alternative in‐vivo biomarkers, mainly in the field of neuroimaging. This study aimed to build a computer‐aided diagnosis system to distinguish between healthy controls (HC) and early Parkinsonian patients (PD). Our classification paradigm encompasses a Convolutional Neural Network built from scratch to extract discriminatory features, followed by a Bayesian‐optimized Random Forest classifier (CNN_RF). We trained and validated our customized model on the MRI images of 178 PD and 124 HC, taken from the benchmark Parkinson's Progression Markers Initiative (PPMI) dataset, as well as their brain tissue segments and Jacobian determinant maps. The classification was evaluated using seven performance metrics. For visual interpretation, we employed Grad‐CAM to generate saliency maps. Our findings demonstrate the robustness of the proposed method, as it outperformed deep‐tuned ResNet18, VGG16, and SqueezeNet, implemented for comparison. Furthermore, it resulted in 98.9% accuracy, 98.6% specificity, 99.0% precision, 99.5% F1‐score, a 97.7% Matthews correlation coefficient (MCC), and an AUC of 99.6% for the classification of fused gray matter and Jacobian map features. This indicates that the tailored CNN_RF possesses superior adaptability to identify intrinsic characteristics linked to the disease, as highlighted in the salient maps showcasing pertinent regions in the striatum, thalamus, frontal, temporal, and insular cortices for Parkinson's disease classification. Moreover, it offers a single modality and cost‐effective CAD, which could pave the way for a feasible early PD diagnosis. As data availability and AI robustness increase, PD diagnosis will no longer be a challenging task in the future.
... Noteworthy approaches include traditional methods such as Grid Search, Random Search, and Bayesian Optimization, as highlighted by Ref. [165]. [7] employ Particle Swarm Optimization (PSO), showcasing the utilization of nature-inspired algorithms for hyperparameter tuning [94]. studied Binary Optimization, Particle Swarm Optimization, and Squared Exponential Kernel, revealing a nuanced strategy for optimization. ...
... Paper Hyperparameter optimization techniques [165] Grid search, Random search, Bayesian optimization [7] Particle Swarm Optimization (PSO) [94] Binary Optimization, Particle Swarm Optimization, Squared Exponential Kernel [59] Tuning learning rate and number of iterations [95] Improved backtracking search algorithm [168] Genetic Algorithm, Firefly Algorithm, Cross-validation, Grid search, Random search, Bayesian Optimization, Adaptive technique [6] Rider Henry Gas Solubility Optimization (RHGSO) [62] Fine-tuning [100] End-to-end trainable attention module [143] Bayesian optimization [166] WOACW (Weight Cooperative Self-Mapping Chaos Optimization Algorithm) [93] Exhaustiveness and Brownian Motion-related Elephant Herding Optimization (EBM-EHO) algorithm [167] Quantum-Inspired Moth Flame Optimizer [67] Bayesian optimization [107] OLIHFA-BA [69] IAOF-CNN [71] Genetic algorithm, Artificial bee colony, Particle swarm optimization [125] Grid search [158] Flower Pollination Algorithm (FPA) [111] Hyperparameter tuning [169] Particle swarm optimization, Artificial fish swarm optimization (AFSO), Efficient artificial fish swarm optimization (EAFSO) [19] Fine-tuning [114] Grid search [115] Water Wave Optimization (WWO) [78] Bayesian optimization [170] Genetic algorithm [80] Hyperparameter tuning B. Gülmez deployment in agriculture is essential to build trust among stakeholders and ensure the responsible use of AI technologies in rice disease detection and management [14]. ...
... The GLCM, histogram of oriented gradients (HoG), and color moments are employed to extract the colors and textures. The features are subsequently merged to create hybrid ones [10]. Effective multivariate analysis necessitates appropriate preparation of near-infrared (NIR) data due to the presence of unforeseen elements including light scattering and background noise [11]. ...
... It was observed that fine-tuned VGG16 outperforms better accuracy as compared to transfer learning. Singh et al. [27] introduced the fine-tuning of the CNN model with the replacement of a softmax classifier with an SVM and a random forest classification technique to enhance performance. This was done to reduce the trainable parameters. ...
... The dataset was obtained from the two sources given in [26,27,32]. The first dataset was obtained from paddy fields maintained by the Bangladesh Rice Research Institute (BRRI) and includes 1426 images of rice diseases [26]. ...
... The input image size is 224 × 224 which is used to train the model. In this paper, images collected from different sources [26,27,32] are used for training and purposes. For residual learning, the loss function is used to train the model, termed FC loss . ...
Modern technology like Artificial Intelligence (AI) must be used in the agricultural sector if sustainable agricultural output is to be achieved. One of the most convenient strategies for resolving current and future issues is data-driven agriculture. For this, disease prediction is a major task for precise farming. For predictive analysis and precise agriculture monitoring systems, with the application of AI, Machine Learning (ML) and Deep Learning (DL) play vital roles in building a more robust system. In this work, we will design a DL-integrated rice disease prediction system to be implemented for precise farming. Improvisation of the developed model to detect rice plant diseases & pest attacks with a high level of precision. In this work, the Progressive Loss-Aware Fine-Tuning Stepwise Learning (PLAFTSL) model is proposed for disease detection. For step-wise learning fine-tuned ResNet50 model is used with the introduction of freezing and unfreezing layers. This reduces the training parameters and thus computational complexity. The introduction of the step-wise and progressive loss-aware layer will result in fast convergence and improved training efficiency during information exchange among layers respectively. Our proposed work uses a dataset from two sources. The result analysis is presented with an ablation study. Additionally, the baseline model, ResNet50, is used to display the outcomes of the ablation. The results demonstrate that the fine-tuned model results in better performance as compared to the transfer learning model. The Conditional Generative Adversarial Network (cGAN) augmentation is also added to the designed model which will improve detection effectiveness and can also manage the imbalance in input data. The model has achieved approx. 98% accuracy and outperforms better with comparative state-of-art models.
... Li et al. [26] addressed the recent trends and problems for identifying plant leaf infection utilizing DL and imaging techniques and a review of various DL-based works plant diagnoses and classifications. Singh et al. [27] offered a CNN-based method to identify diseases from the PlantVillage data set. First, photos were augmented, and in-depth features were identified utilizing CNN. ...
... Moreover, Di and Li [25] suggested the DF-Tiny-YOLO method for detecting apple leaf diseases and obtained mAP and IoU, which were 99.99% and 90.88%, respectively. Singh et al. [27] offered a CNN-based method to identify conditions from the PlantVillage data set. CNN-SVM achieved 92.25% accuracy. ...
Farming supplies nourishment for all humans, especially in times of rapid population growth. The cashew (Anacardium occidentale L.) tree provides nutrition, income, and health benefits through its agricultural products. However, diseases often affect cashew nuts and fruits, resulting in significant production losses. As a result, it is crucial to predict cashew diseases to ensure food supply for the entire population. This study created a database of healthy and diseased cashew nuts and fruits and divided it into two subsets: Training and Testing (Test). Data augmentation was applied to the Training dataset to enhance the images. The CAS-CNN model was developed, and the MobileNetV2 was modified. The performance of the developed CAS-CNN and CAS-MODMOBNET models was evaluated and compared with existing TL models. The CAS-MODMOBNET reached an average accuracy of 99.8% and an Area under the ROC Curve (AUC) of 1.0 on the Test subset. Furthermore, the presented system was analysed with the size, number of layers, and parameters of existing TL models.
... To overcome these problems, some researchers started to use deep learning-based methods, using convolutional neural networks (CNN) and other models to directly learn features from images without human intervention, improving the efficiency and accuracy of identification. For example, Ashutosh Kumard et al. [11] used CNN, Bayesian-optimized SVM, and a random forest classifier based on hybrid features to perform plant leaf disease detection, and the results showed that CNN achieved the highest accuracy of 96.1% in detecting leaf disease in apple, corn, potato, tomato, and rice plants. Nurul Nabilah et al. [12] compared the pepper pest features extracted by the traditional ML method with the deep learning-based methods, which outperformed the traditional feature-based methods. ...
Existing disease detection models for deep learning-based monitoring and prevention of pepper diseases face challenges in accurately identifying and preventing diseases due to inter-crop occlusion and various complex backgrounds. To address this issue, we propose a modified YOLOv7-GCA model based on YOLOv7 for pepper disease detection, which can effectively overcome these challenges. The model introduces three key enhancements: Firstly, lightweight GhostNetV2 is used as the feature extraction network of the model to improve the detection speed. Secondly, the Cascading fusion network (CFNet) replaces the original feature fusion network, which improves the expression ability of the model in complex backgrounds and realizes multi-scale feature extraction and fusion. Finally, the Convolutional Block Attention Module (CBAM) is introduced to focus on the important features in the images and improve the accuracy and robustness of the model. This study uses the collected dataset, which was processed to construct a dataset of 1259 images with four types of pepper diseases: anthracnose, bacterial diseases, umbilical rot, and viral diseases. We applied data augmentation to the collected dataset, and then experimental verification was carried out on this dataset. The experimental results demonstrate that the YOLOv7-GCA model reduces the parameter count by 34.3% compared to the YOLOv7 original model while improving 13.4% in mAP and 124 frames/s in detection speed. Additionally, the model size was reduced from 74.8 MB to 46.9 MB, which facilitates the deployment of the model on mobile devices. When compared to the other seven mainstream detection models, it was indicated that the YOLOv7-GCA model achieved a balance between speed, model size, and accuracy. This model proves to be a high-performance and lightweight pepper disease detection solution that can provide accurate and timely diagnosis results for farmers and researchers.
... Deep learning may be used to detect leaf diseases from collected photos to avert catastrophic crop losses. Using computer vision and artificial intelligence approaches, the authors of [27] have created an intelligent classification method [28] for leaf diseases. These features have been classified in this study using a Bayesian optimum support vector machine classifier, and the accuracy, sensitivity, f-score, and precision of the findings are assessed. ...
Due to the increase in human population, the need for food crops is also increasing day by day. In each year, 10 to 30\(\%\) agricultural yield is lost due to the attack of pests and various diseases. Hence it is challenging to detect the diseased crop early to reduce the loss of crops and retain biodiversity. Several deep-learning models were proposed by researchers for the detection of plant diseases. In this work, we proposed a new energy-efficient convolution neural network architecture and compared it with two existing models, VGG19 and Inception V3. The proposed model is trained and tested by plant village, cassava, and rice data set. The performance analysis shows that the proposed model is able to detect the diseased leaf with 95.17\(\%\) accuracy for the plant village data set, 99.8\(\%\) for the rice data set, and 63\(\%\) for the cassava dataset. The comparison study shows that our proposed architecture performs better compared to the VGG19 and Inception V3 model for both the plant village data set and rice data set. It is also to be noted that for the cassava dataset, the performance of our proposed architecture is at par with the other two models. The experimental results show that the proposed model is 5 times faster than the Inception V3 model and 2 times faster than the VGG19 model on the plant village dataset. It shows the same behavior for the other two datasets also.
... Earlier studies that used machine learning algorithms to identify single or multiple two illnesses in grape plant leaves were created (Singh, Sreenivasu, et al., 2022). The gathered features are down-sampled using a Logistic Regression approach to employ transfer learning to retrain the EfficientNet B7 deep architecture. ...
Plant leaf diseases are challenging to categorize due to the complexity of the pattern variations and the high degrees of inter‐class similarity. Plant ailments harm food quality and production. To ensure the quality and quantity of harvests, it is essential to protect plants from disease. Detection of diseases at an early stage is the main and the most complex task for farmers due to common morphological properties like colour, shape, texture, and edges. In this study, a Hybrid Deep Learning model named Hybrid‐Convolutional Support Machine (H‐CSM) based on ‘Support Vector Machine (SVM)’, ‘Convolutional Neural Network (CNN)’ and ‘Convolutional Block Attention Module (CBAM)’ is proposed for the early diagnosis and classification of leaf diseases in plants leaf. The suggested model can initially identify different plant leaf illnesses, although it is not constrained to these. A database of pictures of plant leaves is used to test the suggested method based on different evaluation parameters. The results were highly promising, with an accuracy of up to 98.72% which has been increased by applying better learning methods. Farmers can quickly identify 36 common diseases with a little instruction for 14 plant categories, enabling them to take prompt preventive measures using the proposed method.
... Tis article has been retracted by Hindawi following an investigation undertaken by the publisher [1]. Tis investigation has uncovered evidence of one or more of the following indicators of systematic manipulation of the publication process: ...
