MDFC–ResNet: An Agricultural IoT System to Accurately Recognize Crop Diseases

Hu, Weijian; Fan, Jun; Du, Ying; Li, Baoshan; Xiong, Naixue; Bekkering, Ernst

doi:10.1109/access.2020.3001237

Cited by 95 publications

(21 citation statements)

References 41 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To work in synergy with the system proposed in [ 52 ], the authors in [ 23 , 55 ] integrated IoT and DL techniques for disease detection in crops. However, the system could not prove its practical application due to low accuracy.…”

Section: Related Workmentioning

confidence: 99%

“…The potential of IoT in data collection, data storage, quick processing, and efficacy of interpretable ML, DL, and transfer learning techniques in object detection, classification, visualization, and pattern matching even with the small-sized labelled dataset [ 19 , 23 , 24 ] motivated the authors to employ the integration of these techniques for developing a framework for detection of disease in pearl millet.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

IoT and Interpretable Machine Learning Based Framework for Disease Prediction in Pearl Millet

Kundu

Rani

Dhaka

et al. 2021

Sensors

122

View full text Add to dashboard Cite

Decrease in crop yield and degradation in product quality due to plant diseases such as rust and blast in pearl millet is the cause of concern for farmers and the agriculture industry. The stipulation of expert advice for disease identification is also a challenge for the farmers. The traditional techniques adopted for plant disease detection require more human intervention, are unhandy for farmers, and have a high cost of deployment, operation, and maintenance. Therefore, there is a requirement for automating plant disease detection and classification. Deep learning and IoT-based solutions are proposed in the literature for plant disease detection and classification. However, there is a huge scope to develop low-cost systems by integrating these techniques for data collection, feature visualization, and disease detection. This research aims to develop the ‘Automatic and Intelligent Data Collector and Classifier’ framework by integrating IoT and deep learning. The framework automatically collects the imagery and parametric data from the pearl millet farmland at ICAR, Mysore, India. It automatically sends the collected data to the cloud server and the Raspberry Pi. The ‘Custom-Net’ model designed as a part of this research is deployed on the cloud server. It collaborates with the Raspberry Pi to precisely predict the blast and rust diseases in pearl millet. Moreover, the Grad-CAM is employed to visualize the features extracted by the ‘Custom-Net’. Furthermore, the impact of transfer learning on the ‘Custom-Net’ and state-of-the-art models viz. Inception ResNet-V2, Inception-V3, ResNet-50, VGG-16, and VGG-19 is shown in this manuscript. Based on the experimental results, and features visualization by Grad-CAM, it is observed that the ‘Custom-Net’ extracts the relevant features and the transfer learning improves the extraction of relevant features. Additionally, the ‘Custom-Net’ model reports a classification accuracy of 98.78% that is equivalent to state-of-the-art models viz. Inception ResNet-V2, Inception-V3, ResNet-50, VGG-16, and VGG-19. Although the classification of ‘Custom-Net’ is comparable to state-of-the-art models, it is effective in reducing the training time by 86.67%. It makes the model more suitable for automating disease detection. This proves that the proposed model is effective in providing a low-cost and handy tool for farmers to improve crop yield and product quality.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

IoT and Interpretable Machine Learning Based Framework for Disease Prediction in Pearl Millet

Kundu

Rani

Dhaka

et al. 2021

Sensors

122

View full text Add to dashboard Cite

show abstract

“…However, this technique poses a high computational cost. Hu et al 18 developed an IoT technique with deep learning for building an IoT model for crop disease detection. This model could determine the crop disease and fed diagnostic outcomes to the farmers.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Hence, the issue relies upon discovering the cause of detection. 18 • The Sine cosine algorithm-based rider neural network is utilized to detect if the plant is affected by disease or not, but this method failed to detect the kind of disease in the plant. 10 IoT consists of different objects that consist of smart devices and are linked to transfer accumulated data to the network.…”

Section: Challengesmentioning

confidence: 99%

Deep computation model to the estimation of sulphur dioxide for plant health monitoring in IoT

Karnati¹,

Rao

Prakash

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

The Internet of Things (IoT) is an emerging domain in recent days as they provided a huge number of applications in day-to-day lives. In contrast to the agricultural sector, the automatic techniques for recognizing plant disease have different benefits and pose several issues. In addition, inappropriate diagnoses are ineffectual in treating the disease and may affect the crop yield. This paper presents a novel technique for plant health monitoring by estimating sulphur dioxide. Here, the simulation of IoT was performed for improved functioning. After that, the cluster head selection and routing are performed using the proposed invasive water cycle (IWC) algorithm, which is devised by integrating the water cycle algorithm (WCA) and invasive weed optimization (IWO) algorithm. Here, the fitness function is newly modeled using certain factors involving Energy, intra and intercluster distance, and delay. After the cluster head selection and routing, the sulphur dioxide content from the soil is estimated. For sulphur dioxide estimation, the soil data is considered the input data, and then the data transformation is performed to transform the data. After that, the feature selection is performed by Mahalanobis distance, and then sulphur dioxide from the soil is estimated using Deep Q-Network, where training is performed using the proposed IWC algorithm. The proposed IWC-based Deep Q-Network offered improved performance with the highest accuracy of 0.941, and the smallest root mean square error (RMSE) of 0.242. In addition, the minimal Energy and highest Throughput are computed by the proposed IWC-based Deep Q-Network.

show abstract

“…The model used the informative regions of images to recognize disease, and the F1-score reached 93.05%. Weijian Hu et al [28] proposed MDF-ResNet for fine-grained identification. The model can fuse species, coarse-grained diseases and fine-grained disease features to identify diseases.…”

Section: Introductionmentioning

confidence: 99%

Apple Leaf Disease Recognition and Sub-Class Categorization Based on Improved Multi-Scale Feature Fusion Network

et al. 2021

View full text Add to dashboard Cite

Apple diseases cause a lot of economic losses to fruit growers in China. Early diagnosis and accurate recognition of apple diseases can control the spread of disease and reduce production costs. However, the significance of disease characteristic of apple leaves in complex environment is relatively weak, and the fine-grain among different diseases of apple leaves is high, and the conventional feature extraction methods will lose the discrimination information. To solve these problems, an apple disease classification model based on multi-scale feature fusion is proposed in this paper. Firstly, the information flow of conventional residual network (ResNet) was improved to achieve efficient information circulation through changing the position of batch normalization and rectified linear unit (ReLU). Secondly, in order to solve the problem of serious loss of information in ResNet downsample, the channel projection and spatial projection of downsample were separated. Lastly, the 3×3 conv in ResBlocks was replaced by pyramid convolution, and the dilated convolution with different dilation rate was introduced into pyramid convolution to enhance the output scale of feature maps and improve the robustness of the model. The optimized model was verified on the dataset of this paper, and the optimized model had stronger anti-noise ability and better robustness, excellent learning effect and fast convergence speed. The classification accuracy on the original dataset is 94.24%, and that on the preprocessed dataset is 94.99%. The results demonstrate that the optimal model has a high accuracy, which can provide a reference for the prevention and control of apple leaf diseases.INDEX TERMS Apple disease, multi-scale feature fusion, deep learning, ResNet, classification.

show abstract

MDFC–ResNet: An Agricultural IoT System to Accurately Recognize Crop Diseases

Cited by 95 publications

References 41 publications

IoT and Interpretable Machine Learning Based Framework for Disease Prediction in Pearl Millet

IoT and Interpretable Machine Learning Based Framework for Disease Prediction in Pearl Millet

Deep computation model to the estimation of sulphur dioxide for plant health monitoring in IoT

Apple Leaf Disease Recognition and Sub-Class Categorization Based on Improved Multi-Scale Feature Fusion Network

Contact Info

Product

Resources

About