Real-time plant health assessment via implementing cloud-based scalable transfer learning on AWS DeepLens

Khan, Asim; Nawaz, Umair; Ulhaq, Anwaar; Robinson, Ross

doi:10.1371/journal.pone.0243243

Cited by 32 publications

(12 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the deep model proposed by A. Khan et al (2020) and implemented on AWS DeepLens, 25 distinct disease categories in Apple, Grape, Peach, Potato, Strawberry along with tomatoes can be constantly predicted. This structure model acquired 98.78% exactness for the real time environment.…”

Section: Associated Workmentioning

confidence: 99%

Plant Disease Recognition Using Residual Convolutional Enlightened Swin Transformer Networks

Ponugoti

Anandan

Abualigah

2023

Preprint

View full text Add to dashboard Cite

Adoption of cutting-edge technology such as the Internet of Things (IoT) as well as Deep Learning ideas in smart agricultural system has expanded dramatically in recent years in order to ensure humanity's long-term viability. It is critical to distinguish the plant photos captured for monitoring and, as a result, disease and pest prevention. Currently, deep learning methods are employed for an efficient recognition of plant disorders. However, categorization and recognition of plant diseases is a difficult task due to the presence of low-intensity data in the image, the presence of noise in the sample, and differences in the position, chrominance, and colour similarities among both healthy and diseased plants. plant images. Hence, the overarching objective is to design the custom and efficient deep learning model that can yield an accurate identification of plant diseases under the above mentioned real time environment. In this research article, novel ensemble of residual convolutional networks and Swin transformers has been proposed. Swin Transformers (ST) is hierarchal architecture which brings the greater efficiency and flexibility at various scales and has linear computational complexity with respect to the image size. Therefore, combining the Swin Transformers and powerful Residual networks will extract the numerous deep key point features that aids for the better classification and recognition of plant diseases under different real time circumstances. PlantVillage Kaggle datasets are used for extended experimentation, and various performance measures including as accuracy, precision, recall, specificity, and F1-score are computed and analysed. To prove the superiority of the proposed model, existing architecture such as FCN-8 s, CED-Net, SegNet, DeepLabv3, Densenets and Centernets. The experimental findings show that the suggested model outperformed the other existing techniques in terms of accuracy, precision, recall, and F1-score. Also comprehensive analysis shows that the proposed model is more capable and reliable in identifying diseases in plants under real time circumstances.

show abstract

Section: Associated Workmentioning

confidence: 99%

Plant Disease Recognition Using Residual Convolutional Enlightened Swin Transformer Networks

Ponugoti

Anandan

Abualigah

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…On the other hand, in practical research work, it is usually difficult to obtain a large amount of labeled image data. Therefore, transfer learning is often applied to train neural networks using relatively small datasets and has been proven to be a very effective method [26].…”

Section: Transfer Learningmentioning

confidence: 99%

Transfer Learning for Leaf Small Dataset Using Improved ResNet50 Network with Mixed Activation Functions

Zhang

Zhu

Ge-Zhang

et al. 2022

Forests

View full text Add to dashboard Cite

Taxonomic studies of leaves are one of the most effective means of correctly identifying plant species. In this paper, mixed activation function is used to improve the ResNet50 network in order to further improve the accuracy of leaf recognition. Firstly, leaf images of 15 common tree species in northern China were collected from the Urban Forestry Demonstration Base of Northeast Forestry University (45°43′–45°44′ N, 126°37′–126°38′ E, forest type was artificial forest), and a small leaf dataset was established. After that, seven commonly used activation functions were selected to improve the ResNet50 network structure, and the improved network was applied to the transfer learning research of the leaf small dataset. On this basis, five activation functions with better performance were selected for the study of mixed activation functions in deep learning. Two of these five activation functions are arbitrarily selected for combination, and a total of twenty combinations are obtained. Further, the first activation function was used in each combination to replace the first ReLU function after all addition operations in the ResNet50 network residual block structure, and another activation function was used to replace the other position ReLU functions. The experimental results show that in the transfer learning of the leaf small dataset using the ResNet50 deep residual network, the appropriate combination of mixed activation functions can increase the performance of the improved network to a certain extent. Among them, the ELU-Swish1 combination has the most significant improvement effect on the network performance, whose final effective validation accuracy reaches 98.17%. Furthermore, the comparison with GoogLeNet and VGG-16 also demonstrates the excellent performance of the improved ELU-Swish1 ResNet50 (ES-ResNet50) network architecture. Finally, tests on the other two small leaf datasets, Flavia and Swedish, also demonstrate the performance improvement of ES-ResNet50. The validation accuracy of the improved ES-Resnet 50 algorithm on these two datasets reaches 99.30% and 99.39%, respectively. All these experiments prove that the recognition performance of leaf transfer learning using the ES-ResNet50 network is indeed improved, which may be caused by the complementarity of the e-exponential gradient of ELU and Swish1 activation functions in the negative region.

show abstract

“…Effective automated detection of apple diseases during production not only promptly monitors the health status of apples but also helps orchard farmers to correctly judge apple diseases. They can then implement timely prevention and control to avoid large-scale diseases, which is crucial for promoting the healthy growth of apples and increasing the economic benefits of orchards [ 3 , 4 ].…”

Section: Introductionmentioning

confidence: 99%

A method of detecting apple leaf diseases based on improved convolutional neural network

2022

PLoS ONE

View full text Add to dashboard Cite

Apple tree diseases have perplexed orchard farmers for several years. At present, numerous studies have investigated deep learning for fruit and vegetable crop disease detection. Because of the complexity and variety of apple leaf veins and the difficulty in judging similar diseases, a new target detection model of apple leaf diseases DF-Tiny-YOLO, based on deep learning, is proposed to realize faster and more effective automatic detection of apple leaf diseases. Four common apple leaf diseases, including 1,404 images, were selected for data modeling and method evaluation, and made three main improvements. Feature reuse was combined with the DenseNet densely connected network and further realized to reduce the disappearance of the deep gradient, thus strengthening feature propagation and improving detection accuracy. We introduced Resize and Re-organization (Reorg) and conducted convolution kernel compression to reduce the calculation parameters of the model, improve the operating detection speed, and allow feature stacking to achieve feature fusion. The network terminal uses convolution kernels of 1 × 1, 1 × 1, and 3 × 3, in turn, to realize the dimensionality reduction of features and increase network depth without increasing computational complexity, thus further improving the detection accuracy. The results showed that the mean average precision (mAP) and average intersection over union (IoU) of the DF-Tiny-YOLO model were 99.99% and 90.88%, respectively, and the detection speed reached 280 FPS. Compared with the Tiny-YOLO and YOLOv2 network models, the new method proposed in this paper significantly improves the detection performance. It can also detect apple leaf diseases quickly and effectively.

show abstract

Real-time plant health assessment via implementing cloud-based scalable transfer learning on AWS DeepLens

Cited by 32 publications

References 43 publications

Plant Disease Recognition Using Residual Convolutional Enlightened Swin Transformer Networks

Plant Disease Recognition Using Residual Convolutional Enlightened Swin Transformer Networks

Transfer Learning for Leaf Small Dataset Using Improved ResNet50 Network with Mixed Activation Functions

A method of detecting apple leaf diseases based on improved convolutional neural network

Contact Info

Product

Resources

About