Assessing the efficacy of machine learning techniques to characterize soybean defoliation from unmanned aerial vehicles

Drone advancements have ushered in new trends and possibilities in a variety of sectors, particularly for small-sized drones. Drones provide navigational interlocation services, which are made possible by the Internet of Things (IoT). Drone networks, on the other hand, are subject to privacy and security risks due to design flaws. To achieve the desired performance, it is necessary to create a protected network. The goal of the current study is to look at recent privacy and security concerns influencing the network of drones (NoD). The current research emphasizes the importance of a security-empowered drone network to prevent interception and intrusion. A hybrid ML technique of logistic regression and random forest is used for the purpose of classification of data instances for maximal efficacy. By incorporating sophisticated artificial-intelligence-inspired techniques into the framework of a NoD, the proposed technique mitigates cybersecurity vulnerabilities while making the NoD protected and secure. For validation purposes, the suggested technique is tested against a challenging dataset, registering enhanced performance results in terms of temporal efficacy (34.56 s), statistical measures (precision (97.68%), accuracy (98.58%), recall (98.59%), F-measure (99.01%), reliability (94.69%), and stability (0.73).

show abstract

“…Based on anomaly elimination using quantile regression [ 42 ], level-1 of physical data security is ensured.…”

Section: Proposed Frameworkmentioning

confidence: 99%

Smart Cybersecurity Framework for IoT-Empowered Drones: Machine Learning Perspective

Aldaej

Ahanger

Atiquzzaman

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…From astronomy [30,32] to agriculture [2,4,47,48] to K-12 education [5,28] to software bugs and analysis [34,38,39], the velocity of dataset creation has surged in recent years. While machine and deep learning algorithms seek to perform classification and segmentation on all datasets, the semantics around these operations vary for each dataset.…”

Section: A Surge In Datasetsmentioning

confidence: 99%

“…We select 4 classical datasets based on popularity: CIFAR-10, CIFAR-100, imagenette2 (a subset of Imagenet), and MNIST ( [8,19,22]). The digital agriculture datasets selected are as follows: fruits-360, PlantVillage, weed seedlings, and leaf defoliation dataset ( [1,16,25,48]). We select these datasets because they each represent a fundamental task in digital agriculture (e.g.…”

Section: Fig 1 Small Fully Connected Classification Networkmentioning

confidence: 99%

“…With the rise of data-driven science, an increasing number of large, discipline-specific image datasets are being introduced to the public [21,45,46,48]. However, despite a widespread increase in datasets, an analysis by a team of Google and Berkeley researchers found that a very small number of datasets are used for computer vision benchmarking [17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Case for Dataset Specific Profiling

Ockerman¹,

Wu²,

Stewart³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Data-driven science is an emerging paradigm where scientific discoveries depend on the execution of computational AI models against rich, discipline-specific datasets. With modern machine learning frameworks, anyone can develop and execute computational models that reveal concepts hidden in the data that could enable scientific applications. For important and widely used datasets, computing the performance of every computational model that can run against a dataset is cost prohibitive in terms of cloud resources. Benchmarking approaches used in practice use representative datasets to infer performance without actually executing models. While practicable, these approaches limit extensive dataset profiling to a few datasets and introduce bias that favors models suited for representative datasets. As a result, each dataset's unique characteristics are left unexplored and subpar models are selected based on inference from generalized datasets. This necessitates a new paradigm that introduces dataset profiling into the model selection process. To demonstrate the need for dataset-specific profiling, we answer two questions:(1) Can scientific datasets significantly permute the rankorder of computational models compared to widely used representative datasets? (2) If so, could lightweight model execution improve benchmarking accuracy? Taken together, the answers to these questions lay the foundation for a new dataset-aware benchmarking paradigm.

show abstract

“…With the rapid development of computer technology, a new visual recognition method based on machine learning [4], has been employed for disease recognition. Using machine learning methods to identify crop diseases generally involves three steps: spot segmentation, feature extraction, and classifier recognition [5].…”

Section: Introductionmentioning

confidence: 99%

GrapeNet: A Lightweight Convolutional Neural Network Model for Identification of Grape Leaf Diseases

et al. 2022

View full text Add to dashboard Cite

Most convolutional neural network (CNN) models have various difficulties in identifying crop diseases owing to morphological and physiological changes in crop tissues, and cells. Furthermore, a single crop disease can show different symptoms. Usually, the differences in symptoms between early crop disease and late crop disease stages include the area of disease and color of disease. This also poses additional difficulties for CNN models. Here, we propose a lightweight CNN model called GrapeNet for the identification of different symptom stages for specific grape diseases. The main components of GrapeNet are residual blocks, residual feature fusion blocks (RFFBs), and convolution block attention modules. The residual blocks are used to deepen the network depth and extract rich features. To alleviate the CNN performance degradation associated with a large number of hidden layers, we designed an RFFB module based on the residual block. It fuses the average pooled feature map before the residual block input and the high-dimensional feature maps after the residual block output by a concatenation operation, thereby achieving feature fusion at different depths. In addition, the convolutional block attention module (CBAM) is introduced after each RFFB module to extract valid disease information. The obtained results show that the identification accuracy was determined as 82.99%, 84.01%, 82.74%, 84.77%, 80.96%, 82.74%, 80.96%, 83.76%, and 86.29% for GoogLeNet, Vgg16, ResNet34, DenseNet121, MobileNetV2, MobileNetV3_large, ShuffleNetV2_×1.0, EfficientNetV2_s, and GrapeNet. The GrapeNet model achieved the best classification performance when compared with other classical models. The total number of parameters of the GrapeNet model only included 2.15 million. Compared with DenseNet121, which has the highest accuracy among classical network models, the number of parameters of GrapeNet was reduced by 4.81 million, thereby reducing the training time of GrapeNet by about two times compared with that of DenseNet121. Moreover, the visualization results of Grad-cam indicate that the introduction of CBAM can emphasize disease information and suppress irrelevant information. The overall results suggest that the GrapeNet model is useful for the automatic identification of grape leaf diseases.

show abstract

Assessing the efficacy of machine learning techniques to characterize soybean defoliation from unmanned aerial vehicles

Cited by 25 publications

References 42 publications

Smart Cybersecurity Framework for IoT-Empowered Drones: Machine Learning Perspective

Smart Cybersecurity Framework for IoT-Empowered Drones: Machine Learning Perspective

A Case for Dataset Specific Profiling

GrapeNet: A Lightweight Convolutional Neural Network Model for Identification of Grape Leaf Diseases

Contact Info

Product

Resources

About