Recognition of Crop Diseases Based on Depthwise Separable Convolution in Edge Computing

Gao, Ming; Li, Kuan‐Ching; Li, Zhongwen; Han, Qiyi; Fan, Wenjie

doi:10.3390/s20154091

Cited by 14 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Likewise, the authors of [ 57 ] proposed an IoT monitoring framework for detecting tomato diseases. First, a pretraining model is constructed on the cloud by using VGG networks.…”

Section: Artificial Intelligence In Edge-based Iot Applications: Lite...mentioning

confidence: 99%

“…All of these features may reduce the accuracy of the model while increasing the execution time and the computational complexity of the analysis. The authors of [ 54 , 57 , 102 , 138 ] used AI for spatial and temporal redundancy, data imputation, sensing coverage, and pipeline data preprocessing at the edge, respectively. However, not all of them consider the mobility, dynamic, and heterogeneity feature of an edge environment.…”

Section: Open Issues and Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

At the Confluence of Artificial Intelligence and Edge Computing in IoT-Based Applications: A Review and New Perspectives

Bourechak

Zedadra

Kouahla

et al. 2023

Sensors

View full text Add to dashboard Cite

Given its advantages in low latency, fast response, context-aware services, mobility, and privacy preservation, edge computing has emerged as the key support for intelligent applications and 5G/6G Internet of things (IoT) networks. This technology extends the cloud by providing intermediate services at the edge of the network and improving the quality of service for latency-sensitive applications. Many AI-based solutions with machine learning, deep learning, and swarm intelligence have exhibited the high potential to perform intelligent cognitive sensing, intelligent network management, big data analytics, and security enhancement for edge-based smart applications. Despite its many benefits, there are still concerns about the required capabilities of intelligent edge computing to deal with the computational complexity of machine learning techniques for big IoT data analytics. Resource constraints of edge computing, distributed computing, efficient orchestration, and synchronization of resources are all factors that require attention for quality of service improvement and cost-effective development of edge-based smart applications. In this context, this paper aims to explore the confluence of AI and edge in many application domains in order to leverage the potential of the existing research around these factors and identify new perspectives. The confluence of edge computing and AI improves the quality of user experience in emergency situations, such as in the Internet of vehicles, where critical inaccuracies or delays can lead to damage and accidents. These are the same factors that most studies have used to evaluate the success of an edge-based application. In this review, we first provide an in-depth analysis of the state of the art of AI in edge-based applications with a focus on eight application areas: smart agriculture, smart environment, smart grid, smart healthcare, smart industry, smart education, smart transportation, and security and privacy. Then, we present a qualitative comparison that emphasizes the main objective of the confluence, the roles and the use of artificial intelligence at the network edge, and the key enabling technologies for edge analytics. Then, open challenges, future research directions, and perspectives are identified and discussed. Finally, some conclusions are drawn.

show abstract

“…Likewise, the authors of [ 57 ] proposed an IoT monitoring framework for detecting tomato diseases. First, a pretraining model is constructed on the cloud by using VGG networks.…”

Section: Artificial Intelligence In Edge-based Iot Applications: Lite...mentioning

confidence: 99%

Section: Open Issues and Future Directionsmentioning

confidence: 99%

At the Confluence of Artificial Intelligence and Edge Computing in IoT-Based Applications: A Review and New Perspectives

Bourechak

Zedadra

Kouahla

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Yang et al [7] proposed a convolutional rebalancing network for classifying rice pests and diseases that outperformed the stateof-the-art methods of the time. Gu et al [8] used lightweight deep neural network structures and edge computing techniques to achieve efficient crop disease identification. Waheed et al [9] proposed a DenseNet optimization model for maize leaf identification that uses fewer parameters to improve efficiency.…”

Section: Introductionmentioning

confidence: 99%

Crop Pest Image Classification Based on Multi-Scale Convolutional Neural Network

Ma,

Li,

et al. 2023

Fuzzy Systems and Data Mining IX

View full text Add to dashboard Cite

Crop diseases and pests are major threats to crop yield and quality, as well as global food security and agricultural livelihoods. Therefore, it is essential to identify crop pests and diseases in a timely, efficient and accurate manner. In this paper, we propose MConvNeXt, a crop pest classification model based on multi-scale feature fusion, which adds a multi-scale module to the original ConvNeXt network model to better capture feature information at different scales. We experimentally analyzed the MConvNeXt model on the IP102 dataset, and the results show that it outperforms the baseline network and other classical image classification models in pest classification.

show abstract

Hybrid optimized deep quantum neural network in Internet of Things platform using routing algorithm for detecting smart maize leaf disease

Gunisetti,

Koduri,

Jagannathan

et al. 2024

Adaptive Control & Signal

View full text Add to dashboard Cite

SummaryThe productivity in the agricultural sector is minimized due to the disease in plants. In general, the ailments that affect plants are identified by the farmers and the losses are minimized, when the diseases are identified early. The early identification of leaf diseases is difficult in the traditional approaches. Hence, in this article, for detecting maize leaf disease, an adaptive competitive shuffled shepherd optimization‐driven deep quantum neural network (adaptive CSSO‐based deep QNN) is implemented. Here, the initial process is the simulation of the IoT nodes and the leaf data are collected. This data are transferred to base station (BS) via the best routes. The optimal routes are identified using the adaptive CCSO algorithm. The adaptive concept, shuffled shepherd optimization algorithm (SSOA) and competitive swarm optimizer (CSO) are merged for forming the adaptive‐CSSO algorithm. The leaf detection is done in the BS and initially, the data is preprocessed using region of interest (ROI). Then, the relevant features are extracted. Finally, the disease in the maize leaf is detected using Deep QNN and the training is done by adaptive CSSO. The devised approach has maximum accuracy of 96.04%, sensitivity of 97.41%, specificity of 94.35%, energy of 0.01 J, and minimum delay of 0.9596 s.

show abstract

Recognition of Crop Diseases Based on Depthwise Separable Convolution in Edge Computing

Cited by 14 publications

References 30 publications

At the Confluence of Artificial Intelligence and Edge Computing in IoT-Based Applications: A Review and New Perspectives

At the Confluence of Artificial Intelligence and Edge Computing in IoT-Based Applications: A Review and New Perspectives

Crop Pest Image Classification Based on Multi-Scale Convolutional Neural Network

Hybrid optimized deep quantum neural network in Internet of Things platform using routing algorithm for detecting smart maize leaf disease

Contact Info

Product

Resources

About