Porting deep neural networks on the edge via dynamic K-means compression: A case study of plant disease detection

Vita, Fabrizio De; Nocera, Giorgio; Bruneo, Dario; Tomaselli, Venera; Giacalone, Davide; Das, Sajal K.

doi:10.1016/j.pmcj.2021.101437

Cited by 13 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A timely detection on crops to stop diseases from spreading was presented in [ 56 ]. The authors proposed a model named deep leaf, a coffee plant disease detector based on edge computing.…”

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

confidence: 99%

“…The quantization requires careful tuning or retraining of the model, which can take a long time and affect the accuracy of the model. Other solutions use dynamic compression with an effort to reduce model complexity and eliminate redundant components, such as in [ 56 ]. Others formulate CNN model compression as a multiobjective optimization problem with three functional objectives: reducing the size, improving classification accuracy of the DCNN, which is related to the reliability of the model, and minimizing the number of neurons in the hidden layer using the Lévy flight optimization algorithm (LFOA) [ 59 ].…”

Section: Open Issues and Future Directionsmentioning

confidence: 99%

“…This model suffers from high complexity in training time. One of the future directions could be the combination of dynamic compression with quantization for more accuracy [ 56 ]. With regard to distributed and parallel computing, we find the following.…”

Section: Open Issues and Future Directionsmentioning

confidence: 99%

See 2 more Smart Citations

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

“…A timely detection on crops to stop diseases from spreading was presented in [ 56 ]. The authors proposed a model named deep leaf, a coffee plant disease detector based on edge computing.…”

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

confidence: 99%

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

show abstract

“…It is the future development trend to deploy disease recognition models to these devices instead of cloud servers [13,14]. However, the storage space and processor performance of resource-constrained devices are limited, and a large number of parameters and calculations limit the further application of complex models on these devices [15,16]. Therefore, designing an efficient and lightweight disease recognition model is the key to achieving model deployment.…”

Section: Introductionmentioning

confidence: 99%

Disease Recognition of Apple Leaf Using Lightweight Multi-Scale Network with ECANet

Yu¹,

Cheng²,

Li³

et al. 2022

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

To solve the problem of difficulty in identifying apple diseases in the natural environment and the low application rate of deep learning recognition networks, a lightweight ResNet (LW-ResNet) model for apple disease recognition is proposed. Based on the deep residual network (ResNet18), the multi-scale feature extraction layer is constructed by group convolution to realize the compression model and improve the extraction ability of different sizes of lesion features. By improving the identity mapping structure to reduce information loss. By introducing the efficient channel attention module (ECANet) to suppress noise from a complex background. The experimental results show that the average precision, recall and F1-score of the LW-ResNet on the test set are 97.80%, 97.92% and 97.85%, respectively. The parameter memory is 2.32 MB, which is 94% less than that of ResNet18. Compared with the classic lightweight networks SqueezeNet and MobileNetV2, LW-ResNet has obvious advantages in recognition performance, speed, parameter memory requirement and time complexity. The proposed model has the advantages of low computational cost, low storage cost, strong real-time performance, high identification accuracy, and strong practicability, which can meet the needs of real-time identification task of apple leaf disease on resource-constrained devices.

show abstract

Novel Biomimicry Techniques for Detecting Plant Diseases

Fadeyibi,

Fadeyibi

2023

Biomimicry Materials and Applications

View full text Add to dashboard Cite

Porting deep neural networks on the edge via dynamic K-means compression: A case study of plant disease detection

Cited by 13 publications

References 13 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

Disease Recognition of Apple Leaf Using Lightweight Multi-Scale Network with ECANet

Novel Biomimicry Techniques for Detecting Plant Diseases

Contact Info

Product

Resources

About