A Cloud-Edge-Smart IoT Architecture for Speeding Up the Deployment of Neural Network Models with Transfer Learning Techniques
Existing edge computing architectures do not support the updating of neural network models, nor are they optimized for storing, updating, and transmitting different neural network models to a large number of IoT devices. In this paper, a cloud-edge smart IoT architecture for speeding up the deployme...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/14/2255 |
| _version_ | 1797439721866002432 |
|---|---|
| author | Tz-Heng Hsu Zhi-Hao Wang Aaron Raymond See |
| author_facet | Tz-Heng Hsu Zhi-Hao Wang Aaron Raymond See |
| author_sort | Tz-Heng Hsu |
| collection | DOAJ |
| description | Existing edge computing architectures do not support the updating of neural network models, nor are they optimized for storing, updating, and transmitting different neural network models to a large number of IoT devices. In this paper, a cloud-edge smart IoT architecture for speeding up the deployment of neural network models with transfer learning techniques is proposed. A new model deployment and update mechanism based on the share weight characteristic of transfer learning is proposed to address the model deployment issues associated with the significant number of IoT devices. The proposed mechanism compares the feature weight and parameter difference between the old and new models whenever a new model is trained. With the proposed mechanism, the neural network model can be updated on IoT devices with just a small quantity of data sent. Utilizing the proposed collaborative edge computing platform, we demonstrate a significant reduction in network bandwidth transmission and an improved deployment speed of neural network models. Subsequently, the service quality of smart IoT applications can be enhanced. |
| first_indexed | 2024-03-09T11:58:12Z |
| format | Article |
| id | doaj.art-143922d19a244eb39998d6a137cef6de |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T11:58:12Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-143922d19a244eb39998d6a137cef6de2023-11-30T23:06:25ZengMDPI AGElectronics2079-92922022-07-011114225510.3390/electronics11142255A Cloud-Edge-Smart IoT Architecture for Speeding Up the Deployment of Neural Network Models with Transfer Learning TechniquesTz-Heng Hsu0Zhi-Hao Wang1Aaron Raymond See2Department of Computer Science and Information Engineering, Southern Taiwan University of Science and Technology, Tainan 710301, TaiwanDepartment of Information Management, Southern Taiwan University of Science and Technology, Tainan 710301, TaiwanDepartment of Electrical Engineering, Southern Taiwan University of Science and Technology, Tainan 710301, TaiwanExisting edge computing architectures do not support the updating of neural network models, nor are they optimized for storing, updating, and transmitting different neural network models to a large number of IoT devices. In this paper, a cloud-edge smart IoT architecture for speeding up the deployment of neural network models with transfer learning techniques is proposed. A new model deployment and update mechanism based on the share weight characteristic of transfer learning is proposed to address the model deployment issues associated with the significant number of IoT devices. The proposed mechanism compares the feature weight and parameter difference between the old and new models whenever a new model is trained. With the proposed mechanism, the neural network model can be updated on IoT devices with just a small quantity of data sent. Utilizing the proposed collaborative edge computing platform, we demonstrate a significant reduction in network bandwidth transmission and an improved deployment speed of neural network models. Subsequently, the service quality of smart IoT applications can be enhanced.https://www.mdpi.com/2079-9292/11/14/2255deep learningtransfer learninglightweight neural networkedge computing |
| spellingShingle | Tz-Heng Hsu Zhi-Hao Wang Aaron Raymond See A Cloud-Edge-Smart IoT Architecture for Speeding Up the Deployment of Neural Network Models with Transfer Learning Techniques Electronics deep learning transfer learning lightweight neural network edge computing |
| title | A Cloud-Edge-Smart IoT Architecture for Speeding Up the Deployment of Neural Network Models with Transfer Learning Techniques |
| title_full | A Cloud-Edge-Smart IoT Architecture for Speeding Up the Deployment of Neural Network Models with Transfer Learning Techniques |
| title_fullStr | A Cloud-Edge-Smart IoT Architecture for Speeding Up the Deployment of Neural Network Models with Transfer Learning Techniques |
| title_full_unstemmed | A Cloud-Edge-Smart IoT Architecture for Speeding Up the Deployment of Neural Network Models with Transfer Learning Techniques |
| title_short | A Cloud-Edge-Smart IoT Architecture for Speeding Up the Deployment of Neural Network Models with Transfer Learning Techniques |
| title_sort | cloud edge smart iot architecture for speeding up the deployment of neural network models with transfer learning techniques |
| topic | deep learning transfer learning lightweight neural network edge computing |
| url | https://www.mdpi.com/2079-9292/11/14/2255 |
| work_keys_str_mv | AT tzhenghsu acloudedgesmartiotarchitectureforspeedingupthedeploymentofneuralnetworkmodelswithtransferlearningtechniques AT zhihaowang acloudedgesmartiotarchitectureforspeedingupthedeploymentofneuralnetworkmodelswithtransferlearningtechniques AT aaronraymondsee acloudedgesmartiotarchitectureforspeedingupthedeploymentofneuralnetworkmodelswithtransferlearningtechniques AT tzhenghsu cloudedgesmartiotarchitectureforspeedingupthedeploymentofneuralnetworkmodelswithtransferlearningtechniques AT zhihaowang cloudedgesmartiotarchitectureforspeedingupthedeploymentofneuralnetworkmodelswithtransferlearningtechniques AT aaronraymondsee cloudedgesmartiotarchitectureforspeedingupthedeploymentofneuralnetworkmodelswithtransferlearningtechniques |