Model pruning techniques in the Internet of things: state of the art, methods and perspectives
In the context of the rapid development of Internet of things (IoT) technology, IoT devices faced challenges in running complex artificial intelligence (AI) algorithms, especially deep learning models, due to the limitations of computing power, storage space, communication bandwidth, and battery lif...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
China InfoCom Media Group
2024-12-01
|
| Series: | 物联网学报 |
| Subjects: | |
| Online Access: | http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2024.00448/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586352780115968 |
|---|---|
| author | ZHAO Junhui LI Huaicheng WANG Dongming LI Jiamin ZHOU Yiqing SHU Feng |
| author_facet | ZHAO Junhui LI Huaicheng WANG Dongming LI Jiamin ZHOU Yiqing SHU Feng |
| author_sort | ZHAO Junhui |
| collection | DOAJ |
| description | In the context of the rapid development of Internet of things (IoT) technology, IoT devices faced challenges in running complex artificial intelligence (AI) algorithms, especially deep learning models, due to the limitations of computing power, storage space, communication bandwidth, and battery life. Model pruning technology could effectively reduce computation and storage requirements by reducing redundant parameters in neural networks without impairing the performance of AI models. This technique was extremely suitable for optimising AI models deployed on IoT devices. Firstly, two typical model pruning techniques-structured pruning and unstructured pruning, which were currently popular and suitable for different application scenarios, were reviewed. Secondly, the diverse applications of these methods in IoT environments were analysed in detail. Finally, the limitations of the current model pruning were discussed in detail in the light of the latest research results, and the future development direction of model pruning methods in IoT was outlooked. |
| format | Article |
| id | doaj-art-8f49c63e943d4a8eae3efb26c892b88d |
| institution | Kabale University |
| issn | 2096-3750 |
| language | zho |
| publishDate | 2024-12-01 |
| publisher | China InfoCom Media Group |
| record_format | Article |
| series | 物联网学报 |
| spelling | doaj-art-8f49c63e943d4a8eae3efb26c892b88d2025-01-25T19:00:29ZzhoChina InfoCom Media Group物联网学报2096-37502024-12-01811379606433Model pruning techniques in the Internet of things: state of the art, methods and perspectivesZHAO JunhuiLI HuaichengWANG DongmingLI JiaminZHOU YiqingSHU FengIn the context of the rapid development of Internet of things (IoT) technology, IoT devices faced challenges in running complex artificial intelligence (AI) algorithms, especially deep learning models, due to the limitations of computing power, storage space, communication bandwidth, and battery life. Model pruning technology could effectively reduce computation and storage requirements by reducing redundant parameters in neural networks without impairing the performance of AI models. This technique was extremely suitable for optimising AI models deployed on IoT devices. Firstly, two typical model pruning techniques-structured pruning and unstructured pruning, which were currently popular and suitable for different application scenarios, were reviewed. Secondly, the diverse applications of these methods in IoT environments were analysed in detail. Finally, the limitations of the current model pruning were discussed in detail in the light of the latest research results, and the future development direction of model pruning methods in IoT was outlooked.http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2024.00448/IoTresource constraintsmodel pruningAIdeep learning |
| spellingShingle | ZHAO Junhui LI Huaicheng WANG Dongming LI Jiamin ZHOU Yiqing SHU Feng Model pruning techniques in the Internet of things: state of the art, methods and perspectives 物联网学报 IoT resource constraints model pruning AI deep learning |
| title | Model pruning techniques in the Internet of things: state of the art, methods and perspectives |
| title_full | Model pruning techniques in the Internet of things: state of the art, methods and perspectives |
| title_fullStr | Model pruning techniques in the Internet of things: state of the art, methods and perspectives |
| title_full_unstemmed | Model pruning techniques in the Internet of things: state of the art, methods and perspectives |
| title_short | Model pruning techniques in the Internet of things: state of the art, methods and perspectives |
| title_sort | model pruning techniques in the internet of things state of the art methods and perspectives |
| topic | IoT resource constraints model pruning AI deep learning |
| url | http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2024.00448/ |
| work_keys_str_mv | AT zhaojunhui modelpruningtechniquesintheinternetofthingsstateoftheartmethodsandperspectives AT lihuaicheng modelpruningtechniquesintheinternetofthingsstateoftheartmethodsandperspectives AT wangdongming modelpruningtechniquesintheinternetofthingsstateoftheartmethodsandperspectives AT lijiamin modelpruningtechniquesintheinternetofthingsstateoftheartmethodsandperspectives AT zhouyiqing modelpruningtechniquesintheinternetofthingsstateoftheartmethodsandperspectives AT shufeng modelpruningtechniquesintheinternetofthingsstateoftheartmethodsandperspectives |