Network heterogeneous information integrated management system based on improved RNN multi-source fusion algorithm
The interconnection of medical information networks results in extremely complex network architectures, and the current management level of multi-source heterogeneous data generated by such networks is difficult to meet the requirements of informatization. Therefore, an improved information integrat...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of XPU
2023-12-01
|
| Series: | Xi'an Gongcheng Daxue xuebao |
| Subjects: | |
| Online Access: | http://journal.xpu.edu.cn/en/#/digest?ArticleID=1418 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The interconnection of medical information networks results in extremely complex network architectures, and the current management level of multi-source heterogeneous data generated by such networks is difficult to meet the requirements of informatization. Therefore, an improved information integration management system is proposed. The article adopted the wild horse optimizer (WHO) algorithm to improve the recurrent neural network (RNN) and designed a multi-source heterogeneous data fusion model. Based on this, a network heterogeneous information integration management system was established with the manufacturing execution system (MES) as the core. By synchronously integrating and processing the data output from the multi-source fusion model, all data was transmitted to the system database for storage, and the integrated management of multi-source heterogeneous data was completed through the designed functional modules. The experimental results show that the data fusion integrity of the network heterogeneous information integration management system with WHO-RNN multi-source fusion algorithm as the core is maintained at a high level of 0.700~0.800, and as the data volume increases, the ultimate update level (UUL) index gradually approaches 80%. The system has great computational efficiency and recognition accuracy for multi-source heterogeneous data, and strong engineering practical application performance. |
|---|---|
| ISSN: | 1674-649X |