Smart City Gnosys
Smart city article details
| Title | Network Traffic Classification Based On Domain Adaptive Migration For Multimedia Services In Smart City Networks |
|---|---|
| ID_Doc | 39025 |
| Authors | Gao B.; Yang Y.; Gao Z.; Zhao L.; Wang Z.; Cui D. |
| Year | 2022 |
| Published | IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB, 2022-June |
| DOI | http://dx.doi.org/10.1109/BMSB55706.2022.9828638 |
| Abstract | Network traffic classification is a key technology for multimedia service management in smart city networks, which is of great significance to broadcast applications to smart cities. According to the characteristics of different network traffic to ensure the full utilization of broadband resources and improve the quality of network service. Due to the wide application of dynamic port number and stream encryption technology, the traditional network traffic classification method based on port number and deep packet inspection is no longer effective. In recent years, machine learning methods can be used to accurately identify categories of network traffic applications by labeled data. However, collecting enough labeled network traffic data is a time-consuming and difficult task, and the distribution of traffic data collected in various networks is different. In order to solve the problem of insufficient labeled samples and domain distribution differences, a network traffic classification method based on domain adaptive migration is proposed in this paper. This paper designs a new domain adaptive method, which reduces distribution differences between domains, makes the distribution of samples under the same category more compact and different application categories more separated. Then migrate the feature extraction module to the target domain. And the unlabeled data and few labeled samples are utilized to jointly classify network traffic applications using a siamese sparse denoising stacked autoencoder. Experimental results show that compared with other algorithms, the network traffic classification algorithm proposed in this paper achieves the best result. © 2022 IEEE. |
| Author Keywords | AI for advanced multimedia service management; broadcast applications to smart cities; domain adaptation; network traffic classification |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
1350  | 0.869 | Mudarakola L.P.; Bukkarayasamudram V.K.; Jadhav S.D.; Goviraboyina S.S.; Sharma S.; Mukherjee S.; Reddy P.C.S. | A Deep Learning Framework For Iot Lightweight Traffic Multi-Classification: Smart-Cities | International Journal of Sensors, Wireless Communications and Control, 14, 3 (2024) |
| 58530 | 0.866 | Zhao S.; Ye K.; Xu C.-Z. | Traffic Classification And Application Identification Based On Machine Learning In Large-Scale Supercomputing Center | Proceedings - 21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2019 (2019) |
| 38981 | 0.864 | Tari Z.; Fahad A.; Almalawi A.; Yi X. | Network Classification For Traffic Management: Anomaly Detection, Feature Selection, Clustering And Classification | Network Classification for Traffic Management (2020) |
| 17265 | 0.857 | Shafiq, SM; Tian, ZH; Bashir, AK; Jolfaei, A; Yu, XZ | Data Mining And Machine Learning Methods For Sustainable Smart Cities Traffic Classification: A Survey | SUSTAINABLE CITIES AND SOCIETY, 60 (2020) |
| 1395 | 0.851 | Tripathi A.N.; Sharma B. | A Deep Review: Techniques, Findings And Limitations Of Traffic Flow Prediction Using Machine Learning | Lecture Notes in Mechanical Engineering (2023) |