A Multi-Task Classification Method for Application Traffic Classification Using Task Relationships
As IT technology advances, the number and types of applications, such as SNS, content, and shopping, have increased across various fields, leading to the emergence of complex and diverse application traffic. As a result, the demand for effective network operation, management, and analysis has increa...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/17/3597 |
| _version_ | 1797582699981963264 |
|---|---|
| author | Ui-Jun Baek Boseon Kim Jee-Tae Park Jeong-Woo Choi Myung-Sup Kim |
| author_facet | Ui-Jun Baek Boseon Kim Jee-Tae Park Jeong-Woo Choi Myung-Sup Kim |
| author_sort | Ui-Jun Baek |
| collection | DOAJ |
| description | As IT technology advances, the number and types of applications, such as SNS, content, and shopping, have increased across various fields, leading to the emergence of complex and diverse application traffic. As a result, the demand for effective network operation, management, and analysis has increased. In particular, service or application traffic classification research is an important area of study in network management. Web services are composed of a combination of multiple applications, and one or more application traffic can be mixed within service traffic. However, most existing research only classifies application traffic by service unit, resulting in high misclassification rates and making detailed management impossible. To address this issue, this paper proposes three multitask learning methods for application traffic classification using the relationships among tasks composed of browsers, protocols, services, and application units. The proposed methods aim to improve classification performance under the assumption that there are relationships between tasks. Experimental results demonstrate that by utilizing relationships between various tasks, the proposed method can classify applications with 4.4%p higher accuracy. Furthermore, the proposed methods can provide network administrators with information about multiple perspectives with high confidence, and the generalized multitask methods are freely portable to other backbone networks. |
| first_indexed | 2024-03-10T23:26:12Z |
| format | Article |
| id | doaj.art-dbd1572a840d412b9993e9f14c3737e9 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T23:26:12Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-dbd1572a840d412b9993e9f14c3737e92023-11-19T08:01:25ZengMDPI AGElectronics2079-92922023-08-011217359710.3390/electronics12173597A Multi-Task Classification Method for Application Traffic Classification Using Task RelationshipsUi-Jun Baek0Boseon Kim1Jee-Tae Park2Jeong-Woo Choi3Myung-Sup Kim4Department of Computer and Information Science, Korea University, Sejong-si 30019, Republic of KoreaKorea Institute of Science and Technology Information, Daejeon 34141, Republic of KoreaDepartment of Computer and Information Science, Korea University, Sejong-si 30019, Republic of KoreaDepartment of Computer and Information Science, Korea University, Sejong-si 30019, Republic of KoreaDepartment of Computer and Information Science, Korea University, Sejong-si 30019, Republic of KoreaAs IT technology advances, the number and types of applications, such as SNS, content, and shopping, have increased across various fields, leading to the emergence of complex and diverse application traffic. As a result, the demand for effective network operation, management, and analysis has increased. In particular, service or application traffic classification research is an important area of study in network management. Web services are composed of a combination of multiple applications, and one or more application traffic can be mixed within service traffic. However, most existing research only classifies application traffic by service unit, resulting in high misclassification rates and making detailed management impossible. To address this issue, this paper proposes three multitask learning methods for application traffic classification using the relationships among tasks composed of browsers, protocols, services, and application units. The proposed methods aim to improve classification performance under the assumption that there are relationships between tasks. Experimental results demonstrate that by utilizing relationships between various tasks, the proposed method can classify applications with 4.4%p higher accuracy. Furthermore, the proposed methods can provide network administrators with information about multiple perspectives with high confidence, and the generalized multitask methods are freely portable to other backbone networks.https://www.mdpi.com/2079-9292/12/17/3597application traffic classificationnetwork managementmultitask learning |
| spellingShingle | Ui-Jun Baek Boseon Kim Jee-Tae Park Jeong-Woo Choi Myung-Sup Kim A Multi-Task Classification Method for Application Traffic Classification Using Task Relationships Electronics application traffic classification network management multitask learning |
| title | A Multi-Task Classification Method for Application Traffic Classification Using Task Relationships |
| title_full | A Multi-Task Classification Method for Application Traffic Classification Using Task Relationships |
| title_fullStr | A Multi-Task Classification Method for Application Traffic Classification Using Task Relationships |
| title_full_unstemmed | A Multi-Task Classification Method for Application Traffic Classification Using Task Relationships |
| title_short | A Multi-Task Classification Method for Application Traffic Classification Using Task Relationships |
| title_sort | multi task classification method for application traffic classification using task relationships |
| topic | application traffic classification network management multitask learning |
| url | https://www.mdpi.com/2079-9292/12/17/3597 |
| work_keys_str_mv | AT uijunbaek amultitaskclassificationmethodforapplicationtrafficclassificationusingtaskrelationships AT boseonkim amultitaskclassificationmethodforapplicationtrafficclassificationusingtaskrelationships AT jeetaepark amultitaskclassificationmethodforapplicationtrafficclassificationusingtaskrelationships AT jeongwoochoi amultitaskclassificationmethodforapplicationtrafficclassificationusingtaskrelationships AT myungsupkim amultitaskclassificationmethodforapplicationtrafficclassificationusingtaskrelationships AT uijunbaek multitaskclassificationmethodforapplicationtrafficclassificationusingtaskrelationships AT boseonkim multitaskclassificationmethodforapplicationtrafficclassificationusingtaskrelationships AT jeetaepark multitaskclassificationmethodforapplicationtrafficclassificationusingtaskrelationships AT jeongwoochoi multitaskclassificationmethodforapplicationtrafficclassificationusingtaskrelationships AT myungsupkim multitaskclassificationmethodforapplicationtrafficclassificationusingtaskrelationships |