| Item type |
SIG Technical Reports(1) |
| 公開日 |
2022-02-28 |
| タイトル |
|
|
タイトル |
Time-Aware Machine Learning-based Traffic QoS Classification |
| タイトル |
|
|
言語 |
en |
|
タイトル |
Time-Aware Machine Learning-based Traffic QoS Classification |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
IOT |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_18gh |
|
資源タイプ |
technical report |
| 著者所属 |
|
|
|
University of Tsukuba |
| 著者所属 |
|
|
|
University of Tsukuba |
| 著者所属 |
|
|
|
University of Tsukuba |
| 著者所属(英) |
|
|
|
en |
|
|
University of Tsukuba |
| 著者所属(英) |
|
|
|
en |
|
|
University of Tsukuba |
| 著者所属(英) |
|
|
|
en |
|
|
University of Tsukuba |
| 著者名 |
Weichang, Zheng
Ziyu, Guo
Yongbing, Zhang
|
| 著者名(英) |
Weichang, Zheng
Ziyu, Guo
Yongbing, Zhang
|
| 論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
With the rapid development and popularization of the Internet and communication technologies, the amount of network traffics has grown explosively. Network resources should be allocated to the applications depending on their requirements for quality of service (QoS). However, fast-growing new applications and protocols bring us difficulties and challenges to classify various traffics correctly. Machine learning-based techniques are expected to be a more time-saving and precise method for traffic classification depending on the quality of services of various applications. In this paper, we focus on the traffic QoS classification based on the deep learning technique with traditional traffic features along with a newly defined feature in this paper, that is, the time period of network traffic. Experimental results show that by considering the time period feature, the classification accuracy can be improved much better than before. |
| 論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
With the rapid development and popularization of the Internet and communication technologies, the amount of network traffics has grown explosively. Network resources should be allocated to the applications depending on their requirements for quality of service (QoS). However, fast-growing new applications and protocols bring us difficulties and challenges to classify various traffics correctly. Machine learning-based techniques are expected to be a more time-saving and precise method for traffic classification depending on the quality of services of various applications. In this paper, we focus on the traffic QoS classification based on the deep learning technique with traditional traffic features along with a newly defined feature in this paper, that is, the time period of network traffic. Experimental results show that by considering the time period feature, the classification accuracy can be improved much better than before. |
| 書誌レコードID |
|
|
収録物識別子タイプ |
NCID |
|
収録物識別子 |
AA12326962 |
| 書誌情報 |
研究報告インターネットと運用技術（IOT）
巻 2022-IOT-56,
号 1,
p. 1-7,
発行日 2022-02-28
|
| ISSN |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
2188-8787 |
| Notice |
|
|
|
SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. |
| 出版者 |
|
|
言語 |
ja |
|
出版者 |
情報処理学会 |
IPSJ-IOT22056001.pdf (1.1 MB)
