Presentation | 2017-03-06 Prediction of the Number of Content Requests by Deep Learning Tatsuya Suda, Kyoko Yamori, Yoshiaki Tanaka, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In content distribution systems such as CDN (Content Delivery Network), the contents with high request rate should be stored in the edge server for efficient distribution. If the request rate of the new content can be predicted, the network can be used more efficiently. In this paper, the number of content requests is predicted by Deep Learning so as to assign the content to the suitable server. The input parameters of deep learning are title and tag information which are metadata of content, and they are vectorized by natural language. The relationship between the created vector and the number of content requests is evaluated by cosine similarity. If the similarity of the contents is high, the ranking of the number of requests will be almost the same. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Deep Learning / Content Request / Prediction / Doc2Vec / LDA |
Paper # | CQ2016-111 |
Date of Issue | 2017-02-27 (CQ) |
Conference Information | |
Committee | MVE / IE / CQ / IMQ |
---|---|
Conference Date | 2017/3/6(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Kyusyu Univ. Ohashi Campus |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Five senses media, Multimedia, Virtual Environment, Image encoding, Ultra realistic, Network quality and reliability, Image media quality, etc. |
Chair | Yoshinari Kameda(Univ. of Tsukuba) / Seishi Takamura(NTT) / Kyoko Yamori(Asahi Univ.) / Yuukou Horita(Univ. of Toyama) |
Vice Chair | Kenji Mase(Nagoya Univ.) / Takayuki Hamamoto(Tokyo Univ. of Science) / Atsuro Ichigaya(NHK) / Takanori Hayashi(NTT) / Hideyuki Shimonishi(NEC) / Kenji Sugiyama(Seikei Univ.) / Toshiya Nakaguchi(Chiba Univ.) |
Secretary | Kenji Mase(Kyushu Univ.) / Takayuki Hamamoto(Kyoto Univ.) / Atsuro Ichigaya(NTT) / Takanori Hayashi(NTT) / Hideyuki Shimonishi(Chiba Inst. of Tech.) / Kenji Sugiyama(Osaka Univ.) / Toshiya Nakaguchi(Keio Univ.) |
Assistant | Hideaki Uchiyama(Kyushu Univ.) / Takatsugu Hirayama(Nagoya Univ.) / Ryosuke Aoki(NTT) / Kei Kawamura(KDDI R&D Labs.) / Keita Takahashi(Nagoya Univ.) / Hirantha Abeysekera(NTT) / Norihiro Fukumoto(KDDI R&D Labs.) / Shinichiro Saito(Sony) / Masaru Tsuchida(NTT) |
Paper Information | |
Registration To | Technical Committee on Multimedia and Virtual Environment / Technical Committee on Image Engineering / Technical Committee on Communication Quality / Technical Committee on Image Media Quality |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Prediction of the Number of Content Requests by Deep Learning |
Sub Title (in English) | |
Keyword(1) | Deep Learning |
Keyword(2) | Content Request |
Keyword(3) | Prediction |
Keyword(4) | Doc2Vec |
Keyword(5) | LDA |
1st Author's Name | Tatsuya Suda |
1st Author's Affiliation | Waseda University(Waseda Univ.) |
2nd Author's Name | Kyoko Yamori |
2nd Author's Affiliation | Asahi University/Waseda University(Asahi Univ./Waseda Univ.) |
3rd Author's Name | Yoshiaki Tanaka |
3rd Author's Affiliation | Waseda University(Waseda Univ.) |
Date | 2017-03-06 |
Paper # | CQ2016-111 |
Volume (vol) | vol.116 |
Number (no) | CQ-497 |
Page | pp.pp.1-6(CQ), |
#Pages | 6 |
Date of Issue | 2017-02-27 (CQ) |