| Presentation | 2019-01-17 A Study on Cache Decision Policy using User Tastes Tsukasa Kitamura, Noriaki Kamiyama, Miki Yamamoto, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Today, the majority of internet traffic is video traffic such as YouTube and NetFlix. Placing copy of original video contents to replication servers nearby users is a general solution to reduce traffic load in networks. In existing research, they focus on the spatial locality and the transition of video contents. In this paper, we focus on user tastes for video contents and propose a new cache decision policy based on measured user tastes. Users which have similar tastes tend to require similar video contents, thus we utilize the measured relation among users’ requests to predict near future video content requests. Our evaluation results using MovieLens dataset show that our proposal can make clusters of users who have similar tastes and improve cache hit ratio in comparison to LRU. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Cache Decision Policy / User Tastes / Machine Learning |
| Paper # | NS2018-180 |
| Date of Issue | 2019-01-10 (NS) |
| Conference Information | |
| Committee | NS |
|---|---|
| Conference Date | 2019/1/17(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Nagasaki Prefectural Art Museum |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Network software (Software Architecture, Middleware), Network Application, SOA/SDP, NGN/IMS/API, Distributed control/Dynamic routing, Grid, Network/System reliability, Network/System evaluation, etc. |
| Chair | Yoshikatsu Okazaki(NTT) |
| Vice Chair | Akihiro Nakao(Univ. of Tokyo) |
| Secretary | Akihiro Nakao(NTT) |
| Assistant | Kenichi Kashibuchi(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Network Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Study on Cache Decision Policy using User Tastes |
| Sub Title (in English) | |
| Keyword(1) | Cache Decision Policy |
| Keyword(2) | User Tastes |
| Keyword(3) | Machine Learning |
| 1st Author's Name | Tsukasa Kitamura |
| 1st Author's Affiliation | Kansai University(Kansai Univ.) |
| 2nd Author's Name | Noriaki Kamiyama |
| 2nd Author's Affiliation | Fukuoka University(Fukuoka Univ.) |
| 3rd Author's Name | Miki Yamamoto |
| 3rd Author's Affiliation | Kansai University(Kansai Univ.) |
| Date | 2019-01-17 |
| Paper # | NS2018-180 |
| Volume (vol) | vol.118 |
| Number (no) | NS-392 |
| Page | pp.pp.13-18(NS), |
| #Pages | 6 |
| Date of Issue | 2019-01-10 (NS) |