| Presentation | 2021-09-09 [Invited Lecture] A Proposal and Implementation of Adaptive Distributed Compressed Sensing with Cooperative Optimization among Edge Devices Masatoshi Sekine, Kengo Okano, Satoshi Ikada, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, monitoring systems that utilize IoT have become important in monitoring social infrastructure and factory equipment. It is important to reduce the amount of transmission on the edge side while suppressing the deterioration of quality of sensor data from multiple locations. We propose a highly efficient multi-agent method for compressing and reconstructing with a smaller amount of transmitted data than our single-agent method. It coordinates transmitting terminals and relay terminals and learns the optimal compression ratio based on multi-agent deep reinforcement learning. In this paper, we introduce the method and evaluate the performance in a distributed environment using sensor nodes composed of Raspberry Pi Zero WH equipped with MEMS accelerometer. As a result, we found that the amount of data transmission can be reduced compared to the single-agent method while suppressing the reconstruction error. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | distributed compressed sensing / multi-agent deep reinforcement learning / sensor data / edge device |
| Paper # | NS2021-64 |
| Date of Issue | 2021-09-02 (NS) |
| Conference Information | |
| Committee | IN / NS / CS |
|---|---|
| Conference Date | 2021/9/9(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Session management (SIP/IMS), Interoperability/Standardization, NGN/NwGN/Future networks, Cloud/Data center networks, SDN (OpenFlow, etc.)/NFV, IPv6, Machine learning, etc. |
| Chair | Kenji Ishida(Hiroshima City Univ.) / Akihiro Nakao(Univ. of Tokyo) / Jun Terada(NTT) |
| Vice Chair | Kunio Hato(Internet Multifeed) / Tetsuya Oishi(NTT) / Daisuke Umehara(Kyoto Inst. of Tech.) |
| Secretary | Kunio Hato(NTT) / Tetsuya Oishi(Univ. of Nagasaki) / Daisuke Umehara(Nagaoka Univ. of Tech.) |
| Assistant | / Kotaro Mihara(NTT) / Takahiro Yamaura(Toshiba) / Yuta Ida(Yamaguchi Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Information Networks / Technical Committee on Network Systems / Technical Committee on Communication Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Invited Lecture] A Proposal and Implementation of Adaptive Distributed Compressed Sensing with Cooperative Optimization among Edge Devices |
| Sub Title (in English) | |
| Keyword(1) | distributed compressed sensing |
| Keyword(2) | multi-agent deep reinforcement learning |
| Keyword(3) | sensor data |
| Keyword(4) | edge device |
| 1st Author's Name | Masatoshi Sekine |
| 1st Author's Affiliation | Oki Electric Industry Co., Ltd.(OKI) |
| 2nd Author's Name | Kengo Okano |
| 2nd Author's Affiliation | Oki Electric Industry Co., Ltd.(OKI) |
| 3rd Author's Name | Satoshi Ikada |
| 3rd Author's Affiliation | Oki Electric Industry Co., Ltd.(OKI) |
| Date | 2021-09-09 |
| Paper # | NS2021-64 |
| Volume (vol) | vol.121 |
| Number (no) | NS-170 |
| Page | pp.pp.42-47(NS), |
| #Pages | 6 |
| Date of Issue | 2021-09-02 (NS) |