Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SeMI |
2021-01-20 13:20 |
Online |
Online |
A Study of Online Training Method for Image-based Wireless Link Quality Prediction Sohei Itahara (Kyoto Univ), Takayuki Nishio (Tokyo Tech), Masahiro Morikura, Koji Yamamoto (Kyoto Univ) SeMI2020-44 |
Machine-learning-based prediction of future wireless link quality is an emerging technique that can potentially improve ... [more] |
SeMI2020-44 pp.7-9 |
SRW, SeMI, CNR (Joint) |
2020-11-26 16:00 |
Online |
Online |
[Poster Presentation]
Feature Extraction Method for Wireless LANs Channel Selection Based on Contextual Bandit Learning Kota Yamashita (Kyoto Univ.), Shotaro Kamiya (Sony Corp.), Koji Yamamoto (Kyoto Univ.), Takayuki Nishio (Tokyo Tech.), Masahiro Morikura (Kyoto Univ.) SeMI2020-24 |
[more] |
SeMI2020-24 pp.39-42 |
SRW, SeMI, CNR (Joint) |
2020-11-26 16:00 |
Online |
Online |
[Poster Presentation]
Adversarial Reinforcement Learning-based Robust Access Point Coordination Against Uncoordinated Interference Yuto Kihira, Yusuke Koda, Koji Yamamoto (Kyoto Univ.), Takayuki Nishio (Tokyo Tech.), Masahiro Morikura (Kyoto Univ.) SeMI2020-25 |
[more] |
SeMI2020-25 pp.43-46 |
SeMI |
2020-01-31 10:00 |
Kagawa |
|
[Poster Presentation]
Communication-Efficient Federated Learning Using Non-Labeled Data Souhei Itahara, Takayuki Nishio, Masahiro Morikura, Koji Yamamoto (Kyoto Univ) SeMI2019-109 |
Federated learning (FL) is a machine learning setting where many mobile devices collaboratively train a machine learning... [more] |
SeMI2019-109 pp.47-48 |
SeMI |
2020-01-31 10:00 |
Kagawa |
|
[Poster Presentation]
Experimental Evaluation of Federated Learning in Real Networks Naoya Yoshida, Takayuki Nishio, Masahiro Morikura, Koji Yamamoto (Kyoto Univ.) SeMI2019-110 |
Federated Learning (FL) is a decentralized learning mechanism, which enables to train machine learning (ML) models using... [more] |
SeMI2019-110 pp.49-50 |
SeMI |
2020-01-31 10:00 |
Kagawa |
|
[Poster Presentation]
A Study of MCS Index Prediction Using Depth Images for Bit-Rate Control in mmWave Communications Tomoya Mikuma, Takayuki Nishio, Masahiro Morikura (Kyoto Univ.), Yusuke Asai, Ryo Miyatake (NTT) SeMI2019-111 |
In millimeter-wave (mmWave) communications, link quality is decreased seriously when a line-of-sight (LOS) path is block... [more] |
SeMI2019-111 pp.51-52 |
SeMI |
2020-01-31 10:00 |
Kagawa |
|
[Poster Presentation]
Sequential WLAN Channel Selection for Mitigating Performance Degradation of Factors Outside System Kazuki Ohtsu, Shotaro Kamiya, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura (Kyoto Univ.), Noriyasu Kato (Allied Telesis) SeMI2019-106 |
We propose a sequential channel allocation method based on multi-objective multi-armed bandit problems.
The proposed me... [more] |
SeMI2019-106 pp.41-42 |
RISING (2nd) |
2019-11-26 14:10 |
Tokyo |
Fukutake Learning Theater, Hongo Campus, Univ. Tokyo |
[Poster Presentation]
A Study for Knowlage Distillation Based Semi-Supervised Federated Learning with Low Communication Cost Sohei Itahara, Takayuki Nishio, Masahiro Morikura, Koji Yamamoto (Kyoto Univ) |
Federated Learning is a decentralized learning mechanism, which enables to train machine learning (ML) model using the r... [more] |
|
RISING (2nd) |
2019-11-27 13:55 |
Tokyo |
Fukutake Learning Theater, Hongo Campus, Univ. Tokyo |
[Poster Presentation]
Handover Control for mmWave Networks with Proactive Performance Prediction Using Depth Images and Deep Reinforcement Learning Yusuke Koda, Kota Nakashima, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura (Kyoto Univ.) |
[more] |
|
RISING (2nd) |
2019-11-27 13:55 |
Tokyo |
Fukutake Learning Theater, Hongo Campus, Univ. Tokyo |
[Poster Presentation]
A Study of mmWave Received Power Prediction from Depth Images Takayuki Nishio, Koji Yamamoto, Masahiro Morikura (Kyoto Univ.) |
[more] |
|
SRW, SeMI, CNR (Joint) |
2019-11-06 13:25 |
Tokyo |
Kozo Keisaku Engineering Inc. |
[Poster Presentation]
A Study of Received Power Prediction Using Ray-tracing Simulation and Deep Learning for mmWave Communications Masahiro Iwasaki, Takayuki Nishio, Masahiro Morikura, Koji Yamamoto (Kyoto Univ) SRW2019-34 SeMI2019-78 CNR2019-28 |
Machine learning based received power prediction has been studied. These methods learn Features such as surrounding map ... [more] |
SRW2019-34 SeMI2019-78 CNR2019-28 pp.53-54(SRW), pp.73-74(SeMI), pp.51-52(CNR) |
MIKA (2nd) |
2019-10-03 11:15 |
Hokkaido |
Hokkaido Univ. |
[Poster Presentation]
A Study of Transfer Learning for Received Power Prediction Using Depth Images in mmWave Communications Tomoya Mikuma, Takayuki Nishio, Masahiro Morikura (Kyoto Univ.), Yusuke Asai, Ryo Miyatake (NTT) |
The received power prediction scheme using camera images in mmWave communications has been proposed. The prediction sche... [more] |
|
MIKA (2nd) |
2019-10-03 11:15 |
Hokkaido |
Hokkaido Univ. |
[Poster Presentation]
Deep Reinforcement Learning-Based Channel Allocation for Wireless LANs
-- Investigation of sampling method of replay buffer -- Kota Nakashima, Shotaro Kamiya, Ohtsu Kazuki, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura (Kyoto Univ.) |
We have proposed the deep reinforcement learning-based channel allocation approach for wireless area local networks to i... [more] |
|
MIKA (2nd) |
2019-10-03 11:15 |
Hokkaido |
Hokkaido Univ. |
[Poster Presentation]
Improving Learning Efficiency of Graph-Based Reinforcement Learning for Wireless LAN Channel Selection Kazuki Ohtsu, Shotaro Kamiya, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura (Kyoto Univ.) |
This report proposes to improve learning efficiency with graph isomorphism for reinforcement learning-based wireless loc... [more] |
|
RCS |
2019-06-19 14:55 |
Okinawa |
Miyakojima Hirara Port Terminal Building |
Policy Gradient Reinforcement Learning for Reducing Transmission Delay in EDCA Masao Shinzaki, Yusuke Koda, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura (Kyoto Univ.) RCS2019-52 |
This paper proposes a packet mapping algorithm among Access Categories (ACs) in Enhanced Distributed Channel Access (EDC... [more] |
RCS2019-52 pp.91-96 |
RCS |
2019-06-19 15:15 |
Okinawa |
Miyakojima Hirara Port Terminal Building |
A Study for Improving Prediction Accuracy on Federated Learning with Non-IID Data in Wireless Networks Naoya Yoshida, Takayuki Nishio, Masahiro Morikura, Koji Yamamoto (Kyoto Univ.), Ryo Yonetani (OMRON SINIC X Corp.) RCS2019-54 |
Federated Learning (FL) is a decentralized learning mechanism, which enables to train machine learning (ML) model using ... [more] |
RCS2019-54 pp.103-108 |
RCS |
2019-06-19 15:25 |
Okinawa |
Miyakojima Hirara Port Terminal Building |
Optimal Path Learning for mmWave Communications in Smart Factory Mayu Mieda, Shotaro Kamiya, Kota Nakashima, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura (Kyoto Univ.) RCS2019-55 |
[more] |
RCS2019-55 pp.109-112 |
ASN |
2019-01-28 14:40 |
Kagoshima |
Kyuukamura Ibusuki |
Deep Reinforcement Learning-Based Optimum Channel Control for Wireless LAN Kota Nakashima, Syotaro Kamiya, Kazuki Ohtsu, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura (Kyoto Univ.) ASN2018-80 |
This report proposes deep reinforcement learning-based channel selection method when access points (APs) are located den... [more] |
ASN2018-80 pp.13-18 |
MoNA |
2019-01-16 10:05 |
Kyoto |
T. B. D. |
A Study on Application of Contextual Bandit Problem to Wireless LAN Access Point Selection Taichi Sakakibara, Takayuki Nishio, Masahiro Morikura, Koji Yamamoto (Kyoto Univ.), Toshihisa Nabetani (TOSHIBA) MoNA2018-58 |
This paper models access point (AP) selection problem wireless LAN as an bandit problem and evaluate a performance of an... [more] |
MoNA2018-58 pp.7-11 |
MoNA, IN, CNR (Joint) [detail] |
2018-11-15 13:40 |
Saga |
Karatsu Civic Exchange Plaza |
Geo-fencing System for Wireless LANs with Camera Go Yamanaka, Takayuki Nishio, Masahiro Morikura (Kyoto Univ.), Yuichi Maki, Shinichiro Eitoku, Takuya Indo (NTT) MoNA2018-27 CNR2018-24 |
Location aware services and networking are attracting a great deal of attentions.
This paper proposes a geo-fencing sys... [more] |
MoNA2018-27 CNR2018-24 pp.31-36(MoNA), pp.37-42(CNR) |