Faculty Profiles - YONEZAWA Takuro

Papers - YONEZAWA Takuro

Division display 101 - 120 of about 307 ／ All the affair displays >>

Time-resolved X-ray photoelectron diffraction using an angle-resolved time-of-flight electron analyzer Reviewed

Ang A.K.R., Fukatsu Y., Kimura K., Yamamoto Y., Yonezawa T., Nitta H., Fleurence A., Yamamoto S., Matsuda I., Yamada-Takamura Y., Hayashi K.

Japanese Journal of Applied Physics Vol. 59 ( 10 ) 2020.10

Language：Japanese Publishing type：Research paper (scientific journal) Publisher：Japanese Journal of Applied Physics

X-ray photoelectron diffraction (XPD) provides atomic resolution, element sensitive local structure information about the surfaces and interfaces of materials. In the work reported in this paper, a two-dimensional angle resolved time-of-flight (2DARTOF) system is used to perform time-resolved XPD experiments on epitaxial silicene. The two Si 2p peak components from the different atomic sites in the silicene layer allow extraction of the individual XPD patterns. Time-resolved measurements captured small angle shifts in the forward focusing peak, indicating laser-induced changes in the silicene structure. At 10 ns, the XPD patterns appear to relax back to the equilibrium state. This work demonstrates that 2DARTOF systems are well suitable for time-resolved XPD measurements.

DOI： 10.35848/1347-4065/abb57e

Scopus

CityFlow: Supporting Spatial-Temporal Edge Computing for Urban Machine Learning Applications Reviewed

Makoto Kawano, Takuro Yonezawa, Tomoki Tanimura, Nam Ky Giang, Matthew Broadbent, Rodger Lea, Jin Nakazawa

EAI/Springer Innovations in Communication and Computing page： 3 - 15 2020

SelfGuard: semi-automated activity tracking for enhancing self-protection against the COVID-19 pandemic: poster abstract. Reviewed

Yuuki Nishiyama, Takuro Yonezawa, Kaoru Sezaki

SenSys '20: The 18th ACM Conference on Embedded Networked Sensor Systems(SenSys) page： 780 - 781 2020

GANonymizer: Image Anonymization Method Integrating Object Detection and Generative Adversarial Network Reviewed

Tomoki Tanimura, Makoto Kawano, Takuro Yonezawa, Jin Nakazawa

EAI/Springer Innovations in Communication and Computing page： 109 - 121 2020

Civic Crowdsensing Through Location-Aware Virtual Monsters. Reviewed

Takuro Yonezawa, Mina Sakamura, Nobuo Kawaguchi, Jin Nakazawa

Distributed, Ambient and Pervasive Interactions - 8th International Conference Vol. 12203 page： 464 - 476 2020

Person-Flow Estimation with Preserving Privacy Using Multiple 3D People Counters. Reviewed

Yoshiteru Nagata, Takuro Yonezawa, Nobuo Kawaguchi

Science and Technologies for Smart Cities - 6th EAI International Conference(SmartCity360°) Vol. 372 page： 615 - 634 2020

Nurse care activity recognition challenge: a comparative verification of multiple preprocessing approaches. Reviewed

Hitoshi Matsuyama, Takuto Yoshida, Nozomi Hayashida, Yuto Fukushima, Takuro Yonezawa, Nobuo Kawaguchi

UbiComp/ISWC '20: 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and 2020 ACM International Symposium on Wearable Computers page： 414 - 418 2020

An End-to-End BLE Indoor Location Estimation Method Using LSTM Reviewed

Urano K., Hiroi K., Yonezawa T., Kawaguchi N.

2019 12th International Conference on Mobile Computing and Ubiquitous Network, ICMU 2019 2019.11

Language：Japanese Publishing type：Research paper (scientific journal) Publisher：2019 12th International Conference on Mobile Computing and Ubiquitous Network, ICMU 2019

Indoor location estimation has long been researched to realize location-based services. In this paper, we propose an indoor location estimation method for Bluetooth Low Energy (BLE) devices using end-to-end LSTM neural network. We focus on large-scale exhibition where is a tough environment for wireless indoor location estimation due to signal strength instability. To achieve higher accuracy, deep learning based methods are proposed rather than trilateration or fingerprint. Existing deep learning based methods estimate the location from the probabilities using the difference of query signal strength and autoencoder-reconstruction of it. Proposed method adopts end-to-end location estimation, which means the neural network takes a time-series of signal strength and outputs the estimated location at the latest time in the input time-series. We also build a loss function which takes how a person walks into account. Considering the difficulty of data collection within a short preparation term of an exhibition, the data generated by a simple simulation is used in the training phase before training with a small amount of real data. As a result, the estimation accuracy is average of 1.92m, using the data collected in GEXPO exhibition in Miraikan, Tokyo. Proposed method outperforms our previous trilateration based method's 4.51m average.

DOI： 10.23919/ICMU48249.2019.9006638

Scopus

Rehabilitation Support Robot for Self-Standing-Up Training of Hemiplegic Stroke Patients - Design of Counterbalance Mechanism Reviewed

Tokinaga T., Yonezawa T., Saito M., Morita Y., Tanabe H., Kiss B.

International Conference on Control Automation and Systems Vol. 2019-October page： 385 - 388 2019.10

Language：Japanese Publishing type：Research paper (scientific journal) Publisher：International Conference on Control Automation and Systems

The objective of the study involved developing a rehabilitation support robot for self-standing-up training of hemiplegic stroke patients to restore normal standing-up motion. Based on our previous analysis of the therapist's guiding movements in standing-up training of patients, a passive-type robot was adopted. However, the link weight of the robot acts as a load at the patient's waist. In this work, we designed a counterbalance mechanism for the robot in order to reduce the load at the patient's waist and determined the optimal parameters for the mechanism. We confirmed by simulation that the specifications of the forces acting on the end-effectors of the robots were satisfied, and thus the proposed counterbalance mechanism was effective.

DOI： 10.23919/ICCAS47443.2019.8971502

Scopus

回転磁石マーカを用いたスマートフォン所持者の2次元経路推定 Reviewed Open Access

渡邊康祐, 廣井慧, 米澤拓郎, 梶克彦, 河口信夫

マルチメディア，分散，協調とモバイル(DICOMO2019)シンポジウム page： 22 - 28 2019.7

ニューラルネットワークを用いた大規模イベント向けBLE屋内位置推定の比較評価 Reviewed Open Access

浦野健太, 廣井慧, 米澤拓郎, 河口信夫

マルチメディア，分散，協調とモバイル(DICOMO2019)シンポジウム page： 29 - 35 2019.7

異なるサービス提供者間におけるトラストモデルとその実装に関する研究 Reviewed Open Access

平野流, 廣井慧, 米澤拓郎, 河口信夫

マルチメディア，分散，協調とモバイル(DICOMO2019)シンポジウム page： 284 - 290 2019.7

人の回避行動を考慮した移動ロボットの経路計画法の検討 Open Access

浅井悠佑, 廣井慧, 米澤拓郎, 河口信夫

マルチメディア，分散，協調とモバイル(DICOMO2019)シンポジウム page： 840 - 845 2019.7

Hybrid Activity Recognition for Ballroom Dance Exercise using Video and Wearable Sensor Reviewed

Hitoshi Matsuyama, Kei Hiroi, Katsuhiko Kaji, Takuro Yonezawa, Nobuo Kawaguchi

International Conference on Activity and Behavior Computing page： Paper66 2019.6

Hybrid activity recognition for ballroom dance exercise using video and wearable sensor Reviewed

Matsuyama H., Hiroi K., Kaji K., Yonezawa T., Kawaguchi N.

2019 Joint 8th International Conference on Informatics, Electronics and Vision, ICIEV 2019 and 3rd International Conference on Imaging, Vision and Pattern Recognition, icIVPR 2019 with International Conference on Activity and Behavior Computing, ABC 2019 page： 112 - 117 2019.5

Language：Japanese Publishing type：Research paper (scientific journal) Publisher：2019 Joint 8th International Conference on Informatics, Electronics and Vision, ICIEV 2019 and 3rd International Conference on Imaging, Vision and Pattern Recognition, icIVPR 2019 with International Conference on Activity and Behavior Computing, ABC 2019

In this paper, we propose a hybrid activity recognition method for ballroom dance exercise using video and wearable sensor. The purpose of our research is to design a mechanism to support ballroom dance exercise, and this paper reports the first part to design a mechanism is to support ballroom dance exercise, and this paper reports the first outcome to achieve the purpose - recognizing ballroom dance exercise. There are two conceivable ways to recognize dance exercise: videos and wearable sensor. However, each of them has its disadvantages. Using video is a good way to recognize the movement of the body. However, it cannot provide us accurate timing or strength of foot actions because the number of their flames per seconds is too small to recognize the fast movements of dancers. On the other hand, while a wearable sensor is good at recognizing foot timing and strength, it is not good at recognizing the movement of the whole body. Therefore we propose a hybrid recognition method utilizing the merits of both video and wearable sensor. This paper focuses to recognize four different types of steps in Latin American, a kind of ballroom dance. For each step, we record wearable sensing data and videos. As a result, it is found that the accuracy of step recognition is improved by adding wearable sensing data to video data shot from two different angles.

DOI： 10.1109/ICIEV.2019.8858524

Scopus

Cruisers: An automotive sensing platform for smart cities using door-to-door garbage collecting trucks. Reviewed

Array,Jin Nakazawa, Takuro Yonezawa, Hideyuki Tokuda

Ad Hoc Networks Vol. 85 page： 32 - 45 2019.3

Sampling rate dependency in pedestrian walking speed estimation using DualCNN-LSTM. Reviewed

Takuto Yoshida, Junto Nozaki, Kenta Urano, Kei Hiroi, Katsuhiko Kaji, Takuro Yonezawa, Nobuo Kawaguchi

Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2019 Adjunct, London, UK, September 9-13, 2019. page： 862 - 868 2019

Ballroom dance step type recognition by random forest using video and wearable sensor. Reviewed

Hitoshi Matsuyama, Kei Hiroi, Katsuhiko Kaji, Takuro Yonezawa, Nobuo Kawaguchi

CityFlow: exploiting edge computing for large scale smart city applications Reviewed Open Access

Giang Nam Ky, Leung Victor C. M., Kawano Makoto, Yonezawa Takuro, Nakazawa Jin, Lea Rodger, Broadbent Matt

2019 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING (BIGCOMP) page： 631-634 2019

Gait Dependency of Smartphone Walking Speed Estimation using Deep Learning. Reviewed

Takuto Yoshida, Junto Nozaki, Kenta Urano, Kei Hiroi, Takuro Yonezawa, Nobuo Kawaguchi

Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services, MobiSys 2019, Seoul, Republic of Korea, June 17-21, 2019. page： 641 - 642 2019

　 PREV - NEXT 　

<YONEZAWA Takuro>

Papers - YONEZAWA Takuro