Faculty Profiles - YONEZAWA Takuro

Papers - YONEZAWA Takuro

Division display 121 - 140 of about 280 ／ All the affair displays >>

ユニバーサルセンサネットワークと清掃車を活用した藤沢市のスマート化

中澤仁, 陳寅, 米澤拓郎, 大越匡, 徳田英幸

デジタルプラクティス Vol. 8 ( 3 ) page： 244 - 252 2017.7

Language：Japanese Publishing type：Research paper (scientific journal)

さまざまなセンシングデータを実空間から収集し，住民や自治体，大学，民間企業をはじめとするステークホルダ間で共有し，情報の利活用を進めていくことで地域課題の解決に繋げることを目的として，まずセンシングデータの流通プラットフォームとしてユニバーサルセンサネットワーク技術(USN)を提案する．同技術では，物理センサや参加型センサをはじめとする多様なセンサで生成されたデータを，統一的なメタデータを伴って柔軟に流通させられ，通信プロトコルXMPP上のpublish/subscribe機能を用いて，センシングデータの生成側と消費側の相互依存性を解消しながら，スケーラブルなデータ流通を実現している．また，USNを用いた神奈川県藤沢市における実空間センシング事例として，清掃車にピギーバックした環境情報センシングと，行政職員による落書きや不法投棄物といった実空間不具合事象に関する参加型センシングを示す．これらのシステムの開発・運用を通じて，USNにおける仮想デバイスの抽象化を用いた多様なセンサの表現や機能の有効性を示すとともに，応用可能性やスケーラビリティを示す．

J-GLOBAL

Likeyboard : Instant Lifelog Data Sharing Using Smartphone Keyboard Interface

石川伶, 佐々木航, 西山勇毅, 大越匡, 米澤拓郎, 中澤仁, 高汐一紀, 徳田英幸

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 Vol. 116 ( 508 ) page： 69 - 74 2017.3

SpoTrip : 観光客リピータ化促進のための隠れスポット情報提供システムの評価 (モバイルネットワークとアプリケーション)

片山晋, 礒川直大, 小渕幹夫, 西山勇毅, 大越匡, 米澤拓郎, 中澤仁, 高汐一紀, 徳田英幸

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 Vol. 116 ( 508 ) page： 157 - 164 2017.3

Likeyboard : Instant Lifelog Data Sharing Using Smartphone Keyboard Interface

石川伶, 佐々木航, 西山勇毅, 大越匡, 米澤拓郎, 中澤仁, 高汐一紀, 徳田英幸

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 Vol. 116 ( 509 ) page： 79 - 84 2017.3

SpoTrip : 観光客リピータ化促進のための隠れスポット情報提供システムの評価 (知的環境とセンサネットワーク)

片山晋, 礒川直大, 小渕幹夫, 西山勇毅, 大越匡, 米澤拓郎, 中澤仁, 高汐一紀, 徳田英幸

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 Vol. 116 ( 509 ) page： 185 - 192 2017.3

C's: Sensing the Quality of Traffic Markings Using Camera-Attached Cars Reviewed

KAWASAKI Takafumi, KAWANO Makoto, IWAMOTO Takeshi, MATSUMOTO Michito, YONEZAWA Takuro, NAKAZAWA Jin, TOKUDA Hideyuki

SICE Journal of Control, Measurement, and System Integration Vol. 10 ( 5 ) page： 393 - 401 2017

Language：English Publishing type：Research paper (scientific journal) Publisher：The Society of Instrument and Control Engineers

Road maintenance requires local city governments to dedicate a substantial amount of funds in finding and repairing damaged traffic marks and pavements. In developed cities, the total road length is so large that the cost becomes unreasonably high. In this paper, we propose a method of sensing damaged traffic marks from images captured by a camera mounted to a car, for the purpose of reducing road maintenance cost. In particular, we utilized convolutional neural networks (CNN), as well as linear support vector machines (SVM) and Random Forest, in developing a system of damage detection. The experiments used thousands of images captured in the wild and showed that the method can detect damages using CNN with 93% accuracy, at maximum, and at reasonable speed (55 images per second).

DOI： 10.9746/jcmsi.10.393

Road Marking Blur Detection with Drive Recorder Reviewed

Kawano Makoto, Mikami Kazuhiro, Yokoyama Satoshi, Yonezawa Takuro, Nakazawa Jin

2017 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA) page： 4092 - 4097 2017

Interruptibility Map: Geographical Analysis of Users' Interruptibility in Smart Cities Reviewed

Mikio Obuchi, Tadashi Okoshi, Takuro Yonezawa, Jin Nakazawa, Hideyuki Tokuda

2017 IEEE INTERNATIONAL CONFERENCE ON PERVASIVE COMPUTING AND COMMUNICATIONS WORKSHOPS (PERCOM WORKSHOPS) page： 357 - 362 2017

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

Investigating users' interruptibility as an indicator of his/her attention status has been essential in recent pervasive computing where the users' attention resources get scarce against ever increasing amounts of information. In this paper, we address research problems related to the users' available interruptibility, their physical activities, and their current locations and situations. We propose the "Interruptibility Map", a geographical tool for analyzing and visualizing the user's local interruptibility status in the context of smart city research. Our map describes where citizens are expected to feel more or less interruptive against notifications produced by computing devices, which are known to have negative effects on work productivity, emotion, and psychological state. We conducted a continuous analysis from our previous research and a new additional in-the-wild user study for 2 weeks with 29 participants to investigate the relationship between one's interruptibility and their locations and situations. As a highlight of our findings, we found certain pairs of user activity change and a location that showed better interruptibility to users, such as an activity change of "when user's riding car(bus) stops" in the bus commute situation.

DOI： 10.1109/PERCOMW.2017.7917588

Web of Science

Scopus

Evaluating the spatio-temporal coverage of automotive sensing for smart cities. Reviewed

Yin Chen, Takuro Yonezawa, Jin Nakazawa, Hideyuki Tokuda

Tenth International Conference on Mobile Computing and Ubiquitous Network, ICMU 2017, Toyama, Japan, October 3-5, 2017 Vol. 2018-January page： 1 - 5 2017

Lokemon:その場に潜むモンスターを介した参加型センシング手法 Reviewed

坂村美奈, 米澤拓郎, 大越匡, 中澤仁, 徳田英幸

研究報告ユビキタスコンピューティングシステム（UBI） Vol. 2017-UBI54 ( 12 ) page： 1 2017

HealthFight: 多数決を用いた食習慣改善ソーシャルメディア Reviewed

栄元優作, 江頭和輝, 河野慎, 西山勇毅, 大越匡, 米澤拓郎, 高汐一紀, 中澤仁

研究報告ユビキタスコンピューティングシステム（UBI） Vol. 2017-UBI55 ( 16 ) page： 1 2017

Shape changing locomotion by spiny multipedal robot. Reviewed

Hiroki Nozaki, Ryuma Niiyama, Takuro Yonezawa, Jin Nakazawa

2017 IEEE International Conference on Robotics and Biomimetics, ROBIO 2017, Macau, Macao, December 5-8, 2017 Vol. 2018-January page： 2162 - 2166 2017

Language：Japanese Publishing type：Research paper (international conference proceedings) Publisher：IEEE

© 2017 IEEE. The use of geometric is an alternative framework for robotic locomotion instead of animal-inspired structures. We propose a spiny, multi-pedal robot that uses radial linear actuators as the legs. We developed a unique telescopic slide actuator that has a stroke up to 250% of its minimum length. The default form of the robot is a sphere with variable diameters. The radial arrangement of the telescopic slide actuators allows a large range of shape transformation and processes for rolling. We first show the basic properties of the actuator to verify the ability to elevate and propel the body. The single module of the actuator has a weight of 0.4 kg and can output a force of 25 N maximum. We demonstrate that the robot with twelve spines can change its shape to adapt to a level ground, wall, and rocky surfaces. We also show that the robot can roll on level ground with triangle-based strides. We expect further applications in surveillance and unmanned exploration.

DOI： 10.1109/ROBIO.2017.8324739

Scopus

Evaluating the Spatio-temporal Coverage of Automotive Sensing for Smart Cities Reviewed

Chen, Y; Yonezawa, T; Nakazawa, J; Tokuda, H

2017 TENTH INTERNATIONAL CONFERENCE ON MOBILE COMPUTING AND UBIQUITOUS NETWORK (ICMU) page： 13 - 17 2017

実況lizer: スポーツ実況のメタファに基づいたライブ都市センサデータの可聴化手法の提案 Reviewed

井上義之, 米澤拓郎, 大越匡, 中澤仁

研究報告ユビキタスコンピューティングシステム（UBI） Vol. 2017-UBI56 ( 6 ) page： 1 2017

SpoTrip: 観光客リピータ化促進のための隠れスポット情報提供システムの評価 Reviewed

片山晋, 礒川直大, 小渕幹夫, 西山勇毅, 大越匡, 米澤拓郎, 中澤仁, 高汐一紀, 徳田英幸

研究報告ユビキタスコンピューティングシステム（UBI） Vol. 2017-UBI53 ( 12 ) page： 1 2017

Shape Changing Locomotion by Spiny Multipedal Robot Reviewed

Nozaki, H; Niiyama, R; Yonezawa, T; Nakazawa, J

2017 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS (IEEE ROBIO 2017) page： 2162 - 2166 2017

Likeyboard: ライフログデータ共有簡易化のためのスマートフォンキーボードインタフェース Reviewed

石川伶, 佐々木航, 西山勇毅, 大越匡, 米澤拓郎, 中澤仁, 高汐一紀, 徳田英幸

研究報告ユビキタスコンピューティングシステム（UBI） Vol. 2017-UBI53 ( 12 ) page： 1 2017

An Empirical Study on Coverage-Ensured Automotive Sensing using Door-to-door Garbage Collecting Trucks Reviewed

Yin Chen, Jin Nakazawa, Takuro Yonezawa, Takafumi Kawasaki, Hideyuki Tokuda

Proceedings of the 2nd International Workshop on Smart, SmartCities 2016 page： 6:1-6:6 - 6 2016.12

Language：English Publishing type：Research paper (international conference proceedings) Publisher：Association for Computing Machinery, Inc

Due to the advance in information and communication technologies, smart cities have become an increasingly appealing vision. One indispensable basis in the research, development and implementation of smart cities is urban sensing technologies, which collect various citywide data that will be processed to generate information for understanding the status of cities. Automotive sensing is a novel urban sensing technology that utilizes the mobility of automobiles to conduct sensing tasks. In a collaborative smart-city project with the city office of Fujisawa City, Japan, we designed and implemented an automotive sensing platform called Cruisers, and have deployed it into the garbage collecting trucks of the city to evaluate the applicability of automotive sensing in realistic urban settings. In this paper, we first detail the system design, implementation and deployment of Cruisers and then evaluate its performance in realistic setting.

DOI： 10.1145/3009912.3009921

Scopus

SOXFire: A Universal Sensor Network System for Sharing Social Big Sensor Data in Smart Cities Reviewed

Takuro Yonezawa, Tomotaka Ito, Jin Nakazawa, Hideyuki Tokuda

Proceedings of the 2nd International Workshop on Smart, SmartCities 2016 page： 2:1-2:6 - 6 2016.12

Language：English Publishing type：Research paper (international conference proceedings) Publisher：Association for Computing Machinery, Inc

We introduce SOXFire, a multi-community city-wide sensor network for sharing social big sensor data in smart cities. The goal of SOXFire is to provide practical distributed and federated infrastructure for IoT sensor data sharing among various users/organizations in a way that is scalable, exten- sible, easy to use and secure with preserving privacy. SOX- Fire supports not only access to physical IoT sensors but also crowd sensing and SNS/Web sensing where city employees, citizen and WEB developers contributed in a different ways but unified APIs. In this paper, we outline the concept of SOXFire and present it's design and implementation with tangible libraries and tools. In addition, we discuss capability and usability of SOXFire based on our experiments in smart city project in Japan.

DOI： 10.1145/3009912.3009922

Scopus

EverCuate: Asynchronously-participatable Tsunami Evacuation Training System

大越匡, 米澤拓郎, 山本慎一郎, 中島円, 神武直彦, 栗田治, 中澤仁, 徳田英幸

情報処理学会論文誌 Vol. 57 ( 10 ) page： 2143 - 2161 2016.10

Language：Japanese Publishing type：Research paper (scientific journal)

大地震発生時の津波から身を守るためには平常時の津波避難訓練が重要とされる．本研究は，従来行われてきたイベント型の津波避難訓練における，災害シナリオ，訓練日時，訓練場所，参加可能な人の面での柔軟性欠如の課題に取り組み，ユビキタス・コンピューティング技術を利用してそれらを解決する「ユーザ非同期参加型津波避難訓練モデル」を提案する．同モデルにおいては，各ユーザが個別に，任意のタイミング・災害シナリオ・地点で避難訓練を実施でき，また避難行動記録や避難中の気づきを集約して可視化分析することで，防災計画の更新に活用できることを特長とする．本研究では同モデルに基づきプロトタイプシステム「EverCuate」を構築した．神奈川県藤沢市において40人の被験者による229回にわたる広範なユーザ評価実証実験，およびアンケート評価を行い，訓練への参加のしやすさへの寄与，防災意識向上への貢献，収集した避難行動やユーザフィードバック情報の可視化による防災計画への活用，既存方式と比較しての施策としての有効性の面で効果が明らかになった．Evacuation trainings have been conducted as an effective action to protect people from incoming tsunamis in case of a big earthquake. This research addresses limitations of existing conventional "event-style" tsunami evacuation trainings, that are inflexible in disaster scenarios, training timings, training locations, and participatable trainees. We propose a new ubiquitous computing technology-supported training model named "Asynchronously-Participatable Tsunami Evacuation Training Model" and a prototype system "EverCuate" based on this model. We evaluated the EverCuate system by conducting an extensive user study in Fujisawa city, Kanagawa, with 40 participants and the total number of 229 trainings. The evaluation results validated the effectiveness of EverCuate in terms of easiness in participation to a training, promotion of understanding necessity of different evacuation behaviour for different disaster scenarios, and easiness of analysing people's real evacuation behaviour from the view point of local authorities.

J-GLOBAL

　 PREV - NEXT 　

<YONEZAWA Takuro>

Papers - YONEZAWA Takuro