| LIKOTIKO EUNICE DAVID | D, 中間発表 | ユビキタスコンピューティングシステム | 安本 慶一, | 清川 清, | 松田 裕貴 | |
|
title: Smart garbage bin system for understanding user behaviour on garbage disposal
abstract: Recently, there is a growing use of smart garbage management systems. Previous work on IoT garbage management systems presents an opportunity to provide a dynamic garbage collection and estimate future garbage growth. However, little attention has been given to understanding users’ garbage disposal behaviour, garbage growth and the type of garbage contents produced and disposed by the households. To examine, we designed and developed a smart garbage bin system “SGBS,” capable of tracking garbage amounts and identifying contents of garbage disposed. The smart garbage bin was fastened with a ToF (time of flight), DHT22 (temperature and humidity), load cell and air quality sensors for measuring the amount of garbage. To evaluate our approach, we conducted two initial experiments to learn patterns, peaks, and trends of garbage growth. In the first experiment, we collected burnable garbage data for one month in a student lab. The ARIMA model was used to predict future garbage growth resulting with an average mean of absolute error of 5.17cm and standard deviation of 0.33cm. In the second experiment, we installed the smart garbage bin in three households for 11-21 days. Household users used a smartphone installed with garbage annotation application to the input type of garbage disposed. Our findings show that households’ garbage disposal behaviour depends on the amount and contents of garbage as well as the routine of disposing such garbage content. We discuss the potential of our system to be scaled in a smart city to influence behaviour change, provide healthier life, and improve garbage management operational efficiency.
language of the presentation: English | ||||||
| 大山 航平 | M, 2回目発表 | ユビキタスコンピューティングシステム | 安本 慶一, | 清川 清, | 諏訪 博彦, | 松田 裕貴 |
|
title: Improving the reliability of responses to participatory sensing by asking for expressing intention to contribute
abstract: In participatory sensing, which requests users to provide information such as the surrounding environment on their mobile devices, respondents sometimes try to complete the request quickly and effortlessly. Due to that, the answer is not always accurate. In this study, we propose a system that suppresses careless responses by introducing the method of expressing intention to contribute, which requires respondents to swear to answer seriously, to participatory sensing using smartphones. In addition, we confirmed the usefulness of the proposed method by conducting evaluation experiments using the system. language of the presentation: Japanese 発表題目: 立場表明を求めることによる参加型センシングの回答信頼性向上 発表概要: モバイル端末上でユーザの周辺環境などの情報提供を依頼する参加型センシングにおいて，回答者が楽に早く依頼を完了しようとし，必ずしも正確に回答しないという問題がある．そこで本研究では，真面目に回答するという宣誓を回答時に回答者に求める立場表明の手法をスマートフォンを用いた参加型センシングに導入し，不良回答を抑制するシステムを開発した．また，本システムを用いて評価実験を行うことで，定手法が不良回答数を優位に減少させることを確認した． | ||||||
| 中岡 黎 | M, 2回目発表 | ユビキタスコンピューティングシステム | 安本 慶一, | 清川 清, | 諏訪 博彦, | 松田 裕貴 |
|
title: Design and basic evaluation of a behavior change support system to promote healthy eating habits
abstract: Meal is one of the most important lifestyle habits that are essential for maintaining physical and mental health. In particular, it is desirable to be able to improve unhealthy habits, such as choosing foods with unbalanced nutrition and eating too fast, because these habits have the risk of causing lifestyle-related diseases. Most of the existing dietary support systems focus on recording meal menus and recognizing eating behaviors, and therefore, mechanisms to promote healthy eating habits have not been sufficiently studied. In this study, we propose a behavior change system that encourages users' healthy eating habits by reframing eating behavior into a task of painting pictures. The system consists of a chopstick sensor that recognizes detailed eating behavior and a digital canvas that visualizes the goodness or badness of eating behavior. In this announcement, we present the results of our evaluation of the chopstick sensor and the digital canvas. language of the presentation: Japanese 発表題目: 健康的な食生活を促す行動変容支援システムの設計と基礎評価 発表概要: 食事は，心身の健康を維持するために欠かせない重要な生活習慣の一つである． 特に，栄養バランスの偏った食品の選択や早食いといった不健康な習慣は，生活習慣病を引き起こす危険性があるため，改善できることが望ましい． 既存の食生活支援システムの多くは，食事メニューの記録や，食事行動の認識に特化しているため，健康的な食生活を促すための仕掛けが十分に検討されていない． 本研究では，食べるという行動を絵に色を塗るというタスクにリフレーミングすることで，ユーザ の健康的な食生活を後押しする行動変容システムを提案する．本システムは詳細な食事行動を認識する箸型センサと食事行動の良し悪しを視覚化するデジタルキャンバスで構成されている． 本発表では，箸型センサとデジタルキャンバスについて評価を行なった結果を報告する． | ||||||
| 大井 一輝 | M, 2回目発表 | ユビキタスコンピューティングシステム | 安本 慶一, | 清川 清, | 藤本 まなと, | 松田 裕貴 |
|
title: Proposal of a Support System for Short Stick Exercise Using IMU sensors
abstract: Recently, stick exercises have been attracting attention for the purpose of preventing falls and improving the health of the elderly. Stick exercises are generally performed in nursing homes under the guidance of an instructor or nursing staff. However, in the situation of COVID-19 ravages, it is desirable for individuals to be able to perform stick exercises correctly on their own. We aim to develop a system to support the improvement of stick exercises by automatically recording the type and amount of exercises the elderly person performed and providing feedback to improve the correct movement. In this presentation, as a first step toward the realization of a stick exercise support system, we propose a motion recognition method for stick exercises using IMU sensors. As an evaluation experiment, we asked 35 subjects to perform basic stick exercises and classified the exercise movements based on the linear acceleration and quaternion data obtained from the IMU. language of the presentation: Japanese 発表題目: IMUセンサを用いた棒体操支援システムの検討 発表概要: 高齢者の転倒予防や健康増進の観点から注目を集めている棒体操は，介護施設等でインストラクターや介護職員の指導のもと実施することが一般的である．しかし，不要不急の外出を控えることが推奨されている現在のコロナ禍のような状況においては，各個人が一人で棒体操を実施できることが望ましい．本研究では，高齢者にリアルタイムで体操のフィードバックを提供できる棒体操支援システムの実現を目指している．今回は棒体操支援システムの実現に向けた第一段階として，IMUセンサを用いた棒体操の動作認識手法を提案する．評価実験として，35人の被験者に基本的な棒体操を行ってもらい，IMUから得られる線形加速度とクォータニオンのデータを基に，体操動作の分類を行なった． | ||||||