【発表】修士1年生沖原君が研究内容を国際会議Empowering the Lifestyle and Well-being of Eastern Asian Elders with intelligent IoTで発表しました – ‘ Material Recognition by Passive Sensing of Vibration of an Object Placed on a Surface Using a Portable Accelerometer’

【採択】学部3年生 泉川君の研究が国際会議ACM HotMobile 2023 poster sessionにacceptされました – ‘ Audio-based Eating Stage Recognition through CNN Model Trained on ASMR Eating Sounds’

Abstract:

A balanced diet and an appropriate calorie intake are the keys to both preventing and treating type II diabetes. Meanwhile, widespread techniques such as manual food logs and food image captures have been posing burdens on those with diabetes and have made diet monitoring difficult to become part of one’s routine. To develop an earable device that monitors a volume of food intake automatically, an-audio based detection of eating instances is necessary. The present research therefore attempted to classify an eating sound, collected from YouTube eating ASMR, into one of the following labels: chew, swallow, or non-eating A CNN machine learning model using sound features as input achieved an accuracy of 81%.

【採択】学部2年生後藤君の研究が国際会議 IEEE PerCom 2023 Work in Progress Sessionにacceptされました – ‘ 3D Spatial Sensing and Analysis Model of ClosedSpace CO2 Concentration’

Abstract:

We propose a 3D CO2 concentration analyzing system to monitor the ventilation of the closed space. This system uses a 3D scan to lower the labor of creating a 3D model of the space. In this research, multiple CO2 sensors are used, and consider the model to map point CO2 concentration data to the spatial CO2 distribution. We experimented to check the accuracy of the model in the real bus space.

【採択】修士1年生浜中君の研究が国際会議ACM HotMobile 2023 poster sessionにacceptされました – ‘ Estimation of user personality traits on the Web Using Multi-Task Learning’

Abstract:

We focus on user’s personality traits and propose a method to estimate user’s personality traits from footprint logs collected from news platform services and search queries, with the aim of constructing a news recommendation system using the personality traits. We constructed supervised machine learning models for 8871 users, using the features calculated from news browsing logs as explanatory variables and personality traits (Big Five) collected via a questionnaire using crowdsourcing as objective variables. Five estimators were constructed for each Big Five traits, and the results of comparative evaluation using multiple algorithms showed that the accuracy of AUC 0.634 was obtained for the agreeableness trait.

卒業生の青木崇行さんが、12/22(木)の授業でゲストスピーカーとして講演されました。青木崇行さんは、2008年に慶應義塾大学大学院 政策・メディア研究科 後期博士課程を修了され、現在はカディンチェ株式会社 代表取締役社長として空間表現技術の研究開発及び製造・販売に携わっています。

修士1年 浜中君らの研究が情報処理学会 IoT行動変容学研究グループ 第２回研究会にて最優秀口頭発表賞を受賞しました。

研究概要：

食事や運動・睡眠などのライフログを記録すると，アルゴリズム・AI によるアドバイスがユーザに提供される健康アプリケーションにおいては，ライフログの入力や健康行動の継続が重要である．一方で，その継続促進に向けた，効果的な情報提示手法が課題である．本研究では，ライフログ入力を促す情報提示において，(a) 物理的行動に基づくタイミング調整や(b) 個人の制御焦点状態に基づく文言の調整およびそれらの複合的調整の，ユーザのサービス利用促進への影響について実証実験を行い効果を明らかにした．

学部4年 高君らの研究がUbiComp/ISWC 2022併設ワークショップ WellComp 2022(https://wellcomp-workshop.github.io/2022/schedule.html) にて発表されました。

Abstract:

Previous studies have shown that not only player skill but also psychological factors contribute to improving archery scores. Therefore, in addition to improving learners’ posture, an archery learning support system is required to improve psychological coping skills, such as mental and physical condition management skills. This study propose a method for estimating the condition of archery learners in order to provide appropriate instruction in accordance with their condition. In previous studies of condition estimation, in- put data are usually objective while label data are usually subjective. Such bias between data is considered as a partial reason of estimation accuracy reduction. Judgments of conditions are subjective and individually different. Subjects’ emotion recognition abilities(ERA) are the individual differences in the judgment of emotions, a part of condition in our study. We utilized interoceptive accuracy to objectively evaluate subjects’ ERA. Based on archery movement data collected from 10 subjects, we compared the baseline method and the proposed method with the addition of objectively evaluated ERA. The results showed that the latter method, which took into account individual differences of ERA among subjects, estimated condition better than baseline method. We believe that proposed condition estimation method, which pays regard to users’ mental and physical condition, is not only useful in sports scenarios, but also necessary for supporting human well-bing based on better understanding of user context.

博士１年黄君の修士論文が、大学院CIプログラム(https://www.sfc.keio.ac.jp/gsmg/education/program/ci.html)にて優れた研究に送られる CI Research Awardを受賞しました。

学部3年 乾君らの研究が情報処理学会第75回UBI研究会にてヤングリサーチャー賞を受賞しました。

乾雄貴, 沖原周佑, 安井慎一郎, 佐々木航, 大越匡, & 中澤仁. (2022). スマートグラスを用いた明確な目的を持たないスマホ使用の検知. 研究報告ユビキタスコンピューティングシステム (UBI), 2022(9), 1-7.

http://id.nii.ac.jp/1001/00219751/

近年のスマートフォンの普及とともに，使いすぎや依存症が問題となっている．病的なインターネットの使用は Pathlogical Internet Use (PIU) と呼ばれ，本研究ではその症状である目的を持たないインターネット使用をスマートフォンにおいて考え，検知することを目的とする．スマートフォンの使用状況と目の動きの関連性が示唆されていることから，本研究では男女 8 名からスマートグラスを用いて視線情報や頭部の加速度，角速度などのデータを取得し，それらのデータから機械学習モデルを構築し，ユーザーのスマートフォン使用のうち目的を持たない使用を推定する機械学習モデルを構築した．結果としては，モデルに勾配ブースティングモデルと決定木モデルを組み合わせて作成された機械学習モデルである XGBoost を用いることで 0.885 の精度で目的を持たないスマートフォン使用を検知することができた．

During Aug. 22~23, the 4th workshop was held in Hakodate city, Hokkaido. In this time, we had a hybrid event in which there were 63 (registered) remote attendees and  25 on-site attendees including 4 from Korea.  4 keynotes and 9 research presentations were made by professors and students from Japan, China and Korea. This is the first time of this project to have in-person communication since its beginning. The visit to Future University Hakodate was also interesting and inspiring.    We sincerely thank all the speakers and attendees for their contributions. We are also grateful to the organizers for their great effort making this gather real.  The next workshop will be held by Korean team in January. See you in Korea!