論文一覧

@article{access2022-ishikawa,

title = {Unsupervised Learning of Domain-Independent User Attributes},

author = {Yuichi Ishikawa, Roberto Legaspi, Kei Yonekawa, Yugo Nakamura, Shigemi Ishida, Tsunenori Mine, Yutaka Arakawa},

doi = {10.1109/ACCESS.2022.3220781},

issn = {2169-3536},

year  = {2022},

date = {2022-11-09},

urldate = {2022-11-09},

journal = {IEEE Access},

volume = {10},

pages = {119649-119665},

abstract = {Learning user attributes is essential for providing users with a service. In particular, for e-commerce portals which deal in variety of goods ranging from clothes to foods to home electronics, it is especially important to learn “domain-independent” attributes such as age, gender, and personality that affect people’s behavior across various domains of daily life (e.g., clothing, eating and housing) because these attributes can be used for personalization in diverse domains their service covers. Thus far, researchers have proposed approaches to learn user representation (UR) from user-item interactions, trying to embed rich information about user attributes in UR. However, very few can learn URs that are domain-independent without confounding them with domain-specific attributes (e.g., food preferences). This could consequently undermine the former’s utility for personalizing services in other domains from which the URs are not learned. To address this, we propose an approach to learn URs that exclusively reflect domain-independent attributes. Our approach introduces a novel multi-layer RNN with two types of layers: Domain Specific Layers (DSLs) for modeling behavior in individual domains and a Domain Independent Layer (DIL) for modeling attributes that affect behavior across multiple domains. By exchanging hidden states between these layers, the RNNs implement the process of domain-independent attributes affecting domain-specific behavior and makes the DIL learn URs that capture domain-independence. Our evaluation results confirmed that the URs learned by our approach have greater utility in predicting behavior in the other domains from which these URs were not learned thereby demonstrating adaptability to various domains.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{access2022-umeki,

title = {Large-Scale Evacuation Shelter Selection Method Through Iterations of Pedestrian Simulations With Dynamic Congestion Reproduction},

author = {Kazuhito Umeki and Tomoki Tanaka and Yugo Nakamura and Manato Fujimoto and Teruhiro Mizumoto and Hirohiko Suwa and Yutaka Arakawa and Keiichi Yasumoto},

doi = {10.1109/ACCESS.2022.3194874},

issn = {2169-3536},

year  = {2022},

date = {2022-08-25},

journal = {IEEE Access},

volume = {10},

pages = {89387-89401},

abstract = {It is necessary to optimize evacuation guidance to shelters in short evacuation time. The state-of-the-art method based on an idea of combinatorial optimization problems related to evacuees’ locations and the capacities of nearby shelters has been developed, while it cannot mitigate the effect of congestion on roads/streets after evacuation starts. In this study, to cover this problem, we develop a new method that utilizes simulations for estimating the effect of congestion on roads/streets during evacuation and reassigning shelters to evacuees based on the simulation results. By iterating this step, our method derives the congestion-aware solutions for shelter selection that can realize more smooth evacuation. To evaluate our method, we conducted multi-agent simulations assuming a disaster situation in a sightseeing spot. Specifically, we examined a hypothetical case scenario involving the evacuation of 30,000 visitors from the Gion Festival. We compared the proposed method with conventional methods, such as the nearest shelter selection method and our previous method. We found that our proposed method reduced average and total evacuation time and congestion on roads compared to the conventional methods including the nearest shelter selection method and our previous method that only employs combinatorial optimization without estimating congestion. From this result, our idea of simulation-based congestion estimation has an impact of easing congestion during evacuation and preventing overcapacity of shelters at the same time. It shows the possibilities of help in developing congestion-aware evacuation strategies in emergency situations of crowded areas like huge cities or sightseeing spots.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{sam2022_oi,

title = {Inertial Measurement Unit-sensor-based Short Stick Exercise Tracking to Improve Health of Elderly People},

author = {Kazuki Oi and Yugo Nakamura and Yuki Matsuda and Manato Fujimoto and Keiichi Yasumoto},

doi = {10.18494/SAM3968},

year  = {2022},

date = {2022-08-02},

journal = {Sensors and Materials},

volume = {34},

number = {8},

pages = {2911-2928},

abstract = {Short stick exercises have been attracting attention from the viewpoint of preventing falls and improving the health of elderly people and are generally performed under the guidance of instructors and nursing staff at nursing homes. However, in situations such as the COVID-19 pandemic, where people should refrain from unnecessary outings, it is advisable that individuals perform short stick exercises at home and record their exercise implementation status. In this paper, we propose an inertial measurement unit (IMU)-sensor-based short stick exercise tracking method that can automatically record the types and amounts of exercises performed using a short stick equipped with an IMU sensor. The proposed method extracts time-domain and frequency-domain features from linear acceleration and quaternion time-series data obtained from the IMU sensor and classifies the type of exercise using an inference model based on machine learning algorithms. To evaluate the proposed method, we collected sensor data from 21 young subjects (in their 20s) and 14 elderly subjects (79–95 years old), where the participants performed three sets (10 times per set) of eight basic types of short stick exercises (five types for elderly people). As a result of evaluating the proposed method using this data set, we confirmed that when LightGBM was used as the learning algorithm, it achieved F values of 90.0% and 86.6% for recognizing the type of exercise for young and elderly people, respectively.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{sam2022_harashima,

title = {Effect of Circadian Rhythm Control Light on Sleep State and Mental Health of Students},

author = {Haruki Harashima and Shuta Matsuo and Yutaka Arakawa},

doi = {10.18494/SAM3952},

year  = {2022},

date = {2022-08-02},

journal = {Sensors and Materials},

volume = {34},

number = {8},

pages = {2973-2983},

abstract = {Many office workers are exposed to fluorescent light from mid-morning to after dark. The changes in the amount of light in the natural world, from bright during the day to dark at night, play an important role in maintaining a regular daily rhythm. In this study, we evaluated the effects of LED lighting equipped with a circadian rhythm control function, Lavigo, by comparing it with conventional fluorescent lighting on students’ sleep quality and stress. Lavigo’s Visual Timing Light (VTL) function adjusts the color and brightness of light according to the biological rhythm of about 24 h cycles. We measured the sleep state using Fitbit and collected subjective responses through a stress-checking questionnaire. A salivary amylase monitor was used to measure objective stress values from a medical perspective. No significant difference in stress values was observed during the experiment. However, only during the week that Lavigo was used, a certain subject showed a significant decrease in waking time during sleep, and another subject showed an increase in deep sleep. It was also found that these subjects tended to lead an irregular life, such as staying up until midnight.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{sam2022_chen,

title = {Quantitative Evaluation System for Online Meetings Based on Multimodal Microbehavior Analysis},

author = {Chenhao Chen, Yutaka Arakawa, Ko Watanabe, Shoya Ishimaru},

doi = {10.18494/SAM3959},

year  = {2022},

date = {2022-08-02},

urldate = {2022-08-02},

journal = {Sensors and Materials},

volume = {34},

number = {8},

pages = {3017-3027},

abstract = {Maintaining a positive interaction is the key to a healthy and efficient meeting. Aiming to improve the quality of online meetings, we present an end-to-end neural-network-based system, named MeetingPipe, which is capable of quantitative microbehavior detection (smiling, nodding, and speaking) from recorded meeting videos. For smile detection, we build a neural network framework that consists of an 18-layer residual network for feature representation, and a self-attention layer to explore the correlation between each receptive field. To perform nodding detection, we obtain head rotation data as the key nodding feature. Then we use a gated recurrent unit followed by a squeeze-and-excitation mechanism to capture the temporal information of nodding patterns from head pitch angles. In addition, we utilize TalkNet, an active speaker detection model, which can effectively recognize active speakers from videos. Experiments demonstrate that with K-fold cross validation, the F1 scores of the smile, nodding, and speaking detection are 97.34, 81.26, and 94.90%, respectively. The processing can be accelerated with multiple GPUs due to the multithread design. The code is available at https://github.com/humanophilic/MeetingPipe.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{sam2022_matsuda,

title = {ParmoSense: Scenario-based Participatory Mobile Urban Sensing Platform with User Motivation Engine},

author = {Yuki Matsuda and Shogo Kawanaka and Hirohiko Suwa and Yutaka Arakawa and Keiichi Yasumoto},

doi = {10.18494/SAM3961},

year  = {2022},

date = {2022-08-02},

journal = {Sensors and Materials},

volume = {34},

number = {8},

pages = {3063-3091},

abstract = {The rapid proliferation of mobile devices with various sensors has enabled participatory mobile sensing (PMS). Several PMS platforms suffer from open issues including the limited use of their functions to a specific scenario/case and the necessity of technical knowledge for organizers. This paper proposes a novel PMS platform named ParmoSense for easy and flexible data collection. To reduce the burden on both organizers and participants, we employ two novel features. First, essential PMS functions implemented as modules can be easily chosen and combined for sensing in different scenarios. Second, the scenario-based description feature allows organizers to easily and quickly prepare a new instance of PMS and enable people to easily participate in the sensing. It also provides multiple functions to motivate participants for sustainable operation. Through a performance comparison with existing PMS platforms, we confirmed that ParmoSense shows the best cost performance in terms of the workload for preparation and the variety of functions. In addition, to evaluate the availability and usability of ParmoSense, we conducted 19 case studies over four years with ordinary citizens. As the result of a questionnaire survey carried out during the case studies, we confirmed that ParmoSense can be easily operated by ordinary citizens without technical skills.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hattori-sandm,

title = {Function-level Access Control System for Home IoT Devices},

author = {Yuichi Hattori, Yutaka Arakawa, Daichi Koike, Shigemi Ishida, Sozo Inoue},

year  = {2022},

date = {2022-06-01},

urldate = {2022-06-01},

journal = {Sensors and Materials},

volume = {36},

number = {6},

pages = {2125-2139},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{access2022-choi,

title = {Wi-CaL: WiFi Sensing and Machine Learning Based Device-Free Crowd Counting and Localization},

author = {Hyuckjin Choi, Manato Fujimoto, Tomokazu Matsui, Shinya Misaki, Keiichi Yasumoto},

doi = {10.1109/ACCESS.2022.3155812},

issn = {2169-3536},

year  = {2022},

date = {2022-03-02},

urldate = {2022-03-02},

journal = {IEEE Access},

volume = {10},

pages = {24395-24410},

abstract = {Wireless sensing represented by WiFi channel state information (CSI) is now enabling various fields of applications such as person identification, human activity recognition, occupancy detection, localization, and crowd estimation these days. So far, those fields are mostly considered as separate topics in WiFi CSI-based methods, on the contrary, some camera and vision-based crowd estimation systems intuitively estimate both crowd size and location at the same time. Our work is inspired by the idea that WiFi CSI also may be able to perform the same as the camera does. In this paper, we construct Wi-CaL, a simultaneous crowd counting and localization system by using ESP32 modules for WiFi links. We extract several features that contribute to dynamic state (moving crowd) and static state (location of the crowd) from the CSI bundles, then assess our system by both conventional machine learning (ML) and deep learning (DL). As a result of ML-based evaluation, we achieved 0.35 median absolute error (MAE) of counting and 91.4% of localization accuracy with five people in a small-sized room, and 0.41 MAE of counting and 98.1% of localization accuracy with 10 people in a medium-sized room, by leave-one-session-out cross-validation. We compared our result with percentage of non-zero elements metric (PEM), which is a state-of-the-art metric for crowd counting, and confirmed that our system shows higher performance (0.41 MAE, 81.8% of within-1-person error) than PEM (0.62 MAE, 66.5% of within-1-person error).},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{gogami-2022-dbsj,

title = {オンラインアンケートにおける不適切回答自動検出に向けた回答操作ログの統計分析},

author = {後上 正樹，松田 裕貴，荒川 豊，安本 慶一},

year  = {2022},

date = {2022-03-01},

urldate = {2022-03-01},

journal = {日本データベース学会和文論文誌},

volume = {20-J},

number = {9},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{weko_215818_1,

title = {タッチ操作ログに基づいた操作形態推定手法},

author = {平部 裕子, 諏訪 博彦, 荒川 豊, 安本 慶一},

url = {https://ipsj.ixsq.nii.ac.jp/ej/index.php?active_action=repository_view_main_item_detail&page_id=13&block_id=8&item_id=215818&item_no=1},

doi = {10.20729/00215710},

year  = {2022},

date = {2022-01-15},

urldate = {2022-01-15},

journal = {情報処理学会論文誌},

volume = {63},

number = {1},

pages = {45--55},

abstract = {ユーザがどのようにスマートフォンを持ち，どの指で操作しているかという情報（操作形態）が分かれば，様々な新しい応用，たとえば，操作形態に適したUI（ユーザインターフェス）への動的切替えや，ながらコンテキスト（スマートフォン操作時に行われている別行動，歩行，喫煙，食事など）の推定など，への道が拓ける可能性がある．本論文では，タッチ操作によって出力されるログに着目し，タッチやスワイプなどの操作領域や頻度からどのような操作形態かを推定する方法を提案する．そのために，Android上でアプリ横断的にタッチ操作を取得可能なTouchAnalyzerから得られた情報を特徴量とし，機械学習手法により代表的な8通りの操作形態を推定する手法を構築する．16名の実験参加者による評価実験を通じて，提案手法によって操作形態をおおむね90%のF値で推定できることが分かった．},

keywords = {},

pubstate = {published},

tppubtype = {article}

}