Publication

@inproceedings{nokey,

title = {Toward detecting maternity neurosis by using passive mobile sensing: preliminary investigation},

author = {Xiuwen Gu, Akihito Taya, Yuuki Nishiyama, Kaoru Sezaki},

url = {https://ieeexplore.ieee.org/document/10880785},

doi = {10.1109/HEALTHCOM60970.2024.10880785},

year  = {2024},

date = {2024-11-18},

booktitle = {2024 IEEE International Conference on E-health Networking, Application & Services (HealthCom)},

address = {Nara, Japan},

abstract = {Child-rearing depression, triggered by the chronic stress of parenting, can lead to serious mental health issues if not detected early. This study uses passive mobile sensing to analyze the behavioral and psychological patterns of households with preschool children. By collecting data from 131 participants (including 18 parents of preschoolers), we aim to differentiate child-rearing anxiety and behavior patterns. Our focus includes step counts, location data, call frequency, and psychological states. Results indicate that parents of preschoolers have fewer steps, visit fewer locations, and have higher call activity. They also show higher stress and anxiety but lower depression levels, suggesting that family support may mitigate depressive symptoms. These insights could aid in developing early detection and intervention strategies for child-rearing depression.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10.1145/3627673.3680050,

title = {Deep Learning-Based Compressed Sensing for Mobile Device-Derived Sensor Data},

author = {Liqiang Xu and Yuuki Nishiyama and Kota Tsubouchi and Kaoru Sezaki},

url = {https://doi.org/10.1145/3627673.3680050},

doi = {10.1145/3627673.3680050},

isbn = {9798400704369},

year  = {2024},

date = {2024-10-23},

urldate = {2024-10-23},

booktitle = {Proceedings of the 33rd ACM International Conference on Information and Knowledge Management},

pages = {5023–5030},

publisher = {Association for Computing Machinery},

address = {Boise, ID, USA},

series = {CIKM '24},

abstract = {As the capabilities of smart sensing and mobile technologies continue to evolve and expand, storing diverse sensor data on smartphones and cloud servers becomes increasingly challenging. Effective data compression is crucial to alleviate these storage pressures. Compressed sensing (CS) offers a promising approach, but traditional CS methods often struggle with the unique characteristics of sensor data-like variability, dynamic changes, and different sampling rates-leading to slow processing and poor reconstruction quality. To address these issues, we developed Mob-ISTA-1DNet, an innovative CS framework that integrates deep learning with the iterative shrinkage-thresholding algorithm (ISTA) to adaptively compress and reconstruct smartphone sensor data. This framework is designed to manage the complexities of smartphone sensor data, ensuring high-quality reconstruction across diverse conditions. We developed a mobile application to collect data from 30 volunteers over one month, including accelerometer, gyroscope, barometer, and other sensor measurements. Comparative analysis reveals that Mob-ISTA-1DNet not only enhances reconstruction accuracy but also significantly reduces processing time, consistently outperforming other methods in various scenarios.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ubicomp2024_sonotify_ito,

title = {Investigating Acceptable Voice-based Notification Timings through Earable Devices: A Preliminary Field Study},

author = {Manaka Ito and Kota Tsubouchi and Nobuhiko Nishio and Masamichi Shimosaka and Akihito Taya and Kaoru Sezaki and Yuuki Nishiyama},

doi = {10.1145/3675094.3677579},

year  = {2024},

date = {2024-10-05},

urldate = {2024-10-05},

booktitle = {Companion of the 2024 on ACM International Joint Conference on Pervasive and Ubiquitous Computing},

pages = {30–34},

publisher = {Association for Computing Machinery},

address = {Melbourne, Australia},

series = {UbiComp '24},

abstract = {Earable devices, a subset of wearable technology, are designed to be worn on the ear and used in daily life. These innovative devices enable users to receive voice-based notifications through a minute built-in speaker without requiring any user operations, seamlessly integrating technology into everyday activities. The timing deemed acceptable for receiving voice-based notifications through earable devices varies based on the user and surrounding situation; thus, inappropriate notification timing may reduce usability. However, determining the safest and most comfortable timing for voice-based notifications using earable devices remains unclear. This study investigates the acceptable timing of voice-based notifications through earable devices. To explore the acceptable timing, we developed a smartphone application, SoNotify, which can send dummy voice-based notifications and collect sensor data on a smartphone and an earable device. Our field studies with eight participants showed that voice-based notifications were highly acceptable during outdoor walking, with an acceptance rate of approximately 86%. However, users tended to refuse notifications in situations in which they needed to concentrate on avoiding collisions with pedestrians, cyclists, or vehicles.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ubicomp2024_alife_wang,

title = {Toward Detecting Student-Athletes' Condition Using Passive Mobile and Wearable Sensing},

author = {Zhenbo Wang and Akihito Taya and Kato Takaaki and Kaoru Sezaki and Yuuki Nishiyama},

doi = {10.1145/3675094.3677583},

year  = {2024},

date = {2024-10-05},

urldate = {2024-10-05},

booktitle = {Companion of the 2024 on ACM International Joint Conference on Pervasive and Ubiquitous Computing},

pages = {51–55},

publisher = {Association for Computing Machinery},

address = {Melbourne VIC, Australia},

series = {UbiComp '24},

abstract = {Student-athletes (SA) face stress from balancing athletic and academic demands, and monitoring their physical and mental stress is crucial for better well-being. Questionnaires and dedicated measurement equipment have been used to assess 

SAs’ mental and physical status. However, these methods are not scalable and are difficult to use continuously. In this paper, we propose a method for monitoring the physical and mental state of SA using passive mobile and wearable sensing technology to monitor it with a low burden. First, we developed a platform for collecting daily, training, and resetting behavior data from smartphones and wearable devices. Second, as a preliminary study, we collected the behavior and Stress and Recovery States Scale (SRSS) data for four weeks with 19 SA and analyzed the collected data to understand their unique behavior patterns and living environments. The results demonstrate that wearable devices and smartphones can automatically collect data on "exercise intensity during competitions" and "lifestyle patterns," specifically tailored to the mental and physical states of SA. Furthermore, this preliminary research establishes a foundation for future efforts using machine learning to predict the physical and mental states of SA.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ICDCS2024_Han,

title = {RideGuard: Micro-Mobility Steering Maneuver Prediction with Smartphones},

author = {Zengyi Han and Xuefu Dong and Liqiang Xu and Zhen Zhu and En Wang and Yuuki Nishiyama and Kaoru Sezaki},

url = {https://icdcs2024.icdcs.org/},

year  = {2024},

date = {2024-07-01},

urldate = {2024-07-01},

booktitle = {2024 IEEE 44th International Conference on Distributed Computing Systems (ICDCS)},

publisher = {IEEE Computer Society},

address = {Jersey City, New Jersey, USA},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{MobiSys2024_Atsumi,

title = {Poster: Towards Estimating UV Index with a Smartphone Utilizing GNSS Signals as a Point Cloud},

author = {Subaru Atsumi and Riku Ishioka and Kota Tsubouchi and Yuuki Nishiyama and Kaoru Sezaki},

url = {https://www.sigmobile.org/mobisys/2024/program.html},

year  = {2024},

date = {2024-06-03},

urldate = {2024-06-03},

booktitle = {Proceedings of the 22nd Annual International Conference on Mobile Systems, Applications and Services},

publisher = {Association for Computing Machinery},

address = {Tokyo, Japan},

series = {MobiSys '24},

abstract = {Monitoring and controlling the exposure of an individual to ultraviolet radiation is crucial for personal health. The use of the global navigation satellite system (GNSS) signals received by a personal off-the-shelf smartphone has been studied as a novel estimation method. In the existing method, satellites are grouped based on their positions and the signal information is represented by group statistics, leading to a coarse estimation. We propose a new ultraviolet (UV) index estimation method that directly utilizes satellite-wise information and their spatial relationships with a point-cloud neural network, considering the similarity between GNSS signals and point clouds. We collected GNSS signals and UV index data from two locations within the same area and demonstrated that the proposed method enhances the estimation accuracy and smoothness.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{MobiSys2024_Peng,

title = {Poster: Location Awareness in AED Retrieval: A Simulation-Based Investigation},

author = {Helinyi Peng and Akihito Taya and Yuuki Nishiyama and Kaoru Sezaki},

url = {https://www.sigmobile.org/mobisys/2024/program.html},

year  = {2024},

date = {2024-06-03},

urldate = {2024-06-03},

booktitle = {Proceedings of the 22nd Annual International Conference on Mobile Systems, Applications and Services},

publisher = {Association for Computing Machinery},

address = {Tokyo, Japan},

series = {MobiSys '24},

abstract = {Public awareness of Automated External Defibrillator (AED) locations is crucial for their prompt retrieval during cardiac emergencies. In this study, we propose a simulation-based approach as a preliminary step toward developing gamified mobile apps that can enhance this awareness. By simulating AED retrieval on real-world pedestrian networks under various scenarios, we identify key elements that can improve retrieval efficiency. Our findings confirm the viability of this framework and highlight crucial aspects for improvement, shedding light on more efficient future application development.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{CHI2024_Dong,

title = {ReHEarSSE: Recognizing Hidden-in-the-Ear Silently Spelled Expressions},

author = {Xuefu Dong and Yifei Chen and Yuuki Nishiyama and Kaoru Sezaki and Yuntao Wang and Kenneth Christofferson and Alex Mariakakis},

url = {https://chi2024.acm.org/},

year  = {2024},

date = {2024-05-14},

urldate = {2024-05-14},

booktitle = {Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems},

publisher = {Association for Computing Machinery},

address = {Hawaii, US},

series = {CHI '24},

abstract = {Silent speech interaction (SSI) allows users to discreetly input text without using their hands. Existing wearable SSI systems typically require custom devices and are limited to a small lexicon, limiting their utility to a small set of command words. This work proposes ReHEarSSE, an earbud-based ultrasonic SSI system capable of generalizing to words that do not appear in its training dataset, providing support for nearly an entire dictionary’s worth of words. As a user silently spells words, ReHEarSSE uses autoregressive features to identify subtle changes in ear canal shape. ReHEarSSE infers words using a deep learning model trained to optimize connectionist temporal classification (CTC) loss with an intermediate embedding that accounts for different letters and transitions between them. We find that ReHEarSSE recognizes unseen words with an accuracy of pmnice89.310.9%.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{maruyama2023optimization,

title = {An Optimization Method for Indoor Trajectory Estimation from Spatially Sparse and Noisy Beacon Data},

author = {Junya Maruyama and Yudai Honma and Yuuki Nishiyama and Yoshihiro Kawahara},

url = {https://sciforum.net/paper/view/17308},

year  = {2024},

date = {2024-04-16},

urldate = {2024-04-16},

booktitle = {OHOW 2023 – The 2nd International Symposium on One Health / Infrastructure Management and sustainable built environment},

pages = {6–8},

publisher = {MDPI},

address = {Basel, Switzerland},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{CCNC2024_Eri,

title = {Exploiting Spatial and Descriptive Information for Generative Compression},

author = {Eri Hosonuma and Taku Yamazaki and Takumi Miyoshi and Akihito Taya and Yuuki Nishiyama and Kaoru Sezaki},

url = {https://ccnc2024.ieee-ccnc.org/program/posters},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

booktitle = {IEEE Consumer Communications & Networking Conference},

address = {Las Vegas, NV, USA},

abstract = {There will be an increase in situations where images taken in specific locations are transmitted through networks for various services. However, this trend can lead to significant communication loads due to simultaneous transmission of images from multiple locations. Therefore, it is important to reduce the amount of network traffic in image transmission. While traditional compression methods focus on minimizing information loss in images, some applications only require the retention of semantic information, suggesting potential improvements in communication efficiency. This paper proposes an image generation-based transmission method for highly-efficient communications exploiting composition and descriptive information. The proposed method extracts specific information from an image to decrease the amount of data transmission, and reconstructs the image using an image-generative model by a receiver. In addition, image compression and reconstruction in the proposed method are demonstrated through an experiment. The experimental results indicate a need for a method to evaluate the output and a method for image reconstruction based on this evaluation.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{CCNC_Ono,

title = {Experimental Evaluation Toward Mobility-Driven Model Integration Between Edges},

author = {Shota Ono and Taku Yamazaki and Takumi Miyoshi and Akihito Taya and Yuuki Nishiyama and Kaoru Sezaki},

url = {https://ieeexplore.ieee.org/document/10454772},

doi = {10.1109/CCNC51664.2024.10454772},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

booktitle = {2024 IEEE 21st Consumer Communications & Networking Conference},

publisher = {IEEE},

address = {Las Vegas, NV, USA},

abstract = {We propose a user mobility-driven federated learning method, which integrates learning models from different regions, leveraging user mobility. This method aims to improve performance of learning models in specific regions by merging them with models from other areas. In regions with less user mobility, our method creates unique regional models, while in areas with high mobility, it integrates models for enhanced performance. Evaluation results indicate that accuracy improved with additional training, although it temporarily decreased after model integration.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10.1145/3613904.3642095,

title = {ReHEarSSE: Recognizing Hidden-in-the-Ear Silently Spelled Expressions},

author = {Xuefu Dong and Yifei Chen and Yuuki Nishiyama and Kaoru Sezaki and Yuntao Wang and Ken Christofferson and Alex Mariakakis},

url = {https://doi.org/10.1145/3613904.3642095},

doi = {10.1145/3613904.3642095},

isbn = {9798400703300},

year  = {2024},

date = {2024-01-01},

booktitle = {Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems},

publisher = {Association for Computing Machinery},

address = {Honolulu, HI, USA},

series = {CHI '24},

abstract = {Silent speech interaction (SSI) allows users to discreetly input text without using their hands. Existing wearable SSI systems typically require custom devices and are limited to a small lexicon, limiting their utility to a small set of command words. This work proposes ReHEarSSE, an earbud-based ultrasonic SSI system capable of generalizing to words that do not appear in its training dataset, providing support for nearly an entire dictionary’s worth of words. As a user silently spells words, ReHEarSSE uses autoregressive features to identify subtle changes in ear canal shape. ReHEarSSE infers words using a deep learning model trained to optimize connectionist temporal classification (CTC) loss with an intermediate embedding that accounts for different letters and transitions between them. We find that ReHEarSSE recognizes 100 unseen words with an accuracy of 89.3%.},

keywords = {Acoustic sensing, autoregressive model, earable computing, silent speech interface, text entry},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Globecom2023_Taya,

title = {Convergence Visualizer of Decentralized Federated Distillation with Reduced Communication Costs},

author = {Akihito Taya and Yuuki Nishiyama and Kaoru Sezaki},

year  = {2023},

date = {2023-12-04},

urldate = {2023-12-04},

booktitle = {Proceedings of IEEE Global Communications (GLOBECOM) 2023},

publisher = {IEEE},

address = {Kuala Lumpur, Malaysia},

series = {GLOBECOM 2023},

abstract = {Federated learning (FL) achieves collaborative learning without the need for data sharing, thus preventing privacy leakage. To extend FL into a fully decentralized algorithm, researchers have applied distributed optimization algorithms to FL by considering machine learning (ML) tasks as parameter optimization problems. Conversely, the consensus-based multi-hop federated distillation (CMFD) proposed in the authors' previous work makes neural network (NN) models get close with others in a function space rather than in a parameter space. Hence, this study solves two unresolved challenges of CMFD: (1) communication cost reduction and (2) visualization of model convergence. Based on a proposed dynamic communication cost reduction method (DCCR), the amount of data transferred in a network is reduced; however, with a slight degradation in the prediction accuracy. In addition, a technique for visualizing the distance between the NN models in a function space is also proposed. The technique applies a dimensionality reduction technique by approximating infinite-dimensional functions as numerical vectors to visualize the trajectory of how the models change by the distributed learning algorithm.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10.1145/3600100.3626263,

title = {A Trajectory Estimation Method from Spatially Sparse and Noisy Beacon Data Based on Spring Dynamics},

author = {Junya Maruyama and Yudai Honma and Yuuki Nishiyama and Yoshihiro Kawahara},

url = {https://doi.org/10.1145/3600100.3626263 

https://buildsys.acm.org/2023/},

doi = {10.1145/3600100.3626263},

isbn = {9798400702303},

year  = {2023},

date = {2023-11-15},

urldate = {2023-11-15},

booktitle = {Proceedings of the 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation},

pages = {286–287},

publisher = {Association for Computing Machinery},

address = {Istanbul, Turkey},

series = {BuildSys '23},

abstract = {Analysis of trajectory data within buildings offers insights for optimizing environmental design and habitability. However, data from indoor location sensors tend to be sparse and noisy. This makes it difficult for conventional route estimation models to be applied effectively. Our study seeks to derive detailed, temporally, and spatially rich trajectory data from this compromised sensor information. We achieve this by interpreting trajectories as continuous stay points. To facilitate this, we introduce a building corridor network that conceptualizes buildings as a series of points. Routes are inferred using a sequence estimation model applied to this network. This approach employs spring dynamics, which balance the resistance to staying with the attraction to specific beacons, via mathematical optimization. Notably, our model can deduce a trajectory of 131 points from only 15 beacons with, an accuracy rate of 87. Our method presents a promising avenue for capturing extensive route data.},

keywords = {Architectural Space, Building corridor Network, Human trajectory},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{UbiComp2023_Nishiyama,

title = {Smartwatch-Based Sensing Framework for Continuous Data Collection: Design and Implementation},

author = {Yuuki Nishiyama and Kaoru Sezaki},

year  = {2023},

date = {2023-10-08},

urldate = {2023-10-08},

booktitle = {Adjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2023 ACM International Symposium on Wearable Computers},

publisher = {Association for Computing Machinery},

address = {Cancun, Mexico},

series = {UbiComp-ISWC '23},

abstract = {Smartwatches are an increasingly popular technology that employs advanced sensors (e.g., location, motion, and microphone) comparable to those used by smartphones. Passive mobile sensing, a method of acquiring human behavior data from mobile and wearable devices inconspicuously, is widely used in research fields related to behavior analysis. In combination with machine learning, passive mobile sensing can be used to interpret various human and environmental contexts without requiring user intervention. Because smartwatches are always worn on the wrist, they have the potential to collect data that cannot be collected by smartphones. However, the effective use of smartwatches as platforms for passive mobile sensing poses challenges in terms of battery life, storage, and communication. To address these challenges, we designed and implemented a tailored framework for off-the-shelf smartwatches. We evaluated power consumption under eight different sensing conditions using three smartwatches. The results demonstrate that the framework can collect sensor data with a battery life of 16-31 h depending on the settings. Finally, we considered potential future solutions for optimizing power consumption in passive sensing with off-the-shelf smartwatches.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}