- Context-Aware Activity Recognition Systems
- IoT and Edge/Fog Computing
- Technology Use by Older Adults
- IoT-based Smart Home Systems
- Speech and Audio Processing
- Human Mobility and Location-Based Analysis
- Green IT and Sustainability
- Anomaly Detection Techniques and Applications
- Ergonomics and Musculoskeletal Disorders
- Non-Invasive Vital Sign Monitoring
- Health disparities and outcomes
- COVID-19 and Mental Health
- Digital Mental Health Interventions
- Smart Grid Energy Management
- Evacuation and Crowd Dynamics
- Disaster Management and Resilience
- Music and Audio Processing
- Esophageal Cancer Research and Treatment
- Gastric Cancer Management and Outcomes
- Advanced Manufacturing and Logistics Optimization
- Trauma and Emergency Care Studies
- Music Technology and Sound Studies
- Esophageal and GI Pathology
- Mental Health Research Topics
- Hand Gesture Recognition Systems
Osaka University
2019-2024
Chiba Institute of Technology
2024
Nara Institute of Science and Technology
2011-2019
Hiroshima University Hospital
2017-2018
Institute of Electrical and Electronics Engineers
2018
University of Gävle
2018
Kyoto University
2008-2011
Institut national de recherche en informatique et en automatique
2011
Laboratoire Lorrain de Recherche en Informatique et ses Applications
2011
Metaverse technologies are transforming how distant individuals interact in immersive virtual environments. These technologies, combination with the latest developments 3D sensing, will create a hybrid metaverse blending and physical spaces. However, high-resolution sensing poses privacy risks from unrestricted spatial data sharing. It may inadvertently expose human visual appearance private objects spaces users' environments to shared metaverse. To mitigate these challenges, this article...
Aiming to realize the application which supports users enjoy walking with an appropriate physical load, we propose a method estimate load and its variation during only available functions of smartphone. Since has linear relationship heart rate, our purpose is rate To this end, build prediction models predict from data including acceleration speed by machine learning. In order track unexpected change focus attention on oxygen uptake similar property devise novel technique GPS so that it used...
Endoscopic submucosal dissection (ESD) is a widely accepted procedure for superficial esophageal squamous cell carcinoma (SESCC) limited to the epithelium or lamina propria mucosae (EP/LPM). We aimed compare efficacy of endoscopic ultrasonography (EUS) and magnifying endoscopy with narrow band imaging (ME-NBI) predicting tumor invasion depth in patients SESCC. Specifically, we evaluated ability these examinations distinguish EP/LPM from SESCC invading muscularis submucosa (MM/SM1) more...
Previous research finds that natural environments and exercise enhance creativity. In this within-subjects design study, we examined the influence of outdoor combined a environment with on creativity compared to an indoor control condition by analyzing cognitive activities related The participants performed Alternative Uses Test (AUT), in which ordinary objects are presented (e.g., brick), prompt as many ideas for alternative uses possible, transformed into score, after running running....
Musicians often have the following problem: they a music score that requires 2 or more players, but no one with whom to practice. So far, score-playing robots exist, lack adaptive abilities synchronize fellow players' tempo variations. In other words, if human speeds up their play, robot should also increase its speed. However, computer accompaniment systems allow exactly this kind of ability. We present first step towards giving these robot. introduce new paradigm beat tracking using types...
A devastating earthquake hit Japan on March 11, 2011. history of frequent and powerful earthquakes in the region, especially great Hanshin-Awaji 1995, led country to develop disaster relief methods preparation for such natural disasters. Nevertheless, following tsunami destroyed much coastland, caused panic, due Fukushima-daiichi nuclear power plant accidents. During this situation, some crisis-management systems performed as expected. However, poor performance others required system...
Information and communication technologies (ICTs) has enabled growth in developed countries urban cities through improvements systems, devices applications. In rural areas, especially developing countries, ICT penetration is not as high, often due to lack of available infrastructure funding. With the increasing availability Internet-of-Things (IoT) devices, low-cost large-scale deployments have become possible even areas. We design, develop implement, Near Cloud, a cloud-less platform that...
Sitting on a chair with incorrect posture, or the same posture for long time, causes burden waist and shoulders of workers, leading to mental stress poor work efficiency. It is therefore important measure workers' sitting advice how improve notify them either adjust their take break from sitting. To achieve this, it necessary continuously worker without affecting worker's ability complete tasks. We developed sensing called "Census" satisfying these requirements. This has function that able...
This paper presents a novel synchronizing method for human-robot ensemble using coupled oscillators. We define an as synchronized performance produced through interactions between independent players. To attain better performance, the robot should predict human's behavior to reduce difference and robot's onset timings. Existing studies in such synchronization only adapts intervals, thus, need considerable time synchronize. use oscillator model behavior. Experimental results show that our...
The automatic sensing and understanding of the contexts are important to make appropriate decision in Smart Systems. Especially, tracing human activities behaviors useful elements that enable system support or imitate them. There many studies identify activity behavior with using various sensors, but them could only rough activities, some badly infringe on privacy. In this study, we propose a micro-behavior Kinect sensor. To reduce invasion privacy Camera device like sensor, our identifies...
Social isolation is an objective absence or paucity of contacts and interactions between a person social network. Loneliness subjective feeling being alone, separated, apart from others. These two highly correlated mental health concerns significantly increase the elderly's risk premature death all causes, that may rival those smoking, obesity, physical inactivity. In this work, we propose integrated design for technology usage to tackle aforementioned healthcare involving elderly community....
Advances in image analysis and deep learning technologies have expanded the use of floor plans, traditionally used for sales rentals, to include 3D reconstruction automated design. However, a typical plan does not provide detailed information, such as type number outlets locations affecting placement furniture appliances. Electrical providing details on electrical installations, are intricate due overlapping symbols lines remain unutilized house manufacturers independently manage them. This...
Loneliness has long affected the elderly community. This issue is significantly worsened by social isolation resulting from COVID-19 pandemic. To address this pressing issue, we employed a sensor-based methodology to predict loneliness and potentially inform interventions. We deployed sensors in residences of 22 participants US Japan, gathering daily activities data through sensor features. Given extensive feature set, identify most effective ensure unobtrusiveness while upholding privacy....
This paper presents a beat-counting robot that can count musical beats aloud, i.e., speak ldquoone, two, three, four, one, ...rdquo along music, while listening to music by using its own ears. Music-understanding robots interact with humans should be able not only recognize internally, but also express their internal states. To develop our robot, we have tackled three issues: (1) recognition of hierarchical beat structures, (2) expression these structures counting beats, and (3) suppression...
In this paper, we design and develop a sensor-embedded office chair that can measure the posture of worker continuously without disturbing their job. our system, eight accelerometers, are attached at back side fabric surface chair, used for recognizing posture. We propose three sitting recognition algorithms by considering initial position difference physique. Through experiment with 28 participants, confirm proposed recognize 75.4% (algorithm 1), 83.7% 2), 85.6% 3) respectively.
In an era where billions of IoT devices have been deployed, edge/fog computing paradigms are attracting attention for their ability to reduce processing delays and communication overhead. order improve Quality Experience (QoE) regional services that create timely geo-spatial information in response users' queries, it is important efficiently allocate sufficient resources based on the computational demand each service. However since assumed be heterogeneous (in terms power, network...
The triage tag is used in Mass Casualty Incident (MCI) to check the priority of patients treatments and conditions. However, it difficult grasp a change patient's information since paper tag. In this paper, we propose system using electronic (eTriage) that facilitates emergency medical technicians locations conditions through visualization. This provides following three views information: (1) Inter-site view which shows on map an overview latest status multiple first-aid stations including...
This paper presents an improved speaker localization method based on the generalized cross-correlation (GCC) weighted by phase transform (PHAT) for binaural robot audition. The problem with conventional direction-of-arrival (DOA) estimation GCC-PHAT is a multipath interference whereby sound wave travels to microphones via front-head path and back-head in describes new time delay factor compensate assumption of spherical head. In addition, restriction difference arrival (TDOA) sampling...
Developing approaches for early detection of possible risk clusters mental health problems among undergraduate university students is warranted to reduce the duration untreated illness (DUI). However, little known about indicators need care by others. Herein, we aimed clarify specific value study engagement and lifestyle habit variables in predicting potentially high-risk cluster students.This cross-sectional used a web-based demographic questionnaire [the Utrecht Work Engagement Scale...