Mobile Computing Lab.

Research Topics

List of research topics from Yamaguchi Laboratory.

All Sub-theme IDs

All Theme IDs

All Keywords

Urban Air Mobility UAM Neural Surrogation Simulation Disaster Communication LoRa LPWA Distributed Scheduling Hazard Map Priority-Aware Transmission Semantic Communication Disaster Response Vision-Language Model Edge Inference DR-IoT Image Captioning Landslide Prediction Physics-Integrated Learning Tank Model Feature Augmentation Urban Disaster Resilience Satellite Formation Flying Distributed Simulation ROS2 D2D Satellite Communication Orbital Mechanics Phased Array ISAC Beyond 5G Ray Tracing Vehicle Recognition Range-Doppler Map Deep Learning Autonomous Driving Environmental Condition Recognition CNN Surrogate Model Decision Tree Machine Unlearning Privacy Mobility WiFi CSI Drone Electric Scooter (E-Scooter) Micromobility Traffic Safety Edge Computing Real-Time Hazard Prediction Route Recommendation Safety Assistance Systems HEMS branch circuit home activity recognition LLM Monitoring Autonomous Navigation Multimodal Fusion FPGA Acceleration LLM (Large Language Model) Socially Compliant Path Planning Dynamic Environment Adaptation Digital Twin Crowd Simulation Railway Station LIDAR Dpeth-camera Pedestrian Tracking Kalman-filter LiDAR Victim Detection Hybrid Metaverse Video Quality Optimization Neural Networks GPS OD estimation Digital twin scaniverse Mobility Data Reconstruction Spatial-Temporal Data Processing Transformer Models Graph Neural Networks (GNNs) Map-Matching Algorithms Visitor Mobility Patterns Wakayama Castle Park Reconstruction of Mobility Trajectories Statistical Analysis Counterfactual Analysis Accessibility Constraints Environmental Conditions Decision-Making Processes Design of Mobility Services 3D point cloud object detection wearable device traffic management multi-agent simulation gradient descent policy optimization Core Body Temperature Estimation Feature Selection Thermography Face Recognition Face Segmentation Driver Assistance Systems Multi-autonomous Vehicle Studies Models Techniques and Simulations Automated Vehicle Operation Motion Planning Navigation Vehicle Routing Problem Optimization Integer Linear Programming Machine Learning Supervised Learning Smart City Large Language Models Agent-Based Modeling Smart Home Simulation Cyber-Physical Systems Point Cloud Visual Language Model AIoT CLIP WiFi Smart Environments Quantum Computing Combinatorial Optimization QUBO QAOA Multi-Person Time-Window Constrained Traveling Salesman Problem TW-TSP Quantum Approximate Algorithm Unconstrained Quadratic Optimization Problem Graph Neural Network GCN Bluetooth Channel Sounding BLE Wireless sensing Unattended Child Detection Unmanned Aerial Vehicle Earthquake Assessments Backscatter Wi-Fi WIS2.0 Pub/Sub Reinforcement Learning Fall Detection Privacy Preservation human identification small-size depth sensor(LiDAR) AR Person Re-ID Deep Metric Learning Wi-Fi CSI Autoencoder Activity Recognition Environment-Independent Generative Adversarial Networks Physics-Informed Models FMCW Radar Range-Doppler Synthetic Data Multi-target Occlusion Step counting Localization User identification Energy harvesting energy-free sensing Wireless Sensing Ultra-low-power Privacy-preserving Re-ID Multi-LiDAR Tracking Onboard Camera Video Mobility Data Vehicle Detection Deep Neural Network(DNN) Face-touch Smartwatch Synthetic mobility OD traffic optimization Traffic simulation sitting posture point cloud deep learning Wheelchair Basketball Sports Sensing Flood water level detection Machine learning Generative adversarial networks Data balancing premature infants/thermal images/parts detection/temperature extraction/deep learning In-Vehicle Network Network Simulation Network Calculus Wi-Fi Sensing Transfer learning Thermal camera Wearable sensor Thermal sensation Time-series processing Image processing Imbalanced Dataset Time-series data LTE-LAA cell-selection In-vehicle Camera Driver Assist System Environment-Agnostic In-home Human Activity Recognition Using Wi-Fi Signals Recovery Estimation Smart Toothbrush Cyber-physical Space User Identification Heart rate Reliability Wrist-worn device Running Target Identification Wi-Fi Imaging Smartphone Offset correction distributed deep learning ultra-low power AI

A Simulation-based Framework for Dynamic Light Pollution Prediction in Urban Air Mobility

Urban air mobility (UAM) is a vision of city transport in which small electric aircraft that take off and land vertically, often called "flying c...

Urban Air Mobility UAM Neural Surrogation +1
Environment-Aware Distributed Scheduling for Emergency LoRa Networks

Environment-Aware Distributed Scheduling for Emergency LoRa Networks

After a large-scale disaster, rapid situational awareness depends on a trustworthy communication infrastructure even when parts of the system are down...

Disaster Communication LoRa LPWA +3
A Lightweight Vision-Language Model for Disaster Image Summarization

A Lightweight Vision-Language Model for Disaster Image Summarization

Immediately after a large-scale disaster, response agencies must obtain accurate situational awareness quickly. Images of on-site conditions are a val...

Semantic Communication Disaster Response Vision-Language Model +3

Physics-Integrated Deep Learning for Urban Landslide Prediction

Climate change has increased the frequency and intensity of extreme rainfall, causing landslides even in regions without historical disaster records. ...

Landslide Prediction Physics-Integrated Learning Tank Model +2
A Simulation Framework for Precision Formation Flying of Massive Satellite Swarms

A Simulation Framework for Precision Formation Flying of Massive Satellite Swarms

Future direct-to-device (D2D) satellite communications may require thousands of ultra-small satellites flying in precise coordination to form a distri...

Satellite Formation Flying Distributed Simulation ROS2 +3

Ray-Tracing-Driven Pattern-Based Vehicle Recognition in ISAC Radar

Integrated Sensing and Communication (ISAC) is a core technology for Beyond 5G/6G, where communication waveforms are reused for sensing. Under realist...

ISAC Beyond 5G Ray Tracing +3

A Questionnaire-Only Counterfactual Machine Learning Approach to Assess the Spatial Impact of Green Mobility Vehicles in Urban Parks

In a large historical park, slopes and distances keep some visitors from reaching places they would like to see. Small electric assistive vehicles rel...

Bayesian Optimization Approach for Crowd Flow Modeling on Railway Station Platforms

Bayesian Optimization Approach for Crowd Flow Modeling on Railway Station Platforms

A railway station platform concentrates a large number of people into a narrow space in bursts timed by arriving trains, which makes faithful reproduc...

Challenges for Federated Crowd Management in Smart Cities

都市で大人数の群衆をうまくさばけるかどうかは、安全の確保にも来場者の体験にも直結します。スマートシティの取り組みではデータを意思決定に活かすことが掲げられていますが、群衆を測っただけでは足りず、そのデータをどう解析してどう使うかまで踏み込む必要があります。この論文は、群衆マネジメントに取り組んできた...

Environment-Aware Modeling and Analysis for LoRa Emergency Network Scheduling

In the hours after a disaster the cellular base stations are often down, and what remains useful is ad-hoc radio between devices themselves. LoRa suit...

Neural Surrogate Model for Autonomous Driving Communications Based on Strategic Sampling

Autonomous driving and vehicle-to-everything applications need to know the communication quality they can expect at a given place and moment, and they...

Rapid Policy Impact Estimation for Pedestrian Flow Using Neural Network Surrogates

Crowd management measures such as making a corridor one-way, opening an extra entrance or shifting the timing of announcements are worth testing befor...

Short-Term Crowd Prediction through Continuous Observation

Predicting how a crowd will move over the next few tens of seconds is what turns crowd sensing into crowd management, because staff can only act on in...

Socially-Aware Robot Navigation Using Large Language Models: System and Evaluation

When a robot moves through a crowded space, avoiding collisions is not sufficient. Whether it crosses in front of someone or waits, how it joins a que...

Transformer-Based Resource and Stage-Aware Scheduling for Model-Parallel LLM Inference

When a large language model does not fit on a single GPU, it has to be split across nodes, and a scheduler decides which work goes where. Existing sch...

When Sensors Talk: LLM-Guided Object-Centric Collaboration for Distributed 3D Scene Understanding

When Sensors Talk: LLM-Guided Object-Centric Collaboration for Distributed 3D Scene Understanding

A single LiDAR or depth sensor cannot see what is hidden behind an object. Placing several sensors so that they cover each other's blind spots so...

Interpretable Environmental Condition Recognition for Autonomous Driving Using Surrogate Decision Trees

Interpretable Environmental Condition Recognition for Autonomous Driving Using Surrogate Decision Trees

In autonomous driving, sensors play a critical role in perceiving the surrounding environment and ensuring safe driving. However, their performance ca...

Autonomous Driving Environmental Condition Recognition CNN +2

Efficient Machine Unlearning for Mobility Logs with Spatio-Temporal and Natural-Language Data

Modern mobility platforms store vast streams of GPS trajectories, temporal metadata, free-form textual notes, and other unstructured data. Privacy sta...

Machine Unlearning Privacy Mobility
Indoor Drone Propeller Speed Estimation Using Wi-Fi CSI

Indoor Drone Propeller Speed Estimation Using Wi-Fi CSI

With the evolution of drone technology, its range of applications has expanded to include logistics, surveillance, inspection, agriculture, and other ...

WiFi CSI Drone
Real-time Path Prediction at the Edge for E-scooter

Real-time Path Prediction at the Edge for E-scooter

In recent years, electric scooters (E-Scooters) have rapidly gained popularity worldwide as a key mode of micromobility. Due to their convenience, low...

Electric Scooter (E-Scooter) Micromobility Traffic Safety Edge Computing +3
Home Activity Recognition Using Low-Grain Branch Circuit Power Consumption

Home Activity Recognition Using Low-Grain Branch Circuit Power Consumption

In recent years, HEMS (Home Energy Management System), which monitors the amount of electricity and gas used in the home and "automatically contr...

HEMS branch circuit home activity recognition
Student Engagement Measurement Through Micro-Action Detection with Multi-Modal Foundation Model

Student Engagement Measurement Through Micro-Action Detection with Multi-Modal Foundation Model

Measuring whether students are engaged in collaborative learning is usually attempted through facial expression or speech analysis, but in a group tha...

On the Impact of Terrain Types in Deep Neural Network-Based Surrogates of Radio Maps

A radio map records how much signal strength is lost at each point of a region, and it underpins decisions about base station placement and link adapt...

Evaluating Attribute Inference Risks in Urban Care Taxi Arrival Time Prediction Models Using Geospatial Data

Care services for older adults are becoming part of urban infrastructure, and machine learning models trained on location data are being considered fo...

SelfLoc: Robust Self-Supervised Indoor Localization with IEEE 802.11az Wi-Fi for Smart Environments

屋内測位を実際の建物に導入しようとすると、精度そのものよりも、事前にどれだけ正解付きのデータを集めなければならないかが障壁になります。場所ごとに人が立って電波を測って回る作業が必要になるためで、環境が変わるたびにこれをやり直すのは現実的ではありません。本研究の SelfLoc は、IEEE 802....

Collaborative LLM Agents for Daily Activity Summarization on Edge Devices

Collaborative LLM Agents for Daily Activity Summarization on Edge Devices

In recent years, with the increase in the number of elderly people living alone, the demand for monitoring systems has increased. There are two main r...

LLM Monitoring
LLM-Driven Adaptive Autonomous Robot Navigation via Multimodal Fusion for Dynamic Environments

LLM-Driven Adaptive Autonomous Robot Navigation via Multimodal Fusion for Dynamic Environments

This research addresses the challenges of autonomous robot navigation in dynamic, high-density environments (e.g., train stations and shopping malls) ...

Autonomous Navigation Multimodal Fusion FPGA Acceleration +3
A Digital Twin Approach for Crowd Flow Modeling on Railway Station Platforms

A Digital Twin Approach for Crowd Flow Modeling on Railway Station Platforms

Effective crowd tracking at railway station platforms is essential for ensuring passenger safety and optimizing pedestrian flow. Traditional tracking ...

Digital Twin Crowd Simulation Railway Station
Design and Implementation of Point Cloud-Based Space Integration with Quality-Aware Optimization

Design and Implementation of Point Cloud-Based Space Integration with Quality-Aware Optimization

A hybrid metaverse that captures real spaces as point clouds and merges them with the spaces of distant participants runs into a bandwidth problem. De...

ICNN Based Distributed Optimization of 3D Point Cloud Quality for Real-Time Physical Space Sharing

ICNN Based Distributed Optimization of 3D Point Cloud Quality for Real-Time Physical Space Sharing

In a hybrid metaverse that merges physical and virtual spaces, managing the quality of the shared 3D objects is where the implementation becomes hard....

Self-Supervised WiFi-Based Identity Recognition in Multi-User Smart Environments

スマート環境で自律的に動く AI エージェントが増えるにつれ、そこにいるのが誰なのかを正確に、かつプライバシーを保った形で知る必要が出てきました。カメラを使えば空間的な情報も文脈も豊富に取れますが、設置コストが高いうえプライバシー上の抵抗が大きく、照明などの環境変化にも影響されます。本研究の Ide...

Reference-Free 3D WiFi AP Localization by Outdoor-to-Indoor Bridging

Knowing where WiFi access points are physically installed matters both for managing wireless infrastructure and for location-based services, yet accur...

Robust Pedestrian Tracking Against Occlusions in Public Spaces Using 3D Point Clouds from Depth/LiDAR Sensors

Robust Pedestrian Tracking Against Occlusions in Public Spaces Using 3D Point Clouds from Depth/LiDAR Sensors

We propose an approach to pedestrian tracking in a public passageway with pedestrians, such as those carrying luggage and baby strollers, and family g...

LIDAR Dpeth-camera Pedestrian Tracking +1

Behavioral-Aware Early Destination Prediction Using LiDAR Point Clouds and Movement Trajectories

Tracking people through a large facility inevitably involves gaps where no sensor sees them. Linking a person who leaves one sensor's coverage to...

Victim Detection Based on Shape Features from 3D Point Clouds

Victim Detection Based on Shape Features from 3D Point Clouds

Japan experiences frequent natural disasters, including large-scale earthquakes. As seen in the case of the Great Hanshin-Awaji Earthquake, delayed vi...

Drone LiDAR Victim Detection

MultiSenseX: A Sustainable Solution for Multi-Human Activity Recognition and Localization in Smart Environments

Wi-Fi の電波を使った人のセンシングは、カメラやウェアラブル端末を使わずに行動を捉えられるため、スマートホームや見守り、患者モニタリングといった場面で注目されています。ただし、これまでの研究の多くは部屋に一人しかいない状況を前提にしており、実際の住宅や施設のように複数人がいる環境ではそのまま使え...

Distributed Optimization of Shared Object Quality in Hybrid Metaverse for Real-World Integration

Distributed Optimization of Shared Object Quality in Hybrid Metaverse for Real-World Integration

Since the outbreak of COVID-19, the metaverse has gained attention as a tool for remote interaction. With the advancement of recent 3D sensing technol...

Hybrid Metaverse Video Quality Optimization Neural Networks

A Precise and Scalable Indoor Positioning System Using Cross-Modal Knowledge Distillation

屋内では GPS の電波が届かないか反射で乱れるため、位置を知るには別の手段が要ります。広く使われているのは Wi-Fi の受信強度（RSSI）を使う方法ですが、環境ノイズやマルチパスフェージングの影響を受けやすく、精度が出しにくいという弱点があります。一方、電波の往復時間を測る RTT を使う方法...

Synthesis of Pedestrian Movement Patterns: Combining Sparse Location Data with Multi-Spot Density Measurements

Synthesis of Pedestrian Movement Patterns: Combining Sparse Location Data with Multi-Spot Density Measurements

In recent years, the utilization of pedestrian flow data has been gaining attention in regional revitalization. Understanding current pedestrian flow ...

GPS OD estimation
Adaptive Indoor Navigation System Using Human Flow Digital Twin

Adaptive Indoor Navigation System Using Human Flow Digital Twin

Digital twin technology is attracting attention as a technology that reproduces objects and systems in physical space in virtual space and coordinates...

Digital twin LiDAR scaniverse

Understanding Privacy Awareness in Immersive Spatial Sharing System

Advances in point cloud capture and in computing power have brought immersive spatial sharing systems within reach, in which distant places are merged...

LocaLingua: Leveraging Language Models for Cross-Building WiFi Mapping

Wi-Fi を使った屋内測位で実運用の妨げになるのは、ある建物で作ったモデルが別の建物では使えないことです。アクセスポイントの配置も台数も建物ごとに違うため、入力の形からして揃わず、新しい建物に持ち込むたびに測り直しと学習し直しが必要になります。本研究の LocaLingua は、この問題を言語モデ...

Privacy-Preserved Taxi Demand Prediction System Utilizing Distributed Data

タクシーの需要をあらかじめ読めれば車両の配置を最適化できますが、そのためには乗客の乗降データを使うことになるため、プライバシーと安全性の問題が避けられません。複数の事業者のデータを一箇所に集めればモデルの精度は上がるものの、事業者間でデータそのものをやり取りするわけにはいかないという事情もあります。...

SimDeep: An Efficient Federated Learning Indoor Localization System with Similarity Aggregation Strategy

屋内測位はナビゲーションやセキュリティ、文脈に応じたサービスの基盤になりますが、研究が進んだわりに実際の環境への導入は限られています。理由の一つが、利用者ごとに集まるデータの分布が揃わないこと、いわゆる非 IID の問題で、もう一つが端末の機種による測定値のばらつきです。これらはいずれも、データを持...

Map-Aware Super-Resolution GPS Trajectory Reconstruction via Machine Learning

Map-Aware Super-Resolution GPS Trajectory Reconstruction via Machine Learning

This research aims to realize a novel system for reconstructing high-resolution GPS trajectory data from truncated or low-resolution inputs, addressin...

Mobility Data Reconstruction Spatial-Temporal Data Processing Transformer Models +2
Understanding Visitor Mobility Patterns in Public Spaces: A Case Study of Wakayama Castle Park

Understanding Visitor Mobility Patterns in Public Spaces: A Case Study of Wakayama Castle Park

Understanding visitor mobility in public spaces is essential for optimizing transportation services and improving accessibility. This study investigat...

Visitor Mobility Patterns Wakayama Castle Park Reconstruction of Mobility Trajectories +6

Metasurface-enabled multifunctional single-frequency sensors without external power

デジタルツインや自動運転、スマートシティのように、現実の空間の状態を細かく取り込んで使うシステムでは、センサの数が際限なく増えていきます。そうなると電池の交換や充電が全体の維持コストを決めてしまうため、外部電源を必要としないセンサが要ります。ただ、電源を持たないセンサは電波の反射特性で情報を返すこと...

Demonstrating OmniCells: A Resilient Indoor Localization System to Devices' Diversity

携帯電話の基地局から届く電波を使う屋内測位は、Wi-Fi のように屋内へのアクセスポイントの設置を前提としないため広い範囲で使えますが、端末の機種が変わると測定される電波の値そのものが変わってしまうという問題を抱えています。学習に使った端末と実際に測位する端末が違うと、それだけで精度が落ちるというこ...

Light-weight Object Detection of 3-D Point Cloud Data by Micro-size LiDAR

Light-weight Object Detection of 3-D Point Cloud Data by Micro-size LiDAR

3-D recognition technology has been attracting attention and developing rapidly in the fields of obstacle detection in automated driving and robotics....

3D point cloud object detection LiDAR +1
Policy Optimization for Pedestrian Traffic Management by Surrogation of Simulation Models

Policy Optimization for Pedestrian Traffic Management by Surrogation of Simulation Models

Sports events, concerts, and live performances attract large crowds, and the congestion during the return home after such events increases the risk of...

traffic management multi-agent simulation gradient descent +1

Joint user association, service caching, and task offloading in multi-tier communication/multi-tier edge computing heterogeneous networks

IoT 機器が身の回りに増え、そこで動かしたいアプリケーションの計算量も上がってきたことで、遅延が小さくスループットの高い基盤をどう作るかが問題になっています。端末側の計算能力には限りがあるので、重い処理はネットワークの近くにあるサーバに肩代わりさせることになりますが、この肩代わり（タスクオフロード...

Investigation of Core Body Temperature Estimation Based on Facial Surface Temperature Using Thermography

Investigation of Core Body Temperature Estimation Based on Facial Surface Temperature Using Thermography

Heat stroke occurs due to an increase in core body temperature, making its monitoring crucial for prevention. Core body temperature is typically measu...

Core Body Temperature Estimation Feature Selection Thermography +3
Lightweight Merging Point Prediction on Highway On-Ramps Using Regression Techniques

Lightweight Merging Point Prediction on Highway On-Ramps Using Regression Techniques

This study introduces a lightweight machine learning framework for forecasting the merging points of vehicles on on-ramps. Our model, in contrast to p...

Driver Assistance Systems Multi-autonomous Vehicle Studies Models +4
Optimizing Nursing Care Taxi Dispatch Leveraging Integer Linear Programming Solvers and Machine Learning

Optimizing Nursing Care Taxi Dispatch Leveraging Integer Linear Programming Solvers and Machine Learning

The aging population is creating crucial demand for the transportation services at the facilities for older people. Vehicles should be assigned proper...

Vehicle Routing Problem Optimization Integer Linear Programming +3

Architecture, Performance, and Usability of Mobile Cellular Network Monitoring Applications for Data-Driven Analysis

Operating a cellular network requires observing how it actually behaves, since neither optimization nor troubleshooting is possible without that. The ...

LLM as Personable Decision-Making Model for Smart Home Simulation

LLM as Personable Decision-Making Model for Smart Home Simulation

This research proposes a method for simulating residents' decision-making and daily activities in a smart home environment using a Large Language...

Large Language Models Agent-Based Modeling Smart Home Simulation +2
Indoor Object Recognition with WiFi RSSI-Integrated Visual-Language Models

Indoor Object Recognition with WiFi RSSI-Integrated Visual-Language Models

This study proposes a novel method for automatic object recognition and classification in indoor environments using visual-language models (VLMs). Tra...

Point Cloud Visual Language Model AIoT +3
Quantum Approximation Method and Neural-Integrated Mathematical Optimization Algorithm for Elderly Care Taxi Dispatch Problem

Quantum Approximation Method and Neural-Integrated Mathematical Optimization Algorithm for Elderly Care Taxi Dispatch Problem

In Japan, the aging population is increasing, leading to a growing number of elderly individuals utilizing nursing care facilities such as day service...

Quantum Computing Combinatorial Optimization QUBO +8

Recognition of House Structures from Complicated Electrical Plan Images

間取り図は本来は売買や賃貸のための資料ですが、画像解析と深層学習が進んだことで、3次元復元や設計の自動化にも使われるようになってきました。ただ間取り図には、コンセントがどの種類でいくつあるか、どこに付いているかといった情報が載っていません。これは家具や家電をどこに置けるかを左右するので、実用上は無視...

Cellular Operator Data Meets Counterfactual Machine Learning

To meet growing demand for mobile data, operators have turned to unlicensed bands and spectrum-sharing standards. Incumbents such as WiFi are already ...

Human Presence Detection Using Bluetooth Channel Sounding

Human Presence Detection Using Bluetooth Channel Sounding

Accidents involving children being left behind in vehicles have become a serious social issue both domestically and internationally. To prevent such i...

Bluetooth Channel Sounding BLE Wireless sensing +1
Anomaly Detection of Building Structure from Incomplete Point Cloud Obtained by UAV

Anomaly Detection of Building Structure from Incomplete Point Cloud Obtained by UAV

Japan has suffered tremendous damage from earthquakes and other natural disasters, including the 1995 Great Hanshin-Awaji Earthquake and the 2016 Kuma...

Point Cloud Unmanned Aerial Vehicle Earthquake Assessments

3D Point Cloud-Based Interaction System Bridging Physical Spaces in Virtual Environments

Many VR technologies and interfaces have been proposed for enriching interaction in virtual spaces, yet conventional systems based on 3D imagery have ...

Privacy Awareness of Spatial Sharing System based on 3D Point Cloud: Insights from a User Survey

Advances in metaverse and sensing technologies have raised expectations for systems that connect distant spaces and support immersive interaction. Spa...

Visual Privacy Control for Metaverse and the Beyond

Metaverse technologies are changing how distant individuals interact in immersive virtual environments, and combined with recent developments in 3D se...

Performance Evaluation of Angle of Arrival Estimation by MUSIC Method Using Backscatter Tags

Performance Evaluation of Angle of Arrival Estimation by MUSIC Method Using Backscatter Tags

Indoor positioning of people and objects has potential applications in various fields, such as shopping malls, nursing homes, and offices. Possible us...

Backscatter Wi-Fi
Adaptive Message Scheduling Assisted by Natural Language Processing Models

Adaptive Message Scheduling Assisted by Natural Language Processing Models

This study proposes an adaptive message delivery mechanism for a broker in the WMO Information System 2.0 (WIS2.0), a next-generation world weather Io...

WIS2.0 Pub/Sub Reinforcement Learning
Point Cloud-based Fall Detection for Healthcare Applications

Point Cloud-based Fall Detection for Healthcare Applications

Falls pose a significant health risk for older adults, with the WHO reporting them as the second leading cause of accidental deaths worldwide.In Japan...

Fall Detection Privacy Preservation LiDAR
Person Identification Method Based on 3D Point Cloud Using Small Depth Sensor

Person Identification Method Based on 3D Point Cloud Using Small Depth Sensor

In recent years, there has been an increasing demand for systems that improve safety to limit the rapid spread of COVID-19.In particular, it is import...

human identification 3D point cloud small-size depth sensor(LiDAR)

LocFree: a WiFi RTT-based Device-Free Indoor Localization System

屋内で人がどこにいるかを、その人にスマートフォンやタグを持たせずに知りたい場面は、IoT やセキュリティを含めて数多くあります。こうしたデバイスフリー測位では、どこにでもある Wi-Fi を使うのが現実的な選択肢になりますが、従来は電波の受信強度（RSSI）かチャネル状態情報（CSI）のどちらかに頼...

Video-based Human Tracking Robust to Dynamic Camera Position and Orientation Changes

Video-based Human Tracking Robust to Dynamic Camera Position and Orientation Changes

In recent years, RGB cameras and depth cameras integrated into Augmented Reality (AR) glasses and smart glasses have been utilized for recognizing peo...

AR Person Re-ID Deep Metric Learning

Criteria for Detection of Possible Risk Factors for Mental Health Problems in Undergraduate University Students

大学生のメンタルヘルスの問題は、本人が不調に気づいて相談に来るまでに時間がかかることが多く、この未治療期間をいかに短くするかが課題になっています。ただ、周囲の教職員が「この学生は気にかけたほうがいい」と判断するための具体的な手がかりについては、これまであまり分かっていませんでした。本研究は、学業への...

Environment-Independent Activity Recognition via Wi-Fi CSI Using an Encoder-Decoder Network

Environment-Independent Activity Recognition via Wi-Fi CSI Using an Encoder-Decoder Network

Human Activity Recognition (HAR) using Wi-Fi Channel State Information (CSI) offers a device-free and cost-effective solution for applications in heal...

Wi-Fi CSI Autoencoder Activity Recognition +1

Integrated Sensing Platform for Detecting Social Isolation and Loneliness In the Elderly Community

高齢者の社会的孤立と孤独感は、早期死亡のリスクを大きく押し上げることが知られており、その影響は喫煙や肥満、運動不足に匹敵するとも言われています。この二つはよく似た言葉ですが区別が必要で、社会的孤立が人とのつながりや交流が客観的に乏しい状態を指すのに対し、孤独感はひとりだと感じる主観的な感覚を指します...

Physics-Informed Generative Adversarial Networks for Range-Doppler Map Generation under Inter-Vehicle Occlusion

Physics-Informed Generative Adversarial Networks for Range-Doppler Map Generation under Inter-Vehicle Occlusion

Deep Learning has recently expanded the potential of radar technology. Integrating neural networks with radar enables automatic feature extraction fro...

Generative Adversarial Networks Physics-Informed Models FMCW Radar +4
Energy-Free Sensing and Context Recognition through Photovoltaic Cells

Energy-Free Sensing and Context Recognition through Photovoltaic Cells

Recently, IoT devices that do not require an external power source, especially energy-free sensing and indoor context recognition, have been attractin...

Step counting Localization User identification +2
Activity Recognition Using CSI Backscatter with Commodity Wi-Fi

Activity Recognition Using CSI Backscatter with Commodity Wi-Fi

Activity recognition using Wi-Fi CSI (Channel State Information) has become popular due to its low deployment cost, requiring only Wi-Fi devices for a...

Backscatter Activity Recognition Wireless Sensing +2
Privacy-preserving Pedestrian Tracking using Distributed 3D LiDARs

Privacy-preserving Pedestrian Tracking using Distributed 3D LiDARs

The growing demand for intelligent environments unleashes an extraordinary cycle of privacy-aware applications that makes individuals' life more ...

Privacy-preserving LiDAR Re-ID +1

Metasurface-inspired maintenance-free Internet of things tags characterised in both frequency and time domains

IoT のタグを大量にばらまく使い方をしようとすると、電池交換の手間が現実的な制約になります。電池を必要としないタグであれば保守が要らなくなりますが、今度は個々のタグをどう区別するかという問題が出てきます。従来は周波数の違いで区別していたため、使えるタグの数が割り当てられる周波数の数で頭打ちになって...

Object Recognition from 3D Point Cloud on Resource-Constrained Edge Device

Making three-dimensional spatial sensing portable removes the need for fixed installation and widens where it can be used. Small devices have limited ...

Semantic Communication for Capacity-aware Remote Collaboration

Semantic Communication for Capacity-aware Remote Collaboration

The global spread of the coronavirus drew considerable interest to technologies that let people who are physically apart communicate without friction....

A Vehicle Tracking Method Based on Distance Estimation Using Dashboard Camera

A Vehicle Tracking Method Based on Distance Estimation Using Dashboard Camera

In recent years, mobility data representing the flow of cars and people in an urban environment is expected to be used for many purposes, such as inve...

Onboard Camera Video Mobility Data Vehicle Detection +1

Multi-Task Learning for Concurrent Prediction of Thermal Comfort, Sensation and Preference in Winters

室内の暑い寒いは在室者の健康や作業能率に効いてくるため、これを計算で推定するモデルは数多く提案されてきましたが、省エネルギーの要請が強まったこともあって、近年は機械学習でデータから直接予測する方向が主流になっています。ただ、人が感じる温熱快適性というのは主観的で、しかも一つの尺度では表しきれません。...

Smartwatch-based Face-touch Prediction Using Deep Representational Learning

Smartwatch-based Face-touch Prediction Using Deep Representational Learning

World Health Organization (WHO) reported that viruses, including COVID-19, can be transmitted by touching the face with contaminated hands and advised...

Face-touch Activity Recognition Smartwatch
A Method for Synthesizing Vehicle Mobility in Urban Areas Using Traffic Surveillance Cameras

A Method for Synthesizing Vehicle Mobility in Urban Areas Using Traffic Surveillance Cameras

We present a case study on synthesizing realistic vehicle mobility using link traffic information extracted from surveillance videos. Our trial has be...

Synthetic mobility OD traffic optimization Traffic simulation
3D Point Cloud-Based Sitting Posture Recognition Using Deep Learning

3D Point Cloud-Based Sitting Posture Recognition Using Deep Learning

The average sitting time for Japanese people is about 7 hours a day, which is the longest among the 20 most developed and middle-income countries. It ...

sitting posture object detection point cloud +1
Localization Focusing on Human Poses Using a Single Camera Towards Social Distance Monitoring During Sports

Localization Focusing on Human Poses Using a Single Camera Towards Social Distance Monitoring During Sports

In recent years, data analysis in sports has become increasingly popular, and recognizing in-game actions plays a crucial role in tactical planning. F...

Wheelchair Basketball Activity Recognition Sports Sensing

A method for improving semantic segmentation using thermographic images in infants

新生児の体温管理は予後に直結するため NICU では常に注意が払われていますが、現場で使われている接触式のプローブでは貼り付けた一点の温度しか分からず、全身のどこがどれだけ冷えているのかまでは把握できません。プローブを何本も貼れば分布は取れるものの、新生児の皮膚への負担を考えると現実的な運用にはなり...

Drone-based water level detection in flood disasters

Drone-based water level detection in flood disasters

Japan was hit by typhoon Hagibis, which came with torrential rains submerging almost eight-thousand buildings. For fast alleviation of and recovery fr...

Drone Flood water level detection
Data Balancing for Thermal Comfort Datasets Using GANs

Data Balancing for Thermal Comfort Datasets Using GANs

Data balancing is an essential preprocessing for proper training of thermal comfort estimators. The development of various machine learning methods he...

Machine learning Generative adversarial networks Data balancing
Body Part Detection from Neonatal Thermal Images Using Deep Learning

Body Part Detection from Neonatal Thermal Images Using Deep Learning

Because premature infants have an immature thermoregulatory function, proper temperature control with an incubator is essential. Currently, the probe ...

premature infants/thermal images/parts detection/temperature extraction/deep learning
An Efficient Method for Evaluating Delay Performance Using Worst-Case Estimates Based on Network Calculus

An Efficient Method for Evaluating Delay Performance Using Worst-Case Estimates Based on Network Calculus

In recent years, modern vehicles have been equipped with a growing number of sensors beyond traditional in-car systems such as navigation systems, ETC...

In-Vehicle Network Network Simulation Network Calculus
Backscatter Tag Detection Method Using Sinusoidal Frames towards Wi-Fi Sensing

Backscatter Tag Detection Method Using Sinusoidal Frames towards Wi-Fi Sensing

There are various methods for recognizing human activities and the status of objects, including camera-based approaches and wearable devices. However,...

Wi-Fi Sensing Backscatter

Successful Reboot of High-Performance Sporting Activities by Japanese National Women's Handball Team in Tokyo, 2020 during the COVID-19 Pandemic

COVID-19 の流行はスポーツ活動を世界的に止めましたが、感染リスクを下げながらトップ選手の練習をどう再開するかについて、実際の手順を検証した報告はほとんどありませんでした。本稿は、東京での流行第3波のさなかにハンドボール女子日本代表の合宿を再開したときに直面した課題と、その対処をまとめたもので...

Estimation of Thermal Sensation Based on Machine Learning via Physiological Sensing

Estimation of Thermal Sensation Based on Machine Learning via Physiological Sensing

Comfortable air-conditioned environment enhances labor productivity and learning efficiency. In office buildings, schools, and other indoor environmen...

Machine learning Transfer learning Thermal camera +4
Time-Series Physiological Data Balancing for Regression

Time-Series Physiological Data Balancing for Regression

Many studies have shown the effectiveness of ma- chine learning in estimating psychological or physiological states using physiological data as input....

Machine learning Imbalanced Dataset Data balancing +1
Operator Data Driven Cell-Selection in LTE-LAA Coexistence Networks

Operator Data Driven Cell-Selection in LTE-LAA Coexistence Networks

Efficient cell-selection is essential to realize the gains in network performance promised by LTE Licensed Assisted Access (LAA) in the 5GHz unlicense...

LTE-LAA cell-selection
Multi-Lane Detection and Tracking Using Vision for Traffic Situation Awareness

Multi-Lane Detection and Tracking Using Vision for Traffic Situation Awareness

In recent years, the number of vehicles equipped with in-vehicle cameras has been increasing. However, most of the images from in-vehicle cameras of o...

In-vehicle Camera Driver Assist System
Environment-Agnostic In-home Human Activity Recognition Using Wi-Fi Signals

Environment-Agnostic In-home Human Activity Recognition Using Wi-Fi Signals

 Recently, Wi-Fi CSI (channel state information) has been widely studied for low-cost activity recognition with low privacy concern. CSI represents ho...

Environment-Agnostic In-home Human Activity Recognition Using Wi-Fi Signals
Mobile Health System using Facial Image for Assessment of Work Engagement, Recovery and Reattachment

Mobile Health System using Facial Image for Assessment of Work Engagement, Recovery and Reattachment

The number of workers' compensation claims and recognized cases related to mental disorders has been increasing annually. In response, the Minist...

Recovery Estimation Smart Toothbrush
Smartphone User Identification in Cyber-phsyical Space

Smartphone User Identification in Cyber-phsyical Space

By utilizing a cyber-physical space composed of constantly scanned objects and people in a three-dimensional physical space using 3D LiDAR and depth c...

Cyber-physical Space User Identification LiDAR

FlowScan: Estimating People Flows on Sidewalks Using Dashboard Cameras Based on Deep Learning

歩行者の流れを把握することは都市計画やイベントの検知に役立ちますが、そのために計測機器を街なかに設置していくとコストがかさみます。一方で、事故の証拠を残す目的や防犯のためにドライブレコーダーを積んだ車はすでに大量に走っているので、その映像を使えれば追加の設置なしに歩道の人流を測れることになります。本...

Reliability Estimation of Heart Rate Measurement Using Wrist-Worn Devices

Reliability Estimation of Heart Rate Measurement Using Wrist-Worn Devices

Heart Rate (HR) measurement using wrist-worn devices suffers from noises owing to body movement. Even though many researchers have proposed sophistica...

Heart rate Reliability Wrist-worn device +1
Identification of Conductive Tags Based on Radio Reflection Patterns Using LSTM

Identification of Conductive Tags Based on Radio Reflection Patterns Using LSTM

Identifying humans and things (i.e., target identification) is essential for various applications such as inventory management, working time managemen...

Target Identification Wi-Fi Imaging Wireless Sensing +1
Dynamic Offset Correction for Smartphone Thermal Cameras Using a Wristband Sensor

Dynamic Offset Correction for Smartphone Thermal Cameras Using a Wristband Sensor

Thermal images are widely used to various healthcare applications. However, thermal images captured by smartphone thermal cameras have insufficient ac...

Thermal camera Smartphone Offset correction +1
MicroDeep: In-network Deep Learning by Micro-sensor Coordination

MicroDeep: In-network Deep Learning by Micro-sensor Coordination

Distributed Execution of Deep Learning in Wireless Sensor NetworksIn wireless sensor networks, microcontrollers associated with sensors are becoming m...

distributed deep learning ultra-low power AI