A5074281035- Indoor and Outdoor Localization Technologies
- UAV Applications and Optimization
- Cardiovascular Health and Disease Prevention
- Cerebrovascular and Carotid Artery Diseases
- Underwater Vehicles and Communication Systems
- Acute Ischemic Stroke Management
- Privacy-Preserving Technologies in Data
- Medical Image Segmentation Techniques
- Distributed Control Multi-Agent Systems
- Image Enhancement Techniques
- Robotic Path Planning Algorithms
- Mobile Crowdsensing and Crowdsourcing
- Image and Signal Denoising Methods
- Advanced Image Processing Techniques
- Speech and Audio Processing
Sungkyunkwan University
2023-2024
Hanyang University
2021-2023
In this article, we propose a novel deep reinforcement learning (DRL) approach for controlling multiple unmanned aerial vehicles (UAVs) with the ultimate purpose of tracking first responders (FRs) in challenging 3-D environments presence obstacles and occlusions. We assume that UAVs receive noisy distance measurements from FRs which are two types, i.e., Line Sight (LoS) non-LoS (NLoS) used by UAV agents order to estimate state (i.e., position) FRs. Subsequently, proposed DRL-based controller...
In this letter, we propose a novel model weight update method that accounts for the reliability of local clients in FL-based indoor localization. FL shows degraded localization performance than centralized learning because non-independent and identically distributed (non-IID) data configuration. Thus, aim to improve by applying clients, which is quantified uncertainty models. Bayesian models provide framework capturing but usually requires substantial computational cost as well, particularly...
Crowdsourcing is considered an efficient and promising paradigm for constructing large-scale signal fingerprint radio maps due to the proliferation of Wi-Fi-enabled devices. However, a crowdsourced indoor positioning system (IPS) has handle diverse devices inherent heterogeneity in received strength (RSS) measurements. To address device problem, differential fingerprinting methods have been explored, which mitigate characteristics that cause RSS from different commercial report differently....
We present an Ultra-Wide Band (UWB)-based multiple Unmanned Aerial Vehicle (UAV) control system architecture to localize and track a ground vehicle. A team of UAVs self-localizes its position measures distance vehicle using the mounted UWB module. The server utilizes estimated UAV measurements collected from radio communication between (i.e., mobile anchor) in order accurately. then sends next setpoint each enables form polygon-shaped formation with located at center. demonstrate our...
Carotid artery is an important vessel that supplies energy to the brain through blood flow. However, if flow in carotid blocked by clot, it can cause fatal damage brain. Therefore, essential measure and predict thickness of clots. In this paper, we propose a method clot vessels from self-produced ultrasound data. From back scatter signal, one-dimensional data such as Bandwidth Center Frequency information obtained, 2D image derived bandwidth applying amplitude-frequency conversion. order...
Blood clot is formed inside a blood vessel with various reasons. Carotid artery major in the neck that supply to brain. If harden carotid artery, of can block and make narrowed vessel. Therefore, it essential predict coagulation vessels. In this paper, we propose method determine progress clot. We use different two data which are waveform frequency spectra obtained by applying Fourier transform data. And then feature vectors extracted from apply an encoder network for attention The...