A5100337303- Ultrasound Imaging and Elastography
- Photoacoustic and Ultrasonic Imaging
- Plasma Diagnostics and Applications
- Plasma Applications and Diagnostics
- Ultrasound and Hyperthermia Applications
- Electrohydrodynamics and Fluid Dynamics
- Social Robot Interaction and HRI
- Ultrasonics and Acoustic Wave Propagation
- Robotics and Automated Systems
- Optical Imaging and Spectroscopy Techniques
- Emotion and Mood Recognition
- Radiomics and Machine Learning in Medical Imaging
- Hand Gesture Recognition Systems
- Robotic Locomotion and Control
- Prosthetics and Rehabilitation Robotics
- AI in cancer detection
- Advanced Manufacturing and Logistics Optimization
- Flow Measurement and Analysis
- Non-Invasive Vital Sign Monitoring
- Radiation Dose and Imaging
- Creativity in Education and Neuroscience
- Robot Manipulation and Learning
- Optimization and Packing Problems
- AI in Service Interactions
- Fire Detection and Safety Systems
Korea Advanced Institute of Science and Technology
2007-2024
Loma Linda University
2024
Seoul National University Bundang Hospital
2023
Kyungpook National University
2018
Hongik University
2009-2015
Non-alcoholic fatty liver disease (NAFLD), prevalent among conditions like obesity and diabetes, is globally significant. Existing ultrasound diagnosis methods, despite their use, often lack accuracy precision, necessitating innovative solutions AI. This study aims to validate an AI-enhanced quantitative (QUS) algorithm for NAFLD severity assessment compare its performance with Magnetic Resonance Imaging Proton Density Fat Fraction (MRI-PDFF), a conventional diagnostic tool. A single-center...
This paper introduces an emotion interaction system for a service robot. The purpose of systems in robots is to make people feel that the robot not mere machine, but reliable living assistant home. composed recognition, generation, and expression systems. A user's recognized by multi-modality, such as voice, dialogue, touch. robot's generated according psychological theory about emotion: OCC (Ortony, Clore, Collins) model, which focuses on emotional state information environment itself....
Abstract In this paper, a robust algorithm that discriminates various eye motions from the ElectroOculoGram (EOG) signals is proposed. Previous researches use EOG only focused on saccadic or blinks. However, we cover all including double/triple blinks and left/right winks. Furthermore, suggest novel method, which removes noises of EOG, to increase robustness discrimination. The method called “an ideal velocity shape algorithm” compares real with an designed under noise free assumption. This...
This paper presents a novel touch pattern recognition algorithm for dynamic proximate interaction between robot and human. At first, in order to guarantee reactive responses various patterns, an online is proposed based on Temporal Decision Tree(TDT). Second, movements of real situation usually deteriorate the confidence level classifier. A robust method compensate inconsistent results by Consistency Index(CI), which estimates consistency degrees human patterns over time. The algorithms are...
The speed of sound (SoS) has great potential as a quantitative imaging biomarker since it is sensitive to pathological changes in tissues. In this paper, target-aware deep neural (TAD) network reconstructing an SoS image quantitatively from pulse-echo phase-shift maps gathered single conventional ultrasound probe presented.In the proposed TAD network, reconstruction process guided by feature created segmented target images for accuracy and contrast. addition, extraction utilizes phase...
Traditional B-mode ultrasound has difficulties distinguishing benign from malignant breast lesions. It appears that Quantitative Ultrasound (QUS) may offer advantages. We examined the QUS imaging system’s potential, utilizing parameters like Attenuation Coefficient (AC), Speed of Sound (SoS), Effective Scatterer Diameter (ESD), and Concentration (ESC) to enhance diagnostic accuracy. images radiofrequency signals were gathered These processed analyzed by a system trained on simulated acoustic...
In this paper, a single-probe ultrasonic imaging system that captures multi-variable quantitative profiles is presented. As pathological changes cause biomechanical property variation, has great potential for lesion characterization. The proposed simultaneously extracts four clinically informative biomarkers, such as the speed of sound, attenuation, effective scatter density, and radius, in real-time using single scalable neural network. performance was evaluated through numerical...
Ionizing radiation and high levels of circulating estradiol are known breast cancer carcinogens. We investigated the risk first primary postmenopausal in relation to combined effects whole-body ionizing exposure prediagnostic sex hormones, particularly bioavailable (bE
Independence of people in need their living environment becomes an imperative notion for any society the years to come. As approach achieve independence, this paper addresses problem controlling assistive home emphasizing a human-friendly man-machine interaction. We introduce new service robot, named Joy, which can be categorized as steward robot. intermediate agent between inhabitants and complex smart house environment, robot provide users with easily accessible, convenient, cost effective...
Low-voltage atmospheric-plasma generation is reported, in which the breakdown voltage significantly reduced by utilizing afterglow ions generated on integrated electrodes. Using micromachining techniques, a microanode and two microcathodes were glass substrate. Atmospheric glow discharge was first narrow gap of 10 μm, resulting utilized as an initiation carrier subsequent induced wide 270 μm. In presence carrier, atmospheric at substantially low voltage. The feasibility proposed scheme...
Significance: Early assessment of local tissue oxygen saturation is essential for clinicians to determine the burn wound severity. Background: We assessed extent and depth in skin extremities using a custom-built 36-channel functional near-infrared spectroscopy system patients with burns. Methods: A total nine burns were analyzed this study. All second-degree categorized as superficial, intermediate, deep burns; non-burned on burned side; healthy contralateral side. Hemodynamic signals from...
Many blog posts deal with current issues, so much attention has been paid to identifying topic trends in blogs. This paper suggests a new metric of selecting words. We empirically tested the accuracy and performance massive corpus. First, we created site groups their indegree influence. Second, ran each group. The test was encouraging because identified key issues matching headlines New York Times when it is applied top expect that this source grouping methods will be developed analysis...
With the recent increase in utilization of logistics and courier services, it is time for research on systems fused with fourth industry sector. Algorithm studies related to object recognition have been actively conducted convergence emerging artificial intelligence field, but so far, algorithms suitable automatic unloading devices that need identify a number unstructured cargoes require further development. In this study, algorithm loading device cargo was selected as subject applicable...
본 연구는 영상 분석에서 최근 좋은 연구 성과를 내고 있는 컨볼루션 신경망 (Convolutional Neural Network: CNN) 기법을 실외 CCTV 분석에 적용하여 객체 유형을 분류하는 방법론은 제안한다. 배경 차분 (background subtraction)을 사용하여 찾고자 하는 후보들을 추출해내고 이를 CNN을 이용해 분류함으로써 계산량을 줄이는 효과를 얻는 방법이다. CNN 학습용 수집을 위해 범죄 발생이 주로 일어나는 골목길, 놀이터 등에서 촬영한 DB를 구축하였으며 우선적으로 사람인 객체만 검출하는 분류기를 학습하였다. 다양한 학습 데이터 사이즈와 세팅에 맞게 실험하였으며 실험 결과 약 80%의 분류 정확도를 보였으며 새로운 영상으로 테스트했을 때 67.5%의 성능을 보였다.
In this paper, we propose a new service agent, called steward robot, which provides inhabitants with accessible, convenient, and cost effective interfaces as an intermediate agent between the user smart home environment. To implement more subtle emotional reaction of adopt novel cue, sentiment relation, address problem modeling intensity transition emotion words, while previous researches have mainly focused on selection discrete words from psychological point view. We also discuss some...