A5101473347- Context-Aware Activity Recognition Systems
- Technology and Data Analysis
- Indoor and Outdoor Localization Technologies
- Mobile Crowdsensing and Crowdsourcing
- Interactive and Immersive Displays
- Risk and Safety Analysis
- Psychosocial Factors Impacting Youth
- Network Security and Intrusion Detection
- Video Surveillance and Tracking Methods
- Tactile and Sensory Interactions
- Human Pose and Action Recognition
- Embedded Systems and FPGA Design
- Advanced Malware Detection Techniques
- Energy Efficient Wireless Sensor Networks
- Reinforcement Learning in Robotics
- Web Application Security Vulnerabilities
- Safety Systems Engineering in Autonomy
- Healthcare Education and Workforce Issues
- Innovation in Digital Healthcare Systems
- Software Testing and Debugging Techniques
- Bluetooth and Wireless Communication Technologies
- Human-Automation Interaction and Safety
- Real-time simulation and control systems
- Manufacturing Process and Optimization
- Teleoperation and Haptic Systems
Korea Advanced Institute of Science and Technology
2019-2024
Kootenay Association for Science & Technology
2023
Chonnam National University
2019-2020
Hyundai Mobis (South Korea)
2020
Recent improvements in deep learning and hardware support offer a new breakthrough mobile sensing; we could enjoy context-aware services healthcare on device powered by artificial intelligence. However, most related studies perform well only with certain level of similarity between trained target data distribution, while practice, specific user's behaviors make sensor inputs different. Consequently, the performance such applications might suffer diverse user conditions as training models...
Due to changes in the automobile market and technology, Korea 2020s has entered era of electric vehicles. However, due lack supply charging stations for vehicles, there is not enough car chargers public. In this situation, if vehicle drivers are notified station status information accurately, they can efficiently share use insufficient numbers chargers. The existing inquiry applications have disadvantage limited range accuracy provided users, such as failing provide sufficient detailed...
Many applications utilize sensors on mobile devices and apply deep learning for diverse applications. However, they have rarely enjoyed mainstream adoption due to many different <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">individual conditions</i> users encounter. Individual conditions are characterized by users' unique behaviors carry, which collectively make sensor inputs different. It is impractical train countless individual...
The machine learning algorithm has been widely used in water-related fields such as water resources, management, hydrology, atmospheric science, quality, level prediction, weather forecasting, discharge quality etc. However, prediction studies based on the are limited compared to other applications because of data. Most previous have predicted monthly which is useful information but not enough from a practical aspect. In this study, we dissolved oxygen (DO) using recurrent neural network...
A fast-speed Unmanned Ground Vehicle (UGV) is utilized for logistics or carrying casualties in dangerous environments, substituting humans. Controlling the UGV's acceleration essential a human operator concerning stability. However, it not possible to recognize accurate of UGV only with visual information. We designed haptic feedback using Stewart platform pilot control and verified its effect through user study. The result showed that could drive less on rough terrain than without feedback.
This paper proposes a novel real-time pose estimation system on embedded devices for driver and front passenger. The main goal of the proposed is to operate in real time with limited hardware resources while preserving high accuracy. divided into an object detection estimation. In detection, we eliminate redundant inaccurate bounding boxes by considering characteristics target image domain. estimation, single-person lightweight deep learning model has been knowledge distillation adopted...
Existing crime prediction systems have limitations in prevention, lack of monitoring personnel compared to the number installed CCTV cameras, and reliance solely on conventional investigation data experience for determining risk levels. To overcome these limitations, this paper introduces a novel machine learning-based video analysis dissemination framework prevention. The is developed providing swift accurate compressed sets videos through assessment algorithms behavior target recognition,...
목적 본 연구는 흔히 상처 입은 치료자 이론(Nouwen, 1999) 통해 대표되는 가설, 즉, 대인 외상을 경험한 상담자가 외상 후 성장을 높은 수준의 직업 정체성을 얻게 되는 과정에 대해 탐색해 보고자 하였다. 이에 연구의 목적은 상담자의 경험에 대한 의도적 반추가 직업정체성에 미치는 영향에서 성장의 매개효과를 살펴보는 것이다. 방법 이를 위해 시⋅군⋅구 청소년상담센터와 같은 공공 상담 기관, Wee센터, 초⋅중⋅고등학교, 사설 교정직 관련 사회복지시설, 대학부설 기관 등의 기관에 근무하고 있는 상담자 280명의 자료를 수집하였다. 수집한 자료에 대해서는 PASW Statistics 18.0, SPSS PROCESS macro 3.5를 이용하여 기술통계, 상관 분석 및 다중회귀분석을 실시하였다. 성장 변인의 매개 효과에 총합 변인으로서의 단순매개효과를 하였고, 추가적으로 외상후 하위 요인들을 각각의 요인으로 설정하여,...
This paper investigates the use of haptic feedback in GoGoHand technique for intuitive virtual object manipulation reality (VR). Our study explores impact design on enhancing body ownership and assesses effectiveness feedback. A pattern hardware implementation are proposed, providing based users' arm hand movement. We conduct a workshop to identify dimensions implemented examples demonstrate their effectiveness. These findings inform systems immersive 3D interaction, embodiment VR users.
Deep mobile sensing applications are suffering from various individual conditions in the wild. We propose a meta-learned adaptation technique to adapt target condition with few labeled data. evaluate our system on public dataset and it outperforms baselines.
본 연구는 유아교사의 행복감과 교사－유아 상호작용의 관계에서 전문성인식의 매개효과를 검증하기 위해 수행되었다. 경인지역에 소재한 유아교육기관에 근무하고 있는 유아교사 320명을 대상으로 행복감 설문지(최영옥, 2011), 상호작용 설문지(김시연, 2014), 전문성 발달 자기평가 설문지(백은주·조부경, 2004)를 배부하고 그 가운데 300명의 자료가 SPSS 23.0에 의해 분석되었다. 연구문제에 따른 분석 결과는 다음과 같다. 첫째, 행복감, 교사－유아의 그리고 세 변인 간에는 유의미한 정적 관련성이 것으로 나타났으며, 각 변인의 하위 영역간에도 관계가 나타났다. 둘째, 전문성인식이 상호작용에 의미 정도의 긍정적 영향을 미치는 더 나아가 부분매개 효과를 검증하였다. 또한, 영역 지식과 기술발달, 생태학적 자기이해 발달의 순서로 부분 매개효과가 크게 이와 같은 행복감이 직접적인 동시에 인식에 매개되어서도 미치고 있음을 보여준다. 특히 전문성인식 교육과정을 계획, 수행,...