Jinwoo Park
Korea Advanced Institute of Science and Technology · Engineering
About the Lab
Professor Jinwoo Park's research lab specializes in intelligent systems and human-centered computing, focusing on the integration of machine learning, computer vision, and embedded systems to solve real-world challenges in healthcare, mixed reality, and networking. The lab develops innovative solutions that combine deep learning with physical sensing—such as in wearable cardiovascular monitoring and real-time illumination estimation for augmented reality—while also advancing efficient and adaptive networking protocols using reinforcement learning. A recurring theme is creating seamless, immersive, and intelligent user experiences through minimal hardware intervention and high system autonomy.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
15Microservice is an architectural style that has been widely adopted in various latency-sensitive applications. Similar to the monolith, autoscaling has attracted the attention of operators for managing resource utilization of microservices. However, it is still challenging to optimize resources in terms of latency service-level-objective (SLO) without human intervention. In this paper, we present GRAF, a graph neural network-based proactive resource allocation framework for minimizing total CPU
In this paper, a novel pulse transit time (PTT) measurement method which employs electrocardiography and bioimpedance measurement (ECG-BIM) is proposed. Unlike conventional method based on ECG and photoplethysmography (ECG-PPG), the proposed method offers a promising technique for continuous and portable monitoring of cardiovascular diseases, as it requires only electrical components that can be fully integrated in a low-power and low-cost silicon circuit. To verify the validity of the proposed
In mixed reality (MR), augmenting virtual objects consistently with real-world illumination is one of the key factors that provide a realistic and immersive user experience. For this purpose, we propose a novel deep learning-based method to estimate high dynamic range (HDR) illumination from a single RGB image of a reference object. To obtain illumination of a current scene, previous approaches inserted a special camera in that scene, which may interfere with user's immersion, or they analyzed r
Nondestructive evaluation using shearography requires a way to stress the inspection target. This technique is able to directly measure the displacement gradient distribution on the object surface. Shearography visualizes the internal structural damages as the anomalous pattern in the shearograpic fringe pattern. A piezoelectric (PZT) excitation system is able to generate loadings in the vibrational, acoustic, and ultrasonic regimes. In this paper, we propose a PZT-excited stroboscopic shearogra
The carrier sense multiple access (CSMA) algorithm has been used in the wireless medium access control (MAC) under standard 802.11 implementation due to its simplicity and generality. An extensive body of research on CSMA has long been made not only in the context of practical protocols, but also in a distributed way of optimal MAC scheduling. However, the current state-of-the-art CSMA (or its extensions) still suffers from poor performance, especially in multi-hop scenarios, and often requires
This paper proposes a novel panoramic texture mapping-based rendering system for real-time, photorealistic reproduction of large-scale urban scenes at a street level. Various image-based rendering (IBR) methods have recently been employed to synthesize high-quality novel views, although they require an excessive number of adjacent input images or detailed geometry just to render local views. While the development of global data, such as Google Street View, has accelerated interactive IBR techniq
This paper proposes a system which enables users to have enhanced interior deigning and authoring tool through augmented reality (AR). The proposed system, which we refer to as DreamHouse, focuses on providing natural user interaction and realistic AR experience by enabling following features: 1) allowing users to utilize bare-hand interaction with an attached egocentric RGB-D camera when trying to make detail adjustments to virtual objects' size, location and orientation, 2) rendering every vir
Abstract Composite material-based aircraft structures have attracted attention due to their lightweight and superior mechanical properties. However, composite structures have a high risk of structural failures when damages occur due to loadings or impacts. Therefore, consistent structural health monitoring (SHM) is needed to ensure the structural integrity and safety of the aircraft. Various methods of sensor installation and measurement systems were developed for the implementation of SHM in ai
Through the application of the Rayleigh criterion for a two-point resolution, the dependence of the depth of focus on the resolution in the image is determined for a rectangular, a Gaussian, and an annular lens aperture. These solutions are posed in terms of the normalized parameters, obviating the need for the specification of the actual physical lengths. A general approach applicable to any aperture topology is discussed.
일반적으로 열차분야에서 분기기 시스템은 안전성과 직접적으로 연관되기 때문에 높은 신뢰성이 요구된다. 특히 자기부상열차의 분기기 시스템은 대차가 궤도를 감싸는 구조적 특징으로, 고가궤도 전체가 움직여야 한다. 이러한 이유로 자기부상열차의 분기기는 강 재질로 설계되었다. 강 거더의 분기기는 콘크리트 거더에 비하여 진동측면뿐만 아니라 거더의 처짐에도 취약하다. 그러므로 자기부상열차가 유연한 분기기 위를 통과 할 때, 부상안정성 예측이 매우 중요하다. 본 논문의 목표는 자기부상열차와 분기기 거더의 연성된 동역학 해석모델을 개발하고, 공진예측 및 차량의 부상안정성 예측에 있다. 이를 위해서 차량의 3차원 다물체 동역학 모델을 개발 하였고, 분기기 거더와 모달중첩법을 이용한 연성모델링을 수행하였다. 개발된 해석모델은 실측 실험과 비교를 통해서 해석모델의 타당성을 검증하였다. Generally, in the train area, switch tracks have required high reli
This study performed earthquake response analyses of underground structures using displacement responses of soil. In this study, spring coefficients of surrounding soil proposed by specifications and researchers were adopted and then their corresponding analysis results were compared. The free field analyses using ProShake were carried out in order to predict ground responses of the field without underground structures. Several earthquakes such as El Centro, Ofunato, and Hachinohe earthquakes we
This paper is intended to provide the background information and justification for Korean highway bridge design code(limit state design)(2012). Limit state design method calculates reliability index and probability of failure through the analysis of the reliability of the experimental database. It has become possible to perform the economical and consistent design by evaluating the safety of a structure quantitatively. In this paper, we used the design specifications of RC slab bridge of superst
Research Areas
Dive deeper into Jinwoo Park's research on Nubint
Open this lab's papers in the app to read with AI, summarize, and cite in your writing.