이진호 교수
Jinho Lee
서울대학교 · 공학
연구실 소개
이 교수의 연구실은 인공지능 기반 금융 시장 예측, 3D 디스플레이 기술, 의료 영상 및 유전자 분석을 융합한 첨단 연구를 수행하고 있습니다. 특히 딥러닝을 활용한 주식 차트 분석과 고성능 그래프 처리 아키텍처 설계, 실시간 눈동자 추적 기반의 자동차용 헤드업 디스플레이 기술 개발에 주력하고 있으며, 유전적 신경병증의 원인 유전자 규명에도 기여하고 있습니다. 연구는 실생활 응용에 초점을 맞추어 기술 혁신과 의료 진료 개선을 동시에 추구합니다.
연구 현황
연구 성과 추이
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
주요 논문
15We applied Deep Q-Network with a Convolutional Neural Network function approximator, which takes stock chart images as input for making global stock market predictions. Our model not only yields profit in the stock market of the country whose data was used for training our model but also generally yields profit in global stock markets. We trained our model only on US stock market data and tested it on the stock market data of 31 different countries over 12 years. The portfolios constructed based
To achieve an immersive natural 3D experience on a large screen, a 300-Mpixel multi-projection 3D display that has a 100-inch screen and a 40° viewing angle has been developed. To increase the number of rays emanating from each pixel to 300 in the horizontal direction, three hundred projectors were used. The projector configuration is an important issue in generating a high-quality 3D image, the luminance characteristics were analyzed and the design was optimized to minimize the variation in the
It is generally recognized that most nosocomial infections are spread by exposure to expelled particles at close range (usually within 1 m) or through contact. Although the Korea Centers for Disease Control established a 2-m cut-off for transmittance from patients during the Middle East Respiratory Syndrome (MERS) outbreak in Korea in 2015, questions have been raised regarding possible infection due to aerosols transported beyond this distance. The aim of this study was to characterize cough-gen
In this paper, we propose ExtraV, a framework for near-storage graph processing. It is based on the novel concept of graph virtualization , which efficiently utilizes a cache-coherent hardware accelerator at the storage side to achieve performance and flexibility at the same time. ExtraV consists of four main components: 1) host processor, 2) main memory, 3) AFU (Accelerator Function Unit) and 4) storage. The AFU, a hardware accelerator, sits between the host processor and storage. Using a coher
We explore the feasibility of implementing stereoscopy-based 3D images with an eye-tracking-based light-field display and actual head-up display optics for automotive applications. We translate the driver's eye position into the virtual eyebox plane via a "light-weight" equation to replace the actual optics with an effective lens model, and we implement a light-field rendering algorithm using the model-processed eye-tracking data. Furthermore, our experimental results with a prototype closely ma
Charcot-Marie-Tooth disease (CMT) is the most common inherited peripheral neuropathy and is a genetically and clinically heterogeneous disorder. We examined a Korean family in which two individuals had an autosomal-dominant axonal CMT with early-onset, sensory ataxia, tremor, and slow disease progression. Pedigree analysis and exome sequencing identified a de novo missense mutation (p.Y223H) in the diacylglycerol O-acyltransferase 2 (DGAT2) gene. DGAT2 encodes an endoplasmic reticulum-mitochondr
In this paper, the analysis of thermal instability of rotating nanofluid layer is revised with a physically more realistic boundary condition on the nanoparticle volumetric fraction i.e. the nanoparticle flux is assumed to be zero rather than prescribing the nanoparticle volumetric fraction on the rigid impermeable boundaries. This shows that the nanoparticle fraction value at the boundary adjusts accordingly. In this respect, the present model is more realistic physically than those of the prev
A fundamental problem in multi-view 3D face modeling is the determination of the set of optimal views (poses) required for accurate 3D shape estimation of a generic face. There is no analytical solution to this problem, instead (partial) solutions require (near) exhaustive combinatorial search, hence the inherent computational difficulty of this task. We build on our previous modeling framework, which uses an efficient contour-based silhouette method and extend it by aggressive pruning of the vi
The phase equilibria in the Y 2 O 3 ‐Nb 2 O 5 system have been studied at temperatures of 1500° and 1700°C in the compositional region of 0‐50 mol% Nb 2 O 5 . The solubility limits of the C‐type Y 2 O 3 cubic phase and the YNbO 4 monoclinic phase are 2.5 (±1.0) mol% Nb 2 O 5 and 0.2 (±0.4) mol% Y 2 O 3 , respectively, at 1700°C. The fluorite (F) single phase exists in the region of 20.1‐27.7 mol% Nb 2 O 5 at 1700°C, and in the region of 21.1‐27.0 mol% Nb 2 O 5 at 1500°C, respectively. Conductivi
대표 연구 분야
이진호 교수의 연구를 Nubint에서 더 깊이 살펴보세요
이 연구실의 논문을 앱에서 열어 AI와 함께 읽고, 핵심을 요약하고, 내 글에 인용하세요.