A5085264693- Integrated Circuits and Semiconductor Failure Analysis
- Industrial Vision Systems and Defect Detection
- Artificial Intelligence in Games
- Anomaly Detection Techniques and Applications
- Air Quality and Health Impacts
- Sports Analytics and Performance
- Reinforcement Learning in Robotics
- Advancements in Photolithography Techniques
- Digital Games and Media
- Air Quality Monitoring and Forecasting
- Remote Sensing and LiDAR Applications
- Machine Learning in Materials Science
- Urban and Freight Transport Logistics
- Educational Games and Gamification
- Face and Expression Recognition
- Traffic Prediction and Management Techniques
- Advanced Chemical Sensor Technologies
- Remote Sensing in Agriculture
- Speech Recognition and Synthesis
- Video Analysis and Summarization
- Protein Structure and Dynamics
- Gait Recognition and Analysis
- Time Series Analysis and Forecasting
- Advanced Manufacturing and Logistics Optimization
- Assembly Line Balancing Optimization
Korea University
2018-2024
New York University
2022
Automatic identification of defect patterns in wafer bin maps (WBMs) stands as a challenging problem for the semiconductor manufacturing industry. Deep convolutional neural networks have recently shown decent progress learning spatial WBMs, but only at expense explicit manual supervision. Unfortunately, clean set labeled WBM samples is often limited both size and quality, especially during rapid process development or early production stages. In this study, we propose self-supervised...
Abstract In the chemical industry, generation of novel molecular structures with beneficial pharmacological and physicochemical properties in de novo design is a critical problem. The advent deep learning neural generative models has recently enabled significant achievements constructing design. Consequently, studies on new continue to generate molecules that exhibit more useful properties. this study, we propose method for utilizes adversarial networks based reinforcement realistic molecule...
To date, investigating respiratory disease patients visiting the emergency departments related with fined dust is limited. This study aimed to analyze effects of two variable-weather and air pollution on who visited departments. utilized National Emergency Department Information System (NEDIS) database. The meteorological data were obtained from Climate Data Service. Each weather factor reflected accumulated 4 days: a patient's visit day 3 days before day. We RandomForestRegressor...
Statistical methods have been widely used to predict pollutant concentrations. However, few efforts made examine spatial and temporal characteristics of ozone in Korea. Ozone monitoring stations are often geographically grouped, the concentrations separately predicted for each group. Although geographic information is useful grouping stations, accuracy prediction can be improved if patterns incorporated into process. The goal this research cluster according using a k-means clustering...
Identifying agricultural fields that grow cabbage in the highlands of South Korea is critical for accurate crop yield estimation. Only grown a limited time during summer, highland accounts significant proportion Korea’s annual production. Thus, it has profound effect on formation prices. Traditionally, labor-extensive and time-consuming field surveys are manually carried out to derive maps highlands. Recently, high-resolution overhead images have become readily available with rapid...
Semi-supervised learning methods have shown promising results in solving many practical problems when only a few labels are available. The existing assume that the class distributions of labeled and unlabeled data equal; however, their performances significantly degraded distribution mismatch scenarios where out-of-distribution (OOD) exist data. Previous safe semi-supervised studies addressed this problem by making OOD less likely to affect training based on However, even if effectively...
Introduction: Fine dust known as a group 1 carcinogen is reportedly related to death, stroke, neuropathy, hypertension, cardiovascular, and respiratory diseases. To date, there no relevant research regarding disease patients who visit emergency departments. This study aimed analyze the effects of weather air pollution variables on visited departments.Materials Method: Among had medical centers in Seoul over last 3 years, those whose classification code (J code; J00–J99) was diseases...
This paper proposes to use machine learning (ML) methods predict wafer quality using Fab inline measured items, DC measurements, and DVS (Dynamic Voltage Stress) at sort. With developed ML approach, the predicted accuracy is more than 80% in 8 nm products used this study. We believe method can be further fine-tuned help enable ICs high level expected for automotive systems. By assigning predictive rankings, also helps best tooling system higher quality.
The game industry has been continually evolving under the name of e-sports. As various competitions are held, it is important to provide viewers with relevant game-related information. In particular, predicting final outcome a based on certain situations one players’ main interests. However, in strategy games such as StarCraft II, difficult predict outcomes because many factors including units, their combinations, and unit upgrades. Previous studies predicted win or loss using only partial...
Overcrowding within emergency departments (ED) affects patient satisfaction and quality of care. The leading causes ED overcrowding are systematic delays between procedures disposition after treatment. Early prediction can improve flow optimize allocation hospital resources. While studies for predicting using machine learning methods have been actively conducted abroad, few in South Korea spite the lagging medical environment. Previous limited to binary predictions; either admission or...
StarCraft, one of the most popular real-time strategy games, is a compelling environment for artificial intelligence research both micro-level unit control and macro-level strategic decision making. In this study, we address an eminent problem concerning making, known as 'fog-of-war', which rises naturally from fact that information regarding opponent's state always provided in incomplete form. For intelligent agents to play like human players, it obvious making accurate predictions status...