Graduate Students
최지환 (Jihwan Choi)
Research Interests
Deep Learning based Multi-Defect Detection scheme in Wafer using Graph Neural Network.
최지환, 김미선, 이하림, "다중 결함 인지 손실 함수 및 머신러닝 기반 웨이퍼 결함 종류 검파 기법 연구," 한국통신학회, 2022.
김미선, 최지환, 이하림, "웨이퍼 맵의 다중 패턴 인지를 위한 벡터 표현 기반 캡슐네트워크 구현", 한국통신학회 논문지, Excellent Paper Selection, 2023.
Recognition of Traffic Lights using Multi-level Features with Ratio-preserving Zero Padding.
J. Choi and H. Lee, "Real-Time Traffic Light Recognition with Lightweight State Recognition and Ratio-Preserving Zero Padding," Electronics, 2024.
Camera-Invariant Domain Adaptation for autonomous driving.
Project Experience
Predicting antenna performance of autonomous driving sensors, LG Aimers, 2022, DACON (upper 6%)
Samsung AI Challenge (3D Metrology), 2022, DACON
Jeju Traffic Forecast, 2022, DACON
Experience
Python Instructor at LG Innotek, (2024.06 ~ current)
김미선 (Misun Kim)
Research Interests
Deep Learning based Multi-Defect Detection scheme in Wafer using Attention Module and GAIN
최지환, 김미선, 이하림, "다중 결함 인지 손실 함수 및 머신러닝 기반 웨이퍼 결함 종류 검파 기법 연구," 한국통신학회, 2022.
Vector-representation based Pattern Recognition using Capsule Network
김미선, 최지환, 이하림, "웨이퍼 맵의 다중 패턴 인지를 위한 벡터 표현 기반 캡슐네트워크 구현", 한국통신학회 논문지, Excellent Paper Selection, 2023.
Development of Thickness Prediction System.
Project Experience
Predicting antenna performance of autonomous driving sensors, LG Aimers, 2022, DACON (upper 6%)
Samsung AI Challenge (3D Metrology), 2022, DACON
서정윤 (Jeongyun Seo)
Research Interests
Design of AI Hardware Accelerator of Various Deep Neural Networks using Verilog HDL.
[Basic Fully-connected Network] 서정윤, 이종윤, 박성준, 이하림, "Implementation and Evaluation of fully-connected network on Hardware using Verilog HDL," 한국정보기술학회 하계학술대회, 2024.
[Lightweight Fully-connected Network][Quantization][LRA] 서정윤, 이종윤, "Design of Lightweight Fully-connected Network in Hardware using Learning-based Low-rank Approximation and Quantization Techniques," in submission to Special Issue of The Transactions of the Korean Institute of Electrical Engineering.
[CNN] 이종윤, 서정윤, 박성준 "Design of Convolution Layer using Verilog HDL," in preparation for the submission of a domestic journal.
H/W oriented Activation Function effectively to reduce the required number of bits for feature maps generated between Neural Layers.
Research grant for master's degree students, National Research Foundation of Korea, 2024 (link) (link).
[Learnable Activation Function with limited upper and lower values] "Development of a learnable activation function for optimal upper and lower values to reduce the required number of bits on memory and bus interface", in preparation for the submission of a domestic conference or an international journal
Development of Various Intelligent Systems using Various Deep Learning Networks.
FATHER: Finding and Tracking Hidden pERson with Object Detection and Face Similarity.
서정윤, 박성준, 이하림, "Implementation of Deep-learning based Specific Person Identification System using Facial Similarity," 한국통신학회 동계학술대회, 2024.
Implementation of Real-time Semantic Segmentation System on Embedded Computer for Autonomous Vehicle
[Preparation] 박성준, 서정윤, 이하림, "Something to implement a system," in preparation.
R²Sys-FTCP: Recognition and Recommendation System for Fitness Exercise Types and Correct Posture.
Project Experience
Intelligent High-precision GPS scheme using Deep Learning, 2022, Campus Patent Universiade.
Samsung AI Challenge (3D Metrology), 2022, DACON.
Honors and Awards
Research grant for master's degree students, National Research Foundation of Korea, 2024 (12 million won) (link) (link).
Campus Patent Universiade, "Intelligent High-precision GPS scheme using Deep Learning", Encouragement Prize, 2022 (link).
Patents
단말기 중심 위치 측위를 위한 딥러닝 네트워크 기반 오차 보정 정보 생성 기법
박성준 (Sungjun Park)
Research Interests
Real-time Segmentation System for Autonomous Driving Vehicle
박성준, 이하림, "Performance Evaluation of Fully Convolutional Network for Autonomous Driving with the Latest Car Daytime Road Data," 한국정보기술학회 하계학술대회, 2024.
[Preparation] 박성준, 서정윤, 이하림, "Something to implement a system," in preparation.
Design of ConvTransopose2D layer for Generative AI.
[Preparation] 박성준, 이하림, "Design of Transposed Convolution Layer for Generative AI", in preparation.
[Basic Fully-connected Network] 서정윤, 이종윤, 박성준, 이하림, "Implementation and Evaluation of fully-connected network on Hardware using Verilog HDL," 한국정보기술학회 하계학술대회, 2024.
[CNN] 이종윤, 서정윤, 박성준 "Design of Convolution Layer using Verilog HDL," in preparation for the submission of a domestic journal.
Project Experience
Predicting antenna performance of autonomous driving sensors, LG Aimers, 2022, DACON (upper 6%).
FATHER: Finding and Tracking Hidden pERson with Object Detection and Face Similarity.
서정윤, 박성준, 이하림, "Implementation of Deep-learning based Specific Person Identification System using Facial Similarity," 한국통신학회 동계학술대회, 2024.
[국내 저널 준비중] Implementing one of the latest object detection networks, YOLOv6 and a convolutional block attention module, CBAM.
이종윤 (Jong Youn Lee), (co-advisor)
Research Interests
Design of AI Hardware Inference for Fully-connected Network using Verilog HDL.
서정윤, 이종윤, 박성준, 이하림, "Implementation and Evaluation of fully-connected network on Hardware using Verilog HDL," 한국정보기술학회 하계학술대회, 2024.
Jong Youn Lee, Jeong Yun Seo, Sung Jun Park, Harim Lee, Yong Hwan Lee*, Hardware Acclerator for Real-time Image Classification, In submission.
Design of Compressed Fully-connected Layer using Low Rank Approximation to reduce the number of weights.
[국내 논문지 준비중] 서정윤, 이종윤, 박성준, Implementation of AI Hardware Inference for Compressed Fully-connected Network using Low Rank Approximation.
Design of AI Hardware Inference for Convolution Layer using Verilog HDL.
[국내 논문지 준비중] 이종윤, 서정윤, 박성준, "Design of Convolution Layer using Verilog HDL."
Undergraduate Students
최혜주 (Hyeju Choi)
Research Interests
Development of Document Summary System using Large-Language Model and Camera Sensor.
Programming skill set: Python, PyTorch, C++
Deep Learning Networks: Transformer, BERT, GPT, KoBART, etc.
Project Experience
Samsung AI Challenge (3D Metrology), 2022, DACON.
Patent Trend Analysis of Natural Language based Generative AI and Establishing a Patent Strategy to alleviate Hallucination, 2023, Campus Patent Universiade.
Honors and Awards
Campus Patent Universiade, "Natural Language Model based Generative AI", Excellence Prize, 2023 (link).
Alumni
Undergraduate
김영섭 (2018 학번)