Global-Leading Research and Education in Brain and Cognitive engineering KOREA UNIVERSITY 고려대학교 뇌공학과는 인간의 인지-정보처리능력의
실제 응용을 목표로 한 뇌공학 전문가 양성을 위해 노력하고 있습니다.

연구실 소개

Pattern Recognition and Machine Learning Lab 지도교수 이성환

Pattern Recognition  and  Machine Learning Lab은 패턴인식 알고리즘을 활용하여 고차원의 영상처리(카메라 영상) 및 신호처리(뇌 신호) 기법을 개발하고 이에 기반한 인공지능 기술 개발을 연구 목표로 하고 있습니다. 구체적으로는, 뇌 신호 분석을 통해 생각만으로 외부 장치를 제어할 수 있도록 하는 Brain-Computer Interface 기술, 카메라 영상 분석을 통해 사람의 행동 분석 및 예측이 가능한 Cognitive Conputer Vision 기술, 사람 두뇌를 모방하는 Deep Machine Learning 기술, 환자의 자발적인 신경 재활이 가능하도록 하는 지능형 Neuro-Rehabilitation 기술을 연구 중에 있습니다.        

Optical Biosignal Processing Lab 지도교수 정지채

광생체신호처리 연구실에서는 Optical Coherence Tomography [OCT], Near Infra-red Spextroscopy [NUIRS], Intra-Body Communication [IBC] 및 Biochip 관련 연구를 하고 있습니다. OCT NIRS를 이용하면 뇌의 hemo-dynamics와 action potential을 탐지하여 뇌의 활성 상태를 계측할 수 있으며, 이러한 뇌 활성 상태 계측 장비를 바탕으로 Biochip과 IBC 기술을 통합하여 최첨단의 Brain-Machine Interface [BMI]를 구성하고 생체 신호를 분석하는 것을 본 연구실의 목표로 삼아 현재 많은 투자와 연구가 활발하게 진행되고 있습니다.        

Cognitive Systems Lab 지도교수 Christian Wallraven

In the cognitive Systems Lab, we have two main goals: -our first goal is to enhance our understanding of the algorithms employed by thr human cognitive system throufn the use of cutting-edge methods from machine learning and computer graphocs coupled with perceptual and cognitiver experiments. -our second goal is to transfer this knowledge to implementations of intelligent, artifical cognitive systems which can be used in rocotrics, computer vision, computer animation, and even in clinical applications. In the lab, we apply this combined experimental and computauional.

Bionics and Photonics Lab 지도교수 한재호

광생체전자공학연구실 (Bionics and Photonics Lab)에세는 광학기반 생체 이미징을 위한 시스템 개방 및 관 신호/영상처리를 중점적으로 연구하고 있다. 본 연구실운 다양한 센서와 영상기법에 대한 기초 및 응용연구를 기반으로, 뇌를 포함하는 생체형태의 신호획득 및 기능의 전기/광학적 반응신호 추출과 분석을 목적으로 한다. 이에 따라, 현재 광간섭단층촬영술, 기반의 다기능성 영상시스템 등의 활발한 연구를 진행하고 있다. 뇌/생체 조직 신호를 효과적으로 획득하고 처리하는 다양한 시스템 개발을 통해 앞으로 뇌공학, 의공학, 및 인공지능 분야의 발전을 이끌어 갈 것이다.

Brain Signal Procesing Lab 지도교수 이종환

뇌신호처리연구실 (Brain Signal Processing Lab; 고려대학교 뇌공학과)은 자기공명영상 (MRI/fMRI) 및 뇌전도 (EEG)  등 다양한 뇌신호 데이터에 머신러닝 기반의 신호처리 기법을 적용하여 뇌의 기능을 분석 및 응용하는 데 주요 연구 목적이 있습니다. 최근에는 딥뉴럴네트워크를 이용한 딥러닝 기법을 뇌신호 데이터, 행동 및 생체신호 데이터에 접목하려는 연구를 활발히 하고 있습니다. 연구의 목표는, 뇌 영상 데이터의 분석을 통한 정상인의 뇌기능을 규명하고 뇌기능 향상 등에 응용하는 연구입니다. 이를 바탕으로, 향후 여러 신경과/정신과 질환 등과 관련한 뇌기능의 차이 규명, 조기진단, 치료의 예후 예측에도 연구의 활용 가능성이 있습니다.

Affective Cognitive Neuroscience Lab 지도교수 김상희

The Affective Cognitive Neuroscience Lab pursues research in the area of emotional cognition. We cobine behavioral and neurscietifix techniquws to understand how emotional informarion is processed differenrly from nonemorional. information, to what extent indiciduaks exert vuluntary and involuntary control over the course of emotion generation processes, and how emotion interacts with other cignitive procrsses. We emphasizw indibidual difference facrors in emotional processing that play key roles in defining individuals` characteristics and that explain.        

Neural Computation Lab 지도교수 곽지현

Neural Computation Lab is interested in understanding how naturally occurring neyral acticities and Signals are used in neural information processing. Especially, we are interested in how such neural sifnals are encoded into information and ultimately stored in the neural network as menory. In addressing these questions, we combine both electrophysiological technique and computational modeling method to study the celluar and network mechanisms under lying information processing anf also study how such neural signals are most effciently stored as memory in the neural network via synaptic plasticty.        

Min Lab 지도교수 민병경

Our lab aims to study the relationship between mind and brain, and ultimately to make useful applications based on the acquired knowledge for the practical purpose. Particularly using EEG, we have investigated several topics related to the human intentional mental property. We have tried to find their electrophysiological correlates, which can be consequently employed as potent EEG parameters to cognitively control the BCI in advance of events. In parallel, using focused-ultrasound, we have also studied how to modulate neural activity in a non-invasive manner, leading to changes in cognitive and behavioral responses. Taken together, using both EEG-based BCI and FUS-based CBI, we`d like to make a new technology of the brain-brain interface, by which people can communicate with each other directly from one brain to another.

Clinical Neuro Modeling Lab 지도교수 김동주

Clinical Neuro Modeling lab investigates brain features associated with various neuro -pathologies [head injury and hydrocephalus], dericed using novel methods and focused on two different approachesL global and structural. In the global approach, the relationship between neurophysiologic. volume and pressure response is computationally analysed in terms of cerebrospinal. volume-pressure compensatory reserve or brain compartmental compliances. Continuos monitor of neurophysiologic signals and Cerebrosponal fiuid[CSF] ressure. These hold the porential to improbe treatment for parients.        

Machine Intelligence Lab 지도교수 석흥일

The Machine Intelligence Laboratory (MiLab) is devoted to the development of computational models for various researches in the brain and cognitive engineering field. Specifically, we focus on 1) machine learning algorithms for data analysis and pattern identification, 2) brain disease/disorder diagnosis or prognosis by analyzing complex patterns inherent in neuroimaging and/or genetic data, and 3) non-invasive brain-computer interfaces to enhance human performance.
       

Neurotechnology Lab 지도교수 Klaus-Robert Müller

The Neurotechnolgy Lab was founded in March 2012 as one of five new research labs within the newly established Department of Brain and Cognitive Engineering sponsored by the Korean World-Class-University Programme. The scientific goal of the deoartmant is fundamental theortical and pracrical research in the field of machine learning and signal processing anf its generic application in the sciences and technology. Moreover, machine learning will be applied to gain a deeper understanding of cognitive brain--brain computer interfacing -- using EEG and NIRS.