이를 위해, BSPL 연구실은 뇌영상 방법들 (MRI, EEG) 등에 다양한 신호처리, 머신러닝, 및 딥러닝 방법들을 접목하여서 인간의 뇌기능을 이해하는 연구를 수행합니다. 대표적인 분석 방법으로는, independent component analysis (ICA), independent vector analysis (IVA), deep neural networks (DNN) 등을 이용하고 있으며 새로운 아이디어를 추가하여 새롭게 개발하고 있습니다. 이러한 분석 방법을 뇌영상 데이터에 접목하여서, 인간의 뇌기능을 이해하고자 하며, 이를 바탕으로 뇌기능의 정량적 측정, 뇌기능 자동분류, 뇌기능 향상, 뇌기능 이상의 조기 진단 및 예후 예측 등의 연구를 수행하고, 이를 바탕으로 궁극적으로 인간의 삶의 질 향상을 위한 목표를 갖고 있습니다.
Our goal is to investigate brain functions measured via various neuroimaging modalities including MRI (MRI) and electroencephalography (EEG) employing various signal processing techniques, machine learning, and deep learning approaches. We have done some interesting works including the fMRI data analyses using novel analytical methods such as independent vector analysis (IVA), iterative dual-regression of group independent component analysis (ICA) with a sparse prior to better estimate true neuronal activity, recursive principal component analysis (PCA) to EEG-segments of simultaneous EEG-fMRI data, and deep neural network (DNN) to fMRI data. The developed methods would gainfully be applied to the neuroimaging data including fMRI, simultaneous EEG-fMRI, and real-time fMRI based neurofeedback method. Based on correct understanding of human brain functions, we would like to focus on the basic neuroscientific researches as well as brain engineering applications including the BCI/BMI and ultimately on preclinical applications to develop an option to diagnose and treat the various neuropsychiatric illnesses such as depression, schizophrenia, and substance abuse. We believe that the proper analytical methods to exploit the hidden information of the neuroimaging data would lead to better understanding of the human brain and to better engineer the brain and ultimately toward enhancement of quality of life.