• 제목/요약/키워드: ${\alpha}-{\beta}-{\gamma}$ filter

검색결과 13건 처리시간 0.022초

Precise spectral analysis using a multiple band-pass filter for flash-visual evoked potentials

  • Asano, Fumitaka;Shimoyama, Ichiro;Kasagi, Yasufumi;Lopez, Alex
    • 한국감성과학회:학술대회논문집
    • /
    • 한국감성과학회 2002년도 춘계학술대회 논문집
    • /
    • pp.44-50
    • /
    • 2002
  • The fast Fourier transform (FFT) is a good method to estimate spectral density, but the frequency resolution is limited to the sampling window, and thus the precise characteristics of the spectral density for short signals are not clear. To solve the limitation, a multiple band-pass filter was introduced to estimate the precise time course of the spectral density for flash visual evoked potentials (VEPs). Signals were recorded during -200 and 600 ms using balanced noncephalic electrodes, and sampled at 1 K Hz in 12 bits. With 1 Hz and 10 ms resolutions, spectral density was estimated between 10 and 100 Hz. Background powers at the alpha-and beta-bands were high over the posterior scalp, and powers around 200ms were evoked at the same bands over the same region, corresponding to P110 and N165 of VEPs. normalized's spectral density showed evoked powers around 200 ms and suppressed powers following the evoked powers over the posterior scalp. The evoked powers above the 20Hz band were not statistically significant. However, the gamma band was significantly evoked intra-individually; details in the gamma bands were varied among the subjects. Details of spectral density were complicated even for a simple task such as watching flashes; both synchronization and desynchronization occurred with different distributions and different time courses.

  • PDF

안정 상태에서의 정량 뇌파를 이용한 기계학습 기반의 경도인지장애 환자의 감별 진단 모델 개발 및 검증 (Development and Validation of a Machine Learning-based Differential Diagnosis Model for Patients with Mild Cognitive Impairment using Resting-State Quantitative EEG)

  • 문기욱;임승의;김진욱;하상원;이기원
    • 대한의용생체공학회:의공학회지
    • /
    • 제43권4호
    • /
    • pp.185-192
    • /
    • 2022
  • Early detection of mild cognitive impairment can help prevent the progression of dementia. The purpose of this study was to design and validate a machine learning model that automatically differential diagnosed patients with mild cognitive impairment and identified cognitive decline characteristics compared to a control group with normal cognition using resting-state quantitative electroencephalogram (qEEG) with eyes closed. In the first step, a rectified signal was obtained through a preprocessing process that receives a quantitative EEG signal as an input and removes noise through a filter and independent component analysis (ICA). Frequency analysis and non-linear features were extracted from the rectified signal, and the 3067 extracted features were used as input of a linear support vector machine (SVM), a representative algorithm among machine learning algorithms, and classified into mild cognitive impairment patients and normal cognitive adults. As a result of classification analysis of 58 normal cognitive group and 80 patients in mild cognitive impairment, the accuracy of SVM was 86.2%. In patients with mild cognitive impairment, alpha band power was decreased in the frontal lobe, and high beta band power was increased in the frontal lobe compared to the normal cognitive group. Also, the gamma band power of the occipital-parietal lobe was decreased in mild cognitive impairment. These results represented that quantitative EEG can be used as a meaningful biomarker to discriminate cognitive decline.

기계학습 알고리즘에 기반한 뇌파 데이터의 감정분류 및 정확도 향상에 관한 연구 (A research on the emotion classification and precision improvement of EEG(Electroencephalogram) data using machine learning algorithm)

  • 이현주;신동일;신동규
    • 인터넷정보학회논문지
    • /
    • 제20권5호
    • /
    • pp.27-36
    • /
    • 2019
  • 본 연구에서는 공개된 뇌파 데이터인 DEAP(A Database for Emotion Analysis using Physiological Signals) 데이터 세트를 활용한 감정분류 분석 및 정확도 향상에 대한 실험을 진행하였다. 실험에는 32명에 대한 32개의 뇌파측정 채널 데이터가 모두 사용되었다. 전처리과정에서는 뇌파 데이터에 대한 256Hz 샘플링작업을 진행하였고, 유한 임펄스 응답 필터를 사용하여 주파수 대역별로 쎄타(4-8Hz), 슬로 알파(8-10Hz), 알파(8-12Hz), 베타(12-30Hz), 감마(31-45Hz) 파형에 대한 데이터를 추출하였다. 추출한 데이터는 시간-주파수 변형을 통하여 데이터의 상태를 구분한 후에, 독립성분분석방법을 통해 잡음(Artifact)을 제거하여 데이터를 정제했다. 도출된 데이터는 분류기 기계학습 알고리즘 실험을 시행할 수 있도록 CSV 파일로 변형 하였으며, 감정분류에는 Arousal-Valence 평면을 사용하였다. 감정은 "긍정적(Positive)", "부정적(Negative)" 이외에 평온한 상태로 존재하는 "중립적(Neutral)"의 3가지 상태로 분류하였다. 정확도를 개선하기 위해서 랜덤 포레스트(Random Forest) 알고리즘에 속성 선택적 분류기(Attribute Selected Classifier: ASC) 방식에 의해 선택된 속성을 적용하여 실험하였다. 정확도는 "각성(Arousal)" 부분에서 Koelstra의 결과보다 "32.48%" 높은 결과가 도출되었고, Liu의 실험의 "정서가(Valence)"와 비교해보면 ASC(Random Forest) 결과가 "8.13%" 더 높은 결과를 도출하였다. 정확도를 개선하기 위해 ASC 방식을 적용한 랜덤 포레스트 분류기 실험결과에서는 전체평균을 기준으로 기존 연구 결과와 대비하여 "2.68%" 높은 정확도가 도출되었다.