CAJ | 학술논문

为了分析语言想像所诱导的脑电信号的时间和频率特性，利用事件相关谱扰动（ERSP）对信号进行时频分析．首先，经ERSP确定能量波动的频率范围；然后，根据该频率范围计算信号的事件相关（去）同步（ERD／ERS ），并利用共空间模式和支持向量机分别对单次实验数据的特征值进行提取和分类．对8位被试的试验结果分析表明，被试间的频率范围具有显著的差异，其中4位被试的频率范围含有α波，3位被试含有α波和β波，1位被试的脑电信号在默读汉字时无明显变化．2个汉字默读时的脑电信号可产生相似的ERD／ERS ．优化频率范围后针对这2个汉字的平均分类正确率分别提高了2.25％和1.39％．时频分析能更好地显示脑电信号的能量变化率，并能改善语言想像脑机接口的性能．
위료분석어언상상소유도적뇌전신호적시간화빈솔특성，이용사건상관보우동（ERSP）대신호진행시빈분석．수선，경ERSP학정능량파동적빈솔범위；연후，근거해빈솔범위계산신호적사건상관（거）동보（ERD／ERS ），병이용공공간모식화지지향량궤분별대단차실험수거적특정치진행제취화분류．대8위피시적시험결과분석표명，피시간적빈솔범위구유현저적차이，기중4위피시적빈솔범위함유α파，3위피시함유α파화β파，1위피시적뇌전신호재묵독한자시무명현변화．2개한자묵독시적뇌전신호가산생상사적ERD／ERS ．우화빈솔범위후침대저2개한자적평균분류정학솔분별제고료2.25％화1.39％．시빈분석능경호지현시뇌전신호적능량변화솔，병능개선어언상상뇌궤접구적성능．
To analyze time and frequency characteristics of electroencephalography signals induced by speech imagery,event-related spectral perturbation (ERSP)is used in the time-frequency analy-sis of signals.First,the frequency range of the energy fluctuation can be determined by ERSP. Then,according to the frequency range,event-related (de)synchronization (ERD/ERS)of the sig-nals is calculated,and the eigenvalues of each experimental data are extracted and classified by com-mon spatial pattern and support vector machine,respectively.The results of eight subjects show that the frequency ranges are obviously different among subjects.The ranges of four subjects include αrhythm and those of three subjects include αand βrhythms.The electroencephalography signals of one subject do not evidently change when he reads a Chinese character in mind.The similar ERD/ERS of electroencephalography signals may produce while reading two Chinese characters in mind. After optimizing the frequency ranges,the average classification accuracy for the two characters are improved by 2. 25% and 1. 39%,respectively.The energy gradient of electroencephalography sig-nals can be exhibited better by time-frequency analysis,and the performance of speech imagery based brain-computer interfaces can be also improved.