基于小波分解和支持向量机的P300识别算法

针对支持向量机方法在P300识别中训练和识别速度相对较慢的不足,本研究提出了一种将小波分解与支持向量机相结合的P300识别方法。该方法通过小波分解实现脑电信号的特征提取,同时利用Span估计方法实现支持向量机最优参数的快速选择;然后借助支持向量机良好的分类性能实现P300的识别。本研究在BCICompetition 2003的P300实验数据集上对该方法进行了验证,结果表明,与传统支持向量机算法相比,本算法具有更高的训练和识别速度,并且在5次重复实验时达到了100%的识别准确率。     

Simulation Studies of Latency Measures of Components of the Event-Related Brain Potential

We compared the accuracy of P300 latency estimates obtained with different procedures under several simulated signal and noise conditions. Both preparatory and signal detection techniques were used. Preparatory techniques included frequency filters and spatial filters (single electrode selection and Vector filter). Signal detection techniques included peak-picking, cross-correlation, and Woody filter. Accuracy in the latency estimation increased exponentially as a function of the signal-to-noise ratio. Both Woody filter and cross-correlation provided better estimates than peak-picking, although this advantage was reduced by frequency filtering. For all signal detection techniques, Vector filter provided better estimates than single electrode selection. Large component overlap impaired the accuracy of the estimates obtained with both single electrode selection and Vector filter, but with Vector filter impairment occurred only when the overlapping component had a scalp distribution that was similar to the scalp distribution of the signal component. The effects of varying noise characteristics, P300 duration and latency, and the parameters of Vector filter were also investigated.     

Analyzing Event-Related Potentials: The Utility of High and Low Pass Filtering in Improving the Relationship Between Various Amplitude Measures and Principal Components Analysis Factor Scores

The present investigation sought to determine whether the relationship between event-related potential (ERP) principal components analysis (PCA) factor scores and analogous waveform amplitude measures could be improved by high- and low-pass filtering the waveforms at a suitable cutoff value. Visual oddball ERPs were submitted to a varimax-rotated PCA performed on the variance/covariance matrix. Principal components corresponding to P300 and Slow Wave were obtained. In keeping with the fact that the variance/covariance PCA analyzes sources of variance around the grand mean waveform, the grand mean waveform was subtracted from each of the original waveforms, and baseline-referenced amplitude measurements were then made of P300 and Slow Wave. P300 was measured both as the maximum positive peak between 275 and 425 ms, and as the average amplitude during that interval. Slow Wave was measured as the average amplitude during the interval 400–700 ms. The P300 measurements were then repeated after high-pass filtering the difference waveforms at 2 Hz. Slow Wave measurements were repeated after low-pass filtering at 2 Hz. The value of 2 Hz was chosen as giving a reasonable cutoff based upon estimates of the wavelengths of the two components derived from inspection of their respective factor loading vectors. The correlation between factor scores and amplitude measurements was .94 for unfiltered Slow Wave and actually declined slightly but significantly to .91 when the waveforms were low-pass filtered. It would appear that Slow Wave factor scores emerging from a PCA can be fairly well approximated by a time-band measurement algorithm, and that this approximation is not improved by low-pass filtering. For both filtered and unfiltered measurements of P300, the amplitude/factor score correlation was significantly higher for the time-band method than for the peak method. Further, high-pass filtering at 2 Hz improved the time-band/factor score correlation significantly from .62 to .75. This improvement is probably because the unfiltered measurements were tapping sources of variance due both to the higher frequency P300 component as well as a simultaneously active, lower frequency Slow Wave component. Theoretical implications of these findings are discussed.     

Perceptual and Motor Space Representation: An Event-Related Potential Study

The purpose of this experiment was to study the brain potentials generated during spatial tasks related to the “schema corporel” (a mental map of sensory-motor relationships). Seven right-handed subjects performed a choice reaction-time task (Experiment 1), in which the spatial position of a visual stimulus (right or left of a fixation point) was varied independently of the spatial position of the response (right or left hand). The subjects also made self-paced extensions and flexions of the right and left index fingers (Experiment 2). Experiments 1 and 2 were performed with the hands both crossed and uncrossed. Spatio-temporal maps showed that the P300 component elicited by the choice RT situation in Experiment 1 was largest ipsilateral to the hand involved in the response, whether or not the hands were crossed. The later part of the pre-movement potentials during Experiment 2 and the motor potential were significantly larger contralateral to the moving hand under all conditions. Thus this pattern of lateralization can be attributed to the superimposition of a bilateral P300 wave on the asymmetrical motor potential. This suggests that distinct neuronal populations are involved in the generation of these two components. P300 latency and RT reflected the spatial conflict: both were longer when the stimulus and response were on opposite sides than when they were on the same side, even when the hands were crossed. However, the average P300 latency was not increased when the hands were crossed, whereas the average RT was substantially increased. Since the additional time required for programming the movement in the crossed hand situation had no effect on P300 generation, we infer that the P300 does not index this motor programming. However, P300 does reflect the stimulus-response spatial matching, since its latency was delayed by spatial conflict.     

P300, Food Consumption, and Memory Performance

The effects of food intake on the P300 (P3) component of the event-related brain potential (ERP) were assessed in two studies. Experiment 1 compared 24 subjects who had not eaten within 6 hours of testing with 24 subjects who had consumed food within 3 hours of testing. P3 target stimulus amplitude was reduced significantly for the subjects who had not eaten relative to those who had eaten, whereas peak P3 latency was only moderately affected by the recency of food consumption over task conditions. In Experiment 2, P3 measurements, memory performance in a word recall task, and blood glucose levels were obtained from 24 subjects at three different times: 1) after a 14-hour fast, 2) 5 min after consuming lunch, and 3) 30 min after consuming lunch. P3 target stimulus amplitude increased initially after food intake and decreased slightly at the third measurement time, while peak P3 latency became somewhat shorter immediately after food intake but then returned to baseline. Recall for recently presented items mimicked the P3 amplitude changes, whereas blood glucose levels increased monotonically across food conditions. The results from both studies suggest that: 1) target stimulus P3 amplitude is affected by the recency of food intake; 2) food-related P3 amplitude changes appear related to memory function; and 3) subjects should eat within several hours before ERPs are acquired to ensure that P3 component measurements reflect values indicative of normal bodily functioning.     

Gender differences in late positive components evoked by human faces

Event-related potentials (ERPs) were recorded in male and female participants in response to 32 male and 32 female faces. Participants were instructed to simply look carefully at each face; after ERP collection they were asked to rate each face on a 5-point attractiveness scale. A positive correlation between average rating and average P300 scores to opposite sex faces was observed in male (r = .40) and in preovulatory (r = .41) and postovulatory (r = .44) female subjects. Correlations to same sex faces were only found in postovulatory females (r = .61). Male participants showed a much larger average P300 than did female participants, and the P300 evoked in female participants was unexpectedly larger to female than to male faces. Neither task relevance nor stimulus probability is a plausible explanations for these findings because they were experimentally controlled. These results support the emotional value hypothesis, according to which classical P300 processes reflect an affective evaluation of the stimulus, which in turn produces context updating.     

情感性精神障碍事件相关电位变异与自杀行为史的相关性

探讨情感性精神障碍患者件相关电位变异的临床意义。方法收集３９例抑郁相和２２例躁狂相患者,以３３例正常人为对照组,记录其事件相关电位Ｐ３００和ＣＮＶ。结论Ｐ３００和ＣＮＶ临床应用价值得到初步证实,自杀行为相关的生物学指标研究中需进一步重视。     

血管性痴呆的智能测验与P300的相关性

目的：观察血管性痴呆患者的智能测验分与事件相关电位Ｐ３００潜伏期的相关性。方法：应用长谷川信彦痴呆量表测验血管性痴呆组（２７例）和智能正常对照组（３３例）两组患者智能。同时检测两组患者Ｐ３００潜伏期,并观察两组患者测验与Ｐ３００潜伏期的相关性。结果：两组患者智能测验分有显著差异（Ｐ〈０．０１）,Ｐ３００潜伏期有显著差异（Ｐ〈０．０１）,智能测验分与Ｐ３００潜伏期呈明显负相关。结论：Ｐ３００潜伏期的     

轻、中度缺氧对事件相关电位的影响及不同刺激模式的比较

目的 观察轻、中度缺氧对脑事件相关电位（ＥＲＰ）的影响,比较不同刺激模式发的ＥＲＰ对缺氧的敏感性,方法１２名受试者在地面、２５００ｍ和４３００ｍ匠心同度（吸放低氧混合气）分别进行视觉Ｏｃｄｄｂａｌｌ、Ｓｔｅｒｎｂｅｒｇ记忆量（ＭＳＥＴ）为１ 和ＭＳＥＴ为３的任务测试,记录ＥＲＰ的Ｐ３潜伏期、波幅和反应时（ＲＴ）及反应错误率（ＥＲ）。结果 ４３００ｍ高度缺氧时Ｐ３潜伏期显著延长,任务难度较大时ＥＲ增