EEG-based lapse detection with high temporal resolution
EEG-based lapse detection with high temporal resolution
复制标题
DOI：
10.1109/tbme.2007.893452
复制
发表时间：
2007-05-01
影响因子：
4.6
通讯作者：
Peiris, Malik T. R.
中科院分区：
文献类型：
--
作者：
Davidson, Paul R.;Jones, Richard D.;Peiris, Malik T. R.
一个能够可靠地检测响应失误（失误）的警报系统有可能防止许多致命事故。我们已经开发了一个系统，能够检测失误，在第二规模的时间分辨率实时。数据来自15名受试者，他们进行了两次1小时的视觉跟踪任务，同时进行脑电图（EEG）和面部视频记录。该检测器使用神经网络，其具有来自两个双极EEG推导的归一化EEG对数功率谱输入，尽管我们也考虑了多通道检测器。使用视频评级和跟踪行为的组合识别的失误被用来训练我们的检测器。我们比较了使用抽头延迟线线性感知器，抽头延迟线多层感知器（TDL-MLP）和以1 Hz连续运行的长短期记忆（LSTM）递归神经网络的检测器。与仅使用最近的估计相比，使用失效前4 s的EEG对数功率谱估计可改善检测。我们报告了LSTM在EEG分析问题中的首次应用。LSTM的性能相当于最好的TDL-MLP网络，但不需要输入缓冲区。总体性能令人满意，接受者操作特征分析的曲线下面积为0.84 +/- 0.02（平均值+/- SE），精确度-召回率曲线下面积为0.41 +/- 0.08。
A warning system capable of reliably detecting lapses in responsiveness (lapses) has the potential to prevent many fatal accidents. We have developed a system capable of detecting lapses in real-time with second-scale temporal resolution. Data was from 15 subjects performing a visuomotor tracking task for two 1-hour sessions with concurrent electroencephalogram (EEG) and facial video recordings. The detector uses a neural network with normalized EEG log-power spectrum inputs from two bipolar EEG derivations, though we also considered a multichannel detector. Lapses, identified using a combination of video rating and tracking behavior, were used to train our detector. We compared detectors employing tapped delay-line linear perceptron, tapped delay-line multilayer perceptron (TDL-MLP), and long short-term memory (LSTM) recurrent neural networks operating continuously at 1 Hz. Using estimates of EEG log-power spectra from up to 4 s prior to a lapse improved detection compared with only using the most recent estimate. We report the first application of a LSTM to an EEG analysis problem. LSTM performance was equivalent to the best TDL-MLP network but did not require an input buffer. Overall performance was satisfactory with area under the curve from receiver operating characteristic analysis of 0.84 +/- 0.02 (mean +/- SE) and area under the precision-recall curve of 0.41 +/- 0.08.