Purpose

Here we aimed to automatically classify human emotion earlier than is typically attempted. There is increasing evidence that the human brain differentiates emotional categories within 100–300 ms after stimulus onset. Therefore, here we evaluate the possibility of automatically classifying human emotions within the first 300 ms after the stimulus and identify the time-interval of the highest classification performance.

Methods

To address this issue, MEG signals of 17 healthy volunteers were recorded in response to three different picture stimuli (pleasant, unpleasant, and neutral pictures). Six Linear Discriminant Analysis (LDA) classifiers were used based on two binary comparisons (pleasant versus neutral and unpleasant versus neutral) and three different time-intervals (100–150 ms, 150–200 ms, and 200–300 ms post-stimulus). The selection of the feature subsets was performed by Genetic Algorithm and LDA.

Results

We demonstrated significant classification performances in both comparisons. The best classification performance was achieved with a median AUC of 0.83 (95 %- CI [0.71; 0.87]) classifying brain responses evoked by unpleasant and neutral stimuli within 100–150 ms, which is at least 850 ms earlier than attempted by other studies.

Conclusion

Our results indicate that using the proposed algorithm, brain emotional responses can be significantly classified at very early stages of cortical processing (within 300 ms). Moreover, our results suggest that emotional processing in the human brain occurs within the first 100–150 ms.

中文翻译：

---

皮层处理早期阶段的自动情绪分类：一项 MEG 研究

目的

在这里，我们旨在比通常尝试更早地对人类情感进行自动分类。越来越多的证据表明，人脑在刺激开始后 100-300 毫秒内区分情绪类别。因此，在这里我们评估在刺激后的前 300 毫秒内自动分类人类情绪的可能性，并确定最高分类性能的时间间隔。

方法

为了解决这个问题，记录了 17 名健康志愿者的 MEG 信号以响应三种不同的图片刺激（令人愉快的、令人不快的和中性的图片）。基于两个二元比较（愉快与中性和不愉快与中性）和三个不同的时间间隔（100-150 毫秒、150-200 毫秒和刺激后 200-300 毫秒）使用六个线性判别分析 (LDA) 分类器. 特征子集的选择由遗传算法和 LDA 执行。

结果

我们在两个比较中都展示了显着的分类性能。中位 AUC 为 0.83（95 %- CI [0.71; 0.87]），对 100-150 毫秒内由不愉快和中性刺激引起的大脑反应进行分类，这实现了最佳分类性能，这比其他研究尝试的时间至少早 850 毫秒.

结论

我们的结果表明，使用所提出的算法，可以在皮层处理的早期阶段（300 毫秒内）对大脑情绪反应进行显着分类。此外，我们的结果表明，人脑中的情绪处理发生在前 100-150 毫秒内。