Electroencephalogram (EEG) based emotional analysis has been employed in medical science, security and human-computer interaction with good success. In the recent past, deep learning-based approaches have significantly improved the classification accuracy when compared to classical signal processing and machine learning based frameworks. But most of them were subject-dependent studies which were not able to generalize on the subject-independent tasks due to the inter-subject variability in EEG. In this work, a novel deep learning framework capable of doing subject-independent emotion recognition is presented, consisting of two parts. First, an unsupervised Long Short-Term Memory (LSTM) with channel-attention autoencoder is proposed for getting a correlated lower dimensional latent space representation of the EEG data for each subject. Secondly, a convolutional neural network (CNN) with attention framework, which takes the first component as input, is presented for performing the task of subject-independent emotion recognition. With the attention mechanism, the proposed approach could highlight the channel of interest as well as the temporal localization of the EEG signal, which contributes to the emotion under consideration as validated by the results. The proposed approach has been validated using various widely employed datasets for EEG signals including DEAP dataset, SEED dataset and CHB-MIT dataset. With proposed methodology, average subject independent accuracies of 65.9%, 69.5% for valence and arousal classification in the DEAP dataset, 76.7% for positive-negative classification in SEED dataset is obtained and further for the CHB-MIT dataset average subject independent accuracies of 69.1%, 67.6%, 72.3% for Pre-Ictal Vs Ictal, Inter-Ictal Vs Ictal, Pre-Ictal Vs Inter-Ictal classification is obtained.

翻译：在医学、安全和人体计算机互动中,基于电动图(EEEG)的情感分析被运用在医学、安全和人体计算机互动中,取得了良好的成功。最近,深层次的基于学习的方法与古典信号处理和机器学习框架相比,大大提高了分类的准确性。但是,大多数这些方法都是基于主题的研究,由于EEEG的跨主题变异性,无法对独立的主题任务进行概括化分析。在这项工作中,提出了能够进行独立情感识别的新型深层次学习框架,由两部分组成。首先,一个未经监控的长期短期内存(LSTM),由频道使用自动自动读取的自动读取器(LSTM),用来获取EEEG数据的相对较低维基层空间。第二,一个带有关注框架的共变神经网络(CNN),将第一个组成部分作为投入,用来执行依赖主题的情感识别任务。在关注机制下,拟议的方法可以突出兴趣的渠道,以及电子EG的及时本地化(EG) 和时间性分类信号(EEEA的确认结果中的情感),包括SEEB平均数据方法。