Nowadays, the recognition of emotions in people with sensory disabilities still represents a challenge due to the difficulty to generalize and model the set of brain signals. In recent years, the technology that has been used to study a person's behaviour and emotions based on brain signals is the Brain-Computer Interface. Although previous works have already proposed the classification of emotions in people with sensory disabilities using machine learning techniques, a model of recognition of emotions in people with visual disabilities has not yet been evaluated. Consequently, in this work, the authors present a two-fold framework focused on people with visual disabilities. Firstly, auditory stimuli have been used, and a component of acquisition and extraction of brain signals has been defined. Secondly, analysis techniques for the modelling of emotions have been developed, and machine learning models for the classification of emotions have been defined. Based on the results, the algorithm with the best performance in the validation is Random-Forest, with an accuracy of 85% and 88% in the classification for negative and positive emotions, respectively. According to the results, the framework is able to classify positive and negative emotions, but the experimentation performed also shows that the framework performance depends on the number of features in the dataset and the quality of the EEG signals is a determining factor.

中文翻译：

---

通过大脑信号对视力障碍者的情绪进行分类的框架

如今，由于难以对大脑信号进行概括和建模，对感觉障碍患者的情绪识别仍然是一个挑战。近年来，基于大脑信号来研究人的行为和情绪的技术是脑机接口。尽管之前的工作已经提出使用机器学习技术对感觉障碍者的情绪进行分类，但尚未评估视觉障碍者的情绪识别模型。因此，在这项工作中，作者提出了一个针对视力障碍人士的双重框架。首先，使用听觉刺激，并定义了脑信号采集和提取的组成部分。其次，开发了用于情绪建模的分析技术，并定义了用于情绪分类的机器学习模型。根据结果​​，验证中性能最好的算法是随机森林，其对消极情绪和积极情绪的分类准确率分别为 85% 和 88%。根据结果​​，该框架能够对积极和消极情绪进行分类，但进行的实验还表明，框架性能取决于数据集中的特征数量，而脑电图信号的质量是决定因素。