Multi-label EEG dataset for classifying Mental Attention states (MEMA)
收藏资源简介:
MEMA数据集由西安交通大学计算机科学与技术学院创建,专门用于在线学习中精神注意力状态的多标签分类。数据集包含20名受试者的脑电信号,每个受试者参与12次试验,总计1060分钟的数据。数据集不仅包含脑电信号,还收集了情绪状态标签、基本个人信息和人格特质,以研究注意力与其他心理状态之间的关系。数据集通过多标签相关性研究进行了广泛的定量和定性分析,验证了脑电注意力数据的质量。该数据集的应用领域主要是在线学习中的注意力分类,旨在解决传统方法在评估学习者注意力状态时的失真问题。
The MEMA dataset was created by the School of Computer Science and Technology, Xi'an Jiaotong University, and is specifically designed for multi-label classification of mental attention states in online learning. The dataset contains electroencephalogram (EEG) signals from 20 subjects, with each subject participating in 12 trials, totaling 1060 minutes of data. In addition to EEG signals, the dataset also collects emotional state labels, basic personal information, and personality traits, aiming to explore the relationship between attention and other psychological states. Extensive quantitative and qualitative analyses have been conducted on the dataset through multi-label correlation studies, which validate the quality of the EEG-based attention data. The primary application of this dataset lies in attention classification in online learning, with the goal of addressing the distortion problem in traditional methods when assessing learners' attention states.




