Li Rui, Ren Chao, Zhang Xiaowei, Hu Bin
Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, China.
Comput Biol Med. 2022 Jan;140:105080. doi: 10.1016/j.compbiomed.2021.105080. Epub 2021 Nov 26.
Emotion recognition is a vital but challenging step in creating passive brain-computer interface applications. In recent years, many studies on electroencephalogram (EEG)-based emotion recognition have been conducted. Ensemble learning has been widely used in emotion recognition because of its superior accuracy and generalization. In this study, we proposed a novel ensemble learning method based on multiple objective particle swarm optimization for subject-independent EEG-based emotion recognition. First, we used a 4 s sliding time window with a 2 s overlap to extract 13 different features from EEG signals and construct a feature vector. Then, we employed L1 regularization to select effective features. Second, a model selection method was applied to choose the optimal basic analysis submodels. Afterward, we proposed an ensemble operator that converts the classification results of a single model from discrete values to continuous values to better characterize the classification results. Subsequently, multiple objective particle swarm optimization was adopted to confirm the optimal parameters of the ensemble learning model. Finally, we conducted extensive experiments on two public datasets: DEAP and SEED. Considering the generalization of the model, we applied leave-one-subject-out cross-validation to evaluate the performance of the model. The experimental results demonstrate that the proposed method achieves a better recognition performance than single methods, commonly used ensemble learning methods, and state-of-the-art methods. The average accuracies for arousal and valence are 65.70% and 64.22%, respectively, on the DEAP database, and the average accuracy on the SEED database is 84.44%.
情感识别是创建被动式脑机接口应用程序中至关重要但具有挑战性的一步。近年来，已经开展了许多基于脑电图（EEG）的情感识别研究。集成学习因其卓越的准确性和泛化能力而在情感识别中得到广泛应用。在本研究中，我们提出了一种基于多目标粒子群优化的新型集成学习方法，用于基于EEG的独立于个体的情感识别。首先，我们使用一个4秒的滑动时间窗口，重叠2秒，从EEG信号中提取13种不同特征并构建一个特征向量。然后，我们采用L1正则化来选择有效特征。其次，应用一种模型选择方法来选择最优的基本分析子模型。之后，我们提出了一种集成算子，将单个模型的分类结果从离散值转换为连续值，以更好地表征分类结果。随后，采用多目标粒子群优化来确定集成学习模型的最优参数。最后，我们在两个公共数据集DEAP和SEED上进行了广泛的实验。考虑到模型的泛化能力，我们应用留一法交叉验证来评估模型的性能。实验结果表明，所提出的方法比单一方法、常用的集成学习方法和当前的先进方法具有更好的识别性能。在DEAP数据库上，唤醒度和效价的平均准确率分别为65.70%和64.22%，在SEED数据库上的平均准确率为84.44%。
