IEEE Trans Neural Syst Rehabil Eng. 2018 Aug;26(8):1481-1494. doi: 10.1109/TNSRE.2018.2850308. Epub 2018 Jun 25.
Intelligent recognition of electroencephalogram (EEG) signals is an important means to detect seizure. Traditional methods for recognizing epileptic EEG signals are usually based on two assumptions: 1) adequate training examples are available for model training and 2) the training set and the test set are sampled from data sets with the same distribution. Since seizures occur sporadically, training examples of seizures could be limited. Besides, the training and test sets are usually not sampled from the same distribution for generic non-patient-specific recognition of EEG signals. Hence, the two assumptions in traditional recognition methods could hardly be satisfied in practice, which results in degradation of model performance. Transfer learning is a feasible approach to tackle this issue attributed to its ability to effectively learn the knowledge from the related scenes (source domains) for model training in the current scene (target domain). Among the existing transfer learning methods for epileptic EEG recognition, transductive transfer learning fuzzy systems (TTL-FSs) exhibit distinctive advantages-the interpretability that is important for medical diagnosis and the transfer learning ability that is absent from traditional fuzzy systems. Nevertheless, the transfer learning ability of TTL-FSs is restricted to a certain extent since only the discrepancy in marginal distribution between the training data and test data is considered. In this paper, the enhanced transductive transfer learning Takagi-Sugeno-Kang fuzzy system construction method is proposed to overcome the challenge by introducing two novel transfer learning mechanisms: 1) joint knowledge is adopted to reduce the discrepancy between the two domains and 2) an iterative transfer learning procedure is introduced to enhance transfer learning ability. Extensive experiments have been carried out to evaluate the effectiveness of the proposed method in recognizing epileptic EEG signals on the Bonn and CHB-MIT EEG data sets. The results show that the method is superior to or at least competitive with some of the existing state-of-art methods under the scenario of transfer learning.
脑电信号的智能识别是检测癫痫发作的重要手段。传统的癫痫脑电信号识别方法通常基于两个假设：1）有足够的训练样本用于模型训练；2）训练集和测试集是从具有相同分布的数据集中采样得到的。由于癫痫发作是偶发性的，因此癫痫发作的训练样本可能是有限的。此外，由于通用的非患者特定的脑电信号识别，训练集和测试集通常不是从同一分布中采样得到的。因此，传统识别方法中的两个假设在实践中很难得到满足，这导致模型性能下降。迁移学习是解决这个问题的一种可行方法，因为它能够有效地从当前场景（目标域）的相关场景（源域）中学习知识进行模型训练。在现有的癫痫脑电识别迁移学习方法中，有向迁移学习模糊系统（TTL-FSs）表现出独特的优势——对医疗诊断很重要的可解释性和传统模糊系统所缺乏的迁移学习能力。然而，TTL-FSs 的迁移学习能力受到一定程度的限制，因为只考虑了训练数据和测试数据之间边缘分布的差异。本文提出了一种增强的有向迁移学习 Takagi-Sugeno-Kang 模糊系统构建方法，通过引入两种新的迁移学习机制来克服这一挑战：1）采用联合知识来减少两个领域之间的差异；2）引入迭代迁移学习过程来增强迁移学习能力。在 Bonn 和 CHB-MIT EEG 数据集上进行了广泛的实验，以评估该方法在识别癫痫脑电信号方面的有效性。结果表明，该方法在迁移学习场景下优于或至少与一些现有的最先进方法具有竞争力。
