计算机科学
一般化
对抗制
领域(数学分析)
算法
图形
人工智能
图论
理论计算机科学
数据建模
模式识别(心理学)
电子邮件
算法设计
频域
泛化误差
信号处理
近似算法
作者
Yuchang Zhao,Chang Li,Le Wu,Yikai Gao,Xun Chen
标识
DOI:10.1109/jsen.2026.3709840
摘要
Predicting seizures using electroencephalogram (EEG) data offers significant potential to enhance patient safety and quality of life. Despite recent advancements in prediction accuracy, most current studies rely on target-patient data, imposing a substantial data burden on target patients and making it difficult to meet the requirements of clinical cold-start scenarios. To this end, we propose a balanced graph convolutional adversarial (BGCA) domain generalization (DG) model, termed BGCA, which predicts seizures in new patients using a model trained on existing patient data, thereby eliminating the data burden of new patients. In particular, BGCA constructs an instance graph from time–frequency features and employs a graph convolutional network to integrate structural information with spectrogram features, enabling multidimensional generalizable feature learning. A balanced domain–class alignment loss is designed to explicitly model domain–class pairs, enhance the similarity of same-class representations across patients, separate different-class representations, and alleviate both interpatient and class imbalance during knowledge transfer. Moreover, the proposed method incorporates multidomain adversarial learning to suppress patient-specific information and promote the construction of domain-invariant representations. Experiments on the Children’s Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) scalp EEG database and Freiburg databases show that BGCA improves the area under the curve (AUC) by 7.6% and 5.8% on CHB-MIT and Freiburg, respectively, compared with the strongest baseline method, while achieving a better balance between sensitivity (Sens) and false positive rate (FPR). These results demonstrate the effectiveness and practical potential of BGCA for patient-independent seizure prediction.
科研通智能强力驱动
Strongly Powered by AbleSci AI