Applied Intelligence, Год журнала: 2025, Номер 55(7)
Опубликована: Апрель 28, 2025
Язык: Английский
Applied Intelligence, Год журнала: 2025, Номер 55(7)
Опубликована: Апрель 28, 2025
Язык: Английский
Frontiers in Human Neuroscience, Год журнала: 2025, Номер 19
Опубликована: Фев. 26, 2025
With the rapid development of deep learning, Electroencephalograph(EEG) emotion recognition has played a significant role in affective brain-computer interfaces. Many advanced models have achieved excellent results. However, current research is mostly conducted laboratory settings for induction, which lacks sufficient ecological validity and differs significantly from real-world scenarios. Moreover, are typically trained tested on datasets collected environments, with little validation their effectiveness situations. VR, providing highly immersive realistic experience, an ideal tool emotional research. In this paper, we collect EEG data participants while they watched VR videos. We propose purely Transformer-based method, EmoSTT. use two separate Transformer modules to comprehensively model temporal spatial information signals. validate EmoSTT passive paradigm environment active dataset environment. Compared state-of-the-art methods, our method achieves robust classification performance can be well transferred between different elicitation paradigms.
Язык: Английский
Процитировано
0Frontiers in Genetics, Год журнала: 2025, Номер 16
Опубликована: Апрель 15, 2025
Long noncoding RNAs (lncRNAs) regulate physiological processes via interactions with macromolecules such as miRNAs, proteins, and genes, forming disease-associated regulatory networks. However, predicting lncRNA-disease associations remains challenging due to network complexity isolated entities. Here, we propose MVIGCN, a graph convolutional (GCN)-based method integrating multimodal data predict these associations. Our framework constructs heterogeneous combining disease semantics, lncRNA similarity, miRNA-lncRNA-disease address isolation issues. By modeling topological features multiscale relationships through deep learning attention mechanisms, MVIGCN prioritizes critical nodes edges, enhancing prediction accuracy. Cross-validation demonstrated improved reliability over single-view methods, highlighting its potential identify disease-related biomarkers. This work advances network-based computational strategies for decoding functions in biology provides scalable tool prioritizing therapeutic targets.
Язык: Английский
Процитировано
0Applied Intelligence, Год журнала: 2025, Номер 55(7)
Опубликована: Апрель 28, 2025
Язык: Английский
Процитировано
0