Papers
1
Total Citations
36
H-Index
1
About
Qile Liu is a rising researcher in affective computing and brain-computer interfaces, with a focus on advancing emotion recognition through electroencephalography (EEG) signal processing. Their key research areas include deep learning architectures for temporal and spatial feature extraction, cross-subject generalization in neural decoding, and the integration of convolutional and transformer models for physiological signal analysis. Liu’s most notable contribution is the development of a Temporal aware Mixed Attention-based Convolution and Transformer Network, a pioneering framework that addresses the critical challenge of cross-subject variability in EEG-based emotion recognition. This work, published in 2024 and already accumulating 36 citations, demonstrates how hybrid attention mechanisms can simultaneously capture local temporal patterns and long-range dependencies in neural signals, significantly improving classification accuracy across different individuals. By bridging the gap between convolutional and transformer architectures, Liu has provided a robust solution for real-world affective computing applications, such as adaptive human-computer interaction and mental health monitoring. Their research holds promise for making emotion-aware systems more reliable and personalized, marking Liu as an emerging leader in the intersection of deep learning and neurotechnology.
Research Focus
Key Achievements
Top Papers
- 1