A Multi-Scale Temporal Framework with Dynamic Fusion for EEG-Based Emotion Recognition
2026-08-10 • Artificial Intelligence
Artificial IntelligenceMachine LearningSound
AI summaryⓘ
The authors studied how to recognize emotions, including mixed feelings, using brain signals called EEG. They created a new method that looks at the brain activity over different time periods instead of just one fixed window. Their model combines information from these different time scales in a smart way, which helped improve accuracy in guessing emotions compared to simpler methods. The results show better performance for both two-emotion and three-emotion categories, though the method requires more computing power.
EEGemotion recognitionmixed emotionstemporal windowsattention-based encoderdynamic fusionsubject-independent protocolbinary classificationmulti-scale analysiscomputational cost
Authors
Stefanos Gkikas, Yang Guo, Guangliang Li, Raul Fernandez Rojas, Giorgos Giannakakis, Randy Gomez
Abstract
Mixed emotions represent a clinically relevant but still underexplored target for automatic emotion recognition. EEG provides millisecond-level access to neural activity, yet most EEG pipelines analyze the signal through a single temporal window, thereby fixing the temporal structure available to the model. This study introduces a multi-scale temporal framework for EEG-based emotion recognition. The EEG waveform is decomposed into windows of one or several durations, processed by a shared attention-based encoder, and integrated through a dynamic fusion module that assigns sample-specific weights across temporal scales. The framework is evaluated under a subject-independent protocol in binary and three-class settings, with the three-class task including the mixed affective category. The best results are 65.22% for the two-class task and 45.43% for the three-class task. Both are obtained with three-scale dynamic-fusion configurations and remain substantially above the full-signal baseline. The best-performing temporal scales differ between the two tasks. Dynamic fusion outperforms concatenation in the highest-scoring two-class configuration and slightly exceeds it in the highest-scoring three-class configuration, although these multi-scale settings require substantially more computation than the full-signal baseline.