Abstract
Convolutional Neural Networks (CNNs) have achieved remarkable performance breakthroughs in a variety of tasks. Recently, CNN-based methods that are fed with hand-extracted EEG features have steadily improved their performance on the emotion recognition task. In this paper, we propose a novel convolutional layer, called the Scaling Layer, which can adaptively extract effective data-driven spectrogram-like features from raw EEG signals. Furthermore, it exploits convolutional kernels scaled from one data-driven pattern to exposed a frequency-like dimension to address the shortcomings of prior methods requiring hand-extracted features or their approximations. ScalingNet, the proposed neural network architecture based on the Scaling Layer, has achieved state-of-the-art results across the established DEAP and AMIGOS benchmark datasets.
Original language | English |
---|---|
Pages (from-to) | 177-184 |
Number of pages | 8 |
Journal | Neurocomputing |
Volume | 463 |
DOIs | |
Publication status | Published - 6 Nov 2021 |
Externally published | Yes |
Keywords
- Convolutional Neural Networks
- Deep learning
- EEG
- Emotion recognition
- ScalingNet