TS-DRN: An EEG Recognition Algorithm for Art Design Decisions Making

Electroencephalogram (EEG) technology is vital in art design decisions making and has become a prevalent research trend. However, With the temporal variability in EEG signals, there is a problem of low model prediction accuracy. Therefore, We propose an EEG signal recognition algorithm called the Time-Slicing and Deep Residual Network (TS-DRN). First, we present the subjects with the patterns of different styles of designs to capture their EEG signals. Second, we employ the time-slicing strategy to process the original signal, enhancing the number of training samples and reducing the sample features' dimensionality. Finally, we use the combined EEG feature maps as inputs to the deep residual network to obtain the classification results. Our experimental results demonstrate that this paper's EEG signal classification accuracy is 85.8%, demonstrating our method's effectiveness for EEG signal classification.