Answers are grounded in this paper and cite their sources.
Introduction To address the issues of feature redundancy in the feature extraction process, as well as the fact that the simulation of biological neural activity remains limited in the SNN encoding layer and the lack of temporal information in the SNN encoding layer, the study proposes an adaptive evaluation model for stereoscopic visual comfort based on HHT-CSP-SSA and improved SNN (AHCSIS). Methods The model includes two innovative core modules. The feature extraction module of AHCSIS utilizes the Hilbert-Huang Transform (HHT) combined with Common Spatial Pattern (CSP) to adaptively extract time-frequency features from multiple brain regions, with optimal feature selection achieved using the Sparrow Search Algorithm (SSA). The classification module employs the spike encoding method based on the self-attention mechanism combined with a single neuron to generate temporal spike sequences that represent biological neural activity. Results The results demonstrate that the performance of the AHCSIS classification model (accuracy: 93.86%, precision: 93.12%) surpasses that of baseline and state-of-the-art models. Discussion The model adaptively extracts optimal features and encodes temporal spikes, which better reflect biological neural activity, providing a novel solution for evaluating stereoscopic visual comfort and discomfort.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: