Abstract:Real-time cognitive load assessment from eye-tracking signals could potentially enable adaptive human-centered-AI such as safety-critical applications such as driver vigilance monitoring or automated flight deck assistance, yet two challenges persist: handling frequent data missingness from blinks and tracking failures, and efficiently modeling long-range temporal dependencies. We propose MambaGaze, a framework that addresses these challenges through 1) XMD encoding, which augments raw features with observation masks and time-deltas to explicitly model data uncertainty, and 2) bidirectional Mamba-2, which captures temporal dependencies with linear computational complexity. Experiments on CLARE and CL-Drive datasets under leave-one-subject-out evaluation show that MambaGaze achieves 76.8% and 73.1% accuracy, respectively, outperforming CNN, Transformer, ResNet, and VGG baselines by 4-12 percentage points. Edge deployment benchmarks on NVIDIA Jetson platforms demonstrate real-time inference at 43-68 FPS with power consumption below 7.5W, confirming feasibility for wearable cognitive load monitoring.
| Comments: | Submitted to IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI 2026) |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| ACM classes: | I.2.6; I.5.4; H.1.2 |
| Cite as: | arXiv:2605.22775 [cs.LG] |
| (or arXiv:2605.22775v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.22775 arXiv-issued DOI via DataCite (pending registration) |
From: Amir Mousavi Seyed [view email]
[v1]
Thu, 21 May 2026 17:33:41 UTC (9,295 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。