A Conflict-aware Evidential Framework for Reliable Sleep Stage Classification
The paper introduces ConfSleepNet, a framework designed for reliable sleep stage classification by addressing conflicts in multi-modal data. It employs a two-phase approach that includes evidence extraction and conflict-aware aggregation to improve decision-making. The effectiveness of this framework is supported by both theoretical analysis and experimental results.
- ▪ConfSleepNet resolves inter-view conflicts in sleep stage classification.
- ▪The framework consists of multi-view evidence extraction and conflict-aware aggregation.
- ▪Experimental results demonstrate the effectiveness of ConfSleepNet in sleep staging tasks.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.17021 (cs) [Submitted on 16 May 2026] Title:A Conflict-aware Evidential Framework for Reliable Sleep Stage Classification Authors:Yunzhi Tian, Dekui Wang, Qirong Bu, Wei Zhou, Xingxing Hao, Jun Feng View a PDF of the paper titled A Conflict-aware Evidential Framework for Reliable Sleep Stage Classification, by Yunzhi Tian and Dekui Wang and Qirong Bu and Wei Zhou and Xingxing Hao and Jun Feng View PDF HTML (experimental) Abstract:Multi-view learning has been widely applied for sleep stage classification using multi-modal data. However, existing methods typically assume that different modalities are well-aligned, which is often unattainable in real-world scenarios, thereby compromising the reliability of the staging results.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
