Research map / Time series / Anomaly detection
Enhancing Sparse Event Detection in Healthcare Time-Series via Adaptive Gate of Context–Detail Interaction
Beomjun Bark, Yun Kwan Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add adaptive gating module (AGM) (ablation) | Proposed framework · MIT-BIH Class 3 | PW-F1: 49.97 -> 90.63 | Improved |
| add adaptive gating module (AGM) (ablation) | Proposed framework · SHDB-AF Class 5 | AF-F1: 61.20 -> 83.78 | Improved |
| add adaptive gating module (AGM) (ablation) | Proposed framework · OPP Class 5 | PW-F1: 51.36 -> 64.98 | Improved |
| add adaptive gating module (AGM) (ablation) | Proposed framework · WESAD Class 8 | AF-F1: 63.39 -> 74.29 | Improved |
| add conditional gate scaler (CGS) to PGI-only model (ablation) | Proposed framework · MIT-BIH Class 3 | PW-F1: 84.41 -> 90.63 | Improved |
| add conditional gate scaler (CGS) to PGI-only model (ablation) | Proposed framework · SHDB-AF Class 5 | PW-F1: 70.88 -> 83.41 | Improved |
| add positional Gaussian injection (PGI) to CGS-only model (ablation) | Proposed framework · MIT-BIH Class 3 | PW-F1: 84.68 -> 90.63 | Improved |
| add positional Gaussian injection (PGI) to CGS-only model (ablation) | Proposed framework · WESAD Class 8 | PW-F1: 61.67 -> 73.59 | Improved |
| add AGM (ablation) | Proposed framework · MIT-BIH Class 6 | PW-F1: 76.46 -> 83.37 | Improved |
| add AGM (ablation) | Proposed framework · MIT-BIH Class 15 | mAP: 43.44 -> 44.55 | No clear effect |
| use proposed framework instead of Deformable-DINO | DETR-based detectors · MIT-BIH Class 3 | PW-F1: 86.41 -> 90.63 | Improved |
| use proposed framework instead of Deformable-DINO | DETR-based detectors · SHDB-AF Class 5 | PW-F1: 66.03 -> 83.41 | Improved |
Closest papers by meaning
- XTSFormer: Cross-Temporal-Scale Transformer for Irregular-Time Event Prediction in Clinical Applications (AAAI 2025 · similarity 0.85)
- Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification (NeurIPS 2024 · similarity 0.84)
- MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series (NeurIPS 2025 · similarity 0.83)
- Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction (NeurIPS 2026 · similarity 0.82)
- Integrating Sequence and Image Modeling in Irregular Medical Time Series Through Self-Supervised Learning (AAAI 2025 · similarity 0.82)
- One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models (NeurIPS 2026 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
