Research map / Probabilistic and scientific modeling / Molecules and proteins
Hierarchical Span-Based Conditional Random Fields for Labeling and Segmenting Events in Wearable Sensor Data Streams
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Replace hierarchical pairwise tree CRF with hierarchical span-based CRF (HNS) for joint event detection and segmentation | segmentation of activity sessions · four mHealth datasets (PM, T, MP, RQS) | segmentation F1: 0.082 to 0.266 F1 on three of four datasets; same on MP | Helped |
| Use max-margin (SSVM) learning instead of maximum likelihood for HNS (ablation) | HNS model · four mHealth datasets | segmentation F1 | Helped |
| Use HNS span-based model instead of LR/T-CRF for event labeling | event detection · four mHealth datasets | event-level F1 | Mixed |
| Use HNS span-based model instead of T-CRF on high event noise synthetic data | event detection · synthetic data, sigma_S=0.25, varying sigma_E | event-level F1 | Helped |
| Hierarchical span model vs. all baselines on low-signal synthetic data vs. clean data | event detection · synthetic data, sigma_E=0.25 | event-level F1 | No clear effect |
Closest papers by meaning
- Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions (ICML 2025 · similarity 0.84)
- SensorLM: Learning the Language of Wearable Sensors (NeurIPS 2025 · similarity 0.84)
- Scaling Wearable Foundation Models (ICLR 2025 · similarity 0.83)
- Large-scale Training of Foundation Models for Wearable Biosignals (ICLR 2024 · similarity 0.83)
- VCR: Learning Valid Contextual Representation for Incomplete Wearable Signals (NeurIPS 2026 · similarity 0.83)
- OpenMHC: Accelerating the Science of Wearable 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.