Research map / Architectures and efficiency / RNNs and normalization
Instance-Wise Dynamic Sensor Selection for Human Activity Recognition
Xiaodong Yang, Yiqiang Chen, Hanchao Yu, Yingwei Zhang, Wang Lu, Ruizhe Sun
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 Mutual DAgger training to MDP policy (IDSS vs pure MDP) (ablation) | IDSS · MHEALTH | balance-index (lambda=1.0): 0.3948 -> 0.7024 | Improved |
| add Mutual DAgger training to MDP policy (ablation) | IDSS · PAMAP2 | balance-index (lambda=1.0): 0.3671 -> 0.6380 | Improved |
| add Mutual DAgger training to MDP policy (ablation) | IDSS · ActivityNet | balance-index (lambda=0.5): 0.3946 -> 0.8225 | Improved |
| use instance-wise dynamic selection instead of random subset | IDSS · MHEALTH | balance-index (lambda=1.0): 0.0506 -> 0.7024 | Improved |
| use instance-wise dynamic selection instead of best fixed sensor set | IDSS · MHEALTH | balance-index (lambda=1.0): 0.5685 -> 0.7024 | Improved |
| use instance-wise dynamic selection instead of best fixed sensor set | IDSS · PAMAP2 | balance-index (lambda=1.0): 0.5910 -> 0.6380 | Improved |
| use instance-wise dynamic selection instead of best fixed sensor set | IDSS · ActivityNet | balance-index (lambda=0): 0.9958 -> 0.9958 | No clear effect |
| use IDSS instead of all sensors | all sensors · MHEALTH | average sensor number: 7 -> 1.78 | Improved |
| increase lambda from small to large | IDSS · three HAR datasets | recognition accuracy | No clear effect |
| increase lambda | IDSS · three HAR datasets | average sensor number | Improved |
Closest papers by meaning
- Decomposing and Fusing Intra- and Inter-Sensor Spatio-Temporal Signal for Multi-Sensor Wearable Human Activity Recognition (AAAI 2025 · similarity 0.85)
- Scalable Hierarchical Deep Neural Network for Time Series Analysis in Wearable Sensor-based Human Activity Recognition (AAAI 2025 · similarity 0.84)
- HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors (AAAI 2024 · similarity 0.84)
- MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition (NeurIPS 2025 · similarity 0.84)
- ConSense: Continually Sensing Human Activity with WiFi via Growing and Picking (AAAI 2025 · similarity 0.83)
- Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning (AAAI 2025 · similarity 0.83)
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.
