Research map / Probabilistic and scientific modeling / Molecules and proteins
DITING: A Weak Degradation Listener for Battery Lifetime Early Prediction
Hao Miao, Ni Zhang, Zefei Ning, Li Wang
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 hierarchical embedding (ablation) | DITING · CALCE | MAPE: 0.229 -> 0.187 | Improved |
| add health prototype construction instead of first-cycle reference (ablation) | DITING · CALCE | MAPE: 0.203 -> 0.187 | Improved |
| add tri-coupled degradation manifestation (ablation) | DITING · CALCE | MAPE: 0.241 -> 0.187 | Improved |
| use anti-phase drive instead of in-phase drive (ablation) | DITING · CALCE | MAPE: 0.212 -> 0.187 | Improved |
| add symmetry constraint (symmetrized response) (ablation) | DITING · CALCE | MAPE: 0.205 -> 0.187 | Improved |
| use both anti-phase drive and symmetry constraint (ablation) | DITING · CALCE | MAPE: 0.227 -> 0.187 | Improved |
| add tri-coupled degradation manifestation (ablation) | DITING · SNL | MAPE: 0.216 -> 0.152 | Improved |
| add tri-coupled degradation manifestation (ablation) | DITING · XJTU | MAPE: 0.073 -> 0.049 | Improved |
| use DITING instead of CPMLP in-domain | CPMLP · CALB | MAPE: 0.148 -> 0.169 | Hurt |
| use DITING instead of CPGRU on HUST | CPGRU · HUST | MAPE: 0.098 -> 0.117 | Hurt |
| use DITING instead of CPMLP on SNL | CPMLP · SNL | MAPE: 0.208 -> 0.152 | Improved |
| use DITING instead of CPMLP in zero-shot transfer | CPMLP · SNL (zero-shot) | MAPE: 0.706 -> 0.537 | Improved |
Closest papers by meaning
- BatteryML: An Open-source Platform for Machine Learning on Battery Degradation (ICLR 2024 · similarity 0.83)
- NOCE-Net: Representation Learning for Battery Operational Context via Nested Sequence Modelling (NeurIPS 2026 · similarity 0.83)
- S$^2$M-Former: Spiking Symmetric Mixing Branchformer for Brain Auditory Attention Detection (NeurIPS 2025 · similarity 0.81)
- A Scalable, Causal, and Energy Efficient Framework for Neural Decoding with Spiking Neural Networks (NeurIPS 2025 · similarity 0.79)
- Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions (ICML 2025 · similarity 0.79)
- POCO: Scalable Neural Forecasting through Population Conditioning (NeurIPS 2025 · similarity 0.79)
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.
