Research map / Video / Video segmentation and tracking
Enabling Delayed-Full Charging Through Transformer-Based Real-Time-to-Departure Modeling for EV Battery Longevity
Yonggeon Lee, Jibin Hwang, Alfred Malengo Kondoro, Juhyun Song, Youngtae Noh
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 |
|---|---|---|---|
| model departure as survival (TTD) instead of regression or classification | EV departure prediction · All days | MAE (hours): 2.57 -> 2.20 (vs SVR); 2.59 -> 2.20 (vs iTransformer) | Improved |
| add contextual passive-sensing features (ablation) | TTD model · All days | MAE (hours): 4.47 -> 2.20 | Improved |
| add positional encoding (ablation) | TTD model · All days | MAE (hours): 4.25 -> 2.20 | Improved |
| add absolute time features (ablation) | TTD model · All days | MAE (hours): 3.01 -> 2.20 | Improved |
| add day-of-week features (ablation) | TTD model · All days | MAE (hours): 2.64 -> 2.20 | Improved |
| add alpha-fusion (ablation) | TTD model · All days | MAE (hours): 2.55 -> 2.20 | Improved |
| add time-scale and Gaussian-smoothed supervision (ablation) | TTD model · All days | MAE (hours): 2.36 -> 2.20 | Improved |
| personalize by fine-tuning last layers per user (ablation) | TTD model · All days | MAE (hours): 2.20 -> 2.13 | Improved |
| use extreme event weight or very large threshold p (ablation) | TTD model · Figure 5 hyperparameters | MAE | Hurt |
Closest papers by meaning
- NOCE-Net: Representation Learning for Battery Operational Context via Nested Sequence Modelling (NeurIPS 2026 · similarity 0.82)
- BatteryML: An Open-source Platform for Machine Learning on Battery Degradation (ICLR 2024 · similarity 0.80)
- Harnessing Event Sensory Data for Error Pattern Prediction in Vehicles: A Language Model Approach (AAAI 2025 · similarity 0.79)
- PowerPM: Foundation Model for Power Systems (NeurIPS 2024 · similarity 0.78)
- MobTA: Bus-Conditioned Zero-Shot Trajectory Generation via Task Arithmetic (NeurIPS 2026 · similarity 0.78)
- Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems (NeurIPS 2025 · similarity 0.77)
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.
