Get Started
Home
Topics
Search
Library
Research questionHow can lithium-ion battery state-of-health be estimated accurately with sparse, uneven labels?Battery state-of-health models depend on labeled cycling data, but practical datasets may provide only a small and uneven sample of health labels. This makes it difficult to learn degradation patterns that generalize across battery cells.
AI
Machine Learning
Research Paper
Statistical Machine Learning
Technology
Latest papersRecent research connected to this question, newest first.Degradation-Aligned Self-Supervised Learning for State of Health Estimation of Lithium-Ion Batteries under Label SparsityThe source studies a CNN-GRU model using degradation-aligned self-supervised pretraining with a cycle-order ranking objective, followed by fine-tuning on sparsely labeled data. Evidence includes results with 1% unevenly distributed labels on a test cell, along with analyses of label distribution and cross-cell robustness.research paper · Sep 4, 2026
Related questions
How should imbalanced multi-label data be sampled to support rare-label inference while accounting for target frequencies and label dependencies?How can deep imbalanced regression avoid underfitting scarce tail labels when uncertainty varies across instances?How can we generate realistic labeled wireless signals without costly measurements and labeling?How can sparse balanced signed graph Laplacians be learned efficiently while preserving positive-graph spectral tools?