Research map / Learning theory and algorithms / Combinatorial and search optimization
Electrophysiological Brain Source Imaging via Combinatorial Search with Provable Optimality
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 |
|---|---|---|---|
| Use ESI-A* instead of conventional ESI baselines | Synthetic ESI · 2 cm activated area, SNR = 40 dB, 30 dB, 20 dB, and 10 dB | LE: 10.7 (04.9) vs 19.1 (09.0); 10.7 (04.9) vs 19.1 (09.0); 10.7 (05.0) vs 19.1 (09.3); 11.1 (05.1) vs 19.4 (10.4) | Helped |
| Use ESI-A* instead of deep-learning baselines | Synthetic ESI · 4 cm activated area at SNR = 40 dB, 30 dB, 20 dB, and 10 dB | AUC: 0.96 (0.05) vs 0.98 (0.08); 0.89 (0.07) vs 0.98 (0.08); 0.86 (0.06) vs 0.98 (0.09); 0.87 (0.06) vs 0.96 (0.12) | Mixed |
| Use ESI-A* instead of conventional ESI baselines | Synthetic ESI · 4 cm activated area, SNR = 10 dB | LE: 15.9 (08.5) vs 21.2 (12.9) | Helped |
| Vary the assumed number of activated vertices k (ablation) | ESI-A* · Synthetic, true activated area has 19 vertices | optimization error | Mixed |
| Use ESI-A* instead of FNN and BiLSTM | Real epilepsy EEG source imaging · 20 patients with drug-resistant epilepsy | concordance with resection and SOZ | Mixed |
Closest papers by meaning
- BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals (NeurIPS 2025 · similarity 0.84)
- CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding (ICLR 2025 · similarity 0.83)
- Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion (NeurIPS 2024 · similarity 0.83)
- NeurIPT: Foundation Model for Neural Interfaces (NeurIPS 2025 · similarity 0.82)
- NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces (NeurIPS 2026 · similarity 0.82)
- CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings (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.