2026-08-04 00:00 China Papers Communication & Language Translated from EN

EEG-fNIRS fusion decodes imagined handwriting

Summary Researchers report FRED, a principled EEG-fNIRS fusion framework for imagined handwriting decoding, posted to arXiv as a preprint on August 4, 2026 and not yet peer reviewed. Imagined handwriting offers a temporally rich paradigm for non-invasive neural decoding, and EEG-fNIRS fusion promises complementary neural information, but fusion is typically heuristic and lacks principled treatment of frequency-band redundancy. FRED builds frequency-decorrelated temporal ensembles for imagined handwriting decoding. The ensemble reaches 0.8076/0.7242/0.7492 accuracy on the public/private/overall test partitions without test-set adaptation or output constraints, and the complete system reaches 0.8498/0.7718/0.7952, ranking fourth on the private split. A modality audit finds fNIRS-only decoding at chance (0.2511 overall), while adding fNIRS to EEG changes accuracy by only +0.0025.

Why it matters fNIRS's contribution to multimodal fusion is often assumed. This preprint's principled framework reports 0.7952 overall accuracy, while its modality audit shows fNIRS alone decodes at chance, an honest baseline the multimodal BCI field needs.

BCIwiki (bciwiki.com) — Researchers report that FRED, a principled EEG-fNIRS fusion framework for imagined handwriting decoding, reaches 0.7952 overall accuracy, while a modality audit finds fNIRS-only decoding at chance, according to a preprint posted to arXiv on August 4, 2026 that has not yet undergone peer review.

Imagined handwriting offers a temporally rich paradigm for non-invasive neural decoding, and EEG-fNIRS fusion promises complementary neural information, but fusion is typically heuristic and lacks principled treatment of frequency-band redundancy. FRED builds frequency-decorrelated temporal ensembles for imagined handwriting decoding. The ensemble reaches 0.8076/0.7242/0.7492 accuracy on the public/private/overall test partitions without test-set adaptation or output constraints, and the complete system reaches 0.8498/0.7718/0.7952, ranking fourth on the private split. The modality audit finds fNIRS-only decoding at chance (0.2511 overall), while adding fNIRS to EEG changes accuracy by only +0.0025.

Compiled by BCIwiki from public sources

Sources · 1

arxiv.org 2026-08-04

Xidian University Decoding Algorithms China

Xidian University timeline

2026-04 Xidian Team Drops Transformer Encoder, MLP Decoder Holds 0.94–0.98 AUC 2026-02 Improved Spontaneous EEG Signal Decoding Efficiency by Function Predefined Convolutional Neural Network All entries →

Read original ↗

Suggest a correction Revisions · none 中 / EN