# A 2-Block Architecture for Real-Time EEG Gait Decoding: A Pilot Study

arXiv: https://arxiv.org/abs/2608.02083 · HTML: https://mlsanity.com/paper/2608.02083/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 23 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Builds on (most cited first, 4 of 4)

- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [On the Parameterization and Initialization of Diagonal State Space Models](https://mlsanity.com/paper/2206.11893/) (2022)
- [BCI-Based Assessment of Ocular Response Time Using Dynamic Time Warping Leveraging an RDWT-Driven Deep Neural Framework](https://mlsanity.com/paper/2605.14883/) (2026)
- [nASR: An End-to-End Trainable Neural Layer for Channel-Level EEG Artifact Subspace Reconstruction in Real-Time BCI](https://mlsanity.com/paper/2605.14941/) (2026)

## Abstract (arXiv)

Closed-loop lower-limb exoskeleton control via Electroencephalography (EEG) remains limited by motion artifacts, low signal-to-noise ratio, and binary gait formulations that fail to capture full cortical gait complexity. We propose a 2-block Brain-Computer Interface (BCI) architecture: a trainable session-specific Feature Extraction Block with real-time artifact suppression and multi-domain feature extraction, coupled with a Decoder Block built on a novel Polynomial Time-Varying Layer (PolyTVL)+LSTM for four-state gait classification (Stand, Initiate, Execute, Terminate). Ablation confirmed v01 (PolyTVL+LSTM) outperformed all variants (validation MCC: 0.435, gap: 0.187), with consistent EEG feature discriminability across ROIs and sub-bands (p<0.05). Closed-loop deployment with v01 achieved 55.3% (Rex-assisted) and 52.7% (volitional) gait initiation success, with a mean end-to-end processing time of 70.5~ms (+/-41.5), validating real-time feasibility in this pilot study.