2026-09-26 00:00 Papers Movement & Control Source language EN

Review Charts a Decade of Algorithms and Chips for EEG Motor Imagery BCIs

Summary A new review surveys the past decade of signal-processing algorithms and hardware for EEG-based motor imagery brain-computer interfaces, which let users drive external devices or retrain motor function simply by imagining a movement. In these systems, users imagine moving a hand or foot while scalp electrodes record signals from the sensorimotor cortex, and algorithms translate them into commands. The authors survey the more practical algorithms of the past ten years, focusing on how machine learning and deep learning improve performance and efficiency. They also review hardware and supporting technologies, including system-on-chip designs, application-specific chips, programmable chips, wearables, the Internet of Things and augmented and virtual reality, discuss how these pair with algorithms, and outline research directions for better real-time performance. The paper is a preprint and has not been peer reviewed.

Why it matters Non-invasive motor imagery is among the lowest-barrier BCI routes and one of the closest to rehabilitation use, but leaving the lab takes both accurate decoding and small, fast hardware; treating the two together is the review's value, though its abstract gives no count of included studies or performance comparisons.

BCIwiki (bciwiki.com) — A review posted to arXiv on September 26, 2026 surveys the most practical algorithms developed over the past decade for decoding sensorimotor cortex signals in EEG-based motor imagery brain-computer interfaces (BCIs), alongside the hardware platforms that could carry them into next-generation systems. The authors are Mohammad Hossein Koohi Ghamsari, Seyede Fatemeh Ghamkhari, Siavash Bayat and Ahmed Hemani. The paper is a preprint and has not been peer reviewed.

In motor imagery (MI), users imagine moving a limb while EEG records the resulting cortical activity, which is decoded into commands for an external device. The authors say the paradigm has gained prominence because it is simple and non-invasive, and could help restore motor function and support rehabilitation for patients with motor impairments.

The review discusses in detail how AI-based algorithms, particularly machine learning and deep learning, have improved the performance and efficiency of MI-BCI systems.

On the hardware side, it covers system-on-chip (SoC) architectures, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), wearable devices, the Internet of Things (IoT) and augmented and virtual reality (AR/VR), and examines how they can be combined with advanced signal processing. The authors also summarize current achievements and outline research directions aimed at improving real-time capabilities.

Compiled by BCIwiki from public sources

Sources · 1

arxiv.org 2026-09-26

EEG Motor Decoding Non-invasive BCI

Read original ↗

Suggest a correction Revisions · none 中 / EN