NeuraDock: A Hackable 7-Channel EEG Workstation

NeuraDock is built for people who want to work directly with EEG data without spending most of their time assembling hardware or writing low-level signal-processing code. It is used by neuroscience researchers, HCI designers, AI engineers, and XR or game developers who want to prototype with brain signals quickly.

A typical project might start with an idea for brain-driven interaction or an experiment using EEG signals. With many existing tools, developers first need to configure hardware, check electrode contact, set up data streaming, and write preprocessing code before they can test anything meaningful. NeuraDock shortens this path by providing a ready-to-use hardware setup and a workflow that helps move from raw signals to usable data more efficiently.

In practice, this means faster iteration. A team can put on the headset, verify signal quality, record data, and begin analysis or application development without rebuilding the same pipeline for every project.

One key challenge in EEG work is the gap between ideas and implementation. Designing a custom feature or metric often requires writing and debugging complex signal-processing code. With NeuraDock, users can describe tasks such as filtering signals, extracting bandpower, or generating visualizations, and the system assists in building the required pipeline. This turns what is often a time-consuming process into a faster and more accessible workflow.

NeuraDock is especially useful in early-stage prototyping, where flexibility and speed matter. It supports use cases such as:

Brain-computer interface research and experiments
EEG-based interaction and interface design
XR, game, and spatial computing prototypes
Machine learning experiments with biosignals
Neurofeedback and cognitive-state visualization
Maker projects requiring raw EEG access

Features & Specifications

Key Features

7-channel EEG acquisition for BCI and biosignal prototyping
Dry-electrode headset for fast setup and repeatable placement
Direct access to raw multichannel EEG data
Bluetooth Low Energy (BLE) and USB Type-C connectivity for real-time streaming
Modular architecture for integration into custom hardware and wearables
Real-time signal inspection for checking data quality during recording
Companion software for recording and data access
Agent-assisted workflow for signal processing, feature extraction, and visualization

Hardware Specifications

Parameter	Specification
EEG Channels	7 channels
Analog Front-End	Texas Instruments ADS1299
ADC Resolution	24-bit
Sampling Rate	250 Hz
Input-Referred Noise	< 1.5 μV p-p
CMRR	110 dB
Electrode Type	Dry electrodes
Electrode Layout	O1, O2, Oz + PO3, PO4, CP5, CP6
Connectivity	Bluetooth Low Energy (BLE), USB Type-C
Wireless	Nordic Semiconductor nRF52840
Battery	Rechargeable Li-ion
Battery Life	~6 hours continuous streaming

Software and Workflow

Companion application for recording and exporting EEG data
Real-time signal visualization for monitoring signal quality
Data export for integration with Python, MATLAB, and common EEG toolchains
Agent-assisted workflow for generating analysis pipelines from natural language prompts
Local processing architecture — EEG data remains on the user’s machine

Open Source

NeuraDock is designed as an open and developer-friendly platform, with key parts of the system made available for customization, research, and integration.

We plan to provide the following resources:

Hardware schematics and PCB design files
Mechanical CAD files for the headset and enclosure
Core software components, including the Python SDK
Documentation for data communication and integration

Licensing:

Hardware design files: CERN-OHL-W
Mechanical CAD files: CC BY-SA 4.0
Software (SDK and tools): MIT License

All resources will be published on our GitHub repository. We welcome contributions from the community, including software improvements, new analysis workflows, and hardware adaptations.

Project Logs

Collapse

SSVEP Paradigm Demo with Data Processing
Neuradock001 • 5 days ago • 0 comments

SSVEP data results
SSVEP experiment and data process video:
Replicating a NeurIPS Visual Decoding Paper with 7-Channel Dry Electrodes
Neuradock001 • 05/27/2026 at 01:58 • 0 comments

# Replicating a NeurIPS Visual Decoding Task with 7-Channel Dry Electrodes

*Can wearable EEG hardware match lab-grade equipment for brain-state decoding? We ran the experiment.*

**Tags:** EEG · BCI · Visual Decoding · NeurIPS 2024 · Dry Electrodes · ADS1299

---

## Overview

EEG-based visual decoding has long been the domain of well-funded neuroscience labs. The bottleneck isn't the algorithms — it's the hardware. A clinical-grade wet-electrode amplifier costs upward $28,000 USD, requires conductive gel, and is far from portable.

We built NeuraDock as a wearable, dry-electrode EEG platform and asked a straightforward question: **can it actually hold up against lab-grade equipment on a state-of-the-art decoding task?**

> **Short answer:** Yes. Using 7-channel dry electrodes in an everyday environment, we replicated the NeurIPS 2024 visual decoding benchmark and matched the paper's reported Top-1 accuracy at equivalent channel counts — at roughly 1/7th the hardware cost.

---

## The Benchmark: NeurIPS 2024 Visual Decoding

We replicated *Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion* (NeurIPS 2024). The paper's core task: decode and reconstruct natural images purely from EEG signals recorded while subjects viewed photos.

The framework has three main technical components:

- **Multimodal latent alignment (CLIP):** EEG features are aligned to CLIP image embeddings via contrastive learning — bridging brain signals and image semantics.
- **ATM encoder (Adaptive Temporal-spatial Modeling):** A custom EEG encoder that extracts spatiotemporal features at state-of-the-art efficiency.
- **Two-stage image generation:** Separate extraction of high-level semantic features ("a cat") and low-level visual features ("edges, color") — followed by a lightweight prior diffusion model — achieving reliable reconstructions from under 500ms of EEG data.

The original paper tested multiple channel configurations. Critically, it reported that **7-channel EEG achieves 16–25% Top-1 accuracy** in image classification — giving us a meaningful comparison point.
The live demo is as below:

---

## Hardware Comparison

| Dimension | Original paper | NeuraDock (this work) |
|---|---|---|
| Channel count | 64-ch subset → 7 for comparison | 7 channels |
| Electrode type | Wet (conductive gel) | Dry (comb-tooth) |
| Hardware | BrainVision actiCHamp | NeuraDock ADS1299-based |
| Portability | Lab-only | Wearable, everyday use |
| Setup time | 20–40 min (gel application) | <5 min |

**NeuraDock device specs:**

| Parameter | Spec |
|---|---|
| Channels | 7 (+ REF + GND) |
| Electrode positions | T5, T6, PO3, PO4, O1, Oz, O2 (occipital + temporal) |
| Sample rate | 250 Hz |
| Resolution | 24-bit |
| Connectivity | Bluetooth / USB |
| Mounting | Wraparound headband, Velcro |

---

## Key Results

| Metric | Original paper (7-ch) | NeuraDock (7-ch) |
|---|---|---|
| Top-1 accuracy | ~20% | 20.5% |
| Top-5 accuracy | ~55% (full config) | ~45% |
| 2-way retrieval | Comparable | Comparable |
| 4-way retrieval | Comparable | Comparable |
| Data trials | Single-trial | Multi-trial average |

On 2-way and 4-way retrieval tasks, NeuraDock's 7-electrode configuration performed on par with the paper's 64-electrode results. Individual image reconstructions capture the primary semantic content and basic contours of the original stimuli — consistent with the paper's 7-channel results.

---

## Engineering Decisions

### 1. Signal Filtering and Timing Calibration

Because we use a software-based marker system (USB + software timestamps) rather than a hardware trigger line, we needed to characterize and compensate for system latency. We swept across delay offsets and three filter bands:

- **1–20 Hz:** Significant accuracy drop — gamma-band (>30 Hz) content is essential for visual decoding.
- **1–45 Hz:** Best trade-off — preserves visual features, rejects power-line and high-frequency muscle artifacts.
- **1–100...
Read more »

View all 2 project logs

NeuraDock Workstation Step-by-Step Wearing Guide

Step-by-Step Wearing Guide

1. Identify the main parts of the NeuraDock EEG Workstation: the main headband, the upper auxiliary headband, the lower auxiliary headband, and the electrode modules.

2. Place the main headband on the forehead and keep the front sensor area centered.

3. Adjust the lower auxiliary headband so it fits securely around the lower back of the head.

4. Adjust the upper auxiliary headband so it supports the headset from the top and helps keep the electrodes stable.

5. Check the electrode positions and make sure the electrodes are aligned with the target EEG locations.

6. Gently adjust the headset until all electrodes maintain stable contact with the scalp.

7. Connect the device and open the NeuraDock recording software.

8. Run the signal quality check before starting the experiment.

9. If any channel shows poor signal quality, slightly adjust the headset or electrode contact until the signal becomes stable.

10. Once the signal quality is verified, the headset is ready for EEG recording and BCI workflow experiments.

NeuraDock: A Hackable 7-Channel EEG Workstation

Description

Details