Skip to main content

​
Julia Streaming Inference

Streaming inference processes preprocessed feature chunks as they arrive from your BCI pipeline. It runs locally in NimbusSDK.jl; no network call is made during chunk inference.
For Python streaming, see Python SDK Streaming Inference. For cross-SDK configuration guidance, see Streaming Inference Configuration.

​
When To Use It

Use Julia streaming when your application needs low-latency feedback before a full trial is complete:
  • Real-time motor imagery control
  • Neurofeedback and training applications
  • Assistive interfaces with confidence-based rejection
  • Long-running monitoring sessions
The Julia SDK streaming API supports NimbusLDA, NimbusQDA, and NimbusProbit.

​
Streaming Flow

EEG hardware -> preprocessing -> feature chunks -> NimbusSDK.jl -> predictions
Nimbus expects feature chunks, not raw EEG. Filtering, artifact handling, and feature extraction should happen before calling process_chunk().

​
Basic Setup

using NimbusSDK

# One-time setup. The core can be cached for later use.
NimbusSDK.install_core("your-api-key")

model = load_model(NimbusLDA, "motor_imagery_4class_v1")

metadata = BCIMetadata(
    sampling_rate = 250.0,
    paradigm = :motor_imagery,
    feature_type = :csp,
    n_features = 16,
    n_classes = 4,
    chunk_size = 250
)

session = init_streaming(model, metadata)

​
Process Chunks

Each chunk should be shaped (n_features, chunk_size). 
for chunk in eeg_feature_stream
    result = process_chunk(session, chunk; iterations=10)

    println("Prediction: $(result.prediction)")
    println("Confidence: $(round(result.confidence, digits=3))")
    println("Posterior: $(result.posterior)")
end

​
Finalize A Trial

After enough chunks have been processed for a trial, aggregate them into a final prediction: 
final = finalize_trial(session; method=:weighted_vote)

if should_reject_trial(final.confidence, 0.7)
    @warn "Trial rejected" confidence=final.confidence
else
    @info "Trial accepted" prediction=final.prediction confidence=final.confidence
end
Supported aggregation methods:
  • :weighted_vote: weight chunk predictions by confidence.
  • :max_confidence: use the prediction from the most confident chunk.
  • :posterior_mean: average chunk-level posterior distributions.
  • :unanimous: require all chunks to agree, with fallback behavior when they do not.

​
Chunk Size Guidance

ParadigmTypical Chunk SizeNotes
Motor imagery250-500 samplesBalances latency and accuracy at 250 Hz.
P300100-200 samplesShort windows for event-related responses.
SSVEP500-1000 samplesLonger windows help frequency estimates.
Smaller chunks reduce latency but can lower per-chunk confidence. Larger chunks improve evidence quality but delay feedback.

​
Production Checklist

  • Validate each chunk shape before calling process_chunk().
  • Warm up the model with a dummy chunk before the user session.
  • Use a confidence threshold for high-stakes actions.
  • Keep preprocessing and feature extraction deterministic between calibration and deployment.
  • Reset or recreate sessions between independent trials when you do not want chunk history to carry over.

​
Next Read

Real-time Setup

Acquisition and hardware setup guidance.

Julia SDK API Reference

Complete Julia SDK function reference.

Batch Processing

Offline trial-level inference patterns.

Preprocessing Requirements

Feature preparation requirements before inference.