Struct DecoderPipeline 

pub struct DecoderPipeline { /* private fields */ }

End-to-end decoder pipeline that ensembles multiple decoding strategies.

Combines KNN, threshold, and transition decoders with configurable ensemble weights, and optionally includes clinical scoring.

Implementations

impl DecoderPipeline

pub fn new() -> Self

Create an empty pipeline with default ensemble weights.

pub fn with_knn(self, k: usize) -> Self

Add a KNN decoder to the pipeline.

pub fn with_thresholds(self) -> Self

Add a threshold decoder to the pipeline.

pub fn with_transitions(self, window: usize) -> Self

Add a transition decoder to the pipeline.

pub fn with_clinical( self, baseline: TopologyMetrics, std: TopologyMetrics, ) -> Self

Add a clinical scorer to the pipeline.

pub fn with_weights(self, weights: [f64; 3]) -> Self

Set custom ensemble weights for [knn, threshold, transition].

pub fn knn_mut(&mut self) -> Option<&mut KnnDecoder>

Get a mutable reference to the KNN decoder (for training).

pub fn threshold_mut(&mut self) -> Option<&mut ThresholdDecoder>

Get a mutable reference to the threshold decoder (for configuring thresholds).

pub fn transition_mut(&mut self) -> Option<&mut TransitionDecoder>

Get a mutable reference to the transition decoder (for registering patterns).

pub fn clinical_mut(&mut self) -> Option<&mut ClinicalScorer>

Get a mutable reference to the clinical scorer.

pub fn decode( &mut self, embedding: &NeuralEmbedding, metrics: &TopologyMetrics, ) -> DecoderOutput

Run the full decoding pipeline on an embedding and topology metrics.

Trait Implementations

impl Default for DecoderPipeline

fn default() -> Self

Returns the “default value” for a type.