EMG work has a settled vocabulary of activation measures, and most general-purpose biosignal tools make you rebuild them. BCILattice ships them as named feature families alongside an EMG band preset and the conditioning chain the modality actually needs.
EMG can also sit in the same study as EEG or fNIRS, which is what a hybrid BCI or a movement-artifact investigation requires.
Conditioning
Bandpass, rectification, envelope extraction and RMS envelope are the recommended starting operations. Each writes a named stage carrying its parameters, so the envelope you analysed is traceable to the filter that produced it.
The EMG band preset covers low (20–50 Hz), mid (50–100), high (100–250) and very high (250–450) — bands chosen for muscle activity rather than borrowed from an EEG default.
The activation measures
Several time-domain families in the catalogue are the standard EMG activation measures: Root Mean Square, Mean Absolute Value, Waveform Length, Slope Sign Changes and Willison Amplitude. Zero crossing rate, signal energy, nonlinear energy and the Hjorth parameters sit alongside them.
They are named columns in the design matrix, so a ranked feature list attributes the discrimination to a measure you can name in a methods section.
Import
EMG imports from EDF, BDF, GDF, FIF, and tabular TXT and CSV. Folder import handles multi-session or multi-subject datasets in one action, and label columns are confirmed at import rather than inferred silently.
Gesture and movement classification
Once features are extracted, the ML Suite canvas is the same one EEG and fNIRS use: classical models for a first baseline, sequence models for temporal structure, and grouped splits so that a gesture classifier is evaluated across sessions or subjects rather than across near-duplicate windows of one recording.
Questions
Which EMG features are available?
The standard activation measures — RMS, mean absolute value, waveform length, slope sign changes and Willison amplitude — plus the wider time-domain catalogue: zero crossing rate, signal energy, nonlinear energy, Hjorth parameters, entropy and fractal dimension families.
Can I combine EMG with EEG in one study?
Yes. A study holds more than one modality, and each step reads sampling rate and channel structure from the recording it is processing.
Does it do envelope extraction?
Yes — rectification, envelope extraction and RMS envelope are part of the recommended EMG conditioning chain, each writing a named stage with its parameters recorded.
Read the reference
Related
EEG Signal Processing Software
Filtering, referencing, resampling and normalization, each writing a named stage that carries the settings it ran with — so a downstream result can always be traced back to the conditioning that produced it.
fNIRS Analysis Software
An fNIRS file holds a HbO and a HbR channel per source-detector pair. Every fNIRS-capable step here exposes a chromophore control, because decomposing or ranking both together mixes two different physiological signals.
BCI Analysis Software
Eleven steps sit between a conditioned recording and a labelled design matrix. In BCILattice each one shows you its result before you commit it, and records what it ran with afterwards.
EEG Machine Learning
A node canvas of 119 blocks covers the pipeline from design matrix to evaluation — and the evaluation half is built to make an inflated score hard to produce by accident.