EMMA-RWAVE v0.2

Warning

Pre-implementation. This page describes proposed contracts. Class signatures, parameter types, schema fields, and behavior are subject to change before code lands. Once implementation exists, content here will be regenerated from docstrings or sourced from running tests.

Dataset. EMMA-RWAVE-v0.2 covers the task, target domain, input, labels, splits, and the download command; this recipe pins only the rfgen configuration. Source. rfgen (primary).

rfgen recipe

  • rfgen commit: <rfgen-commit> (frozen at release; placeholder until pinned).

  • Emitters: the rfgen emitter_zoo group, radar family (classes fmcw, pulsed, lfm), spanning multiple waveform families. Emitter selection comes from the rfgen scene group.

  • Receiver array: 8-element ULA (uniform linear array), half-wavelength spacing (spacing_lambda: 0.5), via the rfgen MultiRXConfig.geometry member ULA. Loaded into ArraySpec at load time.

  • Channel environment(s): E_URBAN and E_RURAL, pinned through the rfgen channel group.

  • Labeler + label extraction: the rfgen label group records the waveform class; LabelExtractor maps emitters[].waveform_family to the classification target.

  • SNR (signal-to-noise ratio) regime: drawn from the rfgen channel.snr_db_range.

  • Sample counts: <to be pinned at v0.2>.

  • Splits + seeds: train / dev / holdout seed ranges pinned at release; the holdout is a frozen secret seed, never published. OOD axis: WAVEFORM_FAMILY.

Real-capture counterpart

To be determined at v0.2 (real radar captures are scarce in the public testbed set).

Notes

  • (depends on rfgen radar-emitter coverage not yet shipped) This recipe cannot pin until rfgen’s radar emitter family covers FMCW (frequency-modulated continuous-wave) and pulsed waveforms with the parameter ranges defense emitter identification requires. The recipe is a placeholder until that coverage lands; do not treat it as complete.

  • The same holdout-identity risk as fingerprinting applies: an unseen waveform family must not share a band or pulse-shape artifact with the training families, or the OOD fold leaks.

References

  • Skolnik, “Introduction to Radar Systems,” McGraw-Hill. The radar textbook of record. (verify edition)

  • 3GPP TR 38.843, “Study on AI/ML for NR.” Names radar-adjacent AI/ML use cases without dataset or baseline. (verify revision-year)

See Also