EMMA-SC-SENSE v1

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-SC-SENSE-v1 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, a heterogeneous mix spread across bands, with scenes ranging from empty to heavily occupied. Frequency placement comes from the rfgen scene and placement groups.

  • 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 per-band occupancy; LabelExtractor maps the occupancy vector to the detection target. The metric is AUC (area under the ROC curve).

  • SNR (signal-to-noise ratio) regime: drawn from the rfgen channel.snr_db_range; the OOD (out-of-distribution) fold includes an unseen noise floor.

  • Sample counts: <to be pinned at v1>.

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

Real-capture counterpart

EMMA-REAL-OOD-v0.1 (fidelity reference).

Notes

  • Sensing is hardest near the noise floor, where the signal-to-noise ratio is low; the OOD fold targets exactly that regime, so a model that exploits a fixed noise-floor estimate will fail.

  • AUC is the threshold-free metric, appropriate because the detection operating point varies by application.

References

  • Davis and Goadrich, “The relationship between Precision-Recall and ROC curves,” ICML 2006. AUC grounding. (verify)

  • Yucek and Arslan, “A Survey of Spectrum Sensing Algorithms for Cognitive Radio Applications,” IEEE Commun. Surveys Tuts. 2009. Spectrum sensing survey. (verify)

See Also