SDP: Sensing Data Protocol For Scalable Wireless Sensing

A protocol-level abstraction and unified benchmark for scalable wireless sensing. SDP enforces deterministic physical-layer sanitization, canonical tensor construction, and standardized training and evaluation procedures, decoupling learning performance from hardware-specific artifacts. The repository is licensed under MIT and was last updated on 2026-05-17.

Use Cases

• Benchmarking wireless sensing algorithms based on the standardized training and evaluation procedures
• Developing hardware-agnostic sensing models based on the decoupling of learning performance from hardware artifacts
• Creating reproducible sensor data pipelines based on the deterministic physical-layer sanitization
• Constructing canonical sensor data tensors for model input based on the described tensor construction method

Strengths

• Provides a standardized benchmark for wireless sensing, which can facilitate fair model comparison
• Enforces deterministic physical-layer sanitization, which may improve data consistency
• Decouples learning performance from hardware-specific artifacts, potentially increasing model portability

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download
• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment

Provenance

Source

github repository by yuanhao-cui

Freshness

Last updated 2026-05-17 09:38:40; freshness should be verified