rUv
9bbe95648c
feat: ADR-024 Contrastive CSI Embedding Model — all 7 phases ( #52 )
...
Full implementation of Project AETHER — Contrastive CSI Embedding Model.
## Phases Delivered
1. ProjectionHead (64→128→128) + L2 normalization
2. CsiAugmenter (5 physically-motivated augmentations)
3. InfoNCE contrastive loss + SimCLR pretraining
4. FingerprintIndex (4 index types: env, activity, temporal, person)
5. RVF SEG_EMBED (0x0C) + CLI integration
6. Cross-modal alignment (PoseEncoder + InfoNCE)
7. Deep RuVector: MicroLoRA, EWC++, drift detection, hard-negative mining, SEG_LORA
## Stats
- 276 tests passing (191 lib + 51 bin + 16 rvf + 18 vitals)
- 3,342 additions across 8 files
- Zero unsafe/unwrap/panic/todo stubs
- ~55KB INT8 model for ESP32 edge deployment
Also fixes deprecated GitHub Actions (v3→v4) and adds feat/* branch CI triggers.
Closes #50
2026-03-01 01:44:38 -05:00
Claude
18170d7daf
feat(adr-017): Complete all 7 ruvector integrations across signal and MAT crates
...
All ADR-017 integration points now implemented:
--- wifi-densepose-signal ---
1. subcarrier_selection.rs — ruvector-mincut: mincut_subcarrier_partition
uses DynamicMinCut to dynamically partition sensitive/insensitive
subcarriers via O(n^1.5 log n) graph bisection. Tests: 8 passed.
2. spectrogram.rs — ruvector-attn-mincut: gate_spectrogram applies
self-attention (Q=K=V, configurable lambda) over STFT time frames
to suppress noise/multipath interference. Tests: 2 added.
3. bvp.rs — ruvector-attention: attention_weighted_bvp uses
ScaledDotProductAttention for sensitivity-weighted BVP aggregation
across subcarriers (vs uniform sum). Tests: 2 added.
4. fresnel.rs — ruvector-solver: solve_fresnel_geometry estimates
unknown TX-body-RX geometry from multi-subcarrier Fresnel observations
via NeumannSolver. Regularization scaled to inv_w_sq_sum * 0.5 for
guaranteed convergence (spectral radius = 0.667). Tests: 10 passed.
--- wifi-densepose-mat ---
5. localization/triangulation.rs — ruvector-solver: solve_tdoa_triangulation
solves multi-AP TDoA positioning via 2×2 NeumannSolver normal equations
(Cramer's rule fallback). O(1) in AP count. Tests: 2 added.
6. detection/breathing.rs — ruvector-temporal-tensor: CompressedBreathingBuffer
uses TemporalTensorCompressor with tiered quantization for 50-75%
CSI amplitude memory reduction (13.4→3.4-6.7 MB/zone). Tests: 2 added.
7. detection/heartbeat.rs — ruvector-temporal-tensor: CompressedHeartbeatSpectrogram
stores per-bin TemporalTensorCompressor for micro-Doppler spectrograms
with hot/warm/cold tiers. Tests: 1 added.
Cargo.toml: ruvector deps optional in MAT crate (feature = "ruvector"),
enabled by default. Prevents --no-default-features regressions.
Pre-existing MAT --no-default-features failures are unrelated (api/dto.rs
serde gating, pre-existed before this PR).
Test summary: 144 MAT lib tests + 91 signal tests = all passed.
cargo check wifi-densepose-mat (default features): 0 errors.
cargo check wifi-densepose-signal: 0 errors.
https://claude.ai/code/session_01BSBAQJ34SLkiJy4A8SoiL4
2026-02-28 16:22:39 +00:00
Claude
6b20ff0c14
feat: Add wifi-Mat disaster detection enhancements
...
Implement 6 optional enhancements for the wifi-Mat module:
1. Hardware Integration (csi_receiver.rs + hardware_adapter.rs)
- ESP32 CSI support via serial/UDP
- Intel 5300 BFEE file parsing
- Atheros CSI Tool integration
- Live UDP packet streaming
- PCAP replay capability
2. CLI Commands (wifi-densepose-cli/src/mat.rs)
- `wifi-mat scan` - Run disaster detection scan
- `wifi-mat status` - Check event status
- `wifi-mat zones` - Manage scan zones
- `wifi-mat survivors` - List detected survivors
- `wifi-mat alerts` - View and acknowledge alerts
- `wifi-mat export` - Export data in various formats
3. REST API (wifi-densepose-mat/src/api/)
- Full CRUD for disaster events
- Zone management endpoints
- Survivor and alert queries
- WebSocket streaming for real-time updates
- Comprehensive DTOs and error handling
4. WASM Build (wifi-densepose-wasm/src/mat.rs)
- Browser-based disaster dashboard
- Real-time survivor tracking
- Zone visualization
- Alert management
- JavaScript API bindings
5. Detection Benchmarks (benches/detection_bench.rs)
- Single survivor detection
- Multi-survivor detection
- Full pipeline benchmarks
- Signal processing benchmarks
- Hardware adapter benchmarks
6. ML Models for Debris Penetration (ml/)
- DebrisModel for material analysis
- VitalSignsClassifier for triage
- FFT-based feature extraction
- Bandpass filtering
- Monte Carlo dropout for uncertainty
All 134 unit tests pass. Compilation verified for:
- wifi-densepose-mat
- wifi-densepose-cli
- wifi-densepose-wasm (with mat feature)
2026-01-13 18:23:03 +00:00
Claude
cd877f87c2
docs: Add comprehensive wifi-Mat user guide and fix compilation
...
- Add detailed wifi-Mat user guide covering:
- Installation and setup
- Detection capabilities (breathing, heartbeat, movement)
- Localization system (triangulation, depth estimation)
- START protocol triage classification
- Alert system with priority escalation
- Field deployment guide
- Hardware setup requirements
- API reference and troubleshooting
- Update main README.md with wifi-Mat section and links
- Fix compilation issues:
- Add missing deadline field in AlertPayload
- Fix type ambiguity in powi calls
- Resolve borrow checker issues in scan_cycle
- Export CsiDataBuffer from detection module
- Add missing imports in test modules
- All 83 tests now passing
2026-01-13 17:55:50 +00:00
Claude
a17b630c02
feat: Add wifi-densepose-mat disaster detection module
...
Implements WiFi-Mat (Mass Casualty Assessment Tool) for detecting and
localizing survivors trapped in rubble, earthquakes, and natural disasters.
Architecture:
- Domain-Driven Design with bounded contexts (Detection, Localization, Alerting)
- Modular Rust crate integrating with existing wifi-densepose-* crates
- Event-driven architecture for audit trails and distributed deployments
Features:
- Breathing pattern detection from CSI amplitude variations
- Heartbeat detection using micro-Doppler analysis
- Movement classification (gross, fine, tremor, periodic)
- START protocol-compatible triage classification
- 3D position estimation via triangulation and depth estimation
- Real-time alert generation with priority escalation
Documentation:
- ADR-001: Architecture Decision Record for wifi-Mat
- DDD domain model specification
2026-01-13 17:24:50 +00:00
