ruv
b3fd0e2951
docs: add HuggingFace models, 17 sensing apps, v0.6.0 to README + user guide
...
README:
- New "Pre-Trained Models" section with HuggingFace download link
- Model table (safetensors, q4, q2, presence head, LoRA adapters)
- Updated benchmarks (0.008ms, 164K emb/s, 51.6% contrastive)
- "17 Sensing Applications" section (health, environment, multi-freq)
- v0.6.0 in release table as Latest
User guide:
- "Pre-Trained Models" section with quick start + huggingface-cli
- What the models do (presence, fingerprinting, anomaly, activity)
- Retraining instructions
- "Health & Wellness Applications" section with all 4 health scripts
- Medical disclaimer
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 10:28:29 -04:00
rUv
aae01a2be8
Merge pull request #356 from ruvnet/fix/large-dataset-training
...
fix: skip triplet JSON export for large datasets (>100K)
2026-04-03 09:37:30 -04:00
ruv
828d0599d7
fix: skip triplet JSON export for large datasets (>100K)
...
JSON.stringify fails on 1M+ triplets. Training succeeded (33.3%
improvement) but export crashed. Now skips export when >100K triplets.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 09:37:08 -04:00
rUv
21fd7c84e2
Merge pull request #355 from ruvnet/fix/windows-bind-addr
...
fix: --bind flag for Windows firewall compatibility
2026-04-03 09:11:01 -04:00
ruv
85417b84a6
fix: add --bind flag for Windows firewall compatibility
...
Windows firewall blocks UDP on 0.0.0.0 — must bind to specific WiFi IP.
- seed_csi_bridge.py: --bind-addr auto (auto-detects WiFi IP)
- rf-scan.js: --bind <ip> option (default 0.0.0.0, use 192.168.1.x on Windows)
Confirmed: 195 frames received from both ESP32 nodes with --bind 192.168.1.20
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 09:09:53 -04:00
rUv
430243c32c
Merge pull request #310 from orbisai0security/fix-v002-display-buffer-uaf
...
fix: remove unsafe exec() in display_task.c
2026-04-03 09:01:41 -04:00
ruv
b7650b5243
feat(server): accuracy sprint 001 — Kalman tracker, multi-node fusion, eigenvalue counting
...
Original work by @taylorjdawson (PR #341 ). Merged with v0.5.5 firmware
preserved (ADR-069 feature vectors, ADR-073 channel hopping, batch-limited
watchdog from #266 fix).
New server features:
- Kalman tracker bridge for temporal smoothing
- Multi-node CSI fusion with field model
- Eigenvalue-based person counting
- Calibration endpoints (start/stop/status)
- Node positions parsing
- Adaptive classifier enhancements
Co-Authored-By: taylorjdawson <taylor@users.noreply.github.com>
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 08:59:17 -04:00
ruv
4fc491dea5
feat: ADR-078 — 5 multi-frequency mesh applications
...
RF tomography (2D backprojection imaging), passive bistatic radar
(neighbor APs as illuminators), frequency-selective material
classification (metal/water/wood/glass), through-wall motion
detection (per-channel penetration weighting), device fingerprinting
(RF emission signatures per SSID)
All impossible with single-channel WiFi — require 6-channel hopping.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 08:52:50 -04:00
ruv
4f6780f884
feat: ADR-077 — 6 novel RF sensing applications
...
Sleep monitor (hypnogram + efficiency), apnea detector (AHI scoring),
stress monitor (HRV + LF/HF via FFT), gait analyzer (cadence + tremor),
material detector (null pattern classification), room fingerprint
(k-means clustering + anomaly scoring)
All validated on overnight data (113K frames). Pure Node.js, zero deps.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 08:50:48 -04:00
ruv
085af0c2be
docs: update quick start with 3 deployment options
...
Option 1: Docker (simulated, no hardware)
Option 2: ESP32 live sensing ($9)
Option 3: Full system with Cognitum Seed ($140)
Also shows RF scan, SNN, and MinCut commands for v0.5.5 capabilities.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 08:47:31 -04:00
ruv
f4e636aaa2
docs: refocus README introduction on WiFi sensing
...
WiFi sensing (presence, vitals, activity, sleep, environment) is now
the primary narrative. Pose estimation repositioned as an advanced
capability. Highlights: multi-frequency mesh, SNN adaptation, witness
chain, Cognitum Seed integration.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 08:45:30 -04:00
ruv
582d51aed6
docs: fix Cognitum Seed pricing — $131 (not $15)
...
Updated all BOM references: ESP32 $9 + Cognitum Seed $131 = $140 total
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 08:44:22 -04:00
ruv
b31efe5e92
docs: improve README benchmarks — results-focused with context
...
Replace dry metric table with human-readable results that explain
why each number matters. 14 benchmarks with real-world significance.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 08:42:52 -04:00
ruv
f03b484dd1
docs: update README limitations — remove 2 resolved items
...
Removed:
- "No pre-trained model weights" — weights now published (v0.5.4+)
- "Multi-person counting overcounts #348 " — fixed by MinCut (ADR-075)
Added:
- Camera-free pose accuracy limitation (2.5% PCK@20, honest about it)
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 08:32:04 -04:00
ruv
7a75277d58
chore: add data/ and models/ to .gitignore
...
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 08:22:29 -04:00
ruv
73ce72d39c
docs: update README with v0.5.5 capabilities and benchmarks
...
- New "What's New in v0.5.5" section: SNN, MinCut (#348 fix), CNN
spectrogram, WiFlow, multi-frequency mesh, graph transformer
- Before/after comparison table (person counting, channels, model)
- 15 new script commands with usage examples
- Release table updated with v0.5.5 as Latest
- v0.5.4 section collapsed (not open by default)
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 08:16:23 -04:00
rUv
4e9e92d713
feat: ADR-074/075/076 — SNN + MinCut + CNN Spectrogram (ruvector advanced sensing)
...
feat: ADR-074/075/076 — SNN + MinCut + CNN Spectrogram (ruvector advanced sensing)
2026-04-03 08:00:07 -04:00
ruv
28368b2c70
feat: ADR-076 CNN spectrogram embeddings + graph transformer fusion
...
CSI-as-image: 64x20 subcarrier×time matrix → 224x224 → CNN → 128-dim
embedding. Same-node similarity 0.95+, cross-node 0.6-0.8.
- csi-spectrogram.js: WASM CNN embedding, ASCII visualization, Seed ingest
- mesh-graph-transformer.js: GATv2 multi-head attention over ESP32 mesh,
fuses multi-node features, generalizes to 3+ nodes
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 00:36:38 -04:00
ruv
4bb8c3303f
feat: ADR-075 min-cut person separation — fixes #348
...
Stoer-Wagner min-cut on subcarrier correlation graph replaces broken
threshold-based person counting (was always 4, now correct).
Validated: 24/24 windows correctly report 1 person on test data
where old firmware reported 4. Pure JS, <5ms per window.
- mincut-person-counter.js: live UDP + JSONL replay, overrides vitals
- csi-graph-visualizer.js: ASCII spectrum + correlation heatmap
- ADR-075: algorithm, comparison, migration path
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 00:34:57 -04:00
ruv
b9778c5ad2
feat: ADR-074 spiking neural network for real-time CSI sensing
...
128→64→8 SNN with STDP online learning — adapts to room in <30s
without labels. Event-driven: 16-160x less compute than FC encoder.
- snn-csi-processor.js: live UDP with ASCII visualization, EWMA
- ADR-073 updated with SNN integration for multi-channel fusion
- Fixed magic number parsing to use ADR-018 format (0xC5110001)
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 00:34:31 -04:00
ruv
b6c032d665
docs: add multi-frequency mesh + RF scanner to README
...
Continuous Deployment / Post-deployment Monitoring (push) Blocked by required conditions
Continuous Deployment / Notify Deployment Status (push) Blocked by required conditions
Continuous Integration / Code Quality & Security (push) Waiting to run
Continuous Integration / Tests (push) Waiting to run
Continuous Integration / Tests-1 (push) Waiting to run
Continuous Integration / Tests-2 (push) Waiting to run
Continuous Integration / Performance Tests (push) Blocked by required conditions
Continuous Integration / Docker Build & Test (push) Blocked by required conditions
Continuous Integration / API Documentation (push) Blocked by required conditions
Continuous Integration / Notify (push) Blocked by required conditions
Firmware CI / Build ESP32-S3 Firmware (push) Waiting to run
Firmware QEMU Tests (ADR-061) / QEMU Test (boundary-min) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (default) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (edge-tier0) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (edge-tier1) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (full-adr060) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (tdm-3node) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / Fuzz Testing (ADR-061 Layer 6) (push) Waiting to run
Firmware QEMU Tests (ADR-061) / NVS Matrix Generation (push) Waiting to run
Firmware QEMU Tests (ADR-061) / Build Espressif QEMU (push) Waiting to run
Firmware QEMU Tests (ADR-061) / QEMU Test (boundary-max) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / Swarm Test (ADR-062) (push) Blocked by required conditions
Security Scanning / License Compliance Scan (push) Waiting to run
Security Scanning / Security Policy Compliance (push) Waiting to run
Security Scanning / Static Application Security Testing (push) Waiting to run
Security Scanning / Dependency Vulnerability Scan (push) Waiting to run
Security Scanning / Container Security Scan (push) Waiting to run
Security Scanning / Infrastructure Security Scan (push) Waiting to run
Security Scanning / Secret Scanning (push) Waiting to run
Security Scanning / Security Report (push) Blocked by required conditions
New capabilities: 6-channel hopping, neighbor APs as passive radar,
real-time RF spectrum visualization with null/reflector/movement detection
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 00:26:48 -04:00
ruv
9d70d621da
feat: ADR-073 enable multi-frequency channel hopping from NVS
...
- main.c: call csi_collector_set_hop_table() at boot when hop_count > 1
- provision.py: add --hop-channels and --hop-dwell flags, write chan_list
blob and dwell_ms to NVS matching firmware's expected format
- Validated: Node 1 hopping ch 1/6/11, Node 2 hopping ch 3/5/9,
200ms dwell, null subcarriers reduced from 19% to 16%
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 00:26:22 -04:00
ruv
b4c9e7743f
feat: ADR-073 multi-frequency mesh RF scanning
...
Live RF room scanner with ASCII spectrum visualization:
- rf-scan.js: single-channel scanner with null/dynamic/reflector classification,
cross-node correlation, phase coherence, Unicode spectrum display
- rf-scan-multifreq.js: wideband view merging 6 channels, null diversity,
per-channel penetration quality, frequency-dependent scatterer detection
- benchmark-rf-scan.js: null diversity gain, spectrum flatness, resolution estimate
Validated: 228 frames in 5s, 23 fps/node, 19% nulls detected,
0.993 cross-node correlation, line-of-sight confirmed
ADR-073: interleaved channel hopping (Node 1: ch 1/6/11, Node 2: ch 3/5/9)
targets 6x subcarrier diversity, <5% null gap, ~15cm resolution
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-03 00:18:29 -04:00
ruv
8f2de7e9f2
feat: ADR-072 WiFlow SOTA architecture — TCN + axial attention + pose decoder
...
Pure JS implementation of WiFlow (arXiv:2602.08661) adapted for ESP32:
- TCN temporal encoder (dilated causal conv, k=7, dilation 1/2/4/8)
- Asymmetric spatial encoder (1x3 residual blocks, stride-2)
- Axial self-attention (width + height, 8 heads, 256 channels)
- Pose decoder (adaptive pooling → 17x2 COCO keypoints)
- SmoothL1 + bone constraint loss (14 skeleton connections)
- 1.8M params (1.6 MB at INT8), 198M FLOPs
Integrated with camera-free pipeline (pose proxy labels from
RSSI triangulation + subcarrier asymmetry + vibration)
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-02 23:40:23 -04:00
ruv
74c965f7ec
docs: remove HuggingFace publishing section from user guide
...
Contains GCloud project ID and secret names — not appropriate for
a public repo. Publishing instructions kept in scripts/ only.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-02 23:14:20 -04:00
ruv
73d4cb9fc2
docs: update README + user guide with v0.5.4 capabilities
...
README:
- Test badge 1300+ → 1463
- Updated capability table (171K emb/s, 100% presence, 0.012ms)
- Added "What's New in v0.5.4" section with full benchmark table
- Training pipeline quick start commands
User guide:
- Camera-Free Pose Training section (10 sensor signals, 5-phase pipeline)
- ruvllm Training Pipeline section (5 phases, quantization options)
- Publishing to HuggingFace section
- Updated table of contents
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-02 23:11:30 -04:00
ruv
ba82fcfc37
feat: camera-free 17-keypoint pose training (10 sensor signals)
...
Multi-modal pipeline using PIR, BME280, reed switch, vibration,
RSSI triangulation, subcarrier asymmetry — no camera needed.
Phases: multi-modal collection → weak label generation → enhanced
contrastive → 5-keypoint pose proxy → 17-keypoint interpolation
→ self-refinement (3 rounds) → LoRA + TurboQuant + EWC
Validated: 2,360 frames, 100% presence, 0 skeleton violations,
82.8 KB model (8 KB at 4-bit), 114.8s training
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-02 23:05:07 -04:00
ruv
ccc543c0e7
feat: Mac Mini M4 Pro training script (7-step pipeline)
...
Clone, copy data via Tailscale, train, benchmark, sync results,
publish to HuggingFace — all automated for M4 Pro hardware.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-02 22:42:32 -04:00
ruv
ade0fe82f6
fix: ruvllm pipeline — 7 critical fixes, all metrics improved
...
Before → After:
- Contrastive loss: -0.0% → 33.9% improvement
- Presence accuracy: 0% → 100%
- Temporal negatives: 0 → 22,396
- Quantization 2-bit: 16KB (4x) → 4KB (16x)
- Quantization 4-bit: 16KB (4x) → 8KB (8x)
- Training samples: 236 → 2,360 (10x augmentation)
- Triplets: 249 → 23,994 (96x more)
Fixes: gradient descent on encoder weights, temporal negative
threshold 30s→10s, PresenceHead (128→1 BCE), bit-packed
quantization, data augmentation (interp+noise+cross-node),
Xavier/Glorot init with batch normalization, live data collection
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-02 22:40:48 -04:00
ruv
a73a17e264
feat: ADR-071 ruvllm training pipeline — contrastive + LoRA + TurboQuant
...
5-phase training pipeline using ruvllm (Rust-native, no PyTorch):
1. Contrastive pretraining (triplet + InfoNCE, 5 triplet strategies)
2. Task head training (presence, activity, vitals via SONA)
3. Per-node LoRA refinement (rank-4, room-specific adaptation)
4. TurboQuant quantization (2/4/8-bit, 6-8x compression)
5. EWC consolidation (prevent catastrophic forgetting)
Exports: SafeTensors, HuggingFace config, RVF, per-node LoRA, quantized
Validated: 249 triplets, 37,775 emb/s, 100% presence accuracy on test data
Target: <5 min training on M4 Pro, <10ms inference on Pi Zero
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-02 22:27:24 -04:00
ruv
c63cf2ee77
feat: GCloud GPU training pipeline + data collection + benchmarking
...
- gcloud-train.sh: L4/A100/H100 VM provisioning, Rust build, training
with --cuda, artifact download, auto-cleanup ($0.80-$8.50/hr)
- training-config-sweep.json: 10 hyperparameter configs (LR, batch,
backbone, windows, loss weights, warmup)
- collect-training-data.py: UDP listener for 2-node ESP32 CSI recording
to .csi.jsonl with interactive/batch labeling and manifest generation
- benchmark-model.py: ONNX latency/throughput/PCK/FLOPs profiling with
multi-model sweep comparison
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-02 22:04:57 -04:00
ruv
9a2bc1839a
feat: HuggingFace model publishing pipeline + model card
...
- publish-huggingface.sh: retrieves HF token from GCloud Secrets,
uploads models to ruvnet/wifi-densepose-pretrained
- publish-huggingface.py: Python alternative with --dry-run support
- docs/huggingface/MODEL_CARD.md: beginner-friendly model card with
WiFi sensing explanation, quick start code, hardware BOM, and citation
GCloud Secret: HUGGINGFACE_API_KEY in project cognitum-20260110
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-02 22:04:16 -04:00
ruv
77a2e7e4e9
docs: add Cognitum Seed pretraining tutorial (530 lines)
...
Continuous Deployment / Post-deployment Monitoring (push) Blocked by required conditions
Continuous Deployment / Notify Deployment Status (push) Blocked by required conditions
Continuous Integration / Tests (push) Waiting to run
Continuous Integration / Tests-1 (push) Waiting to run
Continuous Integration / Tests-2 (push) Waiting to run
Continuous Integration / Code Quality & Security (push) Waiting to run
Continuous Integration / Performance Tests (push) Blocked by required conditions
Continuous Integration / Docker Build & Test (push) Blocked by required conditions
Continuous Integration / API Documentation (push) Blocked by required conditions
Continuous Integration / Notify (push) Blocked by required conditions
Firmware CI / Build ESP32-S3 Firmware (push) Waiting to run
Firmware QEMU Tests (ADR-061) / Swarm Test (ADR-062) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / Build Espressif QEMU (push) Waiting to run
Firmware QEMU Tests (ADR-061) / QEMU Test (boundary-max) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (boundary-min) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (default) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (edge-tier0) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (edge-tier1) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (full-adr060) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (tdm-3node) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / Fuzz Testing (ADR-061 Layer 6) (push) Waiting to run
Firmware QEMU Tests (ADR-061) / NVS Matrix Generation (push) Waiting to run
Security Scanning / Static Application Security Testing (push) Waiting to run
Security Scanning / Dependency Vulnerability Scan (push) Waiting to run
Security Scanning / Container Security Scan (push) Waiting to run
Security Scanning / Infrastructure Security Scan (push) Waiting to run
Security Scanning / Secret Scanning (push) Waiting to run
Security Scanning / License Compliance Scan (push) Waiting to run
Security Scanning / Security Policy Compliance (push) Waiting to run
Security Scanning / Security Report (push) Blocked by required conditions
Step-by-step guide covering hardware setup, Seed pairing, 2-node ESP32
provisioning, bridge operation, 6-scenario data collection protocol,
feature vector explanation, kNN queries, troubleshooting, and next steps.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-02 20:49:05 -04:00
ruv
b46b789e9e
feat: ADR-070 self-supervised pretraining from live ESP32 CSI + Seed
...
4-phase pipeline: data collection (2 nodes), contrastive pretraining,
downstream heads (presence/count/activity/vitals), package & distribute.
Validated: 118 features from 2 nodes in 60s, witness chain intact.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-02 20:42:37 -04:00
ruv
6464023780
docs: update README banner — Alpha → Beta, remove fixed issues
...
- #249 (multi-node person counting) fixed by ADR-068 in v0.5.3
- #318 (training plateau) resolved
- Add #348 (n_persons overcount) as current known issue
- Add Cognitum Seed link for spatial resolution improvement
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-02 20:34:52 -04:00
rUv
7b12b36889
feat: ADR-069 ESP32 CSI → Cognitum Seed RVF pipeline (v0.5.4-esp32)
...
feat: ADR-069 ESP32 CSI → Cognitum Seed RVF pipeline (v0.5.4-esp32)
2026-04-02 19:55:12 -04:00
ruv
27d17431c5
docs: update README and user guide with Cognitum Seed integration
...
- Add ESP32 + Cognitum Seed as recommended hardware option ($27 BOM)
- Add v0.5.4-esp32 to firmware release table
- Add Cognitum Seed setup section to user guide with bridge usage,
feature vector dimensions, and architecture diagram
- Update table of contents
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-02 19:48:01 -04:00
ruv
a4bd2308b7
feat: ADR-069 ESP32 CSI → Cognitum Seed RVF pipeline (v0.5.4-esp32)
...
Hardware-validated pipeline connecting ESP32-S3 CSI sensing to Cognitum
Seed (Pi Zero 2 W) edge intelligence appliance via 8-dim feature vectors.
Firmware:
- New 48-byte feature vector packet (magic 0xC5110003) at 1 Hz with
normalized presence, motion, breathing, heart rate, phase variance,
person count, fall detection, and RSSI
- Compressed frame magic reassigned 0xC5110003 → 0xC5110005
- Guard against uninitialized s_top_k read when count=0
Bridge (scripts/seed_csi_bridge.py):
- UDP→HTTPS ingest with bearer token, hash-based vector IDs
- --validate (kNN), --stats, --compact, --allowed-sources modes
- NaN/inf rejection, retry logic, SEED_TOKEN env var support
Validated on live hardware:
- 941 vectors ingested, 100% kNN exact match
- Witness chain SHA-256 verified (1,325 entries)
- 1,463 Rust tests passed, Python proof VERDICT: PASS
Research: 26 docs covering Arena Physica, Maxwell's equations in WiFi
sensing, SOTA survey 2025-2026, GOAP implementation plan
Security: removed hardcoded credentials, added NVS patterns to
.gitignore, source IP filtering, NaN validation
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-02 19:32:18 -04:00
rUv
a23bd2ec01
fix(server): resolve adversarial review findings C1-C5, H1-H3, H5, M1-M2
...
Critical fixes:
- C1: FieldModel created with n_links=1 (single_link_config) so
feed_calibration/extract_perturbation no longer get DimensionMismatch
- C2: variance_explained now uses centered covariance trace (E[x²]-E[x]²)
matching mode_energies normalization
- C3: MP ratio uses total_obs = frames * links for consistent threshold
between calibration and runtime
- C4: Noise estimator filters to positive eigenvalues only, preventing
collapse to ~0 on rank-deficient matrices (p > n)
- C5: ESP32 paths gate total_persons on presence — empty room reports 0
High fixes:
- H1: Bounding box computed from observed keypoints only (confidence > 0),
preventing collapse from centroid-filled unobserved slots
- H2: fuse_or_fallback returns Option<usize> instead of sentinel 0,
eliminating type ambiguity between "fusion succeeded" and "zero people"
- H3: Monotonic epoch-relative timestamps replace wall-clock/Instant mixing,
preventing spurious TimestampMismatch on NTP steps
- H5: ndarray-linalg gated behind "eigenvalue" feature flag (default=on),
diagonal fallback used with --no-default-features
Moderate fixes:
- M1: calibration_start guards against replacing Fresh calibration
- M2: parse_node_positions logs warning for malformed entries
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-31 18:50:00 +00:00
rUv
3733e54aef
feat: cross-node fusion + DynamicMinCut + RSSI tracking (v0.5.3)
...
Continuous Integration / Tests-2 (push) Has been cancelled
Firmware CI / Build ESP32-S3 Firmware (push) Has been cancelled
Firmware QEMU Tests (ADR-061) / Build Espressif QEMU (push) Has been cancelled
Firmware QEMU Tests (ADR-061) / Fuzz Testing (ADR-061 Layer 6) (push) Has been cancelled
Firmware QEMU Tests (ADR-061) / NVS Matrix Generation (push) Has been cancelled
Security Scanning / Static Application Security Testing (push) Has been cancelled
Security Scanning / Dependency Vulnerability Scan (push) Has been cancelled
Security Scanning / Container Security Scan (push) Has been cancelled
Security Scanning / Infrastructure Security Scan (push) Has been cancelled
Security Scanning / Secret Scanning (push) Has been cancelled
Security Scanning / License Compliance Scan (push) Has been cancelled
Security Scanning / Security Policy Compliance (push) Has been cancelled
Continuous Deployment / Deploy to Staging (push) Has been cancelled
Continuous Deployment / Deploy to Production (push) Has been cancelled
Continuous Deployment / Rollback Deployment (push) Has been cancelled
Continuous Deployment / Post-deployment Monitoring (push) Has been cancelled
Continuous Deployment / Notify Deployment Status (push) Has been cancelled
Continuous Integration / Performance Tests (push) Has been cancelled
Continuous Integration / Docker Build & Test (push) Has been cancelled
Continuous Integration / API Documentation (push) Has been cancelled
Continuous Integration / Notify (push) Has been cancelled
Firmware QEMU Tests (ADR-061) / QEMU Test (boundary-max) (push) Has been cancelled
Firmware QEMU Tests (ADR-061) / QEMU Test (boundary-min) (push) Has been cancelled
Firmware QEMU Tests (ADR-061) / QEMU Test (default) (push) Has been cancelled
Firmware QEMU Tests (ADR-061) / QEMU Test (edge-tier0) (push) Has been cancelled
Firmware QEMU Tests (ADR-061) / QEMU Test (edge-tier1) (push) Has been cancelled
Firmware QEMU Tests (ADR-061) / QEMU Test (full-adr060) (push) Has been cancelled
Firmware QEMU Tests (ADR-061) / QEMU Test (tdm-3node) (push) Has been cancelled
Firmware QEMU Tests (ADR-061) / Swarm Test (ADR-062) (push) Has been cancelled
Security Scanning / Security Report (push) Has been cancelled
* feat(server): cross-node RSSI-weighted feature fusion + benchmarks
Adds fuse_multi_node_features() that combines CSI features across all
active ESP32 nodes using RSSI-based weighting (closer node = higher weight).
Benchmark results (2 ESP32 nodes, 30s, ~1500 frames):
Metric | Baseline | Fusion | Improvement
---------------------|----------|---------|------------
Variance mean | 109.4 | 77.6 | -29% noise
Variance std | 154.1 | 105.4 | -32% stability
Confidence | 0.643 | 0.686 | +7%
Keypoint spread std | 4.5 | 1.3 | -72% jitter
Presence ratio | 93.4% | 94.6% | +1.3pp
Person count still fluctuates near threshold — tracked as known issue.
Verified on real hardware: COM6 (node 1) + COM9 (node 2) on ruv.net.
Co-Authored-By: claude-flow <ruv@ruv.net>
* fix(ui): add client-side lerp smoothing to pose renderer
Keypoints now interpolate between frames (alpha=0.25) instead of
jumping directly to new positions. This eliminates visual jitter
that persists even with server-side EMA smoothing, because the
renderer was drawing every WebSocket frame at full rate.
Applied to skeleton, keypoints, and dense body rendering paths.
Co-Authored-By: claude-flow <ruv@ruv.net>
* feat: DynamicMinCut person separation + UI lerp smoothing
- Added ruvector-mincut dependency to sensing server
- Replaced variance-based person scoring with actual graph min-cut on
subcarrier temporal correlation matrix (Pearson correlation edges,
DynamicMinCut exact max-flow)
- Recalibrated feature scaling for real ESP32 data ranges
- UI: client-side lerp interpolation (alpha=0.25) on keypoint positions
- Dampened procedural animation (noise, stride, extremity jitter)
- Person count thresholds retuned for mincut ratio
Co-Authored-By: claude-flow <ruv@ruv.net>
* docs: update CHANGELOG with v0.5.1-v0.5.3 releases
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-30 21:55:44 -04:00
rUv
cd84c35f8f
feat: cross-node RSSI-weighted feature fusion (benchmarked)
...
Continuous Deployment / Post-deployment Monitoring (push) Blocked by required conditions
Continuous Deployment / Notify Deployment Status (push) Blocked by required conditions
Continuous Integration / Code Quality & Security (push) Waiting to run
Continuous Integration / Tests (push) Waiting to run
Continuous Integration / Tests-1 (push) Waiting to run
Continuous Integration / Tests-2 (push) Waiting to run
Continuous Integration / Performance Tests (push) Blocked by required conditions
Continuous Integration / Docker Build & Test (push) Blocked by required conditions
Continuous Integration / API Documentation (push) Blocked by required conditions
Continuous Integration / Notify (push) Blocked by required conditions
Firmware CI / Build ESP32-S3 Firmware (push) Waiting to run
Firmware QEMU Tests (ADR-061) / Build Espressif QEMU (push) Waiting to run
Firmware QEMU Tests (ADR-061) / QEMU Test (boundary-max) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (boundary-min) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (default) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (edge-tier0) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (edge-tier1) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (full-adr060) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / QEMU Test (tdm-3node) (push) Blocked by required conditions
Firmware QEMU Tests (ADR-061) / Fuzz Testing (ADR-061 Layer 6) (push) Waiting to run
Firmware QEMU Tests (ADR-061) / NVS Matrix Generation (push) Waiting to run
Firmware QEMU Tests (ADR-061) / Swarm Test (ADR-062) (push) Blocked by required conditions
Security Scanning / Static Application Security Testing (push) Waiting to run
Security Scanning / Dependency Vulnerability Scan (push) Waiting to run
Security Scanning / Container Security Scan (push) Waiting to run
Security Scanning / Infrastructure Security Scan (push) Waiting to run
Security Scanning / Secret Scanning (push) Waiting to run
Security Scanning / License Compliance Scan (push) Waiting to run
Security Scanning / Security Policy Compliance (push) Waiting to run
Security Scanning / Security Report (push) Blocked by required conditions
Adds fuse_multi_node_features() that combines CSI features across all
active ESP32 nodes using RSSI-based weighting (closer node = higher weight).
Benchmark results (2 ESP32 nodes, 30s, ~1500 frames):
Metric | Baseline | Fusion | Improvement
---------------------|----------|---------|------------
Variance mean | 109.4 | 77.6 | -29% noise
Variance std | 154.1 | 105.4 | -32% stability
Confidence | 0.643 | 0.686 | +7%
Keypoint spread std | 4.5 | 1.3 | -72% jitter
Presence ratio | 93.4% | 94.6% | +1.3pp
Person count still fluctuates near threshold — tracked as known issue.
Verified on real hardware: COM6 (node 1) + COM9 (node 2) on ruv.net.
2026-03-30 15:48:33 -04:00
rUv
dd45160cc5
fix: skeleton jitter + person count stability (hardware-verified)
...
* chore: update vendored ruvector to latest main (v2.1.0-40)
Was at v2.0.5-172 (f8f2c600a), now at v2.1.0-40 (050c3fe6f).
316 commits with new crates: ruvector-coherence, sona, ruvector-core,
ruvector-gnn improvements, and security hardening.
Co-Authored-By: claude-flow <ruv@ruv.net>
* feat: RuVector Phases 2+3 — temporal smoothing, kinematic constraints, coherence gating
Phase 2 (sensing server):
- Temporal keypoint smoothing via EMA (alpha=0.3) with coherence-adaptive blending
- Coherence scoring: running variance of motion_energy over 20 frames
- Low coherence → reduce alpha to 0.1 (trust measurements less)
- Per-node prev_keypoints for frame-to-frame smoothing
- Bone length clamping (±20%) in derive_single_person_pose
Phase 3 (signal crate):
- SkeletonConstraints: Jakobsen relaxation (3 iterations) on 12-bone
COCO-17 kinematic tree — prevents impossible skeletons
- CompressedPoseHistory: two-tier storage (hot f32 + warm i16 quantized)
for trajectory matching and re-ID
- 8 new tests for constraints + history
Vendored ruvector updated to v2.1.0-40 (latest main, 316 commits).
Workspace deps remain at v2.0.4 (crates.io) until v2.1.0 is published.
647 tests pass across both crates (0 failures).
Refs #296
Co-Authored-By: claude-flow <ruv@ruv.net>
* fix(server): use max instead of sum for multi-node person aggregation
With nodes in the same room, each node sees the same people. Summing
per-node counts double-counted (2 nodes × 1 person = 2 persons).
Now uses max() so 2 nodes × 1 person = 1 person.
Verified on real hardware: COM6 (node 1) + COM9 (node 2) on ruv.net,
estimated_persons=1 with 1 person in room.
Co-Authored-By: claude-flow <ruv@ruv.net>
* fix(server): reduce skeleton jitter + raise person count thresholds
- EMA alpha 0.3→0.15, low-coherence 0.1→0.05
- Remove tick-based noise (main jitter source)
- Breathing 5x slower, extremity jitter 3x smaller, stride 2x smaller
- Person count 1→2 threshold 0.65→0.80
- Aggregation sum→max for same-room nodes
Verified on COM6+COM9: 1 person stable.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-30 15:17:48 -04:00
rUv
5e5781b28a
feat: RuVector all phases — temporal smoothing + kinematic constraints + coherence
...
* chore: update vendored ruvector to latest main (v2.1.0-40)
Was at v2.0.5-172 (f8f2c600a), now at v2.1.0-40 (050c3fe6f).
316 commits with new crates: ruvector-coherence, sona, ruvector-core,
ruvector-gnn improvements, and security hardening.
Co-Authored-By: claude-flow <ruv@ruv.net>
* feat: RuVector Phases 2+3 — temporal smoothing, kinematic constraints, coherence gating
Phase 2 (sensing server):
- Temporal keypoint smoothing via EMA (alpha=0.3) with coherence-adaptive blending
- Coherence scoring: running variance of motion_energy over 20 frames
- Low coherence → reduce alpha to 0.1 (trust measurements less)
- Per-node prev_keypoints for frame-to-frame smoothing
- Bone length clamping (±20%) in derive_single_person_pose
Phase 3 (signal crate):
- SkeletonConstraints: Jakobsen relaxation (3 iterations) on 12-bone
COCO-17 kinematic tree — prevents impossible skeletons
- CompressedPoseHistory: two-tier storage (hot f32 + warm i16 quantized)
for trajectory matching and re-ID
- 8 new tests for constraints + history
Vendored ruvector updated to v2.1.0-40 (latest main, 316 commits).
Workspace deps remain at v2.0.4 (crates.io) until v2.1.0 is published.
647 tests pass across both crates (0 failures).
Refs #296
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-30 14:23:21 -04:00
rUv
6f23e89909
fix: deep review optimizations — firmware + server
...
* feat(signal): subcarrier importance weighting via mincut partition (Phase 1)
Adds subcarrier_importance_weights() to ruvector signal crate — converts
mincut partition into per-subcarrier float weights (>1.0 for sensitive,
0.5 for insensitive subcarriers).
Sensing server now uses weighted mean/variance in extract_features_from_frame
instead of treating all 56 subcarriers equally. This emphasizes body-motion-
sensitive subcarriers and reduces noise from static multipath.
Expected: ~26% reduction in keypoint jitter (±15cm → ±11cm RMS).
284 tests pass (191 trainer + 51 lib + 18 vital_signs + 16 dataset + 8 multi_node).
Co-Authored-By: claude-flow <ruv@ruv.net>
* fix(firmware): stack overflow risk + tick-rate independence (review findings)
Critical fixes from deep review:
1. **Stack overflow prevention**: Moved BPM scratch buffers (br_buf, hr_buf)
from stack to static storage in both process_frame() and
update_multi_person_vitals(). Combined stack was ~6.5-7.5 KB of 8 KB
limit — now reduced by ~4 KB to safe margins.
2. **Tick-rate independence**: Post-batch yield now uses
pdMS_TO_TICKS(20) with min-1 guard instead of raw vTaskDelay(2).
Previously assumed 100Hz tick rate.
3. **EDGE_BATCH_LIMIT to header**: Moved from local const to
edge_processing.h #define for configurability.
Firmware builds clean at 843 KB.
Co-Authored-By: claude-flow <ruv@ruv.net>
* fix(server): stale node eviction, remove unsafe pointer (review findings)
Critical fixes from deep review:
1. **Stale node eviction**: node_states HashMap now evicts nodes with no
frame for >60 seconds, every 100 ticks. Prevents unbounded memory
growth and stale smoothing data when nodes are replaced.
2. **Remove unsafe raw pointer**: Replaced the unsafe raw pointer to
adaptive_model (used to break borrow checker deadlock with
node_states) with a safe .clone() before the mutable borrow.
AdaptiveModel derives Clone so this is a clean copy.
284 tests pass, zero failures.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-30 13:31:07 -04:00
rUv
1dcf5d42eb
feat(signal): subcarrier importance weighting — RuVector Phase 1
...
Adds subcarrier_importance_weights() to ruvector signal crate — converts
mincut partition into per-subcarrier float weights (>1.0 for sensitive,
0.5 for insensitive subcarriers).
Sensing server now uses weighted mean/variance in extract_features_from_frame
instead of treating all 56 subcarriers equally. This emphasizes body-motion-
sensitive subcarriers and reduces noise from static multipath.
Expected: ~26% reduction in keypoint jitter (±15cm → ±11cm RMS).
284 tests pass (191 trainer + 51 lib + 18 vital_signs + 16 dataset + 8 multi_node).
2026-03-30 13:20:05 -04:00
rUv
9814d2bc62
fix(server): correct RSSI byte offset in frame parser ( #332 )
...
Continuous Deployment / Pre-deployment Checks (push) Waiting to run
Continuous Deployment / Deploy to Staging (push) Blocked by required conditions
Continuous Deployment / Deploy to Production (push) Blocked by required conditions
Continuous Deployment / Rollback Deployment (push) Blocked by required conditions
Continuous Deployment / Post-deployment Monitoring (push) Blocked by required conditions
Continuous Deployment / Notify Deployment Status (push) Blocked by required conditions
Continuous Integration / Code Quality & Security (push) Waiting to run
Continuous Integration / Tests (push) Waiting to run
Continuous Integration / Tests-1 (push) Waiting to run
Continuous Integration / Tests-2 (push) Waiting to run
Continuous Integration / Performance Tests (push) Blocked by required conditions
Continuous Integration / Docker Build & Test (push) Blocked by required conditions
Continuous Integration / API Documentation (push) Blocked by required conditions
Continuous Integration / Notify (push) Blocked by required conditions
Security Scanning / Static Application Security Testing (push) Waiting to run
Security Scanning / Dependency Vulnerability Scan (push) Waiting to run
Security Scanning / Container Security Scan (push) Waiting to run
Security Scanning / Infrastructure Security Scan (push) Waiting to run
Security Scanning / Secret Scanning (push) Waiting to run
Security Scanning / License Compliance Scan (push) Waiting to run
Security Scanning / Security Policy Compliance (push) Waiting to run
Security Scanning / Security Report (push) Blocked by required conditions
The server parsed rssi from buf[14] and noise_floor from buf[15], but
the firmware (csi_collector.c) packs them at buf[16] and buf[17]:
Firmware: n_subcarriers=u16(6-7) freq=u32(8-11) seq=u32(12-15) rssi=i8(16)
Server: n_subcarriers=u8(6) freq=u16(8-9) seq=u32(10-13) rssi=i8(14) ← WRONG
This caused RSSI to read the high byte of the sequence counter instead
of the actual signed RSSI value, producing positive values (e.g., +9)
instead of the correct negative values (e.g., -46 dBm).
Added inline documentation of the frame layout matching csi_collector.c.
Closes #332
2026-03-30 11:54:03 -04:00
rUv
74e0ebbd41
feat(server): accuracy sprint 001 — Kalman tracker, multi-node fusion, eigenvalue counting
...
Wire three existing signal-crate components into the live sensing path:
Step 1 — Kalman Tracker (tracker_bridge.rs):
- PoseTracker from wifi-densepose-signal wired into all 5 mutable
derive_pose_from_sensing call sites
- Stable TrackId-based person IDs replace ephemeral 0-based indices
- Greedy Mahalanobis assignment with proper lifecycle transitions
(Tentative → Active → Lost → Terminated)
- Kalman-smoothed keypoint positions reduce frame-to-frame jitter
Step 2 — Multi-Node Fusion (multistatic_bridge.rs):
- MultistaticFuser replaces naive .sum() aggregation at both ESP32 paths
- Attention-weighted CSI fusion across nodes with cosine-similarity weights
- Fallback uses max (not sum) to avoid double-counting overlapping coverage
- Node positions configurable via --node-positions CLI arg
- Single-node passthrough preserved (min_nodes=1)
Step 3 — Eigenvalue Person Counting (field_model.rs upgrade):
- Full covariance matrix accumulation (replaces diagonal variance approx)
- True eigendecomposition via ndarray-linalg Eigh (Marcenko-Pastur threshold)
- estimate_occupancy() for runtime eigenvalue-based counting
- Calibration API: POST /calibration/start|stop, GET /calibration/status
- Graceful fallback to score_to_person_count when uncalibrated
New files: tracker_bridge.rs, multistatic_bridge.rs, field_bridge.rs
Modified: sensing-server main.rs, Cargo.toml; signal field_model.rs, Cargo.toml
Refs: .swarm/plans/accuracy-sprint-001.md
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-30 15:04:30 +00:00
ruv
7f02c87c6f
test(server): add multi-node mesh integration tests (ADR-068)
...
Continuous Deployment / Pre-deployment Checks (push) Has been cancelled
Continuous Integration / Code Quality & Security (push) Has been cancelled
Continuous Integration / Tests (push) Has been cancelled
Continuous Integration / Tests-1 (push) Has been cancelled
Continuous Integration / Tests-2 (push) Has been cancelled
Firmware CI / Build ESP32-S3 Firmware (push) Has been cancelled
Security Scanning / Static Application Security Testing (push) Has been cancelled
Security Scanning / Dependency Vulnerability Scan (push) Has been cancelled
Security Scanning / Container Security Scan (push) Has been cancelled
Security Scanning / Infrastructure Security Scan (push) Has been cancelled
Security Scanning / Secret Scanning (push) Has been cancelled
Security Scanning / License Compliance Scan (push) Has been cancelled
Security Scanning / Security Policy Compliance (push) Has been cancelled
Continuous Deployment / Deploy to Staging (push) Has been cancelled
Continuous Deployment / Deploy to Production (push) Has been cancelled
Continuous Deployment / Rollback Deployment (push) Has been cancelled
Continuous Deployment / Post-deployment Monitoring (push) Has been cancelled
Continuous Deployment / Notify Deployment Status (push) Has been cancelled
Continuous Integration / Performance Tests (push) Has been cancelled
Continuous Integration / Docker Build & Test (push) Has been cancelled
Continuous Integration / API Documentation (push) Has been cancelled
Continuous Integration / Notify (push) Has been cancelled
Security Scanning / Security Report (push) Has been cancelled
8 tests covering per-node state pipeline:
- Frame builder validity (CSI + vitals packet formats)
- Different nodes produce different I/Q patterns
- Multi-node UDP send (1/3/5/7/11 nodes)
- Mesh simulation with variable rates and node dropout
- Large mesh: 100 nodes x 10 frames = 1,000 frames
- Max scale: 255 unique node_ids
All 26 server tests pass (8 new + 18 existing vital signs).
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-28 11:06:57 -04:00
ruv
9a074bdf4f
fix(ci): upgrade Firmware CI to IDF v5.4, replace xxd with od ( #327 )
...
- Container: espressif/idf:v5.2 → v5.4 (matches QEMU workflow)
- Replace xxd calls with od (xxd not available in IDF container)
- Add ota_data_initial.bin to artifact upload
- Extend artifact retention to 90 days
The xxd:not-found error was blocking all Firmware CI builds since the
container migration. This unblocks binary artifact generation for
release assets.
Closes #327
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-28 11:01:44 -04:00
Taylor Dawson
d88994816f
feat: dynamic classifier classes, per-node UI, XSS fix, RSSI fix
...
Complements #326 (per-node state pipeline) with additional features:
- Dynamic adaptive classifier: discover activity classes from training
data filenames instead of hardcoded array. Users add classes via
filename convention (train_<class>_<desc>.jsonl), no code changes.
- Per-node UI cards: SensingTab shows individual node status with
color-coded markers, RSSI, variance, and classification per node.
- Colored node markers in 3D gaussian splat view (8-color palette).
- Per-node RSSI history tracking in sensing service.
- XSS fix: UI uses createElement/textContent instead of innerHTML.
- RSSI sign fix: ensure dBm values are always negative.
- GET /api/v1/nodes endpoint for per-node health monitoring.
- node_features field in WebSocket SensingUpdate messages.
- Firmware watchdog fix: yield after every frame to prevent IDLE1 starvation.
Addresses #237 , #276 , #282
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-27 21:21:15 -07:00
