d9ca9b3684
Builds directly on R5's band-spread observation. If the count-task
signal is spread across the WiFi band (R5: max/mean ratio 2.85× across
56 subcarriers), then RSSI — which is the integral of |H_k|^2 across
the band — keeps most of the information. The naive prior (RSSI throws
away 98% of CSI bytes) is misleading; the relevant metric is how much
of the *signal* is in the integral, not how many bytes are in the
representation.
Tested by aggregating each existing [56 × 20] CSI window down to a
[20]-vector RSSI proxy (mean across subcarriers per frame), training a
tiny MLP (Linear 20→32→8, 656 params, 5 KB) with vanilla NumPy SGD for
200 epochs on the same random 80/20 split as cog-person-count v0.0.2.
Result:
Full CSI v0.0.2 62.3% accuracy
RSSI-only (this) 59.1% accuracy = 94.82% retained
Per-class is also markedly more *balanced* (RSSI: 59.5 / 58.6 ; full
CSI: 86.2 / 34.3) — the tiny model on a low-dim input can't cheat by
leaning on class 0 the way v0.0.2's larger model does at inference.
What this enables on a 10-year horizon: phones, laptops, smart
speakers, smart TVs, smart lights — anything with WiFi reports RSSI
and anything with a CPU can run a 656-param MLP. Person counting
becomes a federated property of any room with WiFi, not a property of
the ESP32-S3 fleet.
What this doesn't prove (called out explicitly in the research note):
- Single room, single operator, single 30-min recording
- 2-class problem (label distribution is {0, 1})
- Single random draw — needs K-fold + multi-room replication
Three follow-up experiments queued in R8-rssi-only-count.md §'What's
next on this thread':
- Multi-room replication once #645 lands
- 3-class extension (0 / 1 / 2+) — measure the info-rate cliff
- Run on a non-ESP32 RSSI source (e.g. iw event on Linux laptop)
Files:
* examples/research-sota/r8_rssi_only_count.py — pure-NumPy, no
framework deps. Trains + evals in 0.72 s on CPU.
* examples/research-sota/r8_rssi_only_results.json — full JSON dump
for cross-tick reproducibility.
* docs/research/sota-2026-05-22/R8-rssi-only-count.md — method,
measured numbers, interpretation, what doesn't work yet.
* docs/research/sota-2026-05-22/PROGRESS.md — updated index + Done
log.
Coordination note: horizon-tracker is working on tools/ruview-mcp/
+ tools/ruview-cli/ + ADR-104 — this commit deliberately stays out
of those paths.
|
||
|---|---|---|
| .. | ||
| environment | ||
| happiness-vector | ||
| medical | ||
| research-sota | ||
| sleep | ||
| stress | ||
| three.js | ||
| README.md | ||
| ruview_live.py | ||
README.md
Examples
Real-time sensing applications built on the RuView platform.
Unified Dashboard (start here)
pip install pyserial numpy
python examples/ruview_live.py --csi COM7 --mmwave COM4
The live dashboard auto-detects available sensors and displays fused vitals, environment data, and events in real-time. Works with any combination of sensors.
Individual Examples
| Example | Sensors | What It Does |
|---|---|---|
| ruview_live.py | CSI + mmWave + Light | Unified dashboard: HR, BR, BP, stress, presence, light, RSSI |
| Medical: Blood Pressure | mmWave | Contactless BP estimation from HRV |
| Medical: Vitals Suite | mmWave | 10-in-1: HR, BR, BP, HRV, sleep stages, apnea, cough, snoring, activity, meditation |
| Sleep: Apnea Screener | mmWave | Detects breathing cessation events, computes AHI |
| Stress: HRV Monitor | mmWave | Real-time stress level from heart rate variability |
| Environment: Room Monitor | CSI + mmWave | Occupancy, light, RF fingerprint, activity events |
Hardware
| Port | Device | Cost | What It Provides |
|---|---|---|---|
| COM7 | ESP32-S3 (WiFi CSI) | ~$9 | Presence, motion, breathing, heart rate (through walls) |
| COM4 | ESP32-C6 + Seeed MR60BHA2 | ~$15 | Precise HR/BR, presence, distance, ambient light |
Either sensor works alone. Both together enable fusion (mmWave 80% + CSI 20%).
Quick Start
pip install pyserial numpy
# Unified dashboard (recommended)
python examples/ruview_live.py --csi COM7 --mmwave COM4
# Blood pressure estimation
python examples/medical/bp_estimator.py --port COM4
# Sleep apnea screening (run overnight)
python examples/sleep/apnea_screener.py --port COM4 --duration 28800
# Stress monitoring (workday session)
python examples/stress/hrv_stress_monitor.py --port COM4 --duration 3600
# Room environment monitor
python examples/environment/room_monitor.py --csi-port COM7 --mmwave-port COM4
# CSI only (no mmWave)
python examples/ruview_live.py --csi COM7 --mmwave none