341d9e05a8
* Add temporal graph evolution & RuVector integration research GOAP Agent 8 output: 1,528-line SOTA research document covering temporal graph models (TGN, JODIE, DyRep), RuVector graph memory design, mincut trajectory tracking with Kalman filtering, event detection pipelines, compressed temporal storage, cross-room transition graphs, and a 5-phase integration roadmap. Part of RF Topological Sensing research swarm (10 agents). https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add transformer architectures for graph sensing research GOAP Agent 4 output: 896-line SOTA document covering Graph Transformers (Graphormer, SAN, GPS, TokenGT), Temporal Graph Transformers (TGN, TGAT, DyRep), ViT for RF spectrograms, transformer-based mincut prediction, positional encoding for RF graphs, foundation models for RF sensing, and efficient edge deployment with INT8 quantization. Part of RF Topological Sensing research swarm (10 agents). https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add attention mechanisms for RF sensing research GOAP Agent 3 output: 1,110-line document covering GAT for RF graphs, self-attention for CSI sequences, cross-attention multi-link fusion, attention-weighted differentiable mincut, spatial node attention, antenna-level subcarrier attention, and efficient attention variants (linear, sparse, LSH, S4/Mamba). 8 ASCII architecture diagrams. Part of RF Topological Sensing research swarm (10 agents). https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add sublinear mincut algorithms research GOAP Agent 5 output: 698-line document covering classical mincut complexity, sublinear approximation (sampling, sparsifiers), dynamic mincut with lazy recomputation hybrid, streaming sketch algorithms, Benczur-Karger sparsification, local partitioning (PageRank-guided cuts), randomized methods reliability analysis, and Rust implementation with const-generic RfGraph, zero-alloc Stoer-Wagner, SIMD batch updates. Part of RF Topological Sensing research swarm (10 agents). https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add CSI edge weight computation research GOAP Agent 2 output: ~700-line document covering CSI feature extraction, coherence metrics (cross-correlation, mutual information, phasor coherence), multipath stability scoring (MUSIC, ESPRIT, ISTA), temporal windowing (EMA, Welford, Kalman), noise robustness (phase noise, AGC, clock drift), edge weight normalization, and implementation architecture showing 32KB memory for 120 edges within ESP32-S3 capability. Part of RF Topological Sensing research swarm (10 agents). https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add contrastive learning for RF coherence research GOAP Agent 7 output: 1,226-line document covering SimCLR/MoCo/BYOL for CSI, AETHER-Topo dual-head extension, coherence boundary detection with multi-scale analysis, delta-driven updates (2-12x efficiency), self-supervised pre-training protocol, triplet networks for 5-state edge classification, and MERIDIAN cross-environment transfer with EWC continual learning. Part of RF Topological Sensing research swarm (12 agents). https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add resolution and spatial granularity analysis research GOAP Agent 9 output: 1,383-line document covering Fresnel zone analysis, node density vs resolution (16-node/5m room → 30-60cm), Cramer-Rao lower bounds with Fisher Information Matrix, graph cut resolution theory, multi-frequency enhancement (6cm coherent dual-band limit), RF tomography comparison, experimental validation protocols, and resolution scaling laws (8.8cm theoretical limit). Part of RF Topological Sensing research swarm (12 agents). https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add RF graph theory and minimum cut foundations research GOAP Agent 1 output: Graph-theoretic foundations covering max-flow/min-cut for RF (Ford-Fulkerson, Stoer-Wagner, Karger), RF as dynamic graph with CSI coherence weights, topological change detection via Fiedler vector and Cheeger inequality, dynamic graph algorithms, comparison to classical RF sensing, formal mathematical framework, and 9 open research questions. Part of RF Topological Sensing research swarm (12 agents). https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add ESP32 mesh hardware constraints research GOAP Agent 6 output: ESP32 CSI capabilities (52/114 subcarriers), 16-node mesh topology with 120 edges, TDM synchronized sensing (3ms slots), computational budget (Stoer-Wagner uses 0.07% of one core), channel hopping, power analysis (0.44W/node), dual-core firmware architecture, and edge vs server computing with 100x data reduction on-device. Part of RF Topological Sensing research swarm (12 agents). https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add system architecture and prototype design research GOAP Agent 10 output: End-to-end architecture with pipeline diagrams, existing crate integration mapping, new rf_topology module design (DDD aggregate roots), 100ms latency budget breakdown, 3-phase prototype plan (4-node POC → 16-node room → 72-node multi-room), benchmark design with 8 metrics, ADR-044 draft, and Rust trait definitions (EdgeWeightComputer, TopologyGraph, MinCutSolver, BoundaryInterpolator). Part of RF Topological Sensing research swarm (12 agents). https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add quantum sensing and quantum biomedical research documents Agent 11: Quantum-level sensors (729 lines) — NV centers, SQUIDs, Rydberg atoms, quantum illumination, quantum graph theory (walks, spectral, QAOA), hybrid classical-quantum architecture, quantum ML (VQC, kernels, reservoir computing), NISQ applications (D-Wave, VQE), hardware roadmap. Agent 12: Quantum biomedical sensing (827 lines) — whole body biomagnetic mapping, neural field imaging without electrodes, circulation sensing, cellular EM signaling, non-contact diagnostics, coherence-based diagnostics (disease as coherence breakdown), neural interfaces, multimodal observatory, room-scale ambient health monitoring, graph-based biomedical analysis. Part of RF Topological Sensing research swarm (12 agents). https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add research index synthesizing all 12 documents (14,322 lines) Master index for RF Topological Sensing research compendium covering: graph theory foundations, CSI edge weights, attention mechanisms, transformers, sublinear algorithms, ESP32 hardware, contrastive learning, temporal graphs, resolution analysis, system architecture, quantum sensors, and quantum biomedical sensing. Includes key findings, proposed ADRs (044, 045), and 5-phase implementation roadmap. https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add SOTA neural decoding landscape and 10 application domains research - Doc 21: Comprehensive SOTA map (2023-2026) of brain sensors, decoders, and visualization systems with RuVector/mincut positioning analysis - Doc 22: Ten application domains for brain state observatory including disease detection, BCI, cognitive monitoring, mental health diagnostics, neurofeedback, dream reconstruction, cognitive research, HCI, wearables, and brain network digital twins with strategic roadmap https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add NV diamond neural magnetometry research document (13/22) Comprehensive 600+ line document covering NV center physics, neural magnetic field sources, sensor architecture, SQUID comparison, signal processing pipeline, RuVector integration, and development roadmap. https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add ruv-neural workspace Cargo.toml with 12 crate definitions Workspace structure for the rUv Neural brain topology analysis system. 12 mix-and-match crates with shared dependencies including RuVector integration, petgraph, rustfft, and WASM/ESP32 support. https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add ruv-neural crate ecosystem — 12 mix-and-match crates (WIP) Initial implementation of the rUv Neural brain topology analysis system: - ruv-neural-core: Core types, traits, errors, RVF format (compiles) - ruv-neural-sensor: NV diamond, OPM, EEG sensor interfaces (in progress) - ruv-neural-signal: DSP, filtering, spectral, connectivity (in progress) - ruv-neural-graph: Brain connectivity graph construction (in progress) - ruv-neural-mincut: Dynamic minimum cut topology analysis (in progress) - ruv-neural-embed: RuVector graph embeddings (in progress) - ruv-neural-memory: Persistent neural state memory + HNSW (compiles) - ruv-neural-decoder: Cognitive state classification + BCI (in progress) - ruv-neural-esp32: ESP32 edge sensor integration (compiles) - ruv-neural-wasm: WebAssembly browser bindings (in progress) - ruv-neural-viz: Visualization + ASCII rendering (in progress) - ruv-neural-cli: CLI tool (in progress) Agents still writing remaining modules. Next: fix compilation, tests, push. https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Fix ruv-neural crate compilation: all 12 crates build and 1200+ tests pass - Fix node2vec.rs type inference error (Vec<_> → Vec<Vec<f64>>) - Fix artifact.rs with full filter-based detection implementations - Fix signal crate ConnectivityMetric re-export and trait method names - Fix embed crate EmbeddingGenerator trait implementations - Complete spectral, topology, and node2vec embedders with tests - Complete preprocessing pipeline with sequential stage processing - All workspace crates compile cleanly, 0 test failures https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * Add ruv-neural-cli README https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv * fix: convert desktop icons from RGB to RGBA for Tauri build Tauri's generate_context!() macro requires RGBA PNG icons. All 5 icon files (32x32.png, 128x128.png, 128x128@2x.png, icon.icns, icon.ico) were RGB-only, causing a proc macro panic on Linux builds. Fixes #200 Co-Authored-By: claude-flow <ruv@ruv.net> * Add Subcarrier Manifold and Vitals Oracle modules for 3D visualizations - Implemented Subcarrier Manifold to visualize amplitude data as a 3D surface with height and age attributes. - Created Vitals Oracle to represent vital signs using toroidal rings and particle trails, incorporating breathing and heart rate dynamics. - Both modules utilize Three.js for rendering and include custom shaders for visual effects. * feat: complete ruv-neural implementation — physics models, security, witness verification Replace all stubs/mocks with production physics-based signal models: - NV Diamond: ODMR Lorentzian dip, 1/f pink noise (Voss-McCartney), brain oscillations - OPM: SERF-mode, 50/60Hz powerline harmonics, full cross-talk compensation via Gaussian elimination with partial pivoting - EEG: 5 frequency bands, eye blink artifacts (Fp1/Fp2), muscle artifacts, impedance-based thermal noise floor - ESP32 ADC: ring-buffer reader with calibration signal generator, i16 clamp Security hardening (SEC-001 through SEC-005): - RVF bounded allocation (16MB metadata, 256MB payload) - sample_rate validation (>0, finite) - Signal NaN/Inf rejection - ADC resolution_bits overflow clamp - HNSW HashSet visited tracking + bounds checks Performance optimizations (PERF-001 through PERF-005): - 67x fewer FFTs via pre-computed analytic signals - VecDeque O(1) eviction in memory store - Thread-local FFT planner caching - BrainGraph::validate() for edge/weight integrity - Eigenvalue convergence early termination Ed25519 witness verification system: - 41 capability attestations across all 12 crates - SHA-256 digest + Ed25519 signature - CLI commands: `witness --output` and `witness --verify` README: ethics warning, hardware parts list (AliExpress), assembly instructions Co-Authored-By: claude-flow <ruv@ruv.net> * docs: add crates.io badges and install instructions to ruv-neural README Add version badges linking to each published crate on crates.io, cargo add instructions, and crate search link in the Crate Map table. Co-Authored-By: claude-flow <ruv@ruv.net> --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| .issue-177-body.md | ||
| ADR-001-wifi-mat-disaster-detection.md | ||
| ADR-002-ruvector-rvf-integration-strategy.md | ||
| ADR-003-rvf-cognitive-containers-csi.md | ||
| ADR-004-hnsw-vector-search-fingerprinting.md | ||
| ADR-005-sona-self-learning-pose-estimation.md | ||
| ADR-006-gnn-enhanced-csi-pattern-recognition.md | ||
| ADR-007-post-quantum-cryptography-secure-sensing.md | ||
| ADR-008-distributed-consensus-multi-ap.md | ||
| ADR-009-rvf-wasm-runtime-edge-deployment.md | ||
| ADR-010-witness-chains-audit-trail-integrity.md | ||
| ADR-011-python-proof-of-reality-mock-elimination.md | ||
| ADR-012-esp32-csi-sensor-mesh.md | ||
| ADR-013-feature-level-sensing-commodity-gear.md | ||
| ADR-014-sota-signal-processing.md | ||
| ADR-015-public-dataset-training-strategy.md | ||
| ADR-016-ruvector-integration.md | ||
| ADR-017-ruvector-signal-mat-integration.md | ||
| ADR-018-esp32-dev-implementation.md | ||
| ADR-019-sensing-only-ui-mode.md | ||
| ADR-020-rust-ruvector-ai-model-migration.md | ||
| ADR-021-vital-sign-detection-rvdna-pipeline.md | ||
| ADR-022-windows-wifi-enhanced-fidelity-ruvector.md | ||
| ADR-023-trained-densepose-model-ruvector-pipeline.md | ||
| ADR-024-contrastive-csi-embedding-model.md | ||
| ADR-025-macos-corewlan-wifi-sensing.md | ||
| ADR-026-survivor-track-lifecycle.md | ||
| ADR-027-cross-environment-domain-generalization.md | ||
| ADR-028-esp32-capability-audit.md | ||
| ADR-029-ruvsense-multistatic-sensing-mode.md | ||
| ADR-030-ruvsense-persistent-field-model.md | ||
| ADR-031-ruview-sensing-first-rf-mode.md | ||
| ADR-032-multistatic-mesh-security-hardening.md | ||
| ADR-033-crv-signal-line-sensing-integration.md | ||
| ADR-034-expo-mobile-app.md | ||
| ADR-035-live-sensing-ui-accuracy.md | ||
| ADR-036-rvf-training-pipeline-ui.md | ||
| ADR-037-multi-person-pose-detection.md | ||
| ADR-038-sublinear-goal-oriented-action-planning.md | ||
| ADR-039-esp32-edge-intelligence.md | ||
| ADR-040-wasm-programmable-sensing.md | ||
| ADR-041-wasm-module-collection.md | ||
| ADR-042-coherent-human-channel-imaging.md | ||
| ADR-043-sensing-server-ui-api-completion.md | ||
| ADR-044-provisioning-tool-enhancements.md | ||
| ADR-045-amoled-display-support.md | ||
| ADR-046-android-tv-box-armbian-deployment.md | ||
| ADR-047-psychohistory-observatory-visualization.md | ||
| ADR-048-adaptive-csi-classifier.md | ||
| ADR-049-cross-platform-wifi-interface-detection.md | ||
| ADR-050-quality-engineering-security-hardening.md | ||
| ADR-052-ddd-bounded-contexts.md | ||
| ADR-052-tauri-desktop-frontend.md | ||
| ADR-053-ui-design-system.md | ||
| README.md | ||
README.md
Architecture Decision Records
This folder contains 44 Architecture Decision Records (ADRs) that document every significant technical choice in the RuView / WiFi-DensePose project.
Why ADRs?
Building a system that turns WiFi signals into human pose estimation involves hundreds of non-obvious decisions: which signal processing algorithms to use, how to bridge ESP32 firmware to a Rust pipeline, whether to run inference on-device or on a server, how to handle multi-person separation with limited subcarriers.
ADRs capture the context, options considered, decision made, and consequences for each of these choices. They serve three purposes:
-
Institutional memory — Six months from now, anyone (human or AI) can read why we chose IIR bandpass filters over FIR for vital sign extraction, not just see the code.
-
AI-assisted development — When an AI agent works on this codebase, ADRs give it the constraints and rationale it needs to make changes that align with the existing architecture. Without them, AI-generated code tends to drift — reinventing patterns that already exist, contradicting earlier decisions, or optimizing for the wrong tradeoffs.
-
Review checkpoints — Each ADR is a reviewable artifact. When a proposed change touches the architecture, the ADR forces the author to articulate tradeoffs before writing code, not after.
ADRs and Domain-Driven Design
The project uses Domain-Driven Design (DDD) to organize code into bounded contexts — each with its own language, types, and responsibilities. ADRs and DDD work together:
- ADRs define boundaries: ADR-029 (RuvSense) established multistatic sensing as a separate bounded context from single-node CSI. ADR-042 (CHCI) defined a new aggregate root for coherent channel imaging.
- DDD models define the language: The RuvSense domain model defines terms like "coherence gate", "dwell time", and "TDM slot" that ADRs reference precisely.
- Together they prevent drift: An AI agent reading ADR-039 knows that edge processing tiers are configured via NVS keys, not compile-time flags — because the ADR says so. The DDD model tells it which aggregate owns that configuration.
How ADRs are structured
Each ADR follows a consistent format:
- Context — What problem or gap prompted this decision
- Decision — What we chose to do and how
- Consequences — What improved, what got harder, and what risks remain
- References — Related ADRs, papers, and code paths
Statuses: Proposed (under discussion), Accepted (approved and/or implemented), Superseded (replaced by a later ADR).
ADR Index
Hardware and firmware
| ADR | Title | Status |
|---|---|---|
| ADR-012 | ESP32 CSI Sensor Mesh for Distributed Sensing | Accepted (partial) |
| ADR-018 | ESP32 Development Implementation Path | Proposed |
| ADR-028 | ESP32 Capability Audit and Witness Record | Accepted |
| ADR-029 | RuvSense Multistatic Sensing Mode (TDM, channel hopping) | Proposed |
| ADR-032 | Multistatic Mesh Security Hardening | Accepted |
| ADR-039 | ESP32-S3 Edge Intelligence Pipeline (on-device vitals) | Accepted (hardware-validated) |
| ADR-040 | WASM Programmable Sensing (Tier 3) | Accepted |
| ADR-041 | WASM Module Collection (65 edge modules) | Accepted (hardware-validated) |
| ADR-044 | Provisioning Tool Enhancements | Proposed |
Signal processing and sensing
| ADR | Title | Status |
|---|---|---|
| ADR-013 | Feature-Level Sensing on Commodity Gear | Accepted |
| ADR-014 | SOTA Signal Processing Algorithms | Accepted |
| ADR-021 | Vital Sign Detection (breathing, heart rate) | Partial |
| ADR-030 | Persistent Field Model and Drift Detection | Proposed |
| ADR-033 | CRV Signal Line Sensing Integration | Proposed |
| ADR-037 | Multi-Person Pose Detection from Single ESP32 | Proposed |
| ADR-042 | Coherent Human Channel Imaging (beyond CSI) | Proposed |
Machine learning and training
| ADR | Title | Status |
|---|---|---|
| ADR-005 | SONA Self-Learning for Pose Estimation | Partial |
| ADR-006 | GNN-Enhanced CSI Pattern Recognition | Partial |
| ADR-015 | Public Dataset Strategy (MM-Fi, Wi-Pose) | Accepted |
| ADR-016 | RuVector Training Pipeline Integration | Accepted |
| ADR-017 | RuVector Signal + MAT Integration | Proposed |
| ADR-020 | Migrate AI Inference to Rust (ONNX Runtime) | Accepted |
| ADR-023 | Trained DensePose Model with RuVector Pipeline | Proposed |
| ADR-024 | Project AETHER: Contrastive CSI Embeddings | Required |
| ADR-027 | Project MERIDIAN: Cross-Environment Generalization | Proposed |
Platform and UI
| ADR | Title | Status |
|---|---|---|
| ADR-019 | Sensing-Only UI with Gaussian Splats | Accepted |
| ADR-022 | Windows WiFi Enhanced Fidelity (multi-BSSID) | Partial |
| ADR-025 | macOS CoreWLAN WiFi Sensing | Proposed |
| ADR-031 | RuView Sensing-First RF Mode | Proposed |
| ADR-034 | Expo React Native Mobile App | Accepted |
| ADR-035 | Live Sensing UI Accuracy and Data Transparency | Accepted |
| ADR-036 | Training Pipeline UI Integration | Proposed |
| ADR-043 | Sensing Server UI API Completion (14 endpoints) | Accepted |
Architecture and infrastructure
| ADR | Title | Status |
|---|---|---|
| ADR-001 | WiFi-Mat Disaster Detection Architecture | Accepted |
| ADR-002 | RuVector RVF Integration Strategy | Superseded |
| ADR-003 | RVF Cognitive Containers for CSI | Proposed |
| ADR-004 | HNSW Vector Search for Fingerprinting | Partial |
| ADR-007 | Post-Quantum Cryptography for Sensing | Proposed |
| ADR-008 | Distributed Consensus for Multi-AP | Proposed |
| ADR-009 | RVF WASM Runtime for Edge Deployment | Proposed |
| ADR-010 | Witness Chains for Audit Trail Integrity | Proposed |
| ADR-011 | Proof-of-Reality and Mock Elimination | Proposed |
| ADR-026 | Survivor Track Lifecycle (MAT crate) | Accepted |
| ADR-038 | Sublinear GOAP for Roadmap Optimization | Proposed |
Related
- DDD Domain Models — Bounded context definitions, aggregate roots, and ubiquitous language
- User Guide — Setup, API reference, and hardware instructions
- Build Guide — Building from source