Initial release: 6-stage ckpt (444M params) + Phone ONNX

README.md

@@ -0,0 +1,80 @@
+---
+language: ko
+library_name: pytorch
+tags:
+  - anomaly-detection
+  - wearable-sensors
+  - elderly-monitoring
+  - imu
+  - heart-rate
+license: mit
+---
+
+# SISA-RoutineGuard
+
+**노인 일상 패턴 이상 감지 시스템** (Galaxy Watch + Jetson Orin Nano)
+
+4-tier hierarchical SSM-Informed Softmax Attention 모델로 노인의 24시간 wearable 데이터에서 routine anomaly를 감지합니다.
+
+## 모델 구성
+
+| Component | Params | 위치 |
+|---|---|---|
+| PatchEncoder | 0.22M | Phone (ONNX) |
+| MinuteEncoder | 48.09M | Jetson |
+| FeatureAdapter | 0.66M | Jetson |
+| HourSlotEncoder | 142.60M | Jetson |
+| HistoryEncoder | 141.86M | Jetson |
+| QueryRefiner | 97.65M | Jetson |
+| VitalGuard | 12.01M | Jetson |
+| OutputHeads | 1.58M | Jetson |
+| **Full model** | **444.66M** | Total |
+
+## 학습 데이터
+- **CAPTURE-24** (Oxford, 151 subjects × 24h wrist accelerometer)
+- **ArWISE V3** (CASAS, 10 subjects × 9 days, 76 days raw)
+- **PPG-DaLiA** (UCI, 15 subjects)
+- **WESAD** (Schmidt 2018, 15 subjects)
+- **MHEALTH** (UCI, 10 subjects)
+
+## 학습 단계 (Plan v1.4)
+
+1. **Stage 1 — PatchEncoder**: reconstruction MSE on CAPTURE-24 + ArWISE V3 raw acc
+2. **Stage 2 — MinuteEncoder + FeatureAdapter**: alignment + InfoNCE on real CAPTURE-24
+3. **Stage 3 — HourSlotEncoder**: slot context + cross-day contrastive (real ArWISE features)
+4. **Stage 4 — HistoryEncoder + QueryRefiner**: day order + neighbor slot alignment
+5. **Stage 5 — Full model**: synthetic anomaly injection on real distribution
+6. **Stage 6 — VitalGuard**: HR regression on PPG-DaLiA + WESAD + MHEALTH
+
+## Files
+
+- `stage1_patch.pt` — PatchEncoder weights (Phone deploy)
+- `stage2_minute.pt`, `stage2_adapter.pt` — MinuteEncoder + Adapter
+- `stage3_hourslot.pt` — HourSlotEncoder
+- `stage4_history.pt`, `stage4_refiner.pt` — History + QueryRefiner
+- `stage5_full.pt` — Full model fine-tuned with anomaly injection
+- `stage6_vitalguard.pt` — VitalGuard module
+- `patch_encoder.onnx` — Phone deploy ONNX (880KB)
+- `normalizer.pkl` — Feature normalizer
+
+## Inference
+
+```python
+import torch
+from src.models.full_model import SISARoutineGuard
+
+model = SISARoutineGuard().cuda().eval()
+state = torch.load("stage5_full.pt", map_location="cpu")["model"]
+model.load_state_dict(state, strict=False)
+
+# Merge Stage 6 VitalGuard
+vg = torch.load("stage6_vitalguard.pt", map_location="cpu")["model"]
+model.vitalguard.load_state_dict(vg, strict=False)
+```
+
+코드: https://github.com/tlstngud/sisa-routineguard (private)
+
+## 평가
+- forward_replay inference: **448 ms / batch=2** (RTX 4090)
+- pytest 57/69 통과
+- 9 시나리오 normal/shift 시연 검증

normalizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:785eb9005f76a63318cfdca4f0075a882f6476bf5dd084c6f45b6c3ddb320780
+size 405

patch_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8a9cd943ea39d200a5231caabe4090beceeb9a41148ed3ac8f3f619758a5da
+size 880620

stage1_patch.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:578c2a04602a59a0d2bde9c826697c620b153b54b72e62072e3128ce692d804f
+size 878862

stage2_adapter.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f099e360f831d4ab9be63f1d4352a9e6aca4ba6c41e8faa11645fcfd6768b525
+size 2656462

stage2_minute.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61ebd23b835ad08035fb8697ef497682bcb84cc866d8e23e6b04ee5cfc75091c
+size 192411630

stage3_hourslot.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4dcdd17f60d2252c12e8ed76677442358d3757b05fc4a4284f1812dcb00b8a
+size 570743966

stage4_history.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9502d232603d513d8c55e6627e746e5abb05b505dda8028fba07b98ed37f7d9d
+size 567507699

stage4_refiner.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb063a1a99e6754c7cb0019d41ff16bb0819caaae6b6020147d399441c109e4d
+size 390625845

stage5_full.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f22774a6633ec1a2d0ab21964160252000dc77cc3b5732806dbbae31ab1cf99b
+size 1779230774

stage6_vitalguard.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c84cbf1ab835ef10f72a8524a990debaf7233dab27750e22888dcd6406a2f2b6
+size 48077842