Update README with project description
Browse files
README.md
CHANGED
|
@@ -1,15 +1,59 @@
|
|
| 1 |
---
|
| 2 |
sdk: gradio
|
| 3 |
-
title: Forensic Triage Intelligence
|
| 4 |
-
emoji:
|
| 5 |
-
colorFrom:
|
| 6 |
-
colorTo:
|
| 7 |
sdk_version: 6.14.0
|
| 8 |
python_version: '3.13'
|
| 9 |
app_file: app.py
|
| 10 |
pinned: false
|
| 11 |
tags:
|
| 12 |
- ml-intern
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
sdk: gradio
|
| 3 |
+
title: "🔬 Forensic Triage & Postmortem Intelligence System"
|
| 4 |
+
emoji: 🔬
|
| 5 |
+
colorFrom: red
|
| 6 |
+
colorTo: gray
|
| 7 |
sdk_version: 6.14.0
|
| 8 |
python_version: '3.13'
|
| 9 |
app_file: app.py
|
| 10 |
pinned: false
|
| 11 |
tags:
|
| 12 |
- ml-intern
|
| 13 |
+
- forensics
|
| 14 |
+
- nlp
|
| 15 |
+
- investigation
|
| 16 |
+
- medical
|
| 17 |
+
short_description: AI-powered forensic investigation support system
|
| 18 |
---
|
| 19 |
|
| 20 |
+
# 🔬 AI-Powered Forensic Triage & Postmortem Intelligence System
|
| 21 |
+
|
| 22 |
+
An intelligent investigative support system that integrates AI, NLP, and data correlation techniques to assist forensic investigations.
|
| 23 |
+
|
| 24 |
+
## Key Features
|
| 25 |
+
|
| 26 |
+
| Module | Description |
|
| 27 |
+
|--------|-------------|
|
| 28 |
+
| 📄 **Autopsy Report NLP** | Extracts forensic entities (cause of death, injuries, toxicology) from unstructured reports |
|
| 29 |
+
| ⏱️ **Time-of-Death Estimation** | Henssge nomogram + postmortem indicators for PMI calculation |
|
| 30 |
+
| 📱 **Digital Evidence Correlation** | Correlates CCTV, mobile metadata, and geolocation data |
|
| 31 |
+
| ⚠️ **Risk Scoring & Anomaly Detection** | Multi-factor risk assessment with pattern identification |
|
| 32 |
+
| 📅 **Investigation Timeline** | Integrated visualization combining all evidence sources |
|
| 33 |
+
|
| 34 |
+
## How to Use
|
| 35 |
+
|
| 36 |
+
1. **Autopsy Report**: Upload or paste an autopsy report → system extracts key forensic entities
|
| 37 |
+
2. **Time of Death**: Enter body temperature and postmortem signs → get PMI estimate with cooling curve
|
| 38 |
+
3. **Digital Evidence**: Upload CCTV/mobile logs as CSV → correlations and patterns identified
|
| 39 |
+
4. **Risk Score**: After analyzing evidence, compute multi-factor risk score
|
| 40 |
+
5. **Timeline**: Build an integrated timeline from all evidence sources
|
| 41 |
+
|
| 42 |
+
## Methodology
|
| 43 |
+
|
| 44 |
+
- **Henssge Nomogram (1988)**: Double-exponential body cooling model for PMI
|
| 45 |
+
- **Pattern-based NLP**: Forensic-domain entity recognition with confidence scoring
|
| 46 |
+
- **Multi-factor Risk Engine**: Weighted scoring across violence, toxicology, digital evidence, temporal consistency
|
| 47 |
+
- **Anomaly Detection**: Identifies cross-factor inconsistencies (e.g., defensive wounds without homicide classification)
|
| 48 |
+
|
| 49 |
+
## ⚠️ Disclaimer
|
| 50 |
+
|
| 51 |
+
This system is **strictly an investigative assistance platform**. It is NOT a replacement for forensic experts, medical professionals, or legal authorities. All outputs are intended to support human decision-making, not automate legal conclusions.
|
| 52 |
+
|
| 53 |
+
## Technical Stack
|
| 54 |
+
|
| 55 |
+
- **Frontend**: Gradio
|
| 56 |
+
- **NLP**: Regex-based forensic entity extraction
|
| 57 |
+
- **Math**: Scipy (Henssge solver), NumPy
|
| 58 |
+
- **Visualization**: Plotly (interactive charts, timelines, radar plots)
|
| 59 |
+
- **Data**: Pandas for evidence processing
|