diff --git "a/haramguard_poster.html" "b/haramguard_poster.html" new file mode 100644--- /dev/null +++ "b/haramguard_poster.html" @@ -0,0 +1,1433 @@ + + + + + +HaramGuard — Capstone Poster 2026 + + + + +
+ + +
+
Tuwaiq Academy · Capstone Project 2026
+
+
+
+ HaramGuard Logo +
+
+

HaramGuard

+
+ Agentic AI Safety System for Real-Time Hajj Crowd Management +
+ Developed by: Adeem Alotaibi, Reem Alamoudi, Munirah Alsubaie, Nourah Alhumaid + Supervised by: Eng. Omer Nacar +
+
+
+
+
+
+
2M+
+
Hajj pilgrims annually
+
+
+
5
+
Agents in pipeline
+
+
+
12
+
Guardrails implemented
+
+
+
+
+ Multi-Agent + ReAct Pattern + Reflection Pattern + YOLOv8 + Computer Vision + FastAPI +
+
+ + +
+
System Architecture
+

HaramGuard Architecture — AISA Framework

+ +
+ +
+
+ +
+
INPUT
+
Aerial Camera Video Feed
+
+
+
+
+ +
+
OUTPUT
+
Arabic Emergency Alert — P0 / P1 / P2
+
+
+
+
+ + +
+
+
Tool & Environment Layer
+
Perception Agent
+
    +
  • YOLOv8 + BoTSORT
    • +
  • Person Count
    • +
  • Density & Spacing
    • +
+
+
→
+
+
Cognitive Agent Layer
+
Risk Agent
+
    +
  • 17-frame Sliding Window
    • +
  • ReleScore (0–1)
    • +
  • LOW / MEDIUM / HIGH
    • +
+
+
→
+
+
Cognitive Agent Layer
+
Reflection Agent
+
    +
  • Bias Detection
    • +
  • Observe → Critique
    • +
  • Corrected Risk
    • +
+
+
+
→
+
Bias
Detected?
+
No ↓
+
Level
Changed?
+
+
+
Yes →
+
+
Correct + Log
+
Critique Recorded
+
+
+
+ + +
+
+
+
Agentic Infrastructure Layer
+
Operations Agent
+
    +
  • Event Classification
    • +
  • P0 / P1 / P2
    • +
  • Arabic Action Output
    • +
+
+
→
+
+
Governance, Ethics & Policy Layer
+
Coordinator Agent (ReAct)
+
    +
  • Governance
    • +
  • Policy Enforcement
    • +
  • Ethical Check (GR-C1..5)
    • +
+
+
→
+
+
+
SQLite — Audit Trail
+
All decisions logged
+
+
+ + +
+
Runs on every frame
+
Fires only when risk level changes (~90% skipped)
+
Fires only on P0 alert
+
Every decision logged to SQLite
+
+ + +
+
Tool & Environment — Perception
+ · +
Cognitive Agent — Risk + Reflection
+ · +
Agentic Infrastructure — Operations
+ · +
Governance, Ethics & Policy — Coordinator
+
+
+
+ + + +
+
Evaluation Results
+

Quantified Performance — 4 Synthetic Ground-Truth Scenes

+ +
+
+
100%
+
System Accuracy
+
4 / 4 scenes correct end-to-end
+
+
+
100%
+
Risk → Priority Alignment
+
727 test cases — HIGH always triggers P0
+
+
+
13×
+
Faster
+
Pipeline Speed vs. Real-Time · 387 fps
+
+
+ +
+
+

Scene-by-Scene Accuracy

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
SceneCrowd SizeExpectedResultConvergence
A — Sparse5–15 personsLOWPASS ✓frame 1
B — Medium25–45 personsMEDIUMPASS ✓frame 1
C — Dense60–90 personsHIGHPASS ✓frame 1
D — Escalating5–90 personsHIGHPASS ✓frame 30
+
+
+

Component Metrics

+
+
Detection Rate
+
+
100%
+
+
+
Alignment
+
+
100%
+
+
+
Refl. Tests
+
+
5/5
+
+
+
System Acc.
+
+
100%
+
+
+
False Pos. Rate
+
+
0.4%
+
+
+
Ops Skip Rate
+
+
90%
+
+
+
+
+ + +
+
Development Process
+

14 Iterative Improvements

+
+
+
1
+
YOLO Model Upgrade
+
+
nano → 3–4 detections
+
YOLOv8 → 31 detections
+
+
+
+
2
+
Count-Based Risk Scoring
+
+
Scene C: 8%
+
Scene C: 100%
+
+
+
+
3
+
Reflection Agent Design
+
+
20-frame blind spot
+
5/5 bias tests ✓
+
+
+
+
4
+
Risk-Priority Alignment
+
+
HIGH-P1 (bug)
+
100% alignment
+
+
+
+
5
+
Modular Architecture
+
+
1 notebook file
+
6 independent modules
+
+
+
+
6
+
SQLite Audit Trail
+
+
Console logs only
+
Full audit history
+
+
+
+
7
+
Evaluation Framework
+
+
Manual testing
+
8 quantified metrics
+
+
+
+
8
+
Condition-Based Risk Factors
+
+
Count only
+
+ Compression / Flow
+
+
+
+
9
+
Coordinator ReAct Pattern
+
+
Single LLM call
+
Self-correcting 3 iters
+
+
+
+
10
+
Weight Recalibration
+
+
W_DENSITY=0.35 → 50%
+
W=0.50 → 100%
+
+
+
+
11
+
Risk Index Direction Fix
+
+
17 persons → 82% risk
+
Current count EMA
+
+
+
+
12
+
Trend Score Bidirectionality
+
+
t_score always ≥ 0.4
+
Decreasing → 0.0
+
+
+
+
13
+
Arabic UI & Decision Log
+
+
English labels, lost history
+
Arabic + cumulative log
+
+
+
+
14
+
Clean Dashboard State
+
+
Fake HIGH alert on load
+
ZERO_STATE on startup
+
+
+
+
+ + +
+
Safety & Ethics
+

Guardrails — 12 Implemented Across 4 Agents

+
Every guardrail is implemented in code and justified architecturally. Human-in-the-Loop (HITL) design: all outputs are recommendations — humans decide.
+
+
+
GR1
+
PerceptionAgent
+
Person Count Cap (MAX=1000)
+
Prevents YOLO hallucinations on busy textures from propagating to risk scoring.
+
+
+
GR2
+
PerceptionAgent
+
Density Score Cap (MAX=50)
+
Prevents density formula overflow on small frames; keeps score interpretable.
+
+
+
GR3
+
RiskAgent
+
Risk Score Clamp [0.0, 1.0]
+
Weighted sum could exceed 1.0 due to floating point. Clamp ensures valid thresholds.
+
+
+
GR4
+
OperationsAgent
+
P0 Rate Limit (1 per 5 min)
+
Prevents alert fatigue — operators who see 20 P0/hour begin ignoring them.
+
+
+
GR-C1
+
CoordinatorAgent
+
Required JSON Fields Enforced
+
LLMs occasionally omit fields. Missing arabic_alert or threat_level breaks dashboard.
+
+
+
GR-C2
+
CoordinatorAgent
+
threat_level Whitelist
+
Prevents GPT returning "EXTREME" or "UNKNOWN" that break downstream logic.
+
+
+
GR-C3
+
CoordinatorAgent
+
Confidence Score [0,1] Validated
+
LLMs sometimes return confidence as percentage (85 vs 0.85) — normalized.
+
+
+
GR-C4
+
CoordinatorAgent
+
Threat Level ↔ Risk Score Consistency
+
Full range enforcement: threat_level is overridden to match actual risk_score thresholds (LOW/MEDIUM/HIGH). Prevents LLM from returning HIGH threat during MEDIUM risk.
+
+
+
GR-C5
+
CoordinatorAgent
+
Arabic Alert Fallback
+
Arabic alert is safety-critical. Empty string on dashboard during P0 is unacceptable.
+
+
+
RF1
+
ReflectionAgent
+
Chronic LOW Bias Detection
+
Sliding window lag causes 20+ frames of LOW during escalation. Guardrail prevents missed emergencies.
+
+
+
RF2
+
ReflectionAgent
+
Rising Trend + LOW → MEDIUM
+
Rising crowd with LOW risk is a contradictory state indicating calibration failure.
+
+
+
RF3
+
ReflectionAgent
+
Count-Risk Mismatch Correction
+
80+ persons + LOW = mathematical impossibility. Absolute count override applied.
+
+
+ +
+
+
12
+
Total Guardrails
+
+
+
4 Perception & Risk Guardrails
+
5 Coordinator (LLM) Guardrails
+
3 Reflection Agent Guardrails
+
+
HITL Design: All outputs are recommendations. No action executed without human approval.
+
+
+ + +
+
Features
+
+

What HaramGuard Offers | ماذا يقدم حارس الحرم

+
+ +
+ +
Real-Time Crowd Perception
+
YOLO-powered person detection and tracking on live video feeds — estimates count, density, spacing, and flow velocity every frame.
+
+ +
+ +
Risk Scoring & Level Detection
+
Sliding-window risk model classifies crowd state as LOW / MEDIUM / HIGH with a rising/stable/falling trend — calibrated for Hajj-scale densities.
+
+ + + + + +
+ +
Human-in-the-Loop Dashboard
+
React dashboard streams live risk state, proposed actions, and coordinator plans. Operators approve or reject every recommendation — the system never acts autonomously.
+
+ +
+ +
Full Audit Trail
+
Every perception result, risk decision, reflection log, and operator action is persisted to SQLite — supporting post-incident review, governance, and compliance.
+
+ +
+
+ + + +
+
Beneficiaries
+

Stakeholders | الجهات المستفيدة

+
+
+ +
General Authority for the Care of the Two Holy Mosques
+
الهيئة العامة للعناية بشؤون الحرمين
+
المشغّل الرئيسي للنظام — يتلقى خطط التدخل وأوامر نشر الأمن وفتح البوابات مباشرةً من HaramGuard.
+
+
+ +
Nusuk
+
نُسك
+
منصة تنظيم الحج والعمرة — تستخدم بيانات الازدحام لإعادة جدولة دفعات الحجاج قبل وصولهم للمناطق عالية الخطورة.
+
+
+ +
Ministry of Hajj and Umrah
+
وزارة الحج والعمرة
+
صاحبة السياسة العليا لإدارة الحج — تستفيد من التقارير التحليلية لتحسين خطط الإدارة السنوية.
+
+
+
+ + + + + + + + +
+
Pilgrims
+
ضيوف الرحمن
+
المستفيد النهائي — سلامتهم هي الهدف الجوهري للنظام. أكثر من ٢ مليون حاج سنوياً.
+
+
+
+ + +
+ + +
+
+
Tech Stack
+
+ Python 3.11 + FastAPI + YOLOv8 + BoTSORT Tracking + GPT-oss-120b + SQLite + React +
+
+
+
HaramGuard
+
Agentic AI Capstone · Tuwaiq Academy 2026
+
100% Accuracy · 100% Risk-Priority Alignment · 12 Guardrails · 14 Iterations
+
+
+ + + \ No newline at end of file