// ML & DL-POWERED SAFETY INTELLIGENCE SYSTEM v2.0

BUILDING SMOKE DETECTION POWERED BY MACHINE LEARNING & DEEP LEARNING

Real-time IoT sensor analysis using 7 ML models plus a MobileNetV2 CNN for image-based fire/smoke detection. Sub-200ms prediction from temperature, humidity, CO₂, TVOC & particulate sensor data.

SCROLL
8MODELS (7 ML + 1 CNN) 62,630+SENSOR RECORDS 98.9%PEAK ACCURACY <200msPREDICTION LATENCY IoTSENSOR FUSION LIVEALERT SYSTEM 7ML MODELS TRAINED 62,630+SENSOR RECORDS 98.9%PEAK ACCURACY <200msPREDICTION LATENCY IoTSENSOR FUSION LIVEALERT SYSTEM

How SmokeGuard Works

01
📡

SENSOR INGESTION

IoT sensors capture temperature, humidity, CO₂ (eCO₂), TVOC, raw H₂ & ethanol, pressure, and PM1.0/PM2.5 particulate readings in real time.

02
⚙️

PREPROCESSING

Data is normalized via a fitted scaler ensuring consistent model input regardless of sensor drift or environmental variation across devices.

03
🧠

ML CLASSIFICATION

7 trained classifiers including Random Forest, SVM, Gradient Boosting analyze features to output a binary smoke/no-smoke decision.

04
🚨

INSTANT ALERT

Results are returned with confidence scores. Positive detections trigger immediate visual alerts and logging for building management.

7 Trained ML Models + 1 CNN

RANDOM FOREST
98.9%
GRADIENT BOOST
98.4%
ADABOOST
97.6%
DECISION TREE
97.1%
SVM
96.2%
K-NEAREST
95.8%
LOGISTIC REG
89.3%
CNN (IMAGE)
96.9%
🔥
⚠ SMOKE DETECTED
CONFIDENCE: 97.3%  |  MODEL: RANDOM FOREST

Zero-Latency Threat Classification

When sensors detect anomalous readings, SmokeGuard cross-references data patterns across all 12 input features to deliver a definitive threat assessment in under 200ms.

12-feature sensor fusion — temp, humidity, CO₂, TVOC, PM1.0, PM2.5...
Real-time confidence score returned with every prediction
Choose from 7 trained ML models per prediction run
Standard scaler preprocessing for consistent cross-sensor accuracy
Django-backed secure admin + user role management portal

Ready to Protect Your Building?

Deploy SmokeGuard AI for instant ML-powered smoke detection.