AI-Driven Environmental and Stress-Responsive Calming System for Zoo Animals

Zoo animals often experience stress due to fluctuating environmental factors, excessive noise, or irregular human activity, which can negatively affect their health and behavior. This research proposes an AI-driven environmental and stress-responsive calming system that continuously
monitors zoo enclosures using a network of IoT sensors and intelligent data analytics. The sensing layer integrates temperature, humidity, air quality, light, sound, and motion sensors to detect environmental variations and behavioral anomalies. Real-time data are processed through an ESP32-based control unit and transmitted to a cloud platform through Wi-Fi and LoRa communication, where a machine learning model predicts stress levels based on environmental and behavioral parameters. When stress indicators exceed safe thresholds, the system automatically activates adaptive calming mechanisms—such as adjusting light intensity, temperature, or playing soothing sounds—to restore comfort. The system provides a user dashboard for zookeepers to visualize animal mood trends, environmental fluctuations,
and intervention logs. Experimental simulations demonstrate that the proposed model can effectively reduce stress levels and maintain optimal living conditions, enhancing both animal welfare and management efficiency.