IAH-NET (INFORMATIVE AIR QUALITY AND HEAT INDEX NETWORK): DRONE-ASSISTED SYSTEM FOR REAL-TIME AIR QUALITY AND HEAT INDEX MONITORING
Document Types
Paper Presentation
School Name
Holy Trinity College of General Santos City
Track or Strand
Science, Technology, Engineering, and Mathematics (STEM)
Research Advisor (Last Name, First Name, Middle Initial)
Rosete, Jannine, C.
Start Date
25-6-2025 10:30 AM
End Date
25-6-2025 12:00 PM
Zoom Link/ Room Assignment
https://zoom.us/j/99613886879?pwd=XPy80hbLCUaaWCllnM7yHo2WN7kquy.1 Meeting ID: 996 1388 6879 Passcode: 259997
Abstract/Executive Summary
Air pollution and rising temperatures threaten public health and safety, necessitating advanced monitoring solutions. This study developed a drone-assisted system for autonomous air quality and heat index monitoring, ensuring real-time alerts even without human presence. By integrating the K-Nearest Neighbors (K-NN) machine learning algorithm, the system provides an innovative and cost-effective approach to identifying environmental risks and raising awareness. The system consists of a Drone system, ESP32, MQ-135 gas sensor, and DHT11 temperature and humidity sensor for data acquisition. Software development includes implementing the K-NN algorithm and calibrating sensors to enhance classification accuracy. The system categorizes air quality as SAFE, RISKY, or HAZARDOUS and the heat index as SAFE, CAUTION, or DANGER based on sensor readings. Performance evaluation through simulated trials measured transmission times, accuracy, precision, and sensitivity. Average transmission times for air quality were 6.6 seconds (SAFE), 8 seconds (RISKY), and 8.6 seconds (HAZARDOUS), while heat index transmission times were 8 seconds (SAFE), 10.8 seconds (CAUTION), and 11.8 seconds (DANGER). Utilizing a confusion matrix, the system achieved 97% accuracy, 97.37% precision, and 98.67% sensitivity, demonstrating high reliability with minimal financial burden. Statistical analysis revealed no significant difference in transmission times across different air quality, while a significant difference was revealed in the heat index classifications, further validating the system’s efficiency. This study presents a viable solution for real-time environmental monitoring, offering substantial implications for mitigating air pollution and heat-related hazards. The system enhances safety in various settings, reducing health and ecological risks through early detection and intervention.
Keywords
Keywords:Air quality index, Heat index, Drone-assisted, Machine learning, Confusion matrix
Research Theme (for Paper Presentation and Poster Presentation submissions only)
Computer and Software Technology, and Robotics (CSR)
Initial Consent for Publication
yes
Statement of Originality
yes
IAH-NET (INFORMATIVE AIR QUALITY AND HEAT INDEX NETWORK): DRONE-ASSISTED SYSTEM FOR REAL-TIME AIR QUALITY AND HEAT INDEX MONITORING
Air pollution and rising temperatures threaten public health and safety, necessitating advanced monitoring solutions. This study developed a drone-assisted system for autonomous air quality and heat index monitoring, ensuring real-time alerts even without human presence. By integrating the K-Nearest Neighbors (K-NN) machine learning algorithm, the system provides an innovative and cost-effective approach to identifying environmental risks and raising awareness. The system consists of a Drone system, ESP32, MQ-135 gas sensor, and DHT11 temperature and humidity sensor for data acquisition. Software development includes implementing the K-NN algorithm and calibrating sensors to enhance classification accuracy. The system categorizes air quality as SAFE, RISKY, or HAZARDOUS and the heat index as SAFE, CAUTION, or DANGER based on sensor readings. Performance evaluation through simulated trials measured transmission times, accuracy, precision, and sensitivity. Average transmission times for air quality were 6.6 seconds (SAFE), 8 seconds (RISKY), and 8.6 seconds (HAZARDOUS), while heat index transmission times were 8 seconds (SAFE), 10.8 seconds (CAUTION), and 11.8 seconds (DANGER). Utilizing a confusion matrix, the system achieved 97% accuracy, 97.37% precision, and 98.67% sensitivity, demonstrating high reliability with minimal financial burden. Statistical analysis revealed no significant difference in transmission times across different air quality, while a significant difference was revealed in the heat index classifications, further validating the system’s efficiency. This study presents a viable solution for real-time environmental monitoring, offering substantial implications for mitigating air pollution and heat-related hazards. The system enhances safety in various settings, reducing health and ecological risks through early detection and intervention.
https://animorepository.dlsu.edu.ph/conf_shsrescon/2025/paper_csr/11
