A Review on Energy-Efficient AI-ML and IoT-Integrated Mobile Air Pollution Monitoring System Design and Development

This chapter reviews and discusses an energy-efficient artificial intelligence-machine learning (AI-ML) and Internet of things (IoT)-integrated mobile air pollution monitoring system (MAPMS). It discusses an extensive review of current literature on suitable sensors, microcontroller/edge devices, communication protocols, and AI-ML-based data analysis for energy-efficient MAPMS. It highlights their challenges, scope for further research, and the best selection of the components for the development of a newly designed MAPMS. It discusses the contemporary scope of developing design strategies for energy-efficient AI-ML and IoT-integrated MAPMS design. It discusses the further research scopes for the selection of power-efficient gas and particulate matter (PM) sensors, energy-efficient wireless communication and onboard computing, selection of low-power microcontrollers and signal conditioning circuits, strategies for sleep mode to save energy, possible optimization scopes for sensor sampling rates and duty cycling, possible scopes for adaptive power management based on pollution trends, possible scopes for edge AI inclusion for low-power real-time inference, possible scopes for intelligent task scheduling and context-aware resource allocation, and possible scopes for development of behavior-aware alerts and human-centric interface design for MAPMS. This further development of the MAPMS will be suitable for urban air quality monitoring and hotspot detection, and flexible for rural and semi-urban environments where power and connectivity are constrained.