Streamline Intelligent Crowd Monitoring with IoT Cloud Computing Middleware

Area of Science:

• Computer Science
• Ubiquitous Computing
• Network Engineering

Background:

• Indoor environments like museums and historical buildings require efficient monitoring systems for visitor tracking and safety.
• Existing solutions often rely on resource-intensive hardware or complex AI techniques, limiting their applicability in budget-constrained or low-power scenarios.

Purpose of the Study:

• To introduce a novel, cost-effective middleware for analyzing wireless sensor network (WSN) data using low-power computing devices.
• To demonstrate the middleware's capability in visitor tracking, occupancy monitoring, and as an evacuation aid in indoor settings.
• To highlight the system's fault tolerance and distributed nature for reliable data analysis.

Main Methods:

• Utilized low-power computing devices (e.g., Raspberry Pi) for data analysis.
• Implemented a basic MapReduce algorithm for data gathering and distribution across nodes.
• Employed RFID sensors for visitor badge data collection and mini-computers for local storage.
• Integrated a leader election algorithm for fault tolerance in the distributed system.

Main Results:

• The middleware successfully gathered and analyzed WSN data, demonstrating visitor tracking and occupancy monitoring capabilities.
• Performance metrics validated the system's viability, matching resource-intensive methods despite using simpler hardware.
• The fault-tolerant, distributed setup using budget-friendly devices proved effective in a real-world historical building.
• The system showed promise for swift prototyping and accurate validation of findings in indoor monitoring applications.

Conclusions:

• The developed middleware offers an innovative, fault-tolerant, and distributed solution for indoor monitoring using low-power devices.
• It provides a cost-effective alternative to resource-heavy systems for applications like visitor tracking and occupancy management.
• The system is particularly relevant for historical buildings, museums, and post-pandemic environments requiring efficient monitoring and crowd management.