An energy-efficient cluster-based vehicle detection on road network using intention numeration method.

Area of Science:

• Computer Science
• Network Engineering
• Data Science

Background:

• Increasing road network traffic necessitates efficient data collection and analysis.
• Existing methods for urban traffic monitoring generate low-quality data and struggle with energy drain rate calculations.
• A significant challenge lies in balancing routing protocol overhead and data quality for energy efficiency.

Purpose of the Study:

• To develop an energy-efficient cluster-based vehicle detection system for road networks.
• To address the limitations of existing schemes in calculating node energy drain rates and optimizing routing protocols.
• To enhance data aggregation and reduce data transmission in vehicular networks.

Main Methods:

• Grouping sensor nodes into clusters for vehicle detection.
• Employing polynomial regression to approximate node energy drain rates within clusters.
• Estimating total node energy through area integration.
• Implementing enhanced data aggregation using a digital signature tree to minimize data transmission.

Main Results:

• The proposed CVDRN-IN method demonstrates superior performance in energy consumption compared to existing approaches.
• The system achieves higher clustering efficiency and effectively manages node drain rates.
• Experimental evaluation using the Dodgers loop sensor dataset validates the effectiveness of the proposed methods.

Conclusions:

• The developed energy-efficient cluster-based vehicle detection method significantly improves energy consumption and clustering efficiency in road networks.
• The CVDRN-IN approach offers a viable solution for intelligent transportation systems requiring low energy expenditure.
• This research contributes to more sustainable and efficient vehicular network management.