Energy efficient hierarchical clustering based dynamic data fusion algorithm for wireless sensor networks in smart...

Area of Science:

• Agricultural Technology
• Computer Science
• Data Science

Background:

• Smart agriculture relies on wireless sensor networks (WSNs) for environmental monitoring.
• WSN data can be noisy, redundant, and energy-constrained, hindering efficient farm management.
• Accurate event detection and resource optimization are critical challenges in smart agriculture.

Purpose of the Study:

• To propose a novel approach for enhancing energy efficiency and event detection precision in WSNs for smart agriculture.
• To address data redundancy and improve the reliability of farm status monitoring.
• To develop a dynamic data fusion technique based on hierarchical clustering for WSNs.

Main Methods:

• Hierarchical clustering is employed to group WSN nodes into clusters.
• Dynamic data fusion is utilized within clusters to aggregate and synthesize sensor data.
• Extreme Learning Machine (ELM) is applied for real-time event classification and prediction.

Main Results:

• The proposed method significantly improves energy efficiency in WSNs.
• Event detection precision is considerably enhanced, enabling real-time identification of critical farming events.
• The system achieved approximately 99.54% accuracy, outperforming existing methods by 1.81%.

Conclusions:

• Hierarchical clustering-based dynamic data fusion offers a robust solution for WSN challenges in smart agriculture.
• The integration of ELM further boosts the system's predictive and classification capabilities.
• This approach represents a valuable contribution to optimizing smart agriculture practices through advanced data processing.