Internet of Things-Based Optimized Routing and Big Data Gathering System for Landslide Detection

Area of Science:

• Geosciences and Environmental Monitoring
• Computer Science and Artificial Intelligence
• Network Engineering

Background:

• Miniaturization of devices generates big data, necessitating efficient collection methods.
• Wireless Sensor Networks (WSNs) with AI capabilities can monitor environmental hazards like landslides.
• Limited energy resources in WSNs pose a challenge for long-term landslide detection networks.

Purpose of the Study:

• To propose an optimized routing and big data gathering system (ORLAW) for landslide detection using AI-based WSNs.
• To address the challenge of network longevity and energy efficiency in landslide monitoring.
• To leverage AI for intelligent, distributed landslide detection without external intervention.

Main Methods:

• Developed an optimized routing and big data gathering system named ORLAW.
• Utilized artificial intelligence (AI) for distributed landslide detection within the WSN.
• Employed the Dynamic Salp Swarm Algorithm for cluster head selection in the WSN.
• Deployed two data collecting sinks in a simulated mountainous area.

Main Results:

• ORLAW demonstrated a 23.9% increase in the network's reliability period compared to existing cluster-based intelligent routing protocols.
• The proposed system shows superior performance in energy-efficient big data management.
• AI played a crucial role in the intelligent, autonomous detection of landslides.

Conclusions:

• ORLAW effectively enhances the reliability and energy efficiency of WSNs for landslide detection.
• The AI-driven distributed routing mechanism contributes to autonomous and timely hazard prediction.
• The system offers a promising solution for long-term environmental monitoring of catastrophic hazards.