Neural Network Clustering and Swarm Intelligence-Based Routing Protocol for Wireless Sensor Networks: A Machine...

Area of Science:

• Computer Science
• Electrical Engineering
• Network Security

Background:

• Wireless Sensor Networks (WSNs) offer rapid deployment for critical applications like military operations and emergency response.
• WSNs require robust routing and intrusion detection mechanisms due to their decentralized nature.
• Limited energy and bandwidth in WSN nodes necessitate efficient data processing and transmission strategies.

Purpose of the Study:

• To address limitations of existing WSN solutions, including poor reliability and short network lifespan.
• To develop an efficient clustering and routing algorithm for WSNs utilizing machine learning (ML).
• To improve data handling and energy efficiency in resource-constrained WSN environments.

Main Methods:

• A novel machine learning-based algorithm was designed for clustering and routing in WSNs.
• Simulations were conducted to evaluate the performance of the proposed algorithm against existing methods.
• Key performance metrics such as accuracy, specificity, and sensitivity were analyzed.

Main Results:

• The proposed ML-based algorithm demonstrated superior performance compared to state-of-the-art models.
• Achieved high accuracy (0.93), specificity (0.93), and sensitivity (0.92) in simulations.
• Indicated significant improvements in network efficiency and data management.

Conclusions:

• The developed ML algorithm offers an effective solution for enhancing WSN performance.
• The approach addresses critical challenges in WSNs, including energy constraints and data transmission.
• This work contributes to more reliable and efficient WSNs for diverse applications.