Neural Intelligence-Driven Energy-Efficient Clustering for IoT-Enable Wireless Sensor Networks

This dataset supports the research titled “Neural Intelligence Driven Energy Efficient Clustering for IoT-enabled Wireless Sensor Network.” It contains simulation data and implementation files used to design and evaluate neural intelligence-based energy-efficient clustering techniques for IoT-enabled Wireless Sensor Networks (WSNs).
The dataset includes device property data generated for different network scenarios with 64, 100, and 200 sensor nodes deployed in a wireless sensing environment. These scenarios represent IoT-based applications such as smart agriculture and environmental monitoring. The device property data is provided in CSV format, where each file contains important node-level parameters such as node ID, node position (X and Y coordinates), initial energy, residual energy, distance to base station, cluster head status, node connectivity, and energy consumption values recorded during simulation rounds.
The dataset also includes MATLAB (.m) files that implement the neural intelligence-based clustering logic and energy optimization process. These files provide the workflow for cluster formation, cluster head selection, and performance evaluation.
In addition, NetSim 14.02 project files and related configuration files are included to reproduce the simulation scenarios and validate the experimental results.
This dataset can be used for testing energy-efficient clustering algorithms, validating neural intelligence models, comparing performance across different node densities, and studying improvements in network lifetime and energy efficiency in IoT-enabled wireless sensor networks. The dataset supports reproducible research and can be reused for academic purposes.