DECISION TREE WITH HILL CLIMBING ALGORITHM BASED SPECTRUM HOLE DETECTION IN COGNITIVE RADIO NETWORK
The radio spectrum is one of the most highly regulated and limited natural resources. Cognitive Radio (CR) technology addresses spectrum scarcity in wireless communication systems by enabling opportunistic spectrum access. Spectrum Sensing (SS) is a vital process in Cognitive Radio Networks (CRNs) f...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
XLESCIENCE
2025-06-01
|
| Series: | International Journal of Advances in Signal and Image Sciences |
| Subjects: | |
| Online Access: | https://xlescience.org/index.php/IJASIS/article/view/287 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The radio spectrum is one of the most highly regulated and limited natural resources. Cognitive Radio (CR) technology addresses spectrum scarcity in wireless communication systems by enabling opportunistic spectrum access. Spectrum Sensing (SS) is a vital process in Cognitive Radio Networks (CRNs) for identifying unused spectrum bands, also known as spectrum holes. This paper proposes a novel hybrid technique, termed Decision Tree with Hill Climbing (DTHC), for efficient spectrum hole detection in CRNs. The objective of the DTHC method is to improve detection accuracy while minimizing false alarm rates. The approach integrates a Decision Tree (DT) algorithm for rapid initial classification of Primary User (PU) activity, followed by a Hill Climbing (HC) optimization algorithm that fine-tunes the detection based on a fitness function. Entropy and throughput metrics are employed as decision conditions at each sensing channel, enhancing uncertainty measurement and maintaining detection robustness under low Signal-to-Noise Ratio (SNR) conditions. The HC algorithm dynamically optimizes the fitness threshold, enabling adaptive decision-making that accommodates environmental variability. Simulation results confirm that the DTHC method achieves a spectrum hole detection accuracy of 99%, with a miss-detection probability below 0.9%, demonstrating its effectiveness in enhancing CRN performance while maintaining low complexity. |
|---|---|
| ISSN: | 2457-0370 |