Outlier Detection and Spectrum Feature Extraction Based on Nearest-Neighbors Correlation and Random Forest Algorithm

Abstract

Most spectrum surveys conducted worldwide demonstrate that the radio-electric spectrum in use at any given location and instant of time is below 25%. Current spectrum management policies and spectrum utilization inefficiency is becoming unsustainable for future development of radio technologies and services. In this context, dynamic spectrum access is a promising technique for improving spectrum utilization efficiency. A key scientific gap is identifying inaccurate spectrum data from hidden nodes that is not homogeneously distributed in the spatial domain and dynamically vary in time and frequency. For bridging this gap, our paper presents the research results of a spectrum feature extraction algorithm based on multi-correlation and Random Forest. Our algorithm is capable of estimating the spectrum utilization pattern in the spatial and frequency domain with a minimum reliability of 92% for a real heterogeneous networking scenario.