Deep Cooperative Spectrum Sensing Based on Residual Neural Network Using Feature Extraction and Random Forest Classifier

Abstract

Some bands in the frequency spectrum have become overloaded and others underutilized due to the considerable increase in demand and user allocation policy. Cognitive radio applies detection techniques to dynamically allocate unlicensed users. Cooperative spectrum sensing is currently showing promising results. Therefore, in this work, we propose a cooperative spectrum detection system based on a residual neural network architecture combined with feature extractor and random forest classifier. The objective of this paper is to propose a cooperative spectrum sensing approach that can achieve high accuracy in higher levels of noise power density with less unlicensed users cooperating in the system. Therefore, we propose to extract features of the sensing information of each unlicensed user, then we use a random forest to classify if there is a presence of a licensed user in each band analyzed by the unlicensed user. Then, information from several unlicensed users are shared to a fusion center, where the decision about the presence or absence of a licensed user is accomplished by a model trained by a residual neural network. In our work, we achieved a high level of accuracy even when the noise power density is high, which means that our proposed approach is able to recognize the presence of a licensed user in 98% of the cases when the evaluated channel suffers a high level of noise power density (−134 dBm/Hz). This result was achieved with the cooperation of 10 unlicensed users.

Passive reputation method with hybrid optimized deep model for spectrum sensing in cognitive radio network based on blockchain

“…The comparison is made with methods, like support vector machine (SVM), 25 logistic regression (LR), 26 random forest (RF), 27 CNN, 28 deep learning, 9 HBRO‐based AlexNet, and proposed BCN_passive reputation+SHBRO.…”

Supervised Learning Spectrum Sensing Method via Geometric Power Feature

“…Ref. [21], the author assumes that the noise process follows the generalized Gaussian distribution, takes the Differential Entropy (DE) in the received observations as the feature vector, and uses SVM, KNN, Random Forest (RF) [22][23][24] and Logistic Regression (LR) [25,26] to compare the performance. The experimental results show that the method based on DE features is superior to the method based on ES in detection probability, and the proposed technology is particularly useful in the low SNR condition, when the noise distribution has a heavy tail.…”

Building the Electromagnetic Situation Awareness in MANET Cognitive Radio Networks for Urban Areas

“…Because radio spectrum is a multi-dimensional space described by geographical coordinates, frequency, and time, its properties depend on the observation point and detection method. Apart from this, propagation conditions play a crucial role in spectrum assessment by specific nodes because terrain shape and obstacles may suppress radio signals at specific locations and disable their detection, and this is the main reason why cooperative spectrum sensing is widely used [ 8 , 9 , 10 , 11 ].…”

“…Additionally, neighbor nodes likely have the same spectrum status, enabling detection reliability or minimizing control traffic by eliminating neighbor nodes from the sensing procedure. Another approach is presented in [ 11 ], where the residual neural network is combined with feature extractor and random forest classifier. The feature extractor reduces the signals’ complexity and speeds up the response time.…”