Machine learning techniques with probability vector for cooperative spectrum sensing in cognitive radio networks

Lu, Yingqi; Zhu, Pai; Wang, Donglin; Fattouche, M.

doi:10.1109/wcnc.2016.7564840

Cited by 68 publications

(40 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the method can only be applied to the neural network method. Reference [20] proposes a method that downconverts a high-dimensional feature vector to a constant two-dimensional feature vector for machine learning techniques while maintaining the same spectrum sensing performance. That method reduces the training and classification time because of its lower feature dimension and can be applied to RAT identification systems, but it cannot improve the classification accuracy.…”

Section: Normalization Methodsmentioning

confidence: 99%

Normalization of Radio Feature for Online Learning for Identification in Cognitive Radio

Asakura

Ichikawa

Kawakita

2019

SICE Journal of Control, Measurement, and System Integration

View full text Add to dashboard Cite

The identification of the radio access technology (RAT) of the primary user by secondary users is important to avoid interference for spectrum-sharing techniques using cognitive radio (CR). RATs have become more diversified with the introduction of various services that use wireless communication. Therefore, it is desirable that a RAT identification system, which can easily cope with the diversification of RATs, is applied to CR. The purpose of this study is to use online learning to identify multiple RATs in the same frequency band. To improve the accuracy of identifying RATs with similar features, we evaluate a normalization of radio feature method proposed in our previous research for the features extracted from the signal's spectrogram. We evaluate the RAT classifier created using the proposed method by calculating the curve of receiver operating characteristics (ROC) and the identification accuracy. The results for the ROC curve show that the proposed method is effective for several supervised learning methods. Moreover, the results for the identification accuracy show that the proposed method improves the identification performance compared to the identification accuracy of conventional methods.

show abstract

Section: Normalization Methodsmentioning

confidence: 99%

Normalization of Radio Feature for Online Learning for Identification in Cognitive Radio

Asakura

Ichikawa

Kawakita

2019

SICE Journal of Control, Measurement, and System Integration

View full text Add to dashboard Cite

show abstract

“…Furthermore, [23] proposed an algorithm incorporating a fuzzy SVM and a nonparallel hyperplane SVM that is more robust to noise uncertainty. A low-dimensional probability vector is proposed as the feature vector for machine learning-based classification for CSS in [24], resulting in small training duration and a short classification time for testing vectors. Authors in [25] designed a framework based on Bayesian machine learning exploiting the mobility of multiple SUs to simultaneously collect spectrum sensing data and cooperatively derive the global spectrum states.…”

Section: Related Workmentioning

confidence: 99%

A Deep Convolutional Neural Network Based Transfer Learning Method for Non-Cooperative Spectrum Sensing

2020

View full text Add to dashboard Cite

In this paper, we investigate machine learning methods for enabling high performance noncooperative spectrum sensing, for future cognitive radio systems. The fulfillment of sensing requirements is crucial for ensuring an efficient reuse of the scarce spectrum by unlicensed users, without causing harmful interference to primary users. In this work, we propose a deep convolutional neural network-based transfer learning framework for non-cooperative spectrum sensing in TV bands, applicable across various locations, wireless environments and even frequency assignments. Specifically, we design a four-layer convolutional neural network for limiting the computational costs while satisfying the sensing requirements, and apply transfer learning by freezing the first two convolutional layers. The performance of the proposed method is evaluated against benchmarks, based on over 29,000 spectrograms collected in UHF TV band from a recent measurement campaign. The experiments show that thanks to transfer learning, the proposed method is able to detect TV signals with high accuracy despite a significantly reduced amount of data, thereby providing a high adaptability to various locations, environments, and frequencies. Furthermore, the proposed method with transfer learning not only guarantees the sensing requirements but also realizes up to 94% reduction of training time of the network, as well as 20% reduction of the required sensing time, compared to the case without transfer learning.

show abstract

“…The vector of the signal energy is considered as a feature vector to train a classifier to decide whether the PU is presence or not. In [25], a spectrum sensing method based on Kmeans clustering and support vector machine algorithms was presented. To reduce the computational burden, a lowdimensional probability vector was designed as the feature vector and used it to obtain a classifier to achieve spectrum sensing.…”

Section: A Related Workmentioning

confidence: 99%

“…Citation information: DOI 10.1109/ACCESS.2020.3019422, IEEE Access Initialize the cluster center Υ 0 and the membership matrix 0Update the cluster centers Υ new by(24) Update the membership matrix new by(25) …”

mentioning

confidence: 99%

Information Geometry-Based Fuzzy-C Means Algorithm for Cooperative Spectrum Sensing

Zhang

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In this paper, the spectrum sensing problem is investigated under the context of information geometry and a novel clustering algorithm based spectrum sensing scheme is developed to obtain a classifier to estimate the channel state of primary user (PU). In order to enhance the sensing performance at complex environment, the empirical mode decomposition (EMD) algorithm is applied to wipe off the noise component of the received signals from all secondary users (SUs). Subsequently, a signal matrix composed of the reconstructed signals is constructed. Based on the information geometry (IG) theory, the covariance matrix of the signal matrix is mapped into a point on a manifold. Then, the sample points on the manifold are collected as a data set. Moreover, a novel clustering algorithm, namely Riemannian distance based Fuzzyc means clustering (RDFCM) algorithm, is developed to cluster the samples on manifold for obtaining a classifier, which is employed to decide the PU state. The simulation results show that compared with other spectrum sensing methods, the proposed scheme improves the performance of detection.

show abstract

Machine learning techniques with probability vector for cooperative spectrum sensing in cognitive radio networks

Cited by 68 publications

References 8 publications

Normalization of Radio Feature for Online Learning for Identification in Cognitive Radio

Normalization of Radio Feature for Online Learning for Identification in Cognitive Radio

A Deep Convolutional Neural Network Based Transfer Learning Method for Non-Cooperative Spectrum Sensing

Information Geometry-Based Fuzzy-C Means Algorithm for Cooperative Spectrum Sensing

Contact Info

Product

Resources

About