Spectrum Sensing Method Based on Information Geometry and Deep Neural Network

Du, Kaixuan; Wan, Pin; Wang, Yonghua; Ai, Xiongzhi; Huang, Chen

doi:10.3390/e22010094

Cited by 15 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, numerous researchers have investigated the combination of deep learning neural networks with spectrum-sensing research. For instance, in [14], scholars Kaixuan Du et al considered the geodetic distances between signals as statistical features and employed deep neural networks (DNNs) for classifying the data based on these distances, achieving spectrum sensing. Additionally, Jianxin Gai et al proposed a spectrum-sensing method based on residual networks (ResNets) in [15].…”

Section: Spectrum Decision Achieve the Optimal Transmission Strategymentioning

confidence: 99%

A Review of Research on Spectrum Sensing Based on Deep Learning

Zhang,

Luo

2023

Electronics

View full text Add to dashboard Cite

In recent years, with the rapid development in wireless communication and 5G networks, the rapid growth in mobile users has been accompanied by an increasing demand for the electromagnetic spectrum. The birth of cognitive radio and its spectrum-sensing technology provides hope for solving the problem of low utilization of the wireless spectrum. Artificial intelligence (AI) has been widely discussed globally. Deep learning technology, known for its strong learning ability and adaptability, plays a significant role in this field. Moreover, integrating deep learning with wireless communication technology has become a prominent research direction in recent years. The research objective of this paper is to summarize the algorithm of cognitive radio spectrum-sensing technology combined with deep learning technology. To review the advantages of deep-learning-based spectrum-sensing algorithms, this paper first introduces the traditional spectrum-sensing methods. It summarizes and compares the advantages and disadvantages of each method. It then describes the application of deep learning algorithms in spectrum sensing and focuses on the typical deep-neural-network-based sensing methods. Then, the existing deep-learning-based cooperative spectrum-sensing methods are summarized. Finally, the deep learning spectrum-sensing methods are discussed, along with challenges in the field and future research directions.

show abstract

Section: Spectrum Decision Achieve the Optimal Transmission Strategymentioning

confidence: 99%

A Review of Research on Spectrum Sensing Based on Deep Learning

Zhang,

Luo

2023

Electronics

View full text Add to dashboard Cite

show abstract

“…Du et al [27] presented a new approach which uses information geometry and deep learning for spectrum sensing. In first stage, covariance matrix is computed and later geodesic distance is computed between signals which is considered as feature vector.…”

Section: Literature Reviewmentioning

confidence: 99%

DRLNet: A Deep Reinforcement Learning Network for Hybrid Features Extraction and Spectrum Sensing in Cognitive Radio Networks

M A,

C R

2023

JAIT

View full text Add to dashboard Cite

Over the past two decades, communication technologies have advanced significantly, but the growing use of various communication methods has led to a shortage of available spectrum. Cognitive Radio (CR) emerges as a solution to this challenge. A crucial aspect of CR is spectrum sensing, which detects available spectrum gaps. However, current spectrum sensing methods have limitations, including insufficient signal representation, inefficiency, and sensitivity to noise. To address these issues, this study embraces a deep learning approach and introduces an innovative spectrum detection architecture for cognitive radio networks. The method combines deep learning and reinforcement learning, leveraging deep learning for energy and energy correlation feature extraction. Additionally, a Recurrent Neural Network (RNN) module is used to capture time-shifted signal correlation. To enhance feature extraction, Short-Time Fourier Transform (STFT) feature extraction is incorporated. The combined feature vector is processed through a reinforcement learning module. Finally, these features are used to train the deep learning classifier which uses residual blocks for better representation of feature while learning. The highest prediction score is considered as the decision threshold in this work. The outcome of this work is compared with other deep learning methods in terms of 𝑷 𝒅 , 𝑷 𝒇 and sensing error for varied sample size and modulation schemes. The comparative analysis shows the robustness of proposed approach by achieving the 𝑷 𝒇 as 0.32 and 0.06 for QAM16 and QPSK modulations.

show abstract

“…The researchers of the papers [19] [20] [21], dedicated to theparallel evolution simulation model of algorithm of dust particles in campus environment, indicated that the basic idea of the Monte-Carlo method is that the solution of the problem is equivalent to a hypothetical-statistical model parameter which can be calculated by using random number, and the parameters are estimated by the statistical model of a testing sample. The paper [22] is proposed a spectrum sensing algorithm based on a deep learning convolutional neural network, which avoided the influence of the accuracy of the hypothetical-statistical model on the detection results and improved the detection probability. The researchers of the work [23] noted that Eco-Driving, a driver behavior-based method, has featured in a number of national policy documents as part of CO 2 emissions reduction or climate change strategies.…”

Section: Literature Reviewmentioning

confidence: 99%

Vehicle Dynamics with Additional Entry Lane of a Roundabout

Nazaryan¹,

Fang²

2022

JTTs

View full text Add to dashboard Cite

This research is dedicated to the study of dynamics of vehicles moving through the additional entry lanes of a roundabout. Using the data created on the base of that model the constant coefficients of the sixth-degree polynomial function, previously proposed by us, have been found. In result of this there were obtained two analytic equations of vehicles' movement, where one of them presented with the positive sign of the leading coefficient and the other one negative. These two equations allowed to make comprehensive investigation of the delays and the kinematics of the vehicles moving by such kinds of lanes. Based on the appropriate calculations it is determined vehicles' consequent delays, velocities, accelerations and decelerations. Analyzing the delays, the dynamics of accelerations and decelerations, it is done an assumption that if the leading coefficient of algorithm of movement of vehicles is negative than it will lead to larger deceleration and consequently higher environmental pollutions and higher noises.

show abstract

Spectrum Sensing Method Based on Information Geometry and Deep Neural Network

Cited by 15 publications

References 26 publications

A Review of Research on Spectrum Sensing Based on Deep Learning

A Review of Research on Spectrum Sensing Based on Deep Learning

DRLNet: A Deep Reinforcement Learning Network for Hybrid Features Extraction and Spectrum Sensing in Cognitive Radio Networks

Vehicle Dynamics with Additional Entry Lane of a Roundabout

Contact Info

Product

Resources

About