Spectrum sensing based on deep learning classification for cognitive radios

Zheng, Shilian; Chen, Shichuan; Qi, Peihan; Zhou, Huaji; Yang, Xiaoniu

doi:10.23919/jcc.2020.02.012

Cited by 127 publications

(84 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, legitimate signal detection results show that transmission learning can further increase classi cation accuracy. Finally, colored noise experiments showed that the proposed method has improved colored noise detection performance, while the classic methods show a major degeneration in performance that con rms the uniqueness of the proposed methodology [11].…”

Section: Related Studymentioning

confidence: 72%

“…Hopefully soon, a multi channel game access and game power optimization model is suggested as well as Consistency and Supremacy of the proposed algorithm[6] was veri ed by the resultant of simulation outcomes. Shilian-Zheng' et al, 2020,[11] proposed a paper related to Cognitive Radio Networks based Spectrum analysis strategies using deep learning principles. In this paper[11], the authors presented such as…”

mentioning

confidence: 99%

“…Shilian-Zheng' et al, 2020,[11] proposed a paper related to Cognitive Radio Networks based Spectrum analysis strategies using deep learning principles. In this paper[11], the authors presented such as…”

mentioning

confidence: 99%

See 2 more Smart Citations

An Energetic Cognitive Radio Network Communication Principles with Attack Identification Strategies using Game Theory

Gayathri

Kalaivani

et al. 2021

Preprint

View full text Add to dashboard Cite

In a wireless communication industry Cognitive Radio Network is the most important concern to deal with long range communications in efficient manner with futuristic remote sensing and channel allocation policies. This kind of communication principles need to tackle the attacks in wide manner. Generally, the attacks come from the intruder end with several variations but the most common attacks are network sniffing, route trapping and so on, but in the case of Cognitive Radio Network the major threat is called Primary User Impersonation (PUI). This kind of PUI attacks acts like a regular Primary User (PU) and raise a signals accordingly to make confuse the Secondary Users to come out from the communication line as well as the entire communication spectrum utilized by the Secondary User gets affected. Due to these kinds of affections the legitimate Secondary Users suffer and left from the respective channels utilized for communication. This type of attacks highly creates an impact over the Cognitive Radio Network and causes the failure over spectrum accessing. The flexible accessibility by some voluntary users maintains a constant selection of actions to determine their appropriate target, so they can differentiate between accomplishing their objectives and being compliant with their goals. The critical role is protected against obstruction and moreover mandated by vitality criteria. At the aim to develop energy saving and power gathering cooperative spectrum, factors that are central to the success of the project must be suggested in the literature as two major protocols, such as: Time Sharing (TS) and Energy Sharing (ES). An energy utilization constraint restriction is imposed on the power cells (battery) to make sure they do not charge and discharge at around the parallel period Primary User Impersonation detection in an efficient manner, in which it uses recent advancements in cooperative spectrum sensing to devise an algorithm called Energetic Cognitive Radio Network Game Planner (ECRNGP). A Game Theory logic provides an intelligent attack identification abilities to the proposed approach to identify the threat signals immediately and notify that to the respective transmitter unit to make appropriate preventive measures for that as well as this proposed approach efficiently identifies the Primary User Impersonation and provides a sufficient protection to the CRN environment as well as Secondary Users to make a perfect communication between entities without any attack oriented constraints.

show abstract

Section: Related Studymentioning

confidence: 72%

mentioning

confidence: 99%

See 1 more Smart Citation

An Energetic Cognitive Radio Network Communication Principles with Attack Identification Strategies using Game Theory

Gayathri

Kalaivani

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…To solve the complex high-latitude state-space problems, Deep-mind combines reinforcement learning with deep learning to develop the deep Q-network (DQN) [12]. In [13], spectrum sensing was presented as a classification problem, and solved by deep learning. In [14], a novel distributed dynamic spectrum access algorithm was developed based on deep multi-user reinforcement leaning.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Multichannel Sensing in Cognitive Radio: Hierarchical Reinforcement Learning

Liu

Jiayun

2021

IEEE Access

View full text Add to dashboard Cite

Efficient use of spectral resources is critical in wireless networks and has been extensively studied in recent years. Dynamic spectrum access (DSA) is one of the key techniques on utilizing the spectral resources. Among them, reinforcement learning (RL) for DSA has gained great attention due to the excellent performance. Limited by the large state space in RL, obtaining the best solution to the spectrum access problem is often computationally expensive. Besides, it is hard to balance multiple objectives of the reward function in RL. To tackle these problems, we explore deep reinforcement learning in a layered framework and propose a hierarchical deep Q-network (h-DQN) model for DSA. The proposed approach divides the original problem into separate "sub problems", each of which is solved using its own reinforcement learning agent. This partitioning simplifies each individual problem, enables modularity, and reduces the complexity of the whole optimization process in the multi-objective case. The performance of Q-learning for dynamic sensing(QADS), deep reinforcement learning for dynamic access (DRLDA), and the proposed h-DQN model is evaluated through simulations. The simulation results show that h-DQN yields better performance with the faster convergence and higher channel utilization than the other two compared methods.INDEX TERMS Dynamic multichannel sensing, deep Q-network, hierarchical reinforcement learning, cognitive radio.

show abstract

“…Recently, machine learning techniques are introduced for spectrum sensing in the industry [7]; artificial neural network (ANN) based spectrum sensing was proposed in [8], and deep learning techniques (e.g. convolutional neural network (CNN) and recurrent neural network (RNN)) to accurately identify the spectrum occupancy were suggested in [9][10][11]. Especially, the technique in [11] is relatively simple to implement but shows good performance even at low signal to noise ratios (SNRs).…”

Section: Introductionmentioning

confidence: 99%

Spectrum Sensing Based On Deep Learning To Increase Spectrum Utilization

et.al¹

2021

TURCOMAT

View full text Add to dashboard Cite

This paper proposes a new spectrum sensing technique for cognitive radio systems. To determine vacancy of the spectrum, the proposed method employs the recurrent neural network (RNN), one of the popular deep learning techniques. The proposed technique determines the spectrum occupancy of the primary user (PU) by observing the received signal’s energy and any information on the PU signal characteristic is not used. To this end, the received signal’s spectrum is obtained by fast Fourier transform (FFT). This process is performed on consecutive received signals and the resulting spectrums are stacked. Finally, a 2-dimensional spectrum (or spectrogram) is made. This 2-D spectrum is cut into sensing channel bandwidths and inputted to the deep learning model to decide the channel’s occupancy. While the recently published spectrum sensing technique based on convolutional neural network (CNN) relies on an empty channel, the proposed technique does not require any empty channel. Only the channel signal of interest to sense is needed. Since spectrum sensing results is two (busy or idle), binary classification deep learning model is developed. According to the computer simulation results, the proposed method has similar performance with the conventional CNN-based method while the spectral efficiency of the proposed method is much higher than that of the existing scheme. In addition, the overall learnable parameters of the proposed deep learning model is only 2/3 of the existing method

show abstract

Spectrum sensing based on deep learning classification for cognitive radios

Cited by 127 publications

References 1 publication

An Energetic Cognitive Radio Network Communication Principles with Attack Identification Strategies using Game Theory

An Energetic Cognitive Radio Network Communication Principles with Attack Identification Strategies using Game Theory

Dynamic Multichannel Sensing in Cognitive Radio: Hierarchical Reinforcement Learning

Spectrum Sensing Based On Deep Learning To Increase Spectrum Utilization

Contact Info

Product

Resources

About