Spectrum-sensing Method Research Articles

A Deep-Learning-Based Method for Spectrum Sensing with Multiple Feature Combination

Cognitive radio networks enable the detection and opportunistic access to an idle spectrum through spectrum-sensing technologies, thus providing services to secondary users. However, at a low signal-to-noise ratio (SNR), existing spectrum-sensing methods, such as energy statistics and cyclostationary detection, tend to fail or become overly complex, limiting their sensing accuracy in complex application scenarios. In recent years, the integration of deep learning with wireless communications has shown significant potential. Utilizing neural networks to learn the statistical characteristics of signals can effectively adapt to the changing communication environment. To enhance spectrum-sensing performance under low-SNR conditions, this paper proposes a deep-learning-based spectrum-sensing method that combines multiple signal features, including energy statistics, power spectrum, cyclostationarity, and I/Q components. The proposed method used these combined features to form a specific matrix, which was then efficiently learned and detected through the designed ‘SenseNet’ network. Experimental results showed that at an SNR of −20 dB, the SenseNet model achieved a 58.8% spectrum-sensing accuracy, which is a 3.3% improvement over the existing convolutional neural network model.

A Review of Research on Spectrum Sensing Based on Deep Learning

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.

Evaluation of 5G techniques affecting the deployment of smart hospital infrastructure: Understanding 5G, AI and IoT role in smart hospital

Smart Hospital will play a key role in improving the quality of services (QoS) related to the health sector. In the present scenario, it is impossible to accommodate an ageing population with the current infrastructure and facilities provided by conventional hospitals. However, the integration of technologies with the conventional hospital is enhancing the medical services and also making it easier for the public, who can save time and money by getting all the necessary medical facilities while sitting at home. The deployment of the fifth generation (5G) is taking place all over the world. The 5G network offers a better service that can be used in hospitals to make it a smart health service provider with online facilities such as video monitoring, suggesting a proper medical prescription based on medical data, remote surgery, and so on. High bandwidth, a fast data rate, low latency, and a low peak-to-average power ratio (PAPR) are some requirements that need to be fulfilled by the 5G radio. In this work, we focus on improving the power savings, spectral access, latency, and Bit error rate (BER) of the advanced 5G waveforms such as non-orthogonal multiple access (NOMA), filter bank multi carrier (FBMC), and orthogonal frequency division multiplexing (OFDM). In the first part of the article, we proposed a PAPR reduction algorithm to improve the power efficiency of the power amplifier (PA) for 5G waveforms. Several algorithms are applied to the 5G waveforms, and their performances are estimated in terms of PAPR curves. In the second part, we have utilised advanced detection algorithms to improve the signal detection of the 5G waveforms. The simulation results reveal that the proposed algorithms efficiently enhance the throughput of the framework. In the third part, we improve the spectral efficiency of the 5G waveforms by applying spectrum sensing (SS) algorithms. It is seen that the SS methods efficiently reduce the spectrum leakage of the multi-carrier waveforms (MCW). Finally, we examined the role and challenges of the Internet of Things (IoT) and artificial intelligence (AI) in smart hospitals. Overall, it is concluded that hospitals can become more effective, cut expenses, and provide better patient care with the aid of AI and IoT. Hospitals can improve patient outcomes and the state of the healthcare system as a whole by utilising these technologies.

Feature-Based Spectrum Sensing of NOMA System for Cognitive IoT Networks

With the rapid increase of the demand for the Internet of Things (IoT), spectrum resources have incremental challenges. Nonorthogonal multiple access (NOMA) and spectrum sensing (SS) are considered key candidate technologies for next-generation wireless communications to improve spectrum utilization. Nevertheless, using both technologies at the same time makes the system more complex and brings new challenges to user differentiation. In order to make better use of these advantages, we creatively propose a feature detection-based SS method for NOMA systems. To better distinguish the relationship between the presence or absence of signals from different NOMA users, we employ feature detection to obtain the feature values of each user. We propose workflows and transceiver architectures combining the two technologies. Based on the relationship among users’ priorities, power, and transmission in common scenarios, we design a downlink mode and two uplink modes and deduce the threshold settings of the corresponding modes. Meanwhile, we also customarily propose enhanced algorithms, to have a marked increase in the performance for the proposed method in various modes. Experimental results illustrate that the proposed technique is feasible and has prominent detection performance and satisfying throughput performance.

Spectrum-Sensing Method for Arc Fault Detection in Direct Current System with Lithium Batteries

Spectrum-Sensing Method for Arc Fault Detection in Direct Current System with Lithium Batteries

Operational Characteristics of Square-Law Combining Energy Detector in MIMO-OFDM Cognitive Radio Systems

To ensure effective spectrum usage, cognitive radio networks (CRNs) are being investigated extensively. The important function of CRNs is spectrum sensing (SS). This is the process of sensing the unused frequency spectrum and deciding whether the signal transmission of a primary user (PU) exists. In this work, the results of a performance analysis related to detecting PU signals using the energy detection (ED) SS method realized by employing the square-law combining (SLC) technique are presented. The assessment of the effectiveness of the ED method is performed in relation to prominent communication technology based on Orthogonal Frequency Division Multiplexing (OFDM) and Multiple-Input Multiple-Output (MIMO) transmissions. Due to the impact of changes in the noise power of the PU signal, referred to as noise uncertainty (NU), the MIMO-OFDM transmission in a real communication environment cannot guarantee accurate sensing performed by employing ED based on the SLC method at the secondary user (SU). More precise SS can be achieved if dynamic detection threshold (DDT) changes are employed according to the channel conditions impacted by NU. Thus, this work investigated the effect of NU variations and DDT adjustments on the detection probability for various levels of false alarm probability. This interdependence is presented as receiver operating characteristic (ROC) curves. A mathematical model including different operational parameters was developed to define the fundamental parameters of the ED method based on the SLC approach. Using the developed mathematical model, an algorithm was created which simulates SLC ED processes using DDT in single-input single-output (SISO)- and MIMO-OFDM communication systems affected by NU. Based on the simulation results, comprehensive analyses of the impact of versatile DDT adaptations and NU variations on the shape of the ROC curves for the ED process performed with different numbers of transmitting and receiving antenna, modulation techniques, detection sample numbers, PU transmitting powers, and SNR values are presented.

CNN-aided multiple PU spectrum sensing in uncalibrated massive antennas SU system

This paper deploys the Convolutional Neural Network (CNN) to learn and set the statistical test in Spectrum Sensing (SS) task of multiple primary user (PU) sources in massive uncalibrated antennas of secondary users (SU) sharing the same spectrum resources. The proposed deep learning-based SS method (DL-SS) is based on the CNN architecture that has the capability of extracting features of the sample covariance matrices (SCMs) that are given as the network input, improving the overall performance and robustness. The proposed CNN-SS method is compared with nine recent multiple-antennas SS methods, namely the arithmetic–geometric detector (AGM), John’s detector (JD), sphericity detector (SD), generalized likelihood test (GLRT), locally most powerful invariant test (LMPIT), maximum–minimum eigenvalue detector (MME), covariance detector (CAV), Hadamard detector (HD) and volume detector (VD) methods; besides, the proposed method is also compared with five recent state-of-art CNN-based SS methodologies. Performance-complexity trade-off of the proposed and reference SS methods are corroborated via Monte Carlo Simulations (MCS). The proposed CNN-SS method under uncalibrated massive antennas reveals substantial benefits w.r.t. the reference methods and is competitive with others CNN-SS methodologies, both in terms of complexity and performance, achieving detection probability of Pd=0.9(@SNR=−20dB) under very low false alarm probability Pf=0.1. Under different figures of merit, the performance of the CNN-based SS detector has revealed to be indubitably superior regarding the state-of-art SS detectors. However, the proposed CNN-based SS detector presents relative computational complexity increases. Hence, to be effective, such a superior operational performance requires a very efficient processing structure in the SU base stations.

Convolutional neural network model for spectrum sensing in cognitive radio systems

SummaryCognitive radio (CR) has become an interesting research field that attracts researchers due to its increasing spectrum efficiency. Therefore, spectrum sensing (SS) is the essential function of cognitive radio systems. This paper presents an efficient SS model based on convolutional neural networks (CNNs). We use the spectrogram images of the received signals as the input to the CNN and use various images for signal and noise at different low primary‐user (PU) signal‐to‐noise ratios (SNRs) to train the network model. The model extracts the main features from the spectrogram images to represent signals and noise. Hence, this model can efficiently discriminate between signal and noise at different SNRs. The detection performance of the suggested model is compared with those of the traditional one‐stage, two‐stage SS methods, and different previous CNN models. The obtained outcomes demonstrate that the suggested model increases the detection accuracy more than those of the previous one‐stage SS methods by 17% at low SNRs of −20 dB and more than the previous two‐stage SS methods by 8% at low SNRs of −20 dB. In addition, it is demonstrated that the suggested model offers shorter sensing times than those of the two‐stage and one‐stage SS methods in the orders of 16.3, 16.6, 1.1, and 1.5 ms at SNRs of −20, −15, −10 and −5 dB, respectively. Furthermore, the proposed model improves the detection accuracy better than the different previously compared CNN models by 28% and 19% at low SNRs of −20 and −15 dB, respectively.

Spectrum sensing via temporal convolutional network

In this paper, we investigate a spectrum-sensing system in the presence of a satellite, where the satellite works as a sensing node. Considering the conventional energy detection method is sensitive to the noise uncertainty, thus, a temporal convolutional network (TCN) based spectrum-sensing method is designed to eliminate the effect of the noise uncertainty and improve the performance of spectrum sensing, relying on the offline training and the online detection stages. Specifically, in the offline training stage, spectrum data captured by the satellite is sent to the TCN deployed on the gateway for training purpose. Moreover, in the online detection stage, the well trained TCN is utilized to perform real-time spectrum sensing, which can upgrade spectrum-sensing performance by exploiting the temporal features. Additionally, simulation results demonstrate that the proposed method achieves a higher probability of detection than that of the conventional energy detection (ED), the convolutional neural network (CNN), and deep neural network (DNN). Furthermore, the proposed method outperforms the CNN and the DNN in terms of a lower computational complexity.

A Metaheuristic Based Approach for Threshold Optimization for Spectrum Sensing in Cognitive Radio Networks

Background: The mounting growth of wireless technology is attracting a high demand for the frequency spectrum. The measurements of spectrum usage depict that a significant portion of the spectrum lays unoccupied or overcrowded. The main cause of the glitch is the existing inefficient and fixed scheme of spectral allocation. Cognitive radio is one such technology that permits wireless devices to detect the unused frequency band and reconfigure its operating parameters to attain the required quality of service. Objective: To permit the dynamic allocation of the frequency band, spectrum sensing is performed which is an essential function of Cognitive radio and involves detection of an unused spectrum space to set up a communication link. Method: This paper presents a meta-heuristic approach for selection of a decision threshold for energy detection based spectrum sensing. At low SNR and in the presence of noise uncertainty, the performance of energy detection method fails. A novel adaptive double threshold based spectrumsensing method is proposed to avoid such a sensing failure. Further, the metaheuristic approach employs Particle Swarm Optimization (PSO) algorithm to compute an optimal value of the threshold to attain robustness against noise uncertainty at low SNR. Results: The simulation results of the proposed metaheuristic double threshold based spectrum sensing method demonstrate enhanced performance in comparison to the existing methods in terms of reduced error rate and increased detection probability. Some of the existing methods have been analyzed and compared from a survey of recent patents on spectrum sensing methods to support the new findings The concept of adaptive thresholding improves the detection probability by 39 % and 27 % at noise uncertainty of 1.02 and 1.04, respectively at a signal to noise ratio of -10 dB. Furthermore, the error probability reduces to 58% at the optimal threshold using Particle Swarm Optimization (PSO) algorithm for the signal to noise ratio of -9 dB. Conclusions: The main outcome of this work is the reduction in the probability of sensing failure and improvement in the detection probability using adaptive double thresholds at low SNR. Further, particle swarm optimization helps in obtaining the minimum probability of error under noise uncertainty with an optimal threshold.

DWT Based Energy Detection Spectrum Sensing Method for Cognitive Radio System

In this paper a new blind energy detection spectrum-sensing method based on Discreet Wavelet Transform (DWT) is proposed. The method utilizes the DWT sub-band to collects the received energy. The proposed method recognizes the Primary User (PU) signal from noise only signal using the differences in the collected energy in first and last sub-bands of one level DWT. The simulation results show that the proposed method achieves improved detection probability especially at low Signal to Noise Ratio (SNR) compared to Conventional Energy Detector (CED). The results also show that the proposed method has shorter sensing time and less Energy Consumption (EC) compared to CED due to using small number of processed sample. Therefore, this method is suitable for Cognitive Radio (CR) applications where only limited energy like device battery is available.

Different Spectrum Sensing Technique in Cognitive Radio Environment

A cognitive radio (CR) is one of the wireless sensor networks and the use of CR is increasing day by day. It is the process of learning via perception, planning, reasoning and continuously updating and upgrading the academic history of information. The cognitive radio has spectrum sensing (SS) problem in opportunistic spectrum access process. The SS, where the second user has to fill the unused spectrum of a licensed user when primary user (PU) not in use. It may arise interference problem to the user by the transmission of information in WSNs. Thus; this paper providing the comprehensive survey with the brief explanation of cognitive radio along with SS methods to reduce the issues appear in CR. The open research problems are discussed by considering previously existed research papers.

A New Method of Spectrum Sensing in Cognitive Radio for Dynamic and Randomly Modelled Primary Users

In this study, a new spectrum sensing method for cognitive radio (CR) is proposed for primary user (PU) signals which are modelled as random with unknown power. It is also assumed that, being dynamic, the PU might exhibit multiple status changes in the channel within the sensing period. As a novel approach for detecting dynamic and randomly modelled PUs, we propose a cumulative sum based weighted energy detector (CuS-WED) that only utilizes the samples between the last status change point (LSCP) of the PU and the end of the sensing period contrary to using all the observed data samples in the sensing period. It is shown that the proposed sensing strategy provides noticeable performance improvement in detecting dynamic and randomly modelled PUs. Probability of detection performance of the proposed sensing scheme is investigated for strictly one, at most two, and at most three status changes of the PU. Based on simulation results, it is concluded that the proposed method performs better than the other existing techniques, especially for low probability of false alarm values.

Effects of Real Instrument on Performance of an Energy Detection-Based Spectrum Sensing Method

In cognitive radio (CR) networks, the role of spectrum sensing (SS) is crucial to enable an efficient exploitation of the radio spectrum resource. The need to measure spectrum occupancy turns CRs to be de facto measurement instruments, so it becomes crucial to analyze how real instrumentation peculiarities could affect performance in spectral measurements (i.e., SS performance). In this paper, a commercial software-defined radio (SDR) is adopted as cognitive device, and its capability to accurately measure occupied spectrum is analyzed in comparison also with a simulation setup, where the same analog-to-digital converter (ADC) is modeled and simulated, and equivalent signal-to-noise ratios (SNRs) are replicated. To this aim, a suitable experimental setup has been designed, metrologically characterized, and tuned. Experimental results prove how nominal SNR typically adopted for testing the performance of SS methods is not sufficient to model the impairments of a real acquisition chain, even jointly with a modeling of the digitization process. To assure a reliable SS method validation, new approaches have to be considered for enhancing the accordance between the performance predicted in the simulation environment and the experimental one reachable on real devices. Since different architectures of CRs are present on the market, the experimental tests should be preferred for a reliable SS performance assessment.

A Novel Multiband Spectrum Sensing Method Based on Wavelets and the Higuchi Fractal Dimension.

In this work, two novel methodologies for the multiband spectrum sensing in cognitive radios are implemented. Methods are based on the continuous wavelet transform (CWT) and the multiresolution analysis (MRA) to detect the edges of available holes in the considered wideband spectrum. Besides, MRA is also combined with the Higuchi fractal dimension (a non-linear measure) to establish the decision rule permitting the detection of the absence or presence of one or multiple primary users in the studied wideband spectrum. Methods were tested on simulated and real signals showing a good performance. The results present these two methods as effective options for detecting primary user activity on the multiband spectrum. The first methodology works for 95% of cases, while the second one presents 98% of effectivity under simulated signals of signal-to-noise ratios (SNR) higher than 0 dB.

An enhanced two‐phase SVM algorithm for cooperative spectrum sensing in cognitive radio networks

SummaryCognitive radio (CR) networks have emerged recently to address the problem of spectrum scarcity. As reliable spectrum sensing (SS) is vital in low signal‐to‐noise ratio (SNR) for CR networks, we propose a novel method of enhancing support vector machines (SVM) classifier named as 2‐Phase SVM for the task of SS in a cooperative sensing structure. In this study, the vectors containing energy levels of primary users (PU) are considered as feature vectors and are fed into the classifier during training and test phase. First, the classifier is trained; afterward, the test feature vectors are labeled as channel available class or channel unavailable class in an online fashion by using 2‐Phase SVM, which is applied during two phases compared with the conventional SVM algorithm. The performance of suggested cooperative SS method is evaluated by receiver operating characteristic (ROC) curve and the functionality of our proposed algorithm is qualified in terms of misclassification error rate in addition to misclassification risk. The results reveal that 2‐Phase SVM outperforms previous methods since it not only increases the classification accuracy and reduces the misclassification risk but also enhances the detection probability.

Wideband Spectrum Sensing Based on Single-Channel Sub-Nyquist Sampling for Cognitive Radio.

Spectrum sensing is an important task in cognitive radio. However, currently available Analog-to-Digital Converters (ADC) can hardly satisfy the sampling rate requirement for wideband signals. Even with such an ADC, the cost is extremely high in terms of price and power consumption. In this paper, we propose a spectrum-sensing method based on single-channel sub-Nyquist sampling. Firstly, a serial Multi-Coset Sampling (MCS) structure is designed to avoid mismatches among sub-ADCs in the traditional parallel MCS. Clocks of the sample/hold and ADC are provided by two non-uniform sampling clocks. The cooperation between these two non-uniform sampling clocks shifts the high sampling rate burden from the ADC to the sample/hold. Secondly, a power spectrum estimation method using sub-Nyquist samples is introduced, and an efficient spectrum-sensing algorithm is proposed. By exploiting the frequency-smoothing property, the proposed efficient spectrum-sensing algorithm only needs to estimate power spectrum at partial frequency bins to conduct spectrum sensing, which will save a large amount of computational cost. Finally, the sampling pattern design of the proposed serial MCS is given, and it is proved to be a minimal circular sparse ruler with an additional constraint. Simulations show that mismatches in traditional parallel MCS have a serious impact on spectrum-sensing performance, while the proposed serial MCS combined with the efficient spectrum-sensing algorithm exhibits outstanding spectrum-sensing performance at much lower computational cost.

A cost-effective approach for spectrum sensing using beamforming

Spectrum sensing (SS) is one of the principal challenges on which the mobile communication is based on. Identifying the available frequency bands, also called white spaces, is the main issue. A novel blind approach for SS in the narrowband context is proposed in order to improve the signal detection. Considering a channel with its angle of arrival (AoA), we use beamforming technique to exploit the maximum and minimum angular energy. Both theoretical developments of the threshold and performance analysis are developed. To validate our contribution, the analytical results of the performance developed in this paper are compared with those from simulation. A comparison of state-of-the-art SS method using the eigenvalue decomposition is provided which brings an interesting trade-off between complexity and performance. Finally, simulation results considering the probability of misdetection under very low signal-to-noise ratio (SNR) are presented.

Optimized Spectrum Sensing Algorithm for Cognitive Radio

The electromagnetic spectrum is a meager resource of nature. The current standing spectrum allocation policy is unable to put up the demands of wireless communication. This leads to self-motivated spectrum allocation policy. Cognitive radio (CR) technology is a radiant way to increase spectrum utilization by identifying unused and under-utilized spectrum in vigorously changing environments. Spectrum sensing is a one of the input technique of cognitive radio which detects the existence of primary user in licensed frequency band using self-motivated spectrum allocation policies to use unoccupied spectrum. Spectrum sensing is generally based on energy detection and cyclostationary feature detection. Energy detection is a basic spectrum sensing technique but becomes bleak at a low signal-to-interference-and-noise ratio. The fundamental cyclostationary feature detection based on cyclic spectrum estimation can actively detect feeble signals from primary users with a cost of maximum complexity on implementation. The objective of this work is to implement precious spectrum-sensing method in field programmable gate array with pragmatic complexity for CR. Particularly, The proposed new spectrum-sensing method called the adaptive absolute-self-coherent-restoral algorithm has been introduced. The complexity of the consequential algorithm is better than the prior self-coherent-restoral (SCORE) algorithm, such as adaptive least-SCORE (ALS), adaptive cross-SCORE (ACS). Their performance for spectrum sensing is analytically appraised and compared in detail.

RF Spectrum Sensing Based on an Overdamped Nonlinear Oscillator Ring for Cognitive Radios.

Existing spectrum-sensing techniques for cognitive radios require an analog-to-digital converter (ADC) to work at high dynamic range and a high sampling rate, resulting in high cost. Therefore, in this paper, a spectrum-sensing method based on a unidirectionally coupled, overdamped nonlinear oscillator ring is proposed. First, the numerical model of such a system is established based on the circuit of the nonlinear oscillator. Through numerical analysis of the model, the critical condition of the system’s starting oscillation is determined, and the simulation results of the system’s response to Gaussian white noise and periodic signal are presented. The results show that once the radio signal is input into the system, it starts oscillating when in the critical region, and the oscillating frequency of each element is fo/N, where fo is the frequency of the radio signal and N is the number of elements in the ring. The oscillation indicates that the spectrum resources at fo are occupied. At the same time, the sampling rate required for an ADC is reduced to the original value, 1/N. A prototypical circuit to verify the functionality of the system is designed, and the sensing bandwidth of the system is measured.