Search

Non-cooperative scenarios in cognitive wireless sensor network (CWSN) are often encountered with shadowing and hidden terminal issues. Cooperative spectrum sensing (CSS) can solve these issues but at the expense of large overhead. It is necessary to optimise the energy of battery-operated unlicensed users, also known as secondary users (SUs). The effect of fading and noise uncertainty is often overlooked when determining CSS performance. Energy efficiency (EE) is a comprehensive parameter that gives a complete picture of the overall performance of the CSS. There are several parameters that affect the EE of CSS. In this paper, the detector threshold is optimised to maximise the EE of the system. A system model is proposed to determine the EE of centralised CSS over different fading channels in noisy reporting conditions. An iterative algorithm is presented which determines the optimum detector threshold for which the EE is maximum. Results show that the optimum value of the detector threshold from the analytical model matches with simulation data. [ABSTRACT FROM AUTHOR]

With the development of wireless communication technology, the number of devices accessing the communication network is increasing. This paper addresses critical issues such as low spectrum resource utilization and the energy constraints of devices. The investigation focuses on the system performance of the shared relay Cognitive Radio Non-Orthogonal Multiple Access (CR-NOMA) network based on Simultaneous Wireless Information and Power Transfer (SWIPT) network model. Unlike the existing CR-NOMA model in which the secondary network user do not participate in the transmission of information from the primary network, we consider the secondary network near user as shared relay. The shared relay utilizes SWIPT technology to harvest energy using a nonlinear energy harvesting model. Additionally, the shared relay assists in transmitting information from the primary network base station to primary user, as well as from the secondary network base station to far user of the secondary network. Subsequently, we conduct a series of simulations to analyze the effects of Signal-to-Noise Ratio (SNR), power distribution factor, interference threshold, and time-switching (TS) factor on system performance. Furthermore, we compare and analyze the performance of our proposed network model against CR-NOMA network across three dimensions: outage probability, throughput, and energy efficiency. Our results demonstrate that the proposed network model exhibits superior outage performance and enhances user throughput compared to the CR-NOMA network. Additionally, it demonstrates improved energy efficiency compared to the shared relay CR-NOMA network, leading to an overall improvement in network performance. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel system integrating reconfigurable intelligent surfaces (RISs) with cognitive radio (CR) technology, presenting a forward-looking solution aligned with the evolving standards of 6G and beyond networks. The proposed RIS-assisted CR networks operate with a base station (BS) transmitting signals to two users, the primary user (PU) and secondary user (SU), through direct and reflected signal paths, respectively. Our mathematical analysis focuses on deriving expressions for SU in the RIS-assisted CR system, validated through Monte Carlo simulations. The investigation covers diverse aspects, including the impact of the signal-to-noise ratio (SNR), power allocations, the number of reflected surfaces, and blocklength variations. The results provide nuanced insights into RIS-assisted CR system performance, highlighting its sensitivity to factors like the number of reflectors, fading severity, and correlation coefficient. Careful parameter selection, such as optimizing the configuration of reflectors, is shown to prevent a complete outage, showcasing the system's robustness. Additionally, the work suggests that the optimization of reflectors configuration can significantly enhance overall system performance, and RIS-assisted CR systems outperform reference schemes. This work contributes a thorough analysis of the proposed system, offering valuable insights for efficient performance evaluation and parameter optimization in RIS-assisted CR networks. [ABSTRACT FROM AUTHOR]

Internet-of-Things (IoT) is being widely embraced with the number of connected devices growing rapidly. Moreover, IoT applications are emerging in diverse verticals such as connected cars, connected factories, and smart agriculture. For new business models, in order to meet key network performance indicators, connectivity must be flexible and agile. An integrated satellite-aerial-terrestrial network (I-SAT) has recently stimulated interest in providing wireless communication due to its high maneuverability, versatile deployment, and pervasive connectivity. The resource planning, task distribution, and action management of an I-SAT can be accomplished through effective acquisition, coordination, transmission, and aggregation of diverse information. This paper considers an I-SAT network, in which multiple unmanned aerial vehicles (UAVs) with aerial stations and a terrestrial base station (BS), in a cognitive setting, in the presence of satellite-receiver communication, are deployed to support smart vehicles on the ground. By taking into account different limitations and Quality of Service (QoS) constraints, the goal is to maximize the average throughput among users by jointly optimizing user association, BS/UAV transmission power, and UAV trajectory. The formulated problem is a non-convex optimization problem with a complicated expression that is hard to solve. To tackle this problem, an alternating iterative algorithm based on the block descent method is proposed. Precisely, the problem is subdivided into three subproblems, transmitter-vehicle association optimization, BS/UAV power allocation optimization, and UAV trajectory control. Then, in an iterative process, these subproblems are solved sequentially. The proposed solution uses a segment-by-segment technique, which breaks the complete UAV flight trajectory into smaller time segments to reduce computation time when the network service period is considerable. As a result, each time segment’s optimization can be solved more quickly. Furthermore, the paper presents the results of network simulations carried out to assess the efficiency of the proposed solution. The findings show that the presented scheme outperforms different benchmark schemes in terms of the average user throughput when observing multiple different scenarios. [ABSTRACT FROM AUTHOR]

With the birth of the IoT era, it is evident that the existing number of devices is going to rise exponentially. Any two devices will communicate with each other using the same frequency band with limited availability. Therefore, it is of vital importance that this frequency band used for communication be used efficiently to accommodate the maximum number of devices with the available radio resources. Cognitive radio (CR) technology serves this exact purpose. The stated one is an intelligent radio that is made to automatically identify the optimal wireless channel in the available wireless spectrum at a given instant. An important functionality of CR is spectrum sensing. Energy detection is a very popular algorithm used for spectrum sensing in CR technology for efficient allocation of radio resources to the devices intended to communicate with each other. Energy detection detects the presence of a primary user (PU) signal by continuously monitoring a selected frequency bandwidth. The conventional energy detection technique is known to perform poorly in lower SNR ranges. This paper works towards the improvement of the energy detection algorithm with the help of machine learning (ML). The ML model uses the general properties of the signal as training data and classifies between a PU signal and noise at very low SNR ranges (− 25 to − 10 dB). In this research, a K-nearest neighbours (KNN) model is selected for its versatility and simplicity. Upon testing the model with an out-of-sample dataset, the KNN model produced a detection accuracy of 94.5%. [ABSTRACT FROM AUTHOR]

Spectrum sensing is a prominent functionality to enable dynamic spectrum access (DSA) in cognitive radio (CR) networks. It provides protection to primary users (PUs) from interference and creates opportunities of spectrum access for secondary users (SUs). It should be performed efficiently to reduce the number of false alarms and missed detections. Continuous sensing for a long time incurs cost in terms of increased energy consumption; thus, spectrum sensing ought to be energy efficient to ensure the prolonged existence of CR devices. This paper focuses on using of history to help achieve energy-efficient spectrum sensing in infrastructure-based CR networks. The scheme employs an iteratively developed history processing database that is used by CRs to make decisions about spectrum sensing, subsequently resulting in reduced spectrum scanning and improved energy efficiency. Two conventional spectrum sensing schemes, i.e., energy detection (ED) and cyclostationary feature detection (CFD), are enriched by history to demonstrate the effectiveness of the proposed scheme. System-level simulations are performed to investigate the sensitivity of the proposed history-based scheme by performing detailed energy consumption analysis for the aforementioned schemes. Results demonstrate that the employment of history ensued in improved energy efficiency due to reduced spectrum scanning. This paper also suggests which spectrum sensing scheme can be the best candidate in a particular scenario by looking into computational complexity before comparative analysis is presented with other states of the art. [ABSTRACT FROM PUBLISHER]

This paper presents a novel design of a compact, wideband tunable microstrip filtenna system for effective spectrum sensing in cognitive radio (CR) applications. The proposed filtenna structure has a total bandwidth of 1.63 GHz and flexible frequency scanning design throughout the frequency range from 1.93 to 3.56 GHz with high selectivity and narrow bandwidths ranging from 39.9 to 53 MHz . Frequency tuning is accomplished electrically via integrating a varactor diode into the filtenna construction. The filtenna is realized on a Rogers TMM4 substrate with h = 1.52 mm thickness and relative dielectric constant of ε r = 4.5 with dimensions of (25 × 35) mm 2 . The obtained gain and efficiency of the filtenna ranged from 0.7 to 2.26 dBi and 49% to 60%, respectively, within the tuning range. Simple biasing circuitry, wideband operation, and compact planar structure are distinctive and appealing aspects of the design. For the manufactured prototypes, a significant level of agreement is found between the simulated and measured results in terms of scattering parameter S 11 and radiation patterns at different operating frequencies. [ABSTRACT FROM AUTHOR]

This paper presents a promising solution to address the scarcity of spectrum resources and enhance spectrum efficiency in the context of cognitive radio (CR)-based soft-switching free-space optical (FSO)/terahertz (THz) radio frequency (RF) dual-hop amplify-and-forward (AF)–non-orthogonal multiple access (ROMANO) links. The impact of maximum tolerable interference power in the primary network, transmit power in the secondary transmitter, and maximum relay transmission power on the link are thoroughly studied. The numerical results ultimately validate the effectiveness of this link in improving performance, and a comparative analysis is conducted with the without-CR scheme, highlighting the distinctive characteristics of the proposed link. [ABSTRACT FROM AUTHOR]

Primary User Emulation Attack (PUEA) is the most serious concern in Cognitive Radio (CR). The PUEA are malevolent users attempt to imitate primary signals and confuse CR users to prevent them from accessing vacant frequency bands. The proposed technique detects energy and assigns an appropriate threshold value for identifying attackers in the network using unique Smart Threshold detection (STD). The free space propagation model and two ray ground models are considered for finding the attacks. The authentication confirmation process (ACP) is carried out for detecting multiple PUEAs; ACP uses DNA sequencing using Binary to Excess One (BEO). The objective of this paper is to identify the PUEAs from the network and not providing the vacant frequency bands to the PUEAs and the frequent bands should be used by the primary and the secondary user efficiently. Here the secondary user will find out whether the PUEA or primary user is accessing the vacant bands using the STD-ACP technique. The simulation process is executed in the MATLAB platform. The Proposed STD-ACP finds out the attack strength, probability of detection, probability of error, probability of false alarms, and identifies the number of PUEAs. By simulating the performance of the primary user will be increased while the PUEAs can be detached from the network. The proposed STD-ACP approach is compared with attack-aware threshold selection (AATS), optimal voting rule, and K-out-of-N rule methods respectively. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the effect of imperfect sensing on the performance of opportunistic spectrum access (OSA) in cognitive radio (CR) networks. We consider a system modeled as a continuous-time Markov chain (CTMC), and then evaluate its performance in terms of the probabilities of users being blocked or dropped. Our results demonstrate that the performance of the underlying system significantly degrades when imperfect sensing is considered; thus, there is a pressing need for a reliable spectrum sensing scheme to improve the overall quality of service in practical scenarios. A simulation study is presented to corroborate the analytical results and to demonstrate the performance of OSA under imperfect sensing conditions. [ABSTRACT FROM PUBLISHER]

This paper presents a comprehensive cognitive management framework for spectrum selection in cognitive radio (CR) networks. The framework uses a belief vector concept as a means to predict the interference affecting the different spectrum blocks (SBs) and relies on a smart analysis of the scenario dynamicity to properly determine an adequate observation strategy to balance the tradeoff between achievable performance and measurement requirements. In this respect, the paper shows that the interference dynamics in a given SB can be properly characterized through the second highest eigenvalue of the interference state transition matrix. Therefore, this indicator is retained in the proposed framework as a relevant parameter to drive the selection of both the observation strategy and spectrum selection decision-making criterion. This paper evaluates the proposed framework to illustrate the capability to properly choose among a set of possible observation strategies under different scenario conditions. Furthermore, a comparison against other state-of-the-art solutions is presented. [ABSTRACT FROM PUBLISHER]

In cognitive radio (CR) networks, the secondary users (SUs) sense the spectrum licensed to the primary users (PUs) to identify and possibly transmit over temporarily unoccupied channels. Cooperative sensing was proposed to improve the sensing accuracy, but in heterogeneous scenarios, SUs do not contribute equally to the cooperative sensing result because they experience different received PU signal quality at their sensors. In this paper, a two-layer cooperative game is developed for distributed sensing and access in multichannel CR ad hoc networks, where the SUs’ transmission opportunities are commensurate with their sensing contributions, thus fostering cooperation and eliminating free-riders. Numerical results show that the proposed two-layer game is computationally efficient and outperforms previously investigated collaborative sensing and spectrum access approaches in heterogeneous multichannel CR scenarios in terms of energy efficiency, throughput, SU fairness, and complexity. Moreover, it is demonstrated that this game is robust to changes in the network topology and the number of SUs. Finally, a new physical-layer approach is proposed to distribute the network-level miss-detection constraints fairly among the interfering SUs for guaranteed PU protection and demonstrate the performance advantages of the AND-rule combining of spectrum sensing results for heterogeneous SUs. [ABSTRACT FROM AUTHOR]

Energy harvesting (EH) from radio frequency realizes simultaneous wireless information delivery and energy transfer, which greatly reduces energy consumption in the energy-constrained Internet of things (IoT) networks. On the other hand, cognitive radio (CR) enables the unlicensed secondary user (SU) to access the spectrum resource authorized to the licensed primary user (PU) to improve spectrum efficiency. Thererfore, the integration between EH and CR can address two critical problems of energy limitation and spectrum scarcity in massive IoT wireless networks. In the state-of-art power splitting-based overlay spectrum sharing strategy, the secondary transmitter superimposes its own signals on the primary signals received and forwards the combined signals with the harvested power from the primary transmitter. However, due to low energy harvested only from one primary transmitter for the combined signal, PU system performance e.g., outage probability (OP) and system throughput, declines seriously. Moreover, a perfect direct link between the secondary transmitter and the secondary receiver must also be required in the scenario. An alternative spectrum sharing strategy based on time switching can increase harvested energy, but cooperative communication cannot be conducted at the EH period, which also reduces the overall system throughput. Based on the consideration, a Two-User Relay protocol in this paper is presented that an energy-constrained relay node, as a center hub, harvests energy from two transmitter, i.e., primary transmitter and secondary transmitter, and perform cooperative communication concurrently for PU and SU systems satisfying the PU's performance requirements (e.g., required target rate and OP). The expressions of OP and system throughput are derived and numerical simulations are made under the different system parameters, e.g., power splitting factor, power assignment factor, transmitting signal-to-noise ratio, channel fading coefficient, and required target rate. The results prove that our proposed Two-User Relay protocol improve spectrum sharing performance. Besides, the relay node can coordinate the harvested energy distribution between PU's signals and SU's signals to achieve the maximum system performance. Generally, the paper provides a new relaying concept for two-user communications in the future IoT wireless networks. [ABSTRACT FROM AUTHOR]

In this paper, we study a generalized framework that combines the three major techniques for 5G communication systems such as the multi-user multi-input multi-output (MuMIMO) techniques for spectral efficiency enhancement, the cognitive radio (CR) techniques for spectrum sharing, and the simultaneous wireless information and power transfer (SWIPT) techniques for convenient power supplies, which is called a MuMIMO-CR-SWIPT network. In this system, we have one base-station that simultaneously supports multiple information decoding (ID) and energy harvesting users under a condition that interference power to the primary ID (P-ID) receivers stays below a certain threshold. With this scenario, our goal is to design an optimal precoder that maximizes the sum-utility cost function for the ID users while satisfying the transmit power constraint at the BS, the energy requirement at each EH user, and the interference power constraint at each P-ID user. As we consider a general sum-utility cost function that puts together different target utilities in a general MuMIMO-CR-SWIPT environment, the previous works for each of the MuMIMO, CR, and SWIPT systems are casted as particular solutions of our framework. The problem has been considered to be challenging, since the weighted minimum mean-squared error problem transformation no longer resolves the non-convexity of the original problem. In this paper, we settle such an issue by demonstrating that the WMMSE transformation guarantees zero-duality gap between the primal and dual problems. Based on the observation, we attain the optimal precoder by solving the dual problem through the sub-gradient ellipsoid method. We also propose a simplified algorithm for the case of a single ID user, which is shown to achieve the globally optimum. Finally, we demonstrate the optimality and efficiency of the proposed algorithms through numerical simulation results. [ABSTRACT FROM AUTHOR]

Orthogonal frequency-division multiplexing (OFDM) is a promising technology for communication systems. This paper investigates the impacts of unknown noise variance on the popular spectrum sensing scheme, i.e., energy detection, for OFDM cognitive radios over multipath fading channels. To study the effects of unknown parameters on the energy detector, a new maximum-likelihood estimation of noise and signal powers employing the cyclic prefix of OFDM is presented in this paper. The mean values and Cram $\acute{\text{e}}$ r–Rao lower bounds of the estimation are obtained. Furthermore, the performances of the energy detector for both hypotheses, i.e., false-alarm rate and detection probability, under the influence of unknown noise variance are validated by both simulation and analytical results. The assessment on the required number of samples for the proposed energy detector is conducted, which indicates that an amount of 40–50% samples can be saved compared to the conventional energy detector. [ABSTRACT FROM AUTHOR]

Summary: This paper analyzes the performance of a cooperative nonorthogonal multiple access (NOMA) in an underlay cognitive radio network aided by an energy harvesting relay. A secondary source transmits signal for two users, where a near user acts as a relay for the far user. The far user applies the selection combining (SC) approach on the signals which were relayed by the near user and received via direct path from the secondary source. We analytically derive the outage probability (OP) of each user separately, the overall system OP, and the throughput of the system. The impact of the power allocation coefficient of NOMA and energy harvesting parameters on outage is indicated. Further, the performance of the network is investigated with imperfection in successive interference cancellation (SIC), maximal ratio combining (MRC) at relay, and Nakagami‐m fading. The results derived analytically are supported by simulation in MATLAB. [ABSTRACT FROM AUTHOR]

This paper presents the design of an arc-shaped near-isotropic self-complementary antenna for spectrum sensing application. An arc-shaped dipole with horizontal and vertical arms is used to achieve a near isotropic radiation pattern. The radiation pattern improved by adjusting the horizontal and vertical arm lengths. Simulated and experimental results show that the proposed antenna has an impedance bandwidth of 146% (2.4–18.4 GHz) for VSWR ≤ 2 with a good radiation pattern. In order to quantify the antenna performance, antenna gain variation, bandwidth, efficiency, and size have been compared with previously reported designs. It is shown that the proposed arc-shaped antenna can achieve nearly isotropic radiation patterns with a maximum radiation efficiency of 92%. The isotropic performance of the antenna has been characterized by observing the radiation pattern and solid angle. The FR4 substrate is used as a dielectric with relative permittivity 4.4 and loss tangent of 0.02. ( ε r = 4.4, h = 1.6 mm) The simulated and measured results are in good comparison, and the proposed design is a suitable candidate for spectrum sensing. [ABSTRACT FROM AUTHOR]

This paper studies robust resource-allocation algorithm design for a multiuser multiple-input–single-output (MISO) cognitive radio (CR) downlink communication network. We focus on a secondary system that provides wireless unicast secure layered video information to multiple single-antenna secondary receivers. The resource-allocation algorithm design is formulated as a nonconvex optimization problem for the minimization of the total transmit power at the secondary transmitter. The proposed framework takes into account a quality-of-service (QoS) requirement regarding video communication secrecy in the secondary system, the imperfection of the channel state information (CSI) of potential eavesdroppers (primary receivers) at the secondary transmitter, and a limit for the maximum tolerable received interference power at the primary receivers. Thereby, the proposed problem formulation exploits the self-protecting architecture of layered transmission and artificial noise generation to ensure communication secrecy. The considered nonconvex optimization problem is recast as a convex optimization problem via semi-definite programming (SDP) relaxation. It is shown that the global optimal solution of the original problem can be constructed by exploiting both the primal and the dual optimal solutions of the SDP-relaxed problem. In addition, two suboptimal resource-allocation schemes are proposed for the case when the solution of the dual problem is unavailable for constructing the optimal solution. Simulation results demonstrate significant transmit power savings and robustness against CSI imperfection for the proposed optimal and suboptimal resource-allocation algorithms employing layered transmission compared to baseline schemes employing traditional single-layer transmission. [ABSTRACT FROM PUBLISHER]

The 5G technology is a revolutionary technology, which will offer an 'unlimited wireless world interconnection' (Badoi et al. in Wirel Pers Commun 57(3):441-464 . doi:; Prasad ) and a large type of services to a vastly number of users, while using a high performance terminal. These services will most probably be provided to the users as cloud based services, with different Quality of Services (QoS) characteristics. More exactly, based on the user subscription and on the required service, the user will be served with a given QoS. Each type of QoS services class will be assured by a 5G virtual network, having a one-to-one QoS class versus 5G virtual network correspondence. In this context, the virtualization and scheduling methods will play an important role regarding the ability to provide such services in 5G networks. In this paper we present the virtualization concept within 5G networks, while also describing the existing work conducted until now in wireless networks and Future Internet fields. Two virtualization methods are also presented in this paper, based on the spectrum sharing principle used in the Cognitive Radio networks (Badoi et al. in Wirel Pers Commun 57(3):441-464 . doi:) and based on partition principle used in Future Internet (Nejbati et al. ). A combination of these two methods should offer a better granularity of 5G networks virtualization, with the price of an increased complexity. [ABSTRACT FROM AUTHOR]

This paper presents a fully integrated ultra wideband (UWB)-based cognitive radio (CR) transceiver for 1\,\textGb/s data-rate energy-efficient short-range wireless connectivity by scavenging triple discrete inactive frequency bands in 3.1–10.6\,\textGHz ISM band. The transceiver including receivers (RXs), transmitters (TXs), spectrum sensors, and synthesizers is implemented in 1\,\textV 65\,\textnm standard CMOS technology. A novel pulse generator (PG) enables the TX to meet UWB emission mask and to reduce spectral sidelobe peak by < -40\,\textdBc with low power consumption of 3.6\,\textmW. A dual-mode RX front-end provides quadrature analog correlation (QAC) for analog domain matched filtering during communication and analog wavelet-based energy detection (ED) during spectrum sensing (SS) without changing circuitry. The transceiver achieves the minimum energy consumption of 59.7\,\textpJ/b with 1.97 \times 10^-4\,\textbit error rate (BER) and the maximum energy consumption of 102.3\,\textpJ/b with 1.25 \times 10^-3\,\textBER. Die area is $4.6\,{{\text{mm}}^{2}}$ with on-die phase-locked loops (PLLs) and pads. [ABSTRACT FROM PUBLISHER]

In this paper, we study cognitive radio (CR) networks that consist of multiple secondary TV band device (TVBD) station–user pairs and one primary digital TV (DTV) station–user pair, where each terminal has a single antenna. Specifically, we consider spectrum sharing (SS)-based secondary TVBD networks to effectively utilize limited spectrum resources in the presence of cochannel primary DTV interference. We first present an opportunistic single secondary network selection scheme to maximize the mutual information over all secondary TVBD networks under the constraint of the availability of the primary DTV service. Then, the performance bound of CR networks with the secondary network selection is obtained through the derivation of an exact and closed-form outage probability. It is shown that the derived outage probability is given as a function of transmission power, channel coefficients, and target rates of both the primary DTV network and the secondary TVBD networks. [ABSTRACT FROM PUBLISHER]

To develop sustainable fifth generation (5G) wireless networks and utilize the unused spectrum, this paper focuses on cognitive radio (CR) based wireless information and energy transmissions from an unmanned aerial vehicle (UAV) to multiple low-power ground terminals (GTs). By practically considering the location-dependent air-to-ground (A2G) channel states and the non-linear energy harvesting (EH), we propose a dynamic fly-hover-transmit scheme, where the UAV successively flies between GTs, and hovers close to each GT for efficient wireless energy transfer (WET) or wireless information transfer (WIT) when the primary user (PU) is idle. By causally and optimally determining the UAV’s mobility and transmit power for each selected transmission mode (WIT, WET, or being silent), we formulate the UAV’s sum-throughput maximization over all GTs as a constrained Markov decision process (MDP) problem with battery energy constraints at all GTs and the UAV. Due to the infinitely large MDP system state space, this problem is difficult to solve. We then decompose this problem into two subproblems, by first deciding the UAV’s transmission mode and power above a given GT, and then optimizing the UAV movement policy over multiple GTs. In the first subproblem, we propose an approximate to the complicated MDP value function of low complexity in closed-form, and then analytically derive the threshold-based suboptimal transmission policies. In the second subproblem, we optimally solve a simple-but-fundamental two-GT case, and then extend the general location-dependent GT weight design to an efficient suboptimal UAV movement policy. Simulation results show the significantly improved system performance under the proposed suboptimal policies over various benchmarks in dynamic networks. [ABSTRACT FROM AUTHOR]

This paper investigates the performance of cooperative spectrum sensing in cognitive radio networks using the stochastic geometry tools. In order to cope with the diversity of received signal-to-noise ratios at secondary users, a practical and efficient cooperative spectrum sensing model is proposed and investigated based on the generalized likelihood ratio test detector. In order to investigate the cooperative spectrum sensing system, the theoretical expressions of the probabilities of false alarm and detection of the local decision are derived. The optimal number of cooperating secondary users is then investigated to achieve the minimum total error rate of the final decision by assuming that the secondary users follow a homogeneous Poisson point process. Moreover, the theoretical expressions for the achievable ergodic capacity and throughput of the secondary network are derived. Furthermore, the technique of determining an appropriate number of cooperating secondary users is proposed in order to maximize the achievable ergodic capacity and throughput of the secondary network based on a target total error rate requirement. The analytical and simulation results validate the chosen optimal number of collaborating secondary users in terms of spectrum sensing, achievable ergodic capacity, and throughput of the secondary network. [ABSTRACT FROM PUBLISHER]

Network planning and management are challenging issues in a two-tier network. Tailoring to cognitive radio networks (CRNs), network operations and transmissions become more challenging due to the dynamic spectrum availability. This paper proposes an adaptive network management system that provides switching between different CRN management structures in response to the spectrum availability and changes in the service time required for the radio access. The considered network management system includes conventional macrocell-only structure, and centralized/distributed structures overlaid with femtocells. Furthermore, analytical expressions of per-tier successful connection probability and throughput are provided to characterize the network performance for different network managements. Spectrum access in dynamic radio environments is formulated according to the quality of service (QoS) constraint that is related to the connection probability and outage probability. Results show that the proposed intelligent network management system improves the maximum capacity and reduces the number of blocked connections by adapting between various network managements in response to free spectrum transmission slots. A road map for the deployment and management of cognitive macro/femto networks is also presented. [ABSTRACT FROM PUBLISHER]

Day by day, the demand for wireless systems is increasing while the available spectrum resources are not sufficient. To fulfil the demand for wireless systems, the spectrum hole (spectrum vacant) should be found and utilised very effectively. Cognitive radio (CR) is a device which intelligently senses the spectrum through various spectrum-sensing detectors. Based on the complexity and licensed user's information present with CR, the appropriate detector should be utilised for spectrum sensing. In this paper, a hybrid detector (HD) is proposed to determine the spectrum hole from the available spectrum resources. HD is designed based on an energy detector (ED) and matched detector (MD). Unlike a single detector such as ED or MD, HD can sense the signal more precisely. Here, HD can work on both conditions whether the primary user (PU) information is available or not. HD is analysed under heterogeneous environments with and without cooperative spectrum sensing (CSS). For CSS, four users were used to implement OR, AND, and majority schemes under low SNR walls. To design the HD, specifications were chosen based on the IEEE Wireless Regional Area Network (WRAN) 802.22 standard for accessing TV spectrum holes. For the HD model, we achieved the best results through OR rule. Under the low SNR circumstances at −20 dB SNR, the probability of detection (PD) is maximised to 1 and the probability of a false alarm (PFA) is reduced to 0 through the CSS environment. [ABSTRACT FROM AUTHOR]

In this paper, the ergodic sum rate of a fading cognitive multiple-access channel (C-MAC) is studied, where a secondary network (SN) with multiple secondary users (SUs) transmitting to a secondary base station shares the spectrum band with a primary user (PU). An interference power constraint (IPC) is imposed on the SN to protect the PU. Under such a constraint and the individual transmit power constraint (TPC) imposed on each SU, we investigate the power allocation strategies to maximize the ergodic sum rate of a fading C-MAC without successive interference cancelation (SIC). In particular, this paper considers two types of constraints: 1) average TPC and average IPC and 2) peak TPC and peak IPC. For the first case, it is proved that the optimal power allocation is dynamic time-division multiple access (D-TDMA), which is exactly the same as the optimal power allocation to maximize the ergodic sum rate of the fading C-MAC with SIC under the same constraints. For the second case, it is proved that the optimal solution must be at the extreme points of the feasible region. It is shown that D-TDMA is optimal with high probability when the number of SUs is large. Moreover, we show that when the SUs can be sorted in a certain order, an algorithm with linear complexity can be used to find the optimal power allocation. [ABSTRACT FROM PUBLISHER]

With the advent of smarter technologies in LTE, often the bands used for lower technologies remain unoccupied in cellular networks (CN). To utilize those, in this paper, a new paradigm of cognitive radio has been proposed for IoT, where the nodes of a self-organized opportunistic ad hoc network, act as the secondary users (SU) to use the white spaces of the co-existing cellular network. Each SU of the ad hoc network, in a self-organized fashion, collaborates with other SUs to reduce the impact of cognitive users on the primary network and also to improve the performance of the ad hoc network. Since it does not require the control of the core network, the device to device communication proposed in 5G CN, also can apply this technique for sharing the cellular spectrum without the control of the core network. We have developed distributed algorithms for cooperative channel sharing to reduce the spectrum latency as well as to improve the channel utilization. The proposed algorithms not only improve the system performance in offloading the traffic but also reduce the control overhead of the backbone network. Simulation results show that the proposed cooperative techniques perform better in terms of channel utilization, energy-efficiency, and call block/drop rate with respect to other cooperative approaches with insignificant additional message overhead at users' end. [ABSTRACT FROM AUTHOR]

Non-orthogonal multiple access (NOMA) and spectrum sharing (SS) are two emerging multiple access technologies for efficient spectrum utilization in future wireless communications standards. In this paper, we present the performance analysis of a NOMA-based cooperative relaying system (CRS) in an underlay spectrum sharing scenario, considering a peak interference constraint (PIC), where the peak interference inflicted by the secondary (unlicensed) network on the primary-user (licensed) receiver (PU-Rx) should be less than a predetermined threshold. In the proposed system the relay and the secondary-user receiver (SU-Rx) are equipped with multiple receive antennas and apply selection combining (SC), where the antenna with highest instantaneous signal-to-noise ratio (SNR) is selected, and maximal-ratio combining (MRC), for signal reception. Closed-form expressions are derived for the average achievable rate and outage probabilities for SS-based CRS-NOMA. These results show that for large values of peak interference power, the SS-based CRS-NOMA outperforms the CRS with conventional orthogonal multiple access (OMA) in terms of spectral efficiency. The effect of the interference channel on the system performance is also discussed, and in particular, it is shown that the interference channel between the secondary-user transmitter (SU-Tx) and the PU-Rx has a more severe effect on the average achievable rate as compared to that between the relay and the PU-Rx. A close agreement between the analytical and numerical results confirm the correctness of our rate and outage analysis. [ABSTRACT FROM AUTHOR]

In this paper, we consider an intelligent reflecting surface (IRS)-assisted downlink cognitive radio (CR) system, in which a secondary access point (SAP) communicates with multiple secondary users (SUs) without affecting multiple primary users (PUs) in the primary network and all nodes are equipped with multiple antennas. Our design objective is to maximize the achievable weighted sum rate (WSR) of SUs subject to the total transmit power constraint at the SAP and the interference constraints at PUs, by jointly optimizing the transmit precoding at the SAP and the reflecting coefficients at the IRS. To deal with the complex objective function, the problem is reformulated by employing the well-known weighted minimum mean-square error (WMMSE) method and an alternating optimization (AO)-based algorithm is proposed. Furthermore, a special scenario with only a single PU and multiple SUs is considered and AO algorithm is adopted again. It is worth mentioning that the proposed algorithm has a much lower computational complexity than the above algorithm without the performance loss. Finally, some numerical simulations have been provided to demonstrate that the proposed algorithm outperforms other benchmark schemes. [ABSTRACT FROM AUTHOR]

Broadcasting is an important operation in wireless networks where control information is usually propagated as broadcasts for the realization of most networking protocols. In traditional ad hoc networks, broadcasts are conducted on a common channel, which is shared by all nodes in the network. However, in cognitive radio (CR) ad hoc networks, unlicensed users may observe heterogeneous spectrum availability, which is unknown to other unlicensed users before the control information was broadcast. Thus, it is extremely challenging that broadcasts can be successfully conducted without knowing the spectrum availability information in advance. In addition, since broadcast collisions (i.e., simultaneous reception of broadcast messages at the same node) often lead to the waste of network resources, they should be efficiently mitigated in multihop scenarios. In this paper, a quality-of-service (QoS)-based broadcast protocol under Blind Information for multihop CR ad hoc networks, i.e., \QB^2\IC, is proposed with the aim of having a high success rate and short broadcast delay. In our design, we do not assume that unlicensed users are aware of the network topology, the spectrum availability information, and time synchronization information. To the best of our knowledge, this is the first paper that investigates the broadcast issue in multihop CR ad hoc networks under blind information. Simulation results show that our proposed \QB^2\IC protocol outperforms other broadcast schemes in terms of a higher success rate and shorter average broadcast delay. [ABSTRACT FROM PUBLISHER]

In this paper, we study the tradeoff between sensing time and achievable throughput of the secondary user that employs robust eigenvalue-based spectrum sensing techniques in the presence of noise uncertainty. First, we study exact distributions of the test statistics for two types of robust eigenvalue-based sensing techniques, namely, the blind generalized likelihood ratio test (B-GLRT) detection and energy with minimum eigenvalue (EME) detection. The developed threshold setting is more accurate than benchmark methods in achieving a target constant false alarm rate (CFAR). Second, prior to the throughput analysis, the necessary asymptotic detection and false alarm probabilities under noise uncertainty are formulated for eigenvalue-based detectors such as maximum eigenvalue detection (MED) and maximum–minimum eigenvalue (MME) detection. Finally, the throughput is maximized using eigenvalue-based spectrum sensing techniques which are B-GLRT, EME, MME, and MED detectors. The results are compared with the commonly used energy detector (ED). An improved achievable throughput is obtained under low-signal-to-noise-ratio (SNR) regime by incorporating the robust eigenvalue-based techniques, which are insusceptible to noise uncertainty. [ABSTRACT FROM PUBLISHER]

The cooperative communication system has gained lots of interest due to effective utilization of the allotted spectrum. Spectrum sensing techniques are a key factor for the cooperative communication system. A number of sensors are deployed to sense the spectrum hole. The group or clusters of the sensor are used to make out the decision about the spectrum hole. The presence of malicious sensor affects the performance of spectrum sensing. In this paper, the trust on the group or cluster has been identified based on the fuzzy classification. The fuzzy classifier takes the input in terms of reporting cluster trust value, neighborhood trust value and primary weight index. The membership values of these three linguistic variables are used by fuzzy interference system to decide the trust value of the group or cluster. The number of malicious user has been introduced during the simulation and performance has been identified. The Eigenvalue-based spectrum sensing is also simulated in this paper and the effect of different SNRs on the decision accuracy is shown. [ABSTRACT FROM AUTHOR]

In cognitive radio (CR) technology, the trend of sensing is no longer to only detect the presence of active primary users, as a large number of applications demand for more comprehensive knowledge on primary network behaviors in spatial, temporal, and frequency domains. To satisfy such requirements, we study the statistical relationship among primary nodes by introducing a Bayesian network (BN)-based framework. How to efficiently learn such a BN structure is a long-standing issue that is not fully understood even in the statistical learning community. To address such an issue in CR, this paper proposes a BN structure learning scheme consisting of a concise directional dependence checking function and a regular BN graph, which achieves significantly lower computational complexity compared with existing approaches. With this result, cognitive users could efficiently understand the statistical behavior patterns in the primary networks, such that more efficient cognitive protocols could be designed across different network layers. [ABSTRACT FROM PUBLISHER]

One of the most important factors that affects the performance of energy detection (ED) is the fading channel between the wireless nodes. This paper investigates the performance of ED-based spectrum sensing, for cognitive radio (CR), over two-wave with diffuse power (TWDP) fading channels. The TWDP fading model characterizes a variety of fading channels, including well-known canonical fading distributions, such as Rayleigh and Rician, as well as worse-than-Rayleigh fading conditions modeled by the two-ray fading model. Novel analytic expressions for the average probability of detection over TWDP fading that account for single-user and cooperative spectrum sensing and square law selection diversity reception are derived. These expressions are used to analyze the behavior of ED-based spectrum sensing over moderate, severe, and extreme fading conditions and to investigate the use of cooperation and diversity as a means of mitigating the fading effects. The obtained results indicate that TWDP fading conditions can significantly degrade sensing performance; however, it is shown that detection performance can be improved when cooperation and diversity are employed. The presented outcomes enable identifying the limits of ED-based spectrum sensing and quantifying the tradeoffs between detection performance and energy efficiency for CR systems deployed within confined environments, such as in-vehicular wireless networks. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a minimized error vector magnitude (M-EVM) scheme to simultaneously reduce the cubic metric (CM) and spectral sidelobe in noncontiguous orthogonal frequency-division multiplexing (NC-OFDM)-based cognitive radio (CR) systems by modifying the constellations on the secondary user (SU) subcarriers and adding canceling symbols on the primary user (PU) subcarriers. The proposed M-EVM scheme formulates an optimization problem, which minimizes the EVM with constraints of the CM and spectral sidelobe. Furthermore, we propose an iterative approximation algorithm to solve the optimization problem. Simulation results show that the M-EVM scheme offers significant reductions of the CM and spectral sidelobe. [ABSTRACT FROM PUBLISHER]

In traditional cognitive radio networks (CRNs), secondary users (SUs) typically access the spectrum of primary users (PUs) by a two-stage “listen-before-talk” (LBT) protocol, i.e., SUs sense the spectrum holes in the first stage before transmitting in the second. However, there exist two major problems: transmission time reduction due to sensing and sensing accuracy impairment due to data transmission. In this paper, we propose a “listen-and-talk” (LAT) protocol with the help of full-duplex (FD) technique that allows SUs to simultaneously sense and access the vacant spectrum. Spectrum utilization performance is carefully analyzed, with the closed-form spectrum waste ratio and collision ratio with the PU provided. In addition, with regard to the secondary throughput, we report the existence of a tradeoff between the secondary transmit power and throughput. Based on the power–throughput tradeoff, we derive the analytical local optimal transmit power for SUs to achieve both high throughput and satisfying sensing accuracy. Numerical results are given to verify the proposed protocol and the theoretical results. [ABSTRACT FROM PUBLISHER]

The dynamic spectrum access (DSA) principle, relying on the cognitive radio (CR) paradigm, allows users to access spectrum over time intervals or spatial areas where it remains unused. Due to the opportunistic nature of DSA/CR, the behavior and performance of DSA/CR networks depends on the perceived spectrum usage pattern. An accurate modeling of spectrum occupancy therefore becomes essential in the context of DSA/CR. In this context, this paper addresses the problem of accurately modeling the spectrum occupancy pattern perceived by DSA/CR users in the spatial domain. A novel spatial modeling approach is introduced to enable a simple yet practical and accurate characterization of spectrum. First, a set of models is proposed to characterize and predict the average level of occupancy perceived by DSA/CR users at various locations based on the knowledge of some simple signal parameters. An extension is then proposed to characterize not only the average occupancy level but the instantaneous channel state perceived simultaneously by DSA/CR users observing the same transmitter from different locations as well. The validity and accuracy of the theoretical models are demonstrated with results from an extensive spectrum measurement campaign. Some illustrative examples of their potential applicability are presented and discussed as well. [ABSTRACT FROM PUBLISHER]

This paper considers a new power strategy and channel-allocation optimization for secondary users (SUs) in an orthogonal frequency-division multiplexing (OFDM)-based cognitive radio (CR) network where the coverage area of the secondary network is divided into an overlay region and a hybrid region. SUs in the overlay region can adopt the overlay spectrum access method, whereas SUs in the hybrid region may adopt the underlay or sensing-free spectrum access method. We first present a general resource-allocation framework that optimizes the power and channel allocation to SUs who adopt these different spectrum access methods, depending on their locations. To enable sensing-free spectrum access, we then propose a new algorithm that incorporates an interference violation test to decide the parameters in the general framework. The proposed scheme intelligently utilizes frequency and space opportunities, avoids unnecessary spectrum sensing, and minimizes overall power consumption while maintaining the quality of service (QoS) of a primary system. Simulation results validate the effectiveness of the proposed method in terms of energy efficiency and show that enhanced performance can be obtained by utilizing spatial opportunities. [ABSTRACT FROM PUBLISHER]

In this paper, a new cooperation structure for spectrum sensing in cognitive radio networks is proposed, which outperforms the existing commonly used ones in terms of energy efficiency. The efficiency is achieved in the proposed design by introducing random interruptions in the cooperation process between the sensing nodes and the fusion center, along with a compensation process at the fusion center. Regarding the hypothesis testing problem concerned, first, the proposed system behavior is thoroughly analyzed and its associated likelihood-ratio test is provided. Next, based on a general linear fusion rule, the statistics of the global test summary are derived and the sensing quality is characterized in terms of the probability of false alarm and probability of detection. Then, the optimization of the overall detection performance is formulated according to the Neyman–Pearson criterion (NPC) and it is discussed that the optimization required is indeed a decision-making process with uncertainty which incurs prohibitive computational complexity. The NPC is then modified to achieve a good affordable solution by using semidefinite programming (SDP) techniques and it is shown that this new solution is nearly optimal according to the deflection criterion. Finally, the effectiveness of the proposed architecture and its associated SDP is demonstrated by simulation results. [ABSTRACT FROM PUBLISHER]

Cognitive radio (CR) is an emerging technique to improve the efficiency of spectrum resource utilization. In CR networks, the selfish behavior of secondary users (SUs) can considerably affect the performance of primary users (PUs). Accordingly, game theory, which considers the game players’ selfish behavior, has been applied to the design of CR networks. Most of the existing studies focus on the network design only from the network perspective to improve system performance, such as utility and throughput. However, the users’ experience to the service, which cannot simply be reflected by quality of service, has been largely ignored. The user-perceived multimedia quality and service can be different from the actual received multimedia quality, and thus is very important to consider the network design. To better serve the network users, quality of experience (QoE) is adopted to measure the network service from the users’ perspective and help improve the users’ satisfaction to the CR network service. As CR networks require a lot of data storage and computation for spectrum sensing, spectrum sharing, and algorithm design, cloud computation comes as a convenient solution, because it can provide massive storage and fast computation. In this paper, we propose to design a user-oriented CR cloud network for multimedia applications, where the user’s satisfaction is reflected in the CR cloud network design. In the proposed framework, the PU and SU game is formulated as Stackelberg game. In particular, a refunding term is defined in the users’ utility function to effectively consider and to reflect the network users’ QoE requirement. Our contributions are twofold: 1) a game-based CR cloud network design for multimedia transmission is proposed, and the network user’s QoE requirement is satisfied in the design and 2) the existence and the uniqueness of the Stackelberg Nash equilibrium are proved, and the design is optimal. Our simulation results demonstrate the effectiveness of the game user-oriented CR cloud network design. [ABSTRACT FROM PUBLISHER]

This paper addresses the problem of accurately modeling the spectrum occupancy patterns of real radio communication systems, which is an essential aspect in the study of cognitive radio (CR) networks. The main drawbacks and limitations of previous works are identified, and the methodological procedures on which they rely are improved and extended. Two sophisticated measurement platforms, providing low and high time resolutions, are used to obtain extensive real-world data from a multiband spectrum measurement campaign, embracing a wide variety of spectrum bands of practical interest for CR applications. A comprehensive, systematical, and rigorous analysis of the statistical properties observed in the measurement data is then performed to find accurate models capable of capturing and reproducing, within reasonable complexity limits, the statistical properties of temporal patterns, at both short and long timescales, in real wireless systems. Innovative modeling approaches capable of simultaneously describing statistical properties at both timescales are developed as well. In summary, this paper contributes realistic and accurate time-dimension spectrum usage models for their application to the study and development of CR. [ABSTRACT FROM PUBLISHER]

The cognitive radio multiple-input multiple-output Gaussian broadcast channels are studied where multiple antennas are available for both primary users and secondary users in a spectrum sharing environment, and the sum-rate capacity is also obtained under both the SUs' transmit power constraint and interference power constraint at the primary receivers. The paper principally consists of two steps. First, a duality technique and dirty paper coding are adopted to simplify the channels. Second, we propose an iterative power allocation algorithm to obtain the maximum sum-rate capacity and examine the effects of the constraint parameters on the concerned quantities. Finally, numerical simulation results are presented to validate the proposed theoretical analysis. [ABSTRACT FROM AUTHOR]

In this paper, we present a power control algorithm in cognitive radio multiple-input–multiple-output (MIMO) system over time-varying fading channels based on the utility-based framework. In particular, a more general objective function framework is proposed under a long- or short-term transmitting and interference power constraints for secondary users, which results the optimization problem is nonconvex. A stochastic optimization algorithm is proposed based on an improved quantum-behaved particle swarm optimization (IQPSO), which can solve the nonconvex optimization problem efficiently. The acceleration coefficients are adjusted with time-varying equations which can help the particles jump out the local optimum. Due to the characteristics of wave function of quantum Delta potential well model, IQPSO can get better optimal solutions in search space for the stochastic optimization problem. To show the efficiency of the proposed algorithm, the utilities of the MIMO CR system got by IQPSO are compared with other approaches in the literature in different case studies, which show that the proposed algorithm can solve the nonconvex problem efficiently and achieve significant throughput. [ABSTRACT FROM AUTHOR]

In this paper, we characterize the worst-case interference for a finite-area TV white space heterogeneous network using the tools of stochastic geometry. We derive closed-form expressions on the probability distribution function (PDF) and an average value of the aggregate interference for various values of path loss exponent under Rayleigh fading channel. The proposed characterization of the interference is simple and can be used in improving the spectrum access techniques. Using the derived PDF, we demonstrate the performance gain in the spectrum detection of an eigenvalue-based detector for cognitive radio networks. [ABSTRACT FROM AUTHOR]

In this paper, a multifunctional reconfigurable filter that can work in three operating modes has been presented. The three operating modes are: all-pass filter, tunable bandpass filter, and tunable band-reject filter. The developed filter has been integrated with an ultrawideband antenna that results in a reconfigurable filtenna. Such four filtennas are arranged on a single substrate, and sufficient isolation is maintained between them by using reflectors to form a four-port multiple-input multiple-output (MIMO) filtenna that can work for midband 5G cognitive radio (CR) applications. By controlling the operating modes of the filter, the final developed structure gives sensing and communicating antennas for spectrum-interweave and spectrum-underlay CRs. Simulated results have been validated by carrying out the measurement. MIMO performance of the proposed antenna has been evaluated by measuring an envelope correlation coefficient and found suitable for practical applications. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Amid the dynamic spectrum access in cognitive radio networks, when complex spectrum conditions should be taken into account, how to price the spectrum in order to benefit primary systems in maximization is still under-investigated. In this paper, we devise a spectrum pricing method to address this issue in cognitive networks. In our proposed mechanism, leasing spectrum is collected for uniform selling and classified into three kinds of channels—high-quality channel, mid-quality channel and low-quality channel, respectively. They will be priced variously according to different interference characteristics caused by versatile path fading and user positions. In respond to heterogeneous channel qualities, secondary users also have own selection preferences. They can purchase one kind of channel for usage in based of channel quality and available budget. Then, we obtain the final pricing solution which is an iterative algorithm converging to a fixed point. Also, the existence of a pure Nash equilibrium is discussed to ensure the rationality of the method. In numerical results, we evaluate the effects of this proposal in spectrum pricing and primary systems' profits. [ABSTRACT FROM AUTHOR]

Automatic modulation recognition (AMR) is an essential and challenging topic in the development of the cognitive radio (CR), and it is a cornerstone of CR adaptive modulation and demodulation capabilities to sense and learn environments and make corresponding adjustments. AMR is essentially a classification problem, and deep learning achieves outstanding performances in various classification tasks. So, this paper proposes a deep learning-based method, combined with two convolutional neural networks (CNNs) trained on different datasets, to achieve higher accuracy AMR. A CNN is trained on samples composed of in-phase and quadrature component signals, otherwise known as in-phase and quadrature samples, to distinguish modulation modes, that are relatively easy to identify. We adopt dropout instead of pooling operation to achieve higher recognition accuracy. A CNN based on constellation diagrams is also designed to recognize modulation modes that are difficult to distinguish in the former CNN, such as 16 quadratic-amplitude modulation (QAM) and 64 QAM, demonstrating the ability to classify QAM signals even in scenarios with a low signal-to-noise ratio. [ABSTRACT FROM AUTHOR]