Search

In this article, we investigate the rate-splitting multiple access (RSMA) framework in a multiuser multiple-input single-output (MISO) underlay cognitive radio system with power-splitting secondary users and information secondary users by using simultaneous wireless information and power transfer. The RSMA framework is a novel multiple access method based on linearly precoded rate splitting at the secondary base station, and successive interference cancellation at the secondary receivers, which has shown better performance compared with the traditional space-division multiple access (SDMA) method. In particular, the objective is to minimize the transmit power at the secondary base station subject to the constraints of minimum energy harvesting, minimum data rate, and a maximum power level for allowable interference with the primary users. The challenging problem under consideration is nonconvex, and the solution relies on dividing it into outer and inner optimization problems. Then, we propose a particle-swarm-optimization-based algorithm to solve the outer problem, with the inner problem managed by the semidefinite relaxation method. In addition, we present a comparative scheme based on the successive convex approximation method and a scheme based on SDMA. Finally, simulation results confirm the superior performance of the proposed approach in comparison with the other schemes.

This paper considers uplink solar-powered cognitive radio networks (CRNs) where multiple secondary users (SUs) transmit data to a secondary base station (SBS) by sharing a licensed channel of a primary system. A deep Q-learning (DQL) algorithm, which combines non-orthogonal multiple access (NOMA) and time division multiple access (TDMA) techniques, is proposed to maximize the long-term throughput of the system. By using our scheme, the agent (i.e. the SBS) can obtain the optimal decision by interacting with the environment to learn about system dynamics. Simulation results validate the superiority of the performance under the proposed scheme, compared with traditional schemes.

This article considers the problem of resource sharing in a virtual mobile network with energy-harvesting base stations (BSs), where several virtual mobile operators (VMOs) lease radio resources (e.g., radio channels and green BSs) from a mobile network owner (MNO). The VMOs want to provide subscribed users with the best performance while ensuring minimal leasing costs. We aim to find the optimal resource leasing scheme for a VMO in order to maximize utility within the uncertainties of harvested energy, request arrivals, and resource prices. We first formulate the problem as a Markov decision process, during which the VMOs compete with each other for the radio resources by dynamically announcing their resource requirements to the MNO. We, then, employ a deep Q-learning algorithm so the VMO can find the optimal solution by interacting with the environment. With this algorithm, artificial neural networks are used to approximate the Q-value function, which can work effectively with large state and action spaces. We further employ the idea of transfer learning, which exploits the strategies learned in historical periods to speed up the learning process of the target task. Finally, we present comprehensive simulations to evaluate the performance of the proposed scheme under various configurations.

The objective of this work is to design a sensor-fault detection and diagnosis system for the Internet of Things and Cyber-Physical Systems. The challenge is, however, achieving this objective within the limited computation, memory, and energy resources of the sensors. More importantly, the detection of faults is time-sensitive, whereas the diagnosis does not necessarily need to be fast. We propose a distributed sensor-fault detection and diagnosis system based on machine learning algorithms where the fault detection block is implemented in the sensor in order to achieve output immediately after data collection. This block consists of an auto-encoder to transform the input signal into a lower-dimensional feature vector, which is then provided to a Support Vector Machine (SVM) for classification as normal or faulty. Once detected, fault diagnosis is performed at a central node, such as a network server, to reduce the computational load on the sensor. In this work, a Fuzzy Deep Neural Network (FDNN) is used for diagnosis to provide further information, such as the type of fault. Here, the input propagates through a deep neural network and a fuzzy representation process. The output of these two components is then fused through densely connected layers. This multi-modal technique learns high-level representations in the data that are missed by conventional methods. To assess the performance of the proposed model, we utilize data obtained from a healthy temperature-to-voltage converter that are then injected with five types of fault: drift, bias, precision degradation, spike, and stuck faults. The performance from fault detection is analyzed in terms of detection accuracy, area under the ROC curve (AUC-ROC), false positive rate, and F1 score. Furthermore, the efficiency of fault diagnosis is shown by the classification accuracy parameter. The experimental results show the efficiency of the proposed fuzzy learning-based model over classic neuro-fuzzy and non-fuzzy learning approaches.

Non-orthogonal multiple access (NOMA) is one of the promising techniques for spectrum efficiency in wireless networks. In this paper, we consider an uplink NOMA cognitive system, where the secondary users (SUs) can jointly transmit data to the cognitive base station (CBS) over the same spectrum resources. Thereafter, successive interference cancellation is applied at the CBS to retrieve signals transmitted by the SUs. In addition, the energy-constrained problem in wireless networks is taken into account. Therefore, we assume that the SUs are powered by a wireless energy harvester to prolong their operations; meanwhile, the CBS is equipped with a traditional electrical supply. Herein, we propose an actor–critic reinforcement learning approach to maximize the long-term throughput of the cognitive network. In particular, by interacting and learning directly from the environment over several time slots, the CBS can optimally assign the amount of transmission energy for each SU according to the remaining energy of the SUs and the availability of the primary channel. As a consequence, the simulation results verify that the proposed scheme outperforms other conventional approaches (such as Myopic NOMA and OMA), so the system reward is always maximized in the current time slot, in terms of overall throughput and energy efficiency.

The objective of this study is to classify the rice grains of seventeen different varieties popularly planted in Vietnam. Image processing is used to extract color, morphological, and texture features of the rice grains. Five feature subsets are formed, namely, morphological, basic color, clustering color, statistical, and gray level co-occurrence matrix (GLCM). These subsets and combined sets are evaluated for classification ability with a support vector machine (SVM). A dataset of 248 features, including a total of color, morphological, and texture features classified with the SVM gives an overall accuracy of 88.29%. To decrease the number of used features and to improve the classification accuracy, the proposed method combining binary particle swarm optimization (BPSO) and the SVM, called BPSO+SVM, is applied to the dataset. In the results, classification accuracy from BPSO+SVM reaches 93.94% using only 96 selected features. The obtained result shows the proposed method achieves higher classification accuracy than the SVM alone, and the required number of features is only 39% of the total dataset. This result can be applied for developing an automatic classification and identification system of rice varieties.

In this paper, we propose deep learning–based energy beamforming in a multi-antennae wireless powered communication network (WPCN). We consider a WPCN where a hybrid access point (HAP) equipped with multiple antennae broadcasts an energy-bearing signal to wireless devices using energy beamforming. We investigate the joint optimization of the time allocation for wireless energy transfer (WET) and wireless information transfer (WIT) with the design for energy beams while minimizing the transmit power at the HAP for efficient use of its available resources. However, this is a non-convex problem, and it is numerically intractable to solve it. In the literature, the traditional approach to solving this problem is based on an iterative algorithm that incurs high computational and time complexity, which is not feasible for real-time applications. We study and analyze a deep neural network (DNN)-based scheme and propose a faster and more efficient approach for the fair approximation of a near-optimal solution to this problem. To train the proposed DNN, we acquire training data samples from a sequential parametric convex approximation (SPCA)-based iterative algorithm. Instead of acquiring data samples and training the DNN, which is highly complex, we use offline training for the DNN to provide a faster solution to the real-time resource allocation optimization problem. Through the simulation results, we show the proposed DNN scheme provides a fair approximation of the traditional SPCA method with low computational and time complexity.

A cognitive radio network (CRN) is a novel solution that promises to solve the spectrum scarcity problem and enhance spectrum utilization. However, unsecured CRN can easily be manipulated in order to attack legacy users on the communication channel. As a result, the network’s performance significantly degrades. Therefore, communication channel security is an important issue that needs to be addressed in a CRN. In this work, we focus on improving the security of multi-channel communication in a CRN, while various jammers try to access channels of interest to prevent SUs from using them. By using game-theoretic concepts and by defining states, actions, and players’ rewards, we propose game–based schemes that find the best channel for the secondary users (SUs) in order to avoid jammer’s attacks on communication channels. Accordingly, the problem is finding the optimal channel to maximize the long-term reward of the SU where communication channels are not used by the primary users (PUs) and are not jammed by attackers. In addition, the idea of transfer learning might be applied to the problem under consideration, and thus, a transfer Game-Actor-Critic (TGACT) scheme is proposed, which uses the transferred knowledge in a double-game period to accelerate the learning process and provide performance improvement in channel selection. Finally, the performance of the proposed schemes is simulated with different configurations. The simulation results show that the proposed schemes are quite resistant to jammer attacks, and achieve better performance compared to other channel selection schemes.

This paper examines the optimal spectrum competing strategy for a virtual network operator in cognitive cellular networks with energy-harvesting base stations. In the scenario for this study, multiple cognitive virtual network operators (CVNOs) obtain spectrum resources from a mobile network operator via spectrum sensing and leasing in order to provide data services to their subscribers. Compared to traditional spectrum leasing via long-term contract, spectrum acquired by sensing is usually cheaper but is unreliable due to the stochastic activities of the licensed users. The CVNOs need to determine the optimal sensing and leasing amount to satisfy the needs of subscribers while guaranteeing a low leasing cost. We aim to find an efficient spectrum sensing and leasing scheme for a CVNO in order to maximize its utility in the long run. The problem is first formulated as the framework of a sequential decision process considering the dynamics of users’ activities, spectrum prices, and harvested energy. We then develop a deep reinforcement learning algorithm that uses deep neural networks as function approximators so the CVNO can learn the optimal decision policy by interacting with the environment. We analyze the performance of our proposed scheme through extensive simulations. The experiment results show that the proposed mechanism can significantly improve the CVNO’s long-term benefit compared to other learning and non-learning methods.

The performance of data aggregation in industrial wireless communications can be degraded by environmental interference on Industrial Scientific Medical (ISM) channels. In this paper, cognitive radio (CR) was applied to enable devices to share primary channels with the aim of enhancing the transmission performance of the WirelessHART network. We considered a linear convergecast system, where the packets generated at each device were routed to the gateway (GW) through the aid of neighboring devices. The solar-powered cognitive access points (CAPs) were deployed to improve the network performance by opportunistically allocating the primary channels to the devices for data transmissions. Firstly, we formulate the scheduling problem of long-term throughput maximization as a framework of a Markov decision process with the constraints of the minimum delay, the number of required ISM channels, and the harvested energy at the CAPs. Then, we propose a deep reinforcement learning-based scheduling scheme to optimally assign multiple ISM and primary channels to the field devices in each superframe. The simulation results confirmed the superiority of the proposed scheme compared to existing methods.

Due to the constantly changing sea surface, there is a high risk of link fragility caused by sea waves when different marine users are intended to establish stable links for communication. To ensure stability with less delay, finding a stable route is one of the crucial aspects of maritime networks. In order to achieve this aim, we propose a routing protocol for cognitive maritime networks based on software-defined networking (SDN). This SDN-based cognitive routing protocol provides stable routes among different marine users. To provide the global view of the whole network, a main controller is placed close to the seashore, whereas the localized views are provided by the cluster heads. Autonomous surface vehicles are used as gateways under sparse network conditions to collect and transport data among clusters, and to and from the main controller. This is an SDN-based ship-to-ship communication scheme where two ships can only establish a link when they not only have consensus about a common idle channel but are also within the communication range of each other. We perform extensive simulations to test the proposed scheme with different parameters and find better performance in comparison with both SDN-based and non-SDN-based schemes in terms of end-to-end delay, packet delivery ratio, and routing overhead ratio.

Physical layer wireless communications are more and more essential, and are vulnerable to malicious users owing to the nature of broadcast channels. Herein, we consider a centralized multi-channel cognitive radio network in the presence of eavesdroppers (EVEs). In the network, the secondary base station (SBS) shares currently free primary channels to simultaneously communicate with secondary users (SUs), while passive eavesdroppers attempt to overhear data in the secondary communications. Each limited-battery SU is equipped with two antennas (one for transmitting signals, and other for receiving signals) and is powered by a solar energy harvester. Meanwhile, the SBS equipped with multiple antennas can operate in full-duplex (FD) transmission mode (simultaneously transmit and receive signals) or in half-duplex (HD) transmission mode (transmit and receive signals in turn during each half of a time slot) with the SUs. In this paper, we propose a novel scheme to maximize the secondary system security of the multi-channel cognitive system in the presence of multiple passive EVEs, in which the EVEs are able to overhear the data of the SBS−SU transmissions on all the primary channels. The problem of decision making is formulated as the framework of a partially observable Markov decision process (POMDP), and an optimal solution is achieved by adopting value iteration−based dynamic programming. Specifically, in each time slot, the SBS allocates optimal channel and optimal action (i.e. either stay silent or employ HD/FD transmission modes with optimal transmission power) for each SU in order to obtain maximum long-term secrecy rate for the secondary system.

In this paper, we consider simultaneous wireless information and power transfer (SWIPT) in a multiple-input single-output interference channel (IC) system where the power-splitting (PS) receivers utilize linear/nonlinear energy-harvesting (EH) models. The functions that express the relationship between the input radio frequency power and the output direct current harvested energy of the EH circuits are usually assumed to be linear in recent SWIPT works, while the nonlinear function is suitable for practical data. In a SWIPT IC system, two important targets are sum harvested energy maximization and harvested energy efficiency maximization at the PS receiver, and they are investigated under linear/nonlinear EH models. Thus, some nonconvex resource allocation problems with the two targets and linear/nonlinear EH models are formulated to jointly optimize beamforming vectors at the transmitters and the PS ratios at the receivers. By exploiting a successive convex approximation method and a semidefinite relaxation (SDR) technique, iterative algorithms are proposed to obtain local optimal solutions. Interestingly, the optimal solution to the subproblem is proven to satisfy the rank-1 constraint of the SDR technique. Finally, numerical experiments illustrate effective performance from the proposed solutions, in comparison with some special schemes.

Multi-access edge computing has become a strategic concept of the Internet of Things. The edge computing market has reached USD several billion and is growing intensively. In the edge-computing paradigm, most of the data is processed close to, or at the edge of, the network. This greatly reduces the computation and communication load of the network core. Moreover, edge computing provides better support for user privacy. On the other hand, an increase in data processing locations will proportionately increase the attack surface. An edge node can be put out of service easily by being flooded with spoofed packets owing to limited capacities and resources. Furthermore, wireless edge nodes are quite vulnerable to energy exhaustion attacks. In this situation, traditional network security mechanisms cannot be used effectively. Therefore, a tradeoff between security and efficiency is needed. This study considered the requirements under which the use of an intrusion detection system (IDS) is justified. To the best of our knowledge, this is a first attempt to combine IDS quality, system performance degradation due to IDS operations, and workload specificity into a unified quantitative criterion. This paper is an extended version of a report published in the proceedings of the ICCSA 2020 and differs from it in many ways. In particular, this paper considers novel mathematical problems regarding the deployment strategies for an IDS and the corresponding inverse problems and provides closed-form solutions for a few previously unsolved problems.

Rising energy demand and the disproportionate utilization of fossil fuels not only result in power imbalance and economic drain but also raise environmental concerns. Under these challenging circumstances, microgrids provide a tactical solution by adopting distributed energy resources at user end. However, this solution is not effective without enough participation by these end users (prosumers) for sustainable energy growth in microgrids. This paper presents a behavioral control theory and various psychological motivational models to improve prosumers’ participation up to the desired level. A framework for peers’ management within a community is also presented. The coalition-based game theory is employed for fair and trustworthy inter-trading which lead to the formation of grand coalition by satisfying all the defined motivational models. Various trading systems i.e. feed in tariff system, peer-to-peer trading with and without storage systems, and demand-side management-based peer-to-peer trading systems are used for energy inter-trading with minimum involvement with the grid. Finally, the proposed system is validated through simulations of various game theoretic-based peer-to-peer trading systems. Simulation results show a considerable reduction in average expenses for energy demand and carbon emissions with improved earnings for peers.

Appropriate coverage prediction is a fundamental task for an operator during the dimensioning process and planning of a digital terrestrial television (DTT) system because it allows offering a satisfactory quality of service to end users. Accordingly, several prediction methods based on propagation path loss estimation and traditional statistical models have been proposed. However, the choice of model depends on many factors, such as the presence of obstacles (buildings, trees, and so on) and propagation paths. This fact leads to increasing the error gap between the predicted and real value, which varies from one propagation model to the next. Therefore, novel techniques are required to achieve a high accuracy in the prediction of the signal strength based on few local measurements over the zone of interest. A machine learning regression algorithm is a novel approach that improves the accuracy of DTT coverage prediction regardless of the aforementioned constraints. To this end, we propose an approach based on clustering and machine regression algorithms, such as random forest regression, AdaBoost regression, and ${K}$ -nearest neighbors regression, where we choose the best algorithm for our approach. We use real measurements in terms of electric field strength corresponding to eight DTT channels operating in the city of Quito, Ecuador. Furthermore, we display the coverage results in Google Maps. We perform extensively simulation analysis based on the tenfold cross validation method to evaluate the performance of the machine learning regressor algorithms and compare the results in three error metrics with support vector regression, lasso regression, multilayer perceptron regression, and ordinary kriging technique. Satisfactorily, the results using random forest regression depict a considerable improvement in the accuracy of coverage prediction under a low computational load.

In this paper, simultaneous wireless information and power transfer (SWIPT) transmissions with multiple-input single-output transceiver pairs are considered. In each pair, a multi-antenna transmitt...

In this paper, we introduce an efficient user-association and bandwidth-allocation scheme based on an actor-critic deep learning framework for downlink data transmission in dense mobile networks. In this kind of network, small cells are densely deployed in a single macrocell, and share the same spectrum band with the macrocell. The small-cell base stations are also called green base stations since they are powered solely by solar-energy harvesters. Therefore, we propose an actor-critic deep learning (ACDL) algorithm for the purpose of maximizing long-term network performance while adhering to constraints on harvested energy and spectrum sharing. For this purpose, the agent of the ACDL algorithm tries to obtain an optimal user-association and bandwidth-allocation policy by interacting with the network’s environment. We first formulate the optimization problem in this paper as a Markov decision process, during which the agent learns about the evolution of the environment through trial and error experience. Then, we use a deep neural network to model the policy function and the value function in the actor and in the critic of the agent, respectively. The actor selects an action based on the output of the policy network. Meanwhile, the critic uses the output of the value network to help the actor evaluate the taken action. Numerical results demonstrate that the proposed algorithm can enhance network performance in the long run.

This paper studies an optimal transmit power decision policy for energy-efficient data transmissions between a sensor node (i.e., the source) and a cluster head (i.e., the destination) in cluster-based wireless sensor networks in the presence of a full-duplex (FD) active eavesdropper. In this network, the source is powered by a wireless energy harvester, while the destination is constantly supplied by the traditional electrical energy. The eavesdropper is capable of FD transmitting and receiving and hence opportunistically launches jamming attacks against the destination while eavesdropping, which affects not just the legitimate transmissions but the eavesdropper itself. The destination can also work in the FD mode to simultaneously receive information signals and send an artificial noise to interfere with the eavesdropper. Therefore, we investigate an optimal power allocation policy for the source in order to maximize the secrecy transmission rate against an FD eavesdropper. In addition, we study the problem of decision making in two different scenarios. First, the legitimate nodes are assumed to have prior information about the arrival of harvested energy and about the eavesdropper’s jamming attack model. The problem is formulated as the framework of a partially observable Markov decision process and is solved with value iteration–based dynamic programming. Second, the legitimate nodes do not know the dynamics of the environment in advance, so the problem becomes a standard Markov decision process. Hence, we propose an actor-critic learning framework to find the solution from practical interactions with the environment. Finally, we verify the performance of the proposed schemes by simulations.

The cognitive radio network (CRN) is not only considered a useful medium for users, but it is also an environment vulnerable to proactive attackers. This paper studies an attack strategy for a legitimate energy-constrained eavesdropper (e.g., a government agency) to efficiently capture the suspicious wireless communications (i.e., an adversary communications link) in the physical layer of a CRN in tactical wireless networks. Since it is powered by an energy harvesting device, a full-duplex active eavesdropper constrained by a limited energy budget can simultaneously capture data and interfere with the suspicious cognitive transmissions to maximize the achievable wiretap rate while minimizing the suspicious transmission rate over a Rayleigh fading channel. The cognitive user operation is modeled in a time-slotted fashion. In this paper, we formulate the problem of maximizing a legitimate attack performance by adopting the framework of a partially observable Markov decision process. The decision is determined based on the remaining energy and a belief regarding the licensed channel activity in each time slot. Particularly, in each time slot, the eavesdropper can perform an optimal action based on two functional modes: (1) passive eavesdropping (overhearing data without jamming) or (2) active eavesdropping (overhearing data with the optimal amount of jamming energy) to maximize the long-term benefit. We illustrate the optimal policy and compare the performance of the proposed scheme with that of conventional schemes where the decision for the current time slot is only considered to maximize its immediate reward.

Cognitive radio is becoming an increasingly important component of Internet of Things technologies, because it improves spectrum efficiency and provides a way to overcome the challenge of excessive demand for wireless communications. Research and development of cognitive radio communication systems are timely and helpful. Recently, Zheng et al. proposed a network stability-aware clustering protocol for cognitive radio sensor networks. In this letter, we discuss its fatal flaws, as well as ways to overcome them.

Sensors&rsquo, existence as a key component of Cyber-Physical Systems makes it susceptible to failures due to complex environments, low-quality production, and aging. When defective, sensors either stop communicating or convey incorrect information. These unsteady situations threaten the safety, economy, and reliability of a system. The objective of this study is to construct a lightweight machine learning-based fault detection and diagnostic system within the limited energy resources, memory, and computation of a Wireless Sensor Network (WSN). In this paper, a Context-Aware Fault Diagnostic (CAFD) scheme is proposed based on an ensemble learning algorithm called Extra-Trees. To evaluate the performance of the proposed scheme, a realistic WSN scenario composed of humidity and temperature sensor observations is replicated with extreme low-intensity faults. Six commonly occurring types of sensor fault are considered: drift, hard-over/bias, spike, erratic/precision degradation, stuck, and data-loss. The proposed CAFD scheme reveals the ability to accurately detect and diagnose low-intensity sensor faults in a timely manner. Moreover, the efficiency of the Extra-Trees algorithm in terms of diagnostic accuracy, F1-score, ROC-AUC, and training time is demonstrated by comparison with cutting-edge machine learning algorithms: a Support Vector Machine and a Neural Network.

Non-orthogonal multiple access (NOMA) is a promising technique to satisfy a host of access demand and provide higher throughput. It enables that multiple users are multiplexed with different power levels by using superposition coding at the transmitter side and successive interference cancellation at the receiver side. In this paper, we deal with the long-term throughput maximization of an uplink NOMA in the cognitive radio network (CRN). The secondary users (SUs) have limited capacity battery, hence, SUs equipped with an energy harvester can harvest energy from solar sources to prolong their operations. Particularly, a combination of NOMA and time division multiple access (TDMA) is proposed in order to reduce the complexity of massive wireless communication systems. By taking into account the practical applications, a deep Q learning algorithm is employed to maximize the long-term throughput of the system, where the agent (i.e secondary base station (SBS)) can interact with an environment to learn about system dynamics. As a result, the SBS learns how to allocate optimal transmission energy to SUs in each time slot. Simulation results demonstrate that the proposed scheme can achieve better performance than conventional schemes.

Bearing is one of the important mechanical components to reduce friction in rotating machines. Early fault diagnosis in bearings is an important challenge to the prevention of full failure and avoiding disorder of the machine. In this paper, an indirect observer and machine learning technique are adopted for fault identification in bearing. To develop an indirect observer, in the first step, the autoregressive with uncertainty modeling technique is proposed to modeling the RMS (indirect) normal signal of bearing. After that, the robust (sliding fault detection) proportional multi integral with autoregressive external input modeling (ARPMI) observer was used to solve the unknown signal estimation in bearing. Besides, the support vector machine (SVM) technique for fault classification is proposed. The effectiveness of the proposed scheme is validated using Case Western Reverse University (CWRU) dataset. Experimental results show that, the proposed scheme improves the average performance for various rotational speed fault identification by about 10.5% and 13.5% compared with the proportional multi integral with autoregressive external input modeling (APMI) observer and proportional-integral with autoregressive external input modeling (API) observer, respectively.

This paper studies a multi-user multiple-input single-output (MISO) simultaneous wireless information and power transfer (SWIPT) system with a power beacon (PB), in which several power-splitting (PS) users co-exist with an energyharvesting (EH) user. The PB is a dedicated source of power for radio frequency EH, and it appears as a candidate solution to help the base station (BS) to satisfy the EH requirements of the users. We aim to obtain the transmit beamforming vectors and the PS ratios that minimize the total transmit power at the BS and PB under the constraints of minimum QoS of the PS users and minimum EH requirements. The non-convex optimization problem is solved by using the semidefinite relaxation technique. Numerical simulations show that the proposed approach achieves the lowest total transmit power in comparison with baseline schemes.

Real-time fault detection of rotating engine components is a fundamental task for aero community, especially for commercial aircraft to cut maintenance costs for airline companies and enhance aviation security. Therefore, the aim of this paper is to develop a diagnostic framework for real-time fault detection of a turbine engine disk for commercial aircraft, particularly for state monitoring of rotating engine components. The proposed framework relies on a machine learning algorithm that can adjust to the shifts of the motion state of a commercial aircraft. In addition, feature selection techniques can reduce the repetitive, or unnecessary features, which might degrade the accuracy of classification. Accordingly, we consider the multi-layer perceptron algorithm to classify a sample between normal or fault and a binary particle swarm optimization-based feature selection scheme. Also, the paper offers comparative approaches such as the perceptron algorithm, the recursive feature elimination as another feature selection method, and so on. The simulation results show that the proposed framework is robust to changes in the operating conditions and achieves the best accuracy between all the methods considered.

In this paper, we aim to provide reliable user connectivity and enhanced security for computation task offloading. Physical layer security is studied in a wireless-powered non-orthogonal multiple access (NOMA) mobile edge computing (MEC) system with a nonlinear energy-harvesting (EH) user and a power beacon (PB) in the presence of an eavesdropper. To further provide a friendly environment resource allocation design, wireless power transfer (WPT) is applied. The secure computation efficiency (SCE) problem is solved by jointly optimizing the transmission power, the time allocations for energy transfer, the computation time, and the central processing unit (CPU) frequency in the NOMA-enabled MEC system. The problem is non-convex and challenging to solve because of the complexity of the objective function in meeting constraints that ensure the required quality of service, such as the minimum value of computed bits, limitations on total energy consumed by users, maximum CPU frequency, and minimum harvested energy and computation offloading times. Therefore, in this paper, a low-complexity particle swarm optimization (PSO)-based algorithm is proposed to solve this optimization problem. For comparison purposes, time division multiple access and fully offloading baseline schemes are investigated. Finally, simulation results demonstrate the superiority of the proposed approach over baseline schemes.

Integration of the Internet into the entities of the different domains of human society (such as smart homes, health care, smart grids, manufacturing processes, product supply chains, and environmental monitoring) is emerging as a new paradigm called the Internet of Things (IoT). However, the ubiquitous and wide-range IoT networks make them prone to cyberattacks. One of the main types of attack is a denial of service (DoS), where the attacker floods the network with a large volume of data to prevent nodes from using the services. An intrusion detection mechanism is considered a chief source of protection for information and communications technology. However, conventional intrusion detection methods need to be modified and improved for application to the IoT owing to certain limitations, such as resource-constrained devices, the limited memory and battery capacity of nodes, and specific protocol stacks. In this paper, we develop a lightweight attack detection strategy utilizing a supervised machine learning-based support vector machine (SVM) to detect an adversary attempting to inject unnecessary data into the IoT network. The simulation results show that the proposed SVM-based classifier, aided by a combination of two or three incomplex features, can perform satisfactorily in terms of classification accuracy and detection time.

Mobile-data traffic exponentially increases day by day due to the rapid development of smart devices and mobile internet services. Thus, the cellular network suffers from various problems, like traffic congestion and load imbalance, which might decrease end-user quality of service. This work compensates for the problem of offloading in the cellular network by forming device-to-device (D2D) links. A game scenario is formulated where D2D-link pairs compete for network resources. In a D2D-link pair, the data of a user equipment (UE) is offloaded to another UE with an offload coefficient, i.e., the proportion of requested data that can be delivered via D2D links. Each link acts as a player in a cooperative game, with the optimal solution for the game found using the Nash bargaining solution (NBS). The proposed solution aims to present a strategy to control different parameters of the UE, including harvested energy which is stored in a rechargeable battery with a finite capacity and the offload coefficients of the D2D-link pairs, to optimize the performance of the network in terms of throughput and energy efficiency (EE) while considering fairness among links in the network. Simulation results show that the proposed game scheme can effectively offload mobile data, achieve better EE and improve the throughput while maintaining high fairness, compared to an offloading scheme based on a maximized fairness index (MFI) and to a no-offload scheme.

This article studies a power beacon (PB)-assisted simultaneous wireless information and power transfer (SWIPT) system, where a base station (BS) sends information, and a PB transfers radio frequency energy to a receiver equipped with a power-splitting (PS) structure to decode information and harvest energy simultaneously. First, we jointly design the transmit power of the PB and the PS ratio, to formulate the minimum transmit power at the PB problem under the constraints of minimum energy harvesting and the minimum signal-to-interference-plus-noise ratio. Unfortunately, the problem is not always feasible, and thus, we provide the conditions to guarantee the feasibility of the problem and derive the analytical optimal solution by the Lagrange method and Karush–Kuhn–Tucker optimality conditions. Second, we consider a receiver with the capability of cancelling the interference from the PB, and we obtain the optimal solution to the minimum PB transmit power problem. Next, we consider the transmission ...

Spectrum sensing is of crucial importance in cognitive radio (CR) networks. In this paper, a reliable spectrum sensing scheme is proposed, which uses K-nearest neighbor, a machine learning algorithm. In the training phase, each CR user produces a sensing report under varying conditions and, based on a global decision, either transmits or stays silent. In the training phase the local decisions of CR users are combined through a majority voting at the fusion center and a global decision is returned to each CR user. A CR user transmits or stays silent according to the global decision and at each CR user the global decision is compared to the actual primary user activity, which is ascertained through an acknowledgment signal. In the training phase enough information about the surrounding environment, i.e., the activity of PU and the behavior of each CR to that activity, is gathered and sensing classes formed. In the classification phase, each CR user compares its current sensing report to existing sensing classes and distance vectors are calculated. Based on quantitative variables, the posterior probability of each sensing class is calculated and the sensing report is classified into either representing presence or absence of PU. The quantitative variables used for calculating the posterior probability are calculated through K-nearest neighbor algorithm. These local decisions are then combined at the fusion center using a novel decision combination scheme, which takes into account the reliability of each CR user. The CR users then transmit or stay silent according to the global decision. Simulation results show that our proposed scheme outperforms conventional spectrum sensing schemes, both in fading and in nonfading environments, where performance is evaluated using metrics such as the probability of detection, total probability of error, and the ability to exploit data transmission opportunities.

Cognitive radio networks (CRNs) have a shortcoming in that attackers can increase their ability to disturb secondary users (SUs). This paper focuses on jamming attacks in the physical layer, in which several attackers try to interrupt SUs by injecting the interference into their communications. Once a jammer transmits interfering signals on the channel during the defined time, all ongoing transmissions on this channel will be corrupted. It is quite difficult for SUs to protect a single-hop data transmission from jammers. So, obtaining a solution for secure multi-hop data transmission in the presence of jammers becomes a more challenging task in CRNs. This paper investigates a strategy to find the optimal route and channels for transmission between cognitive transmitters and receivers in the presence of jammers in CRNs. In this scenario, the jammers are located randomly and their jamming behavior is assumed to follow a Gaussian distribution. We provide an optimal link–channel pair allocation scheme in which the secondary transmitter (the source) selects the best relay and a suitable channel for each hop in the source-to-destination route to protect the information intended to the secondary receiver (the destination) from the jammers. Simulation results prove the efficiency of the proposed scheme in a CR network.

In this paper, we investigate a security mode decision policy for a cognitive radio network (CRN) powered by a non-radio frequency energy harvester. In such a network, a cognitive user (CU), which has a finite battery capacity, senses the presence of the primary user and tries to access the time-slotted primary channel opportunistically to transmit data. However, communication can be vulnerable to sudden attacks that are carried out by hidden eavesdroppers. Therefore, we propose an energy-efficient data encryption scheme for CRNs to increase the effective security level under energy limitation constraints. The operation mode decision policy is formulated as a framework of a partially observable Markov decision process. In this approach, based on the sensing results and the remaining energy at the beginning of each time slot, CUs can decide to stay silent to save energy, or become active and encrypt data using opportune private-key encryption methods considering the effect of the current action on the future reward to maximize the effective security. Finally, we evaluate the performance of the proposed scheme by using numerical simulation results.

Due to the highly dynamic nature of cognitive vehicular networks, several sporadic links induce a long delay in the network. The selection of a stable route is therefore one of the key design factors to improve overall network stability, thereby reducing the end-to-end delay. Software-defined networking (SDN) is a novel approach that improves network intelligence. To this end, we propose a novel SDN-based routing protocol for cognitive vehicular networks that finds a stable route between source and destination. As this is a cognitive routing protocol, spectrum sensing is therefore the primary task of this algorithm to improve network stability by keeping primary user activity safe. We apply a belief propagation algorithm for channel selection. This is an SDN-based vehicular communications scheme where two nodes can only communicate when they have consensus about a common idle channel. The protocol has two phases: the registering phase and the route prediction phase. The SDN main controller (MC) is responsible for a global view of the network, whereas several local controllers (LCs) are responsible for localized global views of the network. This layering of controllers into two kinds (MC and LCs) improves the network performance in terms of end-to-end delay, high delivery ratio, and low overhead. We prove this in our simulation results by comparing our proposed scheme with two existing schemes (one with, and another without, SDN).

In this paper, a physical-layer-security scheme for an underlay relay-based cognitive radio network (CRN) that uses orthogonal frequency-division multiplexing (OFDM) as the medium access technique is proposed. Resource allocation in relay-aided CRNs becomes a hard problem especially if it is under security threat. Different from conventional relay-based OFDM schemes, in the paper, we consider the relay network which has two dedicated relay nodes; one relay which is capable of subcarrier mapping forward the received signal to the destination and the other sends a jamming signal to add noise to the signal received by the eavesdropper. Optimization is performed under a unified framework where power allocation at the source node, power allocation, and subcarrier mapping in the relay network are optimized to maximize the secrecy rate of the CRN while satisfying the maximum transmission power constraints and the interference threshold of the PU. The power allocation problem at the forwarding relaying node is a non-convex optimization problem. Therefore, at first, the optimization problem is simplified and a closed-form solution is obtained which satisfies the maximum PU interference constraint. Afterward, the optimization problem is solved for satisfying the maximum transmission power constraint. An algorithm is also proposed for subcarrier mapping at the forwarding relaying node. The proposed power allocation method and a subcarrier mapping scheme have low complexity, compared with the baseline schemes. Finally, simulation results are provided for different parameters to show the performance improvement of the proposed scheme in terms of secrecy rate.

We study jamming attacks in the physical layer of multihop cognitive radio networks (MHCRNs) where energy-constrained relays forward information from the source to the destination. Meanwhile, a jammer can transmit interfering signals on a channel such that all ongoing transmissions on this channel will be corrupted. In this paper, all jammers can attack only one of the predefined channels in each time slot. Moreover, they can randomly switch channels to start jamming another channel at the beginning of every time slot. The switching behavior is assumed to follow a Gaussian distribution. Due to limited battery capacity in the relays, energy harvesting is utilized to solve the energy-constrained problem in the cognitive radio network. Subsequently, relays are able to harvest energy from non-radio frequency (non-RF) signals such as solar, wind, or temperature. In this paper, we determine the throughput/delay ratio as a key metric to evaluate the performance in MHCRNs. Owing to the limited battery capacity in the relays and the jamming problem, the source needs to select proper relays and channels for each data transmission frame to optimize overall network performance in terms of end-to-end delay, throughput, and energy efficiency. Therefore, we provide two novel multihop allocation schemes to maximize achievable end-to-end throughput while minimizing delay in the presence of jammers. Through simulation results, we validate the effectiveness of the proposed schemes under multiple jamming attacks in MHCRNs.

The integration of computing and modern wireless communications techniques is enabling prolific intelligent monitoring and efficient control of electric power systems in the frameworks of smart grids. In parallel, an enhanced reliance on such technologies has increased the susceptibility of today’s smart grids to cyber-assaults. Recently, a new type of assault, termed covert cyber deception assault , has been introduced to infringe upon the integrity of smart grid data. Such assaults are designed and initiated by hackers who have considerably good knowledge of the power network topology and the security measures in place, and therefore, these assaults cannot be effectively detected by the bad-data detectors in traditional state estimators. In this paper, we propose a supervised machine learning–based scheme to detect a covert cyber deception assault in the state estimation–measurement feature data that are collected through a smart-grid communications network. The distinctive characteristic of the paper is that we use a genetic algorithm–based feature selection in our scheme to improve detection accuracy and reduce computational complexity. The proposed detection scheme is evaluated using standard IEEE 14-bus, 39-bus, 57-bus, and 118-bus test systems. Through performance analysis, it is shown that the proposed scheme provides a significant improvement in covert cyber deception assault detection accuracy, compared with existing machine learning–based schemes.

In this paper, the problem of quality improvement for sensing models in various applications is considered. A choice of sensing model strongly influences the design of wireless sensor networks and the performance of protocols, such as traffic aggregation, broadcasting, energy-efficient routing, target or barrier coverage, and so on. For these reasons, it is useful to investigate the nature of the sensing ability and the manner in which it depends on the characteristics of wireless sensor networks. This paper investigates the impact of experiment design on the evaluation of sensing quality function. This paper provides an approach to a statistically efficient estimation of sensing model parameters.

With long delays due to sporadic routing links in cognitive vehicular communications systems, relay node selection is one of the key design factors, as it significantly improves end-to-end delay, thereby improving overall network performance. To this end, we propose infrastructure-aided hybrid routing that uses a roadside unit (RSU) to help vehicular nodes to select idle channels and relay nodes. Channel selection is done with a belief propagation algorithm, which aggregates individual beliefs with the help of vehicles and RSUs to make a final belief, providing high accuracy in hypotheses about spectrum availability. The selection of a relay node is determined by calculating the message delivery time—the source/relay node selects the one that has the minimum message delivery time from among all the neighboring nodes. This is a hybrid (vehicle-to-vehicle and vehicle-to-RSU) communications scheme where two nodes can communicate only when they have consensus about a common idle channel. The idea is to combine cognitive capabilities with a routing technique in order to simultaneously overcome spectrum scarcity and network connectivity issues. Therefore, both dense and sparse network conditions are considered in this routing protocol for both highway and city scenarios. To enhance the stability of cognitive routing links, different functions for vehicles and RSUs are considered. We prove better performance in delay, delivery ratio, and overhead by comparing the proposed technique with two existing techniques (one dealing with, and another without, RSUs).

With the long propagation delay of an acoustic signal in underwater communications systems, relay node selection is one of the key design factors, because it significantly improves end-to-end delay, thereby improving overall network performance. To this end, the authors propose orthogonal frequency division multiplexing-based spectrum-aware routing (OSAR), a scheme in which spectrum sensing is done by an energy detector, and each sensor node broadcasts its local sensing results to all one-hop nodes via an extended beacon message. Each sensor node then selects nodes that agree on an idle channel, consequentially forming a set of neighbouring nodes. The selection of a relay node is determined by calculating the transmission delay – the source/relay node selected is the one that has the minimum transmission delay from among all nodes in the neighbouring set. To evaluate OSAR, the authors perform extensive simulations via ns-MIRACLE for different numbers of channels using a BELLHOP model, and evaluate the average delay for different sensor nodes within the considered network. The results show a substantial decrease in delay as the number of sensor nodes increases in the network. In addition, the authors verify that the packet delivery ratio increases with increases in the number of sensor nodes, and prove better performance in the overhead ratio. The authors' simulation results verify that OSAR outperforms existing solutions.

Herein, the authors consider harvested energy powered cognitive radio networks (CRNs) in which harvested energy is stored in a rechargeable battery which has finite capacity. In addition, a practical scenario in which the amount of harvested power is finite is taken into account. Cognitive users (CUs) opportunistically access a licensed channel (or primary channel); meanwhile, it should be ensured that their confidential communications are not leaked to an eavesdropper. We investigate an optimal spectrum sensing schedule and the optimal amount of transmission energy for the CUs in each processing time slot. In particular, at the beginning of each time slot, based on the remaining energy in the battery, CU transmitter decides either: 1) to be active to sense the channel and transmit its data if the channel is found vacant or 2) to stay inactive during the current time slot in order to save energy and wait for more incoming energy for use in the next time slots. The decision is based on expected secrecy transmission rate calculated for both cases over subsequent $K$ time slots. The proposed scheme aims to improve long-term secrecy transmission rate of CRNs in comparison with a conventional scheme where the decision for the current time slot is made to maximize current secrecy transmission rate without considering any future reward.

Edge computing becomes a strategic concept of IoT. The edge computing market reaches several billion USD and grows intensively. In edge computing paradigm, the data can be processed close to, or at the edge of the network. This way greatly reduces the computation and communication load of the network core. Moreover, processing data near the sources of data also provides better support for the user privacy. However, an increase in the number of data processing locations will proportionately increase the attack surface. Due to limited capacities and resources, an edge node cannot perform too many complex operations. Especially for the applications with high real-time requirements, efficiency becomes a crucial issue in secure data analytics. Therefore, it is important to get a tradeoff between security and efficiency. We focus on this problem in this paper.

Cyber-Physical System (CPS) emerges as a potential direction to improve the applications relating to object-to-object, human-to-human and human-to-object communications in both the real world and virtual world. The examples of CPSs include Smart Girds (SG), Wireless Sensor Networks (WSNs), transportation networks etc. However, the Ubiquitiy of CPSs pose extra challenges to the systems, such as intrusions from external agent and failures originated internally in nodes of the networks. These internally appeared failures are generally referred to as faults. The Drift fault, that result in increasing linearly the output of sensor from normal value, is the most commonly occured fault in sensor nodes. In this paper, a fault detection model is proposed using machine learning to identify drift fault immediately after it appears in sensor. The proposed approach uses an Auto-Encoder (AE) to extract features from the raw signal of sensor. The vector of features is forwrded to Support Vector Machine (SVM) for fault identification. We compare the performance of four different architectures of AE: primary AE, Stacked AE (SAE), Denoising AE (DAE), and Stacked Denoising AE (SDAE). The number of features extracted by these network is varied from 2 to 15. The accuracy of the SVM is used as a parameter for comparison. The results shows that the DAE outperform the counter AE, SAE, and SDAE architectures.

From smart industries to smart cities, sensors in the modern world plays an important role by covering a large number of applications. However, sensors get faulty sometimes leading to serious outcomes in terms of safety, economic cost and reliability. This paper presents an analysis and comparison of the performances achieved by machine learning techniques for realtime drift fault detection in sensors using a low-computational power system, i.e., Raspberry Pi. The machine learning algorithms under observation include artificial neural network, support vector machine, naive Bayes classifier, k-nearest neighbors and decision tree classifier. The data was acquired for this research from digital relative temperature/humidity sensor (DHT22). Drift fault was injected in the normal data using Arduino Uno microcontroller. The statistical time-domain features were extracted from normal and faulty signals and pooled together in training data. Trained models were tested in an online manner, where the models were used to detect drift fault in the sensor output in real-time. The performance of algorithms was compared using precision, recall, f1-score, and total accuracy parameters. The results show that support vector machine (SVM) and artificial neural network (ANN) outperform among the given classifiers.

IoT will enable a plethora of new applications in various areas of human activity. However, the implementation of IoT is hampered by fears that societal costs of the IoT outweigh its benefits. Security experts have warned of the potential risk of huge numbers of unsecured devices united into the global ubiquitous system. IoT intrusions will disable home security systems, destroy crops, destabilize hospitals etc. To unlock the IoT potential it needs to improve the IoT security and support IoT applications survivability. For this purpose, it needs to get a tradeoff between resources of IoT devices and system survivability. In this work we investigate the mentioned problem and offer the corresponding approach.

As one of the most diversified cyber-physical systems, the smart grid has become more decumbent to cyber vulnerabilities. An intelligently crafted, covert, data-integrity assault can insert biased values into the measurements collected by a sensor network, to elude the bad data detector in the state estimator, resulting in fallacious control decisions. Thus, such an attack can compromise the secure and reliable operations of smart grids, leading to power network disruptions, economic loss, or a combination of both. To this end, in this paper, we propose a novel idea for the reconstruction of sensor-collected measurement data from power networks, by removing the impacts of the covert data-integrity attack. The proposed reconstruction scheme is based on a latterly developed, unsupervised learning algorithm called a denoising autoencoder, which learns about the robust nonlinear representations from the data to root out the bias added into the sensor measurements by a smart attacker. For a robust, multivariate reconstruction of the attacked measurements from multiple sensors, the denoising autoencoder is used. The proposed scheme was evaluated utilizing standard IEEE 14-bus, 39-bus, 57-bus, and 118-bus systems. Simulation results confirm that the proposed scheme can handle labeled and non-labeled historical measurement data and results in a reasonably good reconstruction of the measurements affected by attacks.

Integration of the internet into the entities of the different domains of human society is emerging as a new paradigm called the Internet of Things. At the same time, the ubiquitous and wide-range systems make them prone to attacks. Security experts have warned of the potential risk of huge numbers of unsecured devices united into the global ubiquitous system. To unlock the potential of Internet of Things it needs to improve the security of applications. An intrusion detection mechanism is an important element of security paradigm. However conventional intrusion detection methods are expected to fail, because many user devices have constrained resources. In this paper, we consider a lightweight attack detection strategy utilizing machine learning techniques, which is appropriate for low-resource IoT devices.