Search

As an aerial base station, unmanned aerial vehicle (UAV) has been considered as a promising technology to assist future wireless communications due to its flexible, swift and low cost features, where resource allocation is the basis for ensuring energy-efficient UAV-assisted networks. This paper formulates a joint optimization problem of user association, UAV trajectory design and power control to maximize the channel capacity among all ground users at a limited power level in a downlink transmission. To tackle the mixed-integer non-linear programming problem, this paper proposes a clustering-aided reinforcement learning approach consisting of three consecutive stages. Firstly, modified expectation-maximization unsupervised learning algorithm is investigated to cluster the ground users, which reduces the dimensions and hence, the association complexity is reduced as well. Then, Kuhn-Munkres algorithm is incorporated for user association, which associates a UAV with the ground users via matching to the cluster, and assigns the UAVs to the centroid of the matching cluster for pre-placement, with the aim of speeding up the convergence of the following deep reinforcement learning algorithm. Finally, a multi-agent twin delayed deep deterministic (MATD3) policy gradient is proposed to solve the non-convex sub-problem, which determines the transmit power and designs the fine-tuned trajectory of UAVs. By incorporating low-bias value estimation technique, the reward of the proposed MATD3 algorithm is improved. Simulation results have demonstrated that our proposed approach achieves higher reward as well as converging faster than existing reinforcement algorithms. Besides, the clustering-aided reinforcement learning has lower computational complexity than the benchmark schemes. [ABSTRACT FROM AUTHOR]

Due to the strong penetration ability and high transmission rate of ultra-wideband (UWB) signals, UWB technology plays a very significant role in the field of precise indoor positioning. However, the harsh and volatile indoor environment leads to non-line-of-sight (NLOS) propagation and severe attenuation of UWB signals, which may generate significant ranging and positioning errors. To mitigate NLOS effect and improve positioning accuracy, existing methods use ranging information and channel impulse response (CIR) to identify UWB signal propagation channels. However, these NLOS identification methods often require a priori knowledge and suitable thresholds, and most of them only perform a binary classification between LOS and NLOS in a particular scenario. To address these disadvantages, this paper proposes a novel multi-classification method to classify UWB signal propagation channels based on one-dimensional wavelet packet analysis (ODWPA) and convolutional neural network (CNN). This method first decomposes the CIR of known categories into colored coefficients images using a one-dimensional wavelet packet function, then uses these images to train CNNs with different structures, and finally selects CNN model with the best performance to identify the unknown category of UWB signal propagation channels. The experimental results show that the performance of the proposed method is always the best, regardless of the type of experimental scenario, and the identification accuracy is always higher than 90% and up to 100%. [ABSTRACT FROM AUTHOR]

Automotive radars have faced to various jamming signals with different types and parameters. One counter measure is to identify the fine-grained modulation types of these jamming signals, which can provide supplementary information for intercepting. Most existing signal modulation recognition methods attempt to establish a machine-learning mechanism by training with a large number of annotated samples, which is hardly applicable in real-world electronic reconnaissance scenarios where only a few samples can be intercepted in advance. Few-Shot Learning aims to learn from base classes with many samples and infuse this knowledge to support classes with only a few samples, thus realizing model generalization. In this paper, inspired by the fact that the energy distribution of the signal of interest is always concentrated in time-frequency images, a novel few-shot learning framework based on foreground segmentation is proposed, which benefits from its powerful filtering to remove the noise and clutter from background. The experimental results show that the proposed method can achieve excellent performance for fine-grained signal modulation recognition even with only one support sample and is robust under different signal-to-noise-ratio conditions. [ABSTRACT FROM AUTHOR]

Air ground integrated mobile cloud computing (MCC) provides unmanned aerial vehicles (UAVs) the capability to act as an aerial relay with more flexibility and resilience. In the cloud computing architecture, the data generated by ground users (GUs) can be offloaded to the remote server for fast processing. However, the heterogeneity of mobile tasks makes the data size distributed among GUs unbalanced. Besides, the energy efficiency of UAVs movement should be carefully considered for sustainable flight and obstacle avoidance. In general, such a joint trajectory issue can hardly be formulated as a convex optimization in unpredictable and dynamic environments. This paper proposes a potential game combined multi-agent deep deterministic policy gradient (MADDPG) approach to optimize multiple UAVs' trajectory with the consideration of GUs' offloading delay, energy efficiency as well as obstacle avoidance system. In specific, we first model the issue as a mixed integer non-linear problem (MINP), in which the service assignment between multi-user and multi-UAV is solved by potential game. The convergence to a Nash Equilibrium (NE) can be achieved by distributive service assignment update with infinite iteration. Then, we optimize the trajectory with obstacle avoidance at each UAV by MADDPG approach, which has a great advantage of centralized-training and decentralized-execution to reduce the global synchronized communication overhead. UAVs movement can be optimized in continuity rather than other deep reinforcement learning (DRL) approaches generating discrete simple actions. Experiments demonstrate the proposed game-combined learning algorithm can minimize the offloading delay, enhance UAVs’ energy efficiency and avoid the obstacles at the same time. [ABSTRACT FROM AUTHOR]

In this paper, we first derive the channel capacity of the full-duplex spatial modulation (FD-SM) system and its upper and lower bounds. Furthermore, different from the traditional optimization-driven decision, we use the data-driven prediction method to solve the transmit antenna selection (TAS) problem in the FD-SM system. Specifically, two novel TAS methods based on the support vector machine (SVM) and deep neural network (DNN) are proposed for reducing the effect of residual self-interference (RSI) on the FD-SM system performance. In our design, we propose a novel feature extraction method based on the principal component analysis (PCA) to help the proposed classifiers improve training. Our simulation results show that our data-driven TAS schemes can approach the optimal performance achieved by exhaustive search while significantly reducing complexity. [ABSTRACT FROM AUTHOR]

Nowadays, adaptive filters in complex domain have received increasing attention since they can be applied to a wider scenario than real valued cases. As two typical information theoretic criteria, the minimum complex kernel risk-sensitive loss (MCKRSL) and maximum complex correntropy criterion (MCCC) have shown robustness to non-Gaussian noises in complex domain adaptive filtering. However, since both criteria cannot consider the probability distribution of error, they are not optimal in the presence of some non-Gaussian noises. This paper firstly defines a complex Shannon entropy in terms of the probability distribution of error. Then, a novel adaptive filter is proposed using the minimum complex Shannon entropy (MCSE) criterion. More significantly, the convergence behavior of the MCSE algorithm is discussed, and thus the steady-state excess mean square error (EMSE) is calculated for theoretical analysis. Finally, simulated results on system identification and channel estimation validate the obtained theoretical results and the merits of the proposed MCSE algorithm. [ABSTRACT FROM AUTHOR]

Non-orthogonal multiple access based cooperative relaying system (NOMA-CRS) has been proposed to alleviate the decay in spectral efficiency of the conventional CRS. However, existing NOMA-CRS studies assume perfect successive interference canceler at the relay and mostly investigate sum rate whereas the error performance has not been taken into consideration. In this paper, we analyze error performance of the NOMA-CRS and the closed-form bit error probability (BEP) expression is derived over Nakagami-m fading channels. Then, thanks to the high performance of machine learning (ML) in challenging optimization problems, a joint power sharing-power allocation (PS-PA) scheme is proposed to minimize the bit error rate (BER) of the NOMA-CRS. The proposed ML-assisted optimization has a very low online implementation complexity. Based on provided extensive simulations, theoretical BEP analysis is validated. Besides, the proposed ML-aided PS-PA provides minimum BER (MBER) and outperforms previous PA strategies for the NOMA-CRS notably. [ABSTRACT FROM AUTHOR]

Wi-Fi fingerprint-based indoor localization has recently attracted significant research interest since Wi-Fi devices are widely deployed and practical, and no additional infrastructure is required. However, the Received Signal Strength (RSS) is significantly different on heterogeneous devices, and this difference has a negative impact on localization results. In this paper, we propose a multi-fingerprint and multi-classifier fusion (MFMCF) localization method to improve the localization accuracy and solve the problem of heterogeneous hardware. First, the individual feature set of original RSS fingerprint, signal strength difference (SSD) fingerprint and hyperbolic location fingerprint (HLF) are fused as a composite fingerprint set (CFS), and then the data dimension is reduced by linear discriminant analysis (LDA). Second, three representative machine learning algorithms including K-Nearest Neighbor (KNN), Support Vector Machine (SVM) and Random Forest (RF) are selected and trained to construct an integrated fusion model. Finally, in order to get more accurate predictions, in the online phase, a selective strategy based on entropy is proposed by calculating the entropy of each classifier’s prediction result. Experiments show that MFMCF is an effective scheme to solve the localization problem of heterogeneous devices and improve the localization accuracy. [ABSTRACT FROM AUTHOR]

The multi-hop unmanned aerial vehicle (UAV) network can serve as data relays where ground users (GUs) do not have reliable direct connections to the base station (BS). Existing works mainly focus on simple dual-hop system. In this paper, we investigate the packet routing problem in a multi-hop UAV relay network to minimize the data transmission time and enhance the network throughput. However, the dynamic network topology due to UAV mobility makes the packet routing challenging since the limited communication range of each UAV leads to volatile wireless connection. Moreover, the line-of-sight communication links may cause strong interference among UAVs. Towards this end, we propose a novel multi-agent deep reinforcement learning based algorithm, named as multi-agent QMIX (MAQMIX) to: 1) design proper UAVs’ trajectories to serve the moving GUs while maintaining the network connection; 2) allocate frequency resource properly among UAVs to alleviate the impact of interference; and 3) choose a proper next hop UAV for each data packet to reduce the transmission time and probability of network congestion. The proposed MAQMIX has two novel training mechanisms, i.e., intra-UAV and inter-UAV training mechanisms, which can tackle the large action space issue and coordinate the training among UAVs in the multi-hop UAV relay network. Simulation results demonstrate that the MAQMIX outperforms baseline schemes in terms of the network congestion avoidance, throughput, and transmission time. [ABSTRACT FROM AUTHOR]

The efficiency of link adaptation in wireless communications relies greatly on the accuracy of channel knowledge and transmission mode selection. In this paper, a novel deep learning based link adaptation framework is proposed for the orthogonal frequency-division multiplexing (OFDM) systems with compressed-sensing-assisted index modulation, termed as OFDM-CSIM, communicating over millimeter-wave (mmWave) channels. To achieve link adaptation, a novel multi-layer sparse Bayesian learning (SBL) algorithm is proposed for accurately and instantaneously providing the required channel state information. Meanwhile, a deep neural networks (DNN)-assisted adaptive modulation algorithm is proposed to choose the best possible transmission mode to maximize the achievable throughput. Simulation results show that the proposed multi-layer SBL algorithm enables more accurate channel estimation than the conventional techniques. The DNN-based adaptive modulator is capable of achieving a higher throughput than the learning-assisted solution based on the $k$ nearest neighbor ($k$ -NN) algorithm, and also the classic average signal-to-noise ratio (SNR)-based solutions. Moreover, analysis shows that both the multi-layer SBL algorithm and the DNN-assisted adaptive modulator achieve better performance than their respective conventional counterparts while at a significantly lower computational complexity cost. [ABSTRACT FROM AUTHOR]

In a platoon-based vehicular cyber-physical system (VCPS), the traffic capacity and the fuel efficiency can be significantly improved by maintaining a small inter-vehicle distance (IVD). Meanwhile, the vehicle-to-infrastructure (V2I) communications provided by the roadside unit (RSU) are important for promoting the development of autonomous vehicles and reshaping the driving experience. However, as maintaining a small IVD inside the platoon may result in severe inter-beam interference, there is a tradeoff between the traffic capacity and the communication efficiency. In this paper, we formulate an optimization problem to minimize the IVD (a.k.a spacing) under the V2I quality-of-service (QoS) requirements by jointly controlling the transmit power, the beamwidth, and the IVD in a platoon-based VCPS. The traffic and channel uncertainties significantly complicate the analytical characterization of the impact of IVD, transmit power, and beamwidth on the QoS requirements. To solve the intractable challenging problem and capture the inherent timescale difference between the communication and vehicular systems, we propose a novel data-driven two-timescale reinforcement learning framework to control the beamforming and the spacing of the platoon at two timescales. With elaborately designed state, action, and reward, we develop a soft actor-critic based two-timescale deep reinforcement learning (DRL) algorithm to learn an effective policy for the control-communication co-design problem. Simulation results validate the effectiveness of spacing control and show that the proposed two-timescale DRL algorithm can significantly improve the traffic capacity and reduce the air drag coefficient while satisfying the QoS requirements of V2I communications. [ABSTRACT FROM AUTHOR]

This paper develops a novel Machine Learning (ML)-based strategy to distribute aperiodic Cooperative Awareness Messages (CAMs) through cellular Vehicle-to-Vehicle (V2V) communications. According to it, an ML algorithm is employed by each vehicle to forecast its future CAM generation times; then, the vehicle autonomously selects the radio resources for message broadcasting on the basis of the forecast provided by the algorithm. This action is combined with a wise analysis of the radio resources available for transmission, that identifies subchannels where collisions might occur, to avoid selecting them. Extensive simulations show that the accuracy in the prediction of the CAMs’ temporal pattern is excellent. Exploiting this knowledge in the strategy for radio resource assignment, and carefully identifying idle resources, allows to outperform the legacy LTE-V2X Mode 4 in all respects. [ABSTRACT FROM AUTHOR]

For vehicle-to-network communications, handover (HO) management enables vehicles to maintain the connection with the network while transiting through coverage areas of different base stations (BSs). However, the high mobility of vehicles means shorter connection periods with each BS that leads to frequent HOs, hence raises the necessity for optimal HO decision making for high quality infotainment services. Machine learning is capable of capturing underlying pattern via data driven methods to find optimal solutions to complex problems, and much learning-based HO optimization research has been conducted focusing on specific network setups. However, attention still needs to be paid to the actual deployment aspect and standardized datasets or simulation environments for evaluation. This paper proposes a deep reinforcement learning-based HO algorithm using the input parameters that are configurable in the existing measurement report of cellular networks. The performance of the proposed algorithm is evaluated using the well-known network simulator ns-3 with its official LTE module. A realistic network setup in the city center of Glasgow (U.K.) is configured with vehicle trajectories generated by the routes mobility model using Google Maps Directions API. Evaluation results reveal that the proposed algorithm significantly outperforms the A3 RSRP baseline with an average of 25.72% packet loss reduction per HO, suggesting significant improvement in quality of service of phone call and video streaming, etc. The proposed algorithm also has a small implementation cost compared to some state-of-the-art and should be deployed by a software update to a local BS controller. [ABSTRACT FROM AUTHOR]

Due to the deployment of 5G technology, the number of IoV (Internet of Vehicle) devices connected to the Internet will explosively grow. However, as a kind of edge network device, IoV devices also face some problems including weak password authentication, lack of security protection, and lagged firmware updating, which largely threaten the security and legitimacy of these devices. IoV device identification is important in discovering, monitoring, and protecting these devices. Although existing proactive identification methods based on device fingerprints can be used to identify the large-scale Internet-connected IoV devices, they can not meet the fine-grained requirements for security risk assessment. Due to the increase in the types and brands of IoV devices, the fingerprint granularity will be insufficient. In this paper, we proposed a retransmission-based TCP fingerprints for large-scale fine-grained proactive device identification. Firstly, a probing scheme was designed to obtain TCP retransmission packet and increase the granularity space of traditional TCP fingerprint by selecting the multi-group features of TCP retransmission messages. Then, according to the bagging strategy of ensemble learning, a combined classifier with five predominant machine learning algorithms was generated. The experimental results showed that the identification accuracy and recall of IoV devices respectively reached 96.7% and 95.2%. [ABSTRACT FROM AUTHOR]

Recently, model-free power control approaches have been developed to achieve the near-optimal performance of cell-free (CF) massive multiple-input multiple-output (MIMO) with affordable computational complexity. In particular, deep reinforcement learning (DRL) is one of such promising techniques for realizing effective power control. In this paper, we propose a model-free method adopting the deep deterministic policy gradient algorithm (DDPG) with feedforward neural networks (NNs) to solve the downlink max-min power control problem in CF massive MIMO systems. Our result shows that compared with the conventional convex optimization algorithm, the proposed DDPG method can effectively strike a performance-complexity trade-off obtaining 1,000 times faster implementation speed and approximately the same achievable user rate as the optimal solution produced by conventional numerical convex optimization solvers, thereby offering effective power control implementations for large-scale systems. Finally, we extend the DDPG algorithm to both the max-sum and the max-product power control problems, while achieving better performance than that achieved by the conventional deep learning algorithm. [ABSTRACT FROM AUTHOR]

In an Internet of Vehicle (IoV) system, federated learning (FL) is a new approach to process real-time vehicle data in a distributed way, which can improve the driving experience and service quality. However, due to the high mobility and uncertainty of vehicles, the existing federated learning protocols are difficult to meet the full requirements from an IoV system, such as efficient resource allocation, high precision learning, and fast convergence of learning algorithm. To solve the above problems, in this paper, we propose a semi-synchronous federated learning (Semi-SynFed) protocol, to improve the performance of machine learning at Internet of Vehicles. In Semi-SynFed, we first select appropriate nodes to participate the aggregation by its computing capacity, network capacity and learning value of training samples. Meanwhile, the dynamic waiting time technique is designed to adjust the server waiting time at each round dynamically, which makes federated learning process work much more efficient. Finally, a dynamic aggregation scheme is designed to aggregate model parameters in an asynchronous way. To evaluate the reliability of Semi-SynFed, we establish a simulation of IoVs based on the real world data. In the comparative experiments, the results show that the Semi-SynFed outperforms the existing federated learning protocols in terms of convergence speed and resource consumption. [ABSTRACT FROM AUTHOR]

In order to solve the manual labelling, long-tail effect and driving conservatism of the existing decision-making algorithm. This paper proposed an integrated decision-making framework (IDF) for highway autonomous vehicles. Firstly, states of the highway traffic are extracted by the velocity, time headway (TH) and the probabilistic lane distribution of the surrounding vehicles. With the extracted traffic state, the reinforcement learning (RL) is adopted to learn the optimal state-action pair for specific scenario. Analogously, by mapping millions of traffic scenarios, huge amounts of state-action pairs can be stored in the experience pool. Then the imitation learning (IL) is further employed to memorize the experience pool by deep neural networks. The learning result shows that the accuracy of the decision network can reach 94.17%. Besides, for some imperfect decisions of the network, the rule-based method is taken to rectify by judging the long-term reward. Finally, the IDF is simulated in G25 highway and has promising results, which can always drive the vehicle to the state with high efficiency while ensuring safety. [ABSTRACT FROM AUTHOR]

Federated Edge Learning (FEL) enables a massive number of edge devices (e.g. smart phones) to train machine learning models collaboratively. Due to the inherent unreliability of participating edge devices and the unpredictable network conditions, the final model accuracy is largely determined by the communication time between edge devices and the parameter server (PS). However, there exists very limited work to quantify the influence of the communication time in FEL and show how to minimize its negative impacts from a theoretic perspective. In this paper, we are among the first to develop a formal model of the communication time in FEL and its influence on the final model accuracy. In our work, the set of edge devices involved in each global iteration is defined as the ECP (Engaged Client Pool). We model the communication time cost as a function with respect to the response time distribution of individual devices and the ECP size. By incorporating communication time cost into the convergence rate analysis, we propose the ECPA and H-ECPA algorithms to automatically adjust the size of the ECP so as to maximize the model accuracy in both homogeneous and heterogeneous networks. We also analyze how the tail shape of response time affects the convergence rate, and prove that the heavy tail shape can significantly lower the model accuracy. Finally, we conduct extensive experiments with real datasets, and the results confirm the correctness of our analysis and demonstrate the superiority of our proposed algorithms. [ABSTRACT FROM AUTHOR]

In this paper, collaborative task offloading in edge computing is studied, where computation requesters can offload tasks to not only the edge server, but also nearby smartphone users. By considering the fact that smartphone users may not always be willing to provide such computation service because of the consumption of their own energy and resources, a truthful mechanism is designed to provide incentive to smartphone users. The design aims to maximize the net revenue of the service provider and addresses more practical, but more complicated, scenarios of unknown a prior distribution information on smartphone users’ private information. To tackle this high computational complexity, which makes the traditional mechanism design methods infeasible, a new approach, called truthful deep mechanism, is proposed by leveraging a multi-task machine learning model, where inherently inter-connected collaborator selection and pricing policy determination are decided by designing two deep neural networks. The numerical results show that the proposed deep truthful mechanism can ensure a convergence to a stable state and can satisfy all required economical properties, including individual rationality, incentive compatibility, and budget balance. [ABSTRACT FROM AUTHOR]

In an ultra-dense network (UDN), how to associate the mobile user equipments (UEs) with the appropriate low power nodes (LPNs) is a very essential and challenging problem, especially when the UEs are moving and may suffer from frequent handovers. In this paper, the UE association problem is investigated from a long-term perspective, where the UE's mobility pattern, i.e., the moving velocity and direction, is taken into consideration. To predict the UE's positions based on their previous activity data, a practical scheme, i.e., the classification and batch online learning method (CBOM), is proposed for achieving the UE's velocity and direction transition matrices. Then the UE association problem with the objective of maximizing the UEs’ expected achievable rate while minimizing the number of handovers is formulated. Since the proposed problem is a NP-hard mixed integer nonlinear programming problem, we reformulate it into a matching game, and propose a mobility-based long-term matching game algorithm to find the near-optimal solutions. We prove that our proposed algorithm is convergent and has low computational complexity. Simulation results show our two proposed schemes outperform the existing schemes in terms of the achieved data rate, the number of handovers, and the overall system utility. [ABSTRACT FROM AUTHOR]

Machine learning (ML) is playing an increasingly important role in processing large amounts of data generated by communication networks, since it can efficiently solve the problems of non-linearity and unstructured data. Recently, ML has been widely used in the processing of wireless channel data, as the noisy channel in real propagation environment is usually non-linear and unstructured. In this paper, a denoising method based on ML is presented. Two ML algorithms are used to classify and remove noise in channel impulse responses. Then, the results of the traditional noise threshold denoising are compared with ML denoising, and it is found that the denoising classifier using the bidirectional recurrent neural network has the better denoising performance. Finally, some channel parameters such as RMS delay spread are estimated based on measured channel data using different denoising methods. The results are evaluated and compared to explore the impact of denoising method on the extracted channel parameters. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicles (UAVs) are emerging as important users of next-generation cellular networks. By operating in the sky, UAV users experience very different radio conditions than terrestrial users, due to factors such as strong Line-of-Sight (LoS) channels (and interference) and Base Station (BS) antenna misalignment. As a consequence, the UAVs may experience significant degradation to their received quality of service, particularly when they are moving and are subject to frequent handovers. The solution is to allow the UAV to be aware of its surrounding environment, and intelligently connect into the cellular network taking advantage of this awareness. In this paper we present REgression and deep Q-learning for Intelligent UAV cellular user to Base station Association (REQIBA), a solution that allows a UAV flying over an urban area to intelligently connect to underlying BSs, using information about the received signal powers, the BS locations, and the surrounding building topology. We demonstrate how REQIBA can as much as double the total UAV throughput, when compared to heuristic association schemes similar to those commonly used by terrestrial users. We also evaluate how environmental factors such as UAV height, building density, and throughput loss due to handovers impact the performance of our solution. [ABSTRACT FROM AUTHOR]

In the era of ubiquitous computing, offloading certain computing tasks to the mobile ad hoc cloud (MAHC) could help mobile devices reduce execution time. However, if multiple resource demanders (RDs) offload tasks to the MAHC without a proper scheduling policy, it may cause unbalanced load distribution among resource providers (RPs), which will affect the overall quality of service (QoS). To this end, in this paper, we propose a multi-agent independent learning approach aiming to optimize the QoS of MAHC. Firstly, for the distributed MAHC, we formulate the QoS optimization model as a non-cooperative game, where each RD competes for maximizing its own utility. Secondly, based on the potential game theory, we prove the existence of Nash equilibrium. A multi-agent independent learning algorithm is then proposed to obtain the equilibrium points, and the convergence of this algorithm is analyzed. Simulation results confirm that the proposed approach helps balance the load distribution and enhances the QoS of MAHC. [ABSTRACT FROM AUTHOR]

The development of Autonomous Vehicles (AVs) envisions the promising technology of future Intelligent Transportation Systems (ITS). However, the complex road structures and increased vehicles cause traffic congestion and road safety, which eventually leads to horrible accidents. Cooperative driving of AVs, a groundbreaking initiative of vehicle platooning, epitomizes the next wave in vehicular technology through minimizing accident risks, transport times, costs, energy, and fuel consumption. However, the traditional machine learning-based platooning approaches fail to regulate the policy with the dynamic feature of AVs. This paper proposes a hybrid Deep Reinforcement learning and Genetic algorithm for Smart-Platooning (DRG-SP) the AVs. The leverage of the deep reinforcement learning mechanism addresses the computational complexity and accommodates the high dynamic platoon environments. Adopting the Genetic Algorithm in Deep Reinforcement learning overcomes the slow convergence problem and offers long-term performance. The simulation results reveal that the Smart-Platooning effectively forms and maintains the platoons by minimizing traffic congestion and fuel consumption. [ABSTRACT FROM AUTHOR]

Federated Learning (FL) as a promising technique is able to address the privacy issues in machine learning. However, due to the broadcast nature of wireless channel, one of the key challenges of FL is its vulnerability to wireless security threats. Thus, in this paper, we consider the model update security in FL. In particular, we propose to adopt a covert communication technique with which a friendly jammer transmits jamming signals to prevent a warden from detecting local model update transmissions of mobile devices in FL. The use of jamming signals reduces the transmission rate of the devices. Thus, we formulate an optimization problem that jointly determines the jamming power, local model transmission power, and local training accuracy to minimize the FL latency, given a security performance requirement. The problem is non-convex, and we propose an alternating descent algorithm to solve it. Extensive simulations are conducted and the results demonstrate the effectiveness and network performance improvement of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Predicting the future trajectories of surrounding agents has become an crucial problem to be solved for the safety of autonomous vehicles. Recent studies based on Long Short Term Memory (LSTM) networks have shown powerful abilities to model social interactions. However, many of these approaches focus on spatial interactions of the neighborhood agents but ignore temporal interactions that accompany spatial interactions. In this paper, we propose a Hierarchical Spatio-Temporal Attention architecture (HSTA), which activates the utilization of spatial interactions with different weights, and jointly considers the temporal interactions across time steps of all agents. More specially, the graph attention mechanism (GAT) is presented to capture spatial interactions, the multi-head attention mechanism (MHA) is conducted to encode temporal correlations of interactions and a state gated fusion (SGF) layer is used to integrate spatial and temporal interactions. We evaluate our proposed method against baselines on both pedestrian and vehicle datasets. The results show that our model is effective and achieves state-of-the-art achievements. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel unified framework to protect multi-function wireless systems from jamming attacks. Examples of such multi-function system include joint radar and communication (JRC) systems and simultaneous wireless information and power transfer (SWIPT) systems. By abstracting the system functionalities as a joint optimization problem of multiple queues, we achieve effective resistance against jammers for the multi-functions simultaneously. We incorporate different anti-jamming techniques into one framework. Deception mechanism is adopted to lure the jammer to attack and make its actions more predictable, and ambient backscatter technology is used to leverage the jamming signals. Since conventional Markov decision process (MDP) has only one decision epoch at every time slot, it cannot be used to model the deception strategy which needs two decision epochs to leverage the jamming signals. We therefore formulate the problem using an advanced two-step MDP. After that, a deep reinforcement learning algorithm with a prioritized double deep Q-Learning architecture is proposed to learn optimal strategies in different system states. We show that by jointly considering the multi-functions of the system with potential jamming attacks during design phase, significant improvement can be achieved for both of the system functionalities. [ABSTRACT FROM AUTHOR]

Radar radio source (RRS) recognition plays an important role in the fields of military electronic support systems (ESM) and civilian autonomous driving. The rapid development of machine learning technology, especially deep learning, has effectively and efficiently improved RRS intelligent recognition performances when operating in the increasingly complex electromagnetic environment. However, the data sampling limitation and computation cost are still severe challenges in real RRS recognition scenarios. In this paper, we propose a novel network based on meta-transfer learning, called RRSARNet, to achieve effective adaptive RRS recognition in the context of low signal-to-noise ratio (SNR). First, by using the short-time Fourier transform, a six-type small samples RRS simulation dataset with different SNR levels is constructed. Then, a novel RRSARNet, based on metric learning, is proposed, which consists of a four-layer embedding module and a four-layer relational module. Finally, the RRS dataset is divided into training, supporting and testing subsets, which are used to train and test the RRSARNet in a meta-transfer learning method. Experiments on the RRS dataset show that the proposed RRSARNet can achieve an overall accuracy (OA) above 96% and 99% when the SNR is above −15 dB and −10 dB, respectively. Even when the SNR is -30 dB, OA can reach more than 70%. For 5-way 1-shot and 5-way 5-shot experiments, the inference time of an image is about 0.043 and 0.140 milliseconds, respectively. Besides, experiments on the RRS simulation dataset and the two benchmark datasets, the RRSARNet performs better or more competitive than many existing state-of-the-art technologies in terms of recognition accuracy. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the detection problem for a massive machine-type communication (mMTC) system that has correlated user activities. Two deep learning assisted algorithms are proposed to exploit the user activity correlation to facilitate channel estimation and user identification. Due to the dependency among user activities, conventional element-wise minimum mean square error (MMSE) denoiser used in the orthogonal approximate message passing (OAMP) algorithm cannot achieve satisfying performance during the two-step iterative process. Therefore, we propose a deep learning modified OAMP (DL-mOAMP) algorithm, which iteratively modifies the user activity ratio via exploiting the user activity correlation in the MMSE denoiser based on the estimated sequence during each OAMP iteration. Moreover, given a specific false alarm probability, a constant threshold employed in the conventional user identification is not optimal in the presence of user activity correlation. Thus, we propose a neural network framework that is dedicated to the user identification (DL-mOAMP-UI algorithm), which minimizes the missed detection probability under a pre-determined false alarm probability. Numerical results show that the proposed DL-mOAMP algorithm provides a substantial mean squared error performance gain compared to the conventional OAMP algorithm and the DL-mOAMP-UI algorithm can further improve the user identification accuracy of an mMTC system. [ABSTRACT FROM AUTHOR]

Vehicular Visible Light Communication (VVLC) is preferred as a vehicle to everything (V2X) communications scheme due to its highly secure, low complexity and radio frequency (RF) interference free characteristics, exploiting the line of sight (LoS) propagation of visible light and usage of already existing vehicle light emitting diodes (LEDs). Current VVLC channel models based on deterministic and stochastic methods provide limited accuracy for path loss prediction since deterministic methods heavily depend on site-specific geometry and stochastic models average out the model parameters without considering environmental effects. Moreover, there exists no wireless channel model that can be adopted for channel frequency response (CFR) prediction. In this paper, we propose a novel framework for the machine learning (ML) based channel modeling of the VVLC with the goal of improving the model accuracy for path loss and building the CFR model through the consideration of multiple input variables related to vehicle mobility and environmental effects. The proposed framework incorporates multiple measurable input variables, e.g., distance, ambient light, receiver inclination angle, and optical turbulence, with the exploitation of feed forward neural network based multilayer perceptron neural network (MLP-NN), radial basis function neural network (RBF-NN) and decision tree based Random Forest learning methods. The framework also includes data pre-processing step, with synthetic minority over sampling technique (SMOTE) data balancing, and hyper-parameter tuning based on iterative grid search, to further improve the accuracy. The accuracy of the proposed ML based channel modeling is demonstrated on the real world VVLC vehicle-to-vehicle (V2V) communication channel data. The proposed MLP-NN, RBF-NN and Random Forest based channel models generate highly accurate path loss predictions with 3.53 dB, 3.81 dB, 3.95 dB root mean square error (RMSE), whereas the best performing stochastic model based on two-term exponential fitting provides prediction accuracy of 7 dB RMSE. Moreover, MLP-NN and RBF-NN models are demonstrated to predict VVLC CFR with 3.78 dB and 3.60 dB RMSE, respectively. [ABSTRACT FROM AUTHOR]

Recent workat the U.S. Army CCDC Ground Vehicle Systems Center has shown that machine learning classifiers can quickly construct high-fidelity mobility maps. Training these classifiers, on the other hand, is still a challenge, since each data instance is labeled by performing a computationally intensive, physics-based simulation. In this paper we introduce an active learning framework, based on the query-by-bagging algorithm, that substantially reduces the number of simulations needed to train a classifier. Experimental results suggest that our sampling algorithm can train a neural network, with higher accuracy, using less than half the number of simulations when compared to random sampling. [ABSTRACT FROM AUTHOR]

Wireless Virtual Reality (VR) users are able to enjoy immersive experience from anywhere at anytime. However, providing full spherical VR video with high quality under limited VR interaction latency is challenging. If the viewpoint of the VR user can be predicted in advance, only the required viewpoint is needed to be rendered and delivered, which can reduce the VR interaction latency. Therefore, in this paper, we use offline and online learning algorithms to predict viewpoint of the VR user using real VR dataset. For the offline learning algorithm, the trained learning model is directly used to predict the viewpoint of VR users in continuous time slots. While for the online learning algorithm, based on the VR user's actual viewpoint delivered through uplink transmission, we compare it with the predicted viewpoint and update the parameters and input viewpoints of the online learning algorithm to further improve the prediction accuracy. To guarantee the reliability of the uplink transmission, we integrate the Proactive retransmission scheme into our proposed online learning algorithm. Simulation results show that our proposed online learning algorithm for uplink wireless VR network with the proactive retransmission scheme only exhibits about 5 $\%$ prediction error. [ABSTRACT FROM AUTHOR]

We investigate the resource blocks (RBs) allocation problem in the Single-Carrier Frequency Division Multiple Access (SC-FDMA) based heterogeneous uplink networks from a game-theoretical viewpoint. First, a general network model that considers the co-tier, cross-tier, and inter-cell interference caused by the co-channel deployment is presented. Then, we design an effective throughput-optimizing utility function and prove it an exact potential game. The $\gamma$ -logit is a learning algorithm which commonly used to achieve the optimal solution in potential game and is very sensitive to the changes of the network structures, making it hard in practice. To obtain the optimal solution under the different network structures stably, we propose a Self-adaptive logit algorithm, which can achieve the optimal solution automatically and is a variant of the well-established $\gamma$ -logit learning algorithm. Additionally, to speed up the convergence, we propose the corresponding suboptimal algorithm based on the better response principle. Simulation results show that the proposed Self-adaptive logit algorithm is throughput optimal and network structure adaptive, outperforming the existing Binary-logit, Max-logit, and Round Robin algorithm. Moreover, the proposed suboptimal algorithm is near-optimal throughput achieved and converges efficiently. In addition, we also study the impact of the initial point selection on our proposed two alogithms. [ABSTRACT FROM AUTHOR]

The accuracy of machine learning depends largely on the quantity and quality of the training data. However, it is generally difficult to prepare a large number of high-quality data. To generate diverse image data, image generation techniques using deep learning, such as a generative adversarial network, can be used. However, because these methods require a large number of training data and a significant calculation time, they are unsuitable for generating training data for machine learning. In this article, we propose an image data augmentation model based on the statistical properties of the training data. With the proposed method, each image is divided into sub-regions based on the correlation calculated using a set of images. The image of each sub-region is modeled through a Gaussian mixture, and data augmentation is conducted by generating images based on this model. The proposed method does not require a large number of training data and can generate data within a relatively short calculation time. The proposed method is applied to the task of road environment recognition. The experiment results showed that the accuracy was improved through image augmentation using the proposed model. [ABSTRACT FROM AUTHOR]

The superior spectral efficiency (SE) and user fairness feature of non-orthogonal multiple access (NOMA) systems are achieved by exploiting user clustering (UC) more efficiently. However, a random UC certainly results in a suboptimal solution while an exhaustive search method comes at the cost of high complexity, especially for systems of medium-to-large size. To address this problem, we develop two efficient unsupervised machine learning based UC algorithms, namely k-means++ and improved k-means++, to effectively cluster users into disjoint clusters in cell-free massive multiple-input multiple-output (CFmMIMO) system. Adopting full-pilot zero-forcing at access points (APs) to comprehensively assess the system performance, we formulate the sum SE optimization problem taking into account power constraints at APs, necessary conditions for implementing successive interference cancellation, and required SE constraints at user equipments. The formulated optimization problem is highly non-convex, and thus, it is difficult to obtain the global optimal solution. Therefore, we develop a simple yet efficient iterative algorithm for its solution. In addition, the performance of collocated massive MIMO-NOMA (COmMIMO-NOMA) system is also characterized. Numerical results are provided to show the superior performance of the proposed UC algorithms compared to baseline schemes. The effectiveness of applying NOMA in CFmMIMO and COmMIMO systems is also validated. [ABSTRACT FROM AUTHOR]

With the gradual popularization of self-driving, it is becoming increasingly important for vehicles to smartly make the right driving decisions and autonomously obey traffic rules by correctly recognizing traffic signs. However, for machine learning-based traffic sign recognition on the Internet of Vehicles (IoV), a large amount of traffic sign data from distributed vehicles is needed to be gathered in a centralized server for model training, which brings serious privacy leakage risk because of traffic sign data containing lots of location privacy information. To address this issue, we first exploit privacy-preserving federated learning to perform collaborative training for accurate recognition models without sharing raw traffic sign data. Nevertheless, due to the limited computing and energy resources of most devices, it is hard for vehicles to continuously undertake complex artificial intelligence tasks. Therefore, we introduce powerful Spike Neural Networks (SNNs) into traffic sign recognition for energy-efficient and fast model training, which is the next generation of neural networks and is practical and well-fitted to IoV scenarios. Furthermore, we design a novel encoding scheme for SNNs based on neuron receptive fields to extract information from the pixel and spatial dimensions of traffic signs to achieve high-accuracy training. Numerical results indicate that the proposed federated SNN outperforms traditional federated convolutional neural networks in terms of accuracy, noise immunity, and energy efficiency as well. [ABSTRACT FROM AUTHOR]

This work investigates a random access (RA) game for a time-slotted RA system, where $N$ players choose a set of slots of a frame and each frame consists of $M$ multiple time slots. We obtain the pure strategy Nash equilibria (PNEs) of this RA game, where slots are fully utilized as in the centralized scheduling. As an algorithm to realize a PNE (Pure strategy Nash Equilibrium), we propose an Exponential-weight algorithm for Exploration and Exploitation (EXP3)-based multi-agent (MA) learning algorithm, which has the computational complexity of $O(N N_{\max }^{2} T)$. EXP3 is a bandit algorithm designed to find an optimal strategy in a multi-armed bandit (MAB) problem that users do not know the expected payoff of each strategy. Our simulation results show that the proposed algorithm can achieve PNEs. Moreover, it can adapt to time-varying environments, where the number of players varies over time. [ABSTRACT FROM AUTHOR]

We consider a mission-driven multiple unmanned aerial vehicles (multi-UAVs) network with millimeter-wave (mmWave) transmissions, where a leader UAV (LUAV) communicates with a large number of follower UAVs (FUAVs) simultaneously via a uniform planar array with only a limited number of radio frequency chains. Since only a few orthogonal beams are available and mission-driven UAV networks are autonomous and delay-sensitive, non-orthogonal multiple access (NOMA) over these beams is considered for agility and efficiency. In particular, aiming to address these challenges of highly dynamic mobility, we propose a machine learning framework to enable agile analog beam management for mmWave-NOMA transmissions. The proposed beam management aims to achieve efficient beam tracking and NOMA-grouping-aware analog beamforming optimization to facilitate mmWave-NOMA transmissions by judiciously utilizing angular domain information (ADI). More specifically, a Gaussian process machine learning-based ADI prediction scheme is proposed to track the angular dynamics of FUAVs, which facilitates fast beam-tracking for mmWave-NOMA transmissions. Moreover, by exploiting the predicted ADI, an unsupervised-learning-based FUAV grouping scheme is proposed to facilitate mmWave-NOMA transmissions with high radio-frequency chain efficiency, while a deep learning-based NOMA-grouping-aware fast transmit beamforming optimization scheme is proposed to improve the coverage of mmWave-NOMA transmissions in highly dynamic multi-UAVs networks. Simulation results validate the performance advantages of our proposed beam management scheme against state-of-the-art schemes. [ABSTRACT FROM AUTHOR]

We investigate optimal band/channel selection in hybrid radio frequency and visible light communication (RF/VLC) networks. Particularly, we first develop a robust hybrid RF/VLC based system model for the optimal band/channel selection. We then formulate it as an online stochastic budget-constrained multi-armed bandit (MAB) problem. Two online learning algorithms based on different optimal policies are proposed to choose the appropriate band, i.e., energy-aware band selection with upper confidence bound (EABS-UCB) and energy-aware band selection with Thompson sampling (EABS-TS). The cost/budget is the battery consumption of the transmitting device according to the selected band. Through extensive simulations, it is confirmed that the proposed EABS-TS emerges as the superior technique compared with the random, brute-force, and EABS-UCB band selection schemes, in terms of energy efficiency, average throughput, and convergence performance. [ABSTRACT FROM AUTHOR]

Machine learning has provided great potential in intelligent signal processing, e.g., channel estimation and signal detection. But still, it is difficult to deploy deep neural network (DNN) on low-cost and low-power edge devices, e.g., in both training and inference phases. For one thing, the training of massive network parameters incurs a huge computational complexity and rarely becomes feasible; and for another, even a trained DNN involves still high computations and demands considerable storage size. In this work, we present a tiny machine learning (Tiny-ML) approach for hardware-efficient channel estimation and signal detection. The key innovation of our Tiny-ML is that we replace each large dense layer of DNN with three small cascading sub-layers; and therefore, the computation/storage of a large matrix is replaced with that of small ones. To enable the lightweight training of our Tiny-ML, a novel rank-restricted back-propagation algorithm is further designed. Numerical simulations demonstrate the advantages of our new method. Without sacrificing the estimation and detection accuracy, our Tiny-ML attains an acceleration of $\rm {\mathbf {2.5\sim\!3\times }}$ in model training and $\rm {\mathbf {\sim\!4.5\times }}$ in model inference, as well as a substantial storage reduction of $\rm {\mathbf {\sim\!4.5\times }}$ , when compared to classical fully-connected (FC) DNN. As such, our method paves the way for deploying tiny AI onto low-cost and low-power hardware devices, thereby exploiting the full potential of intelligent signal processing. [ABSTRACT FROM AUTHOR]

Lossless turbo source coding with decremental/incremental redundancy is a variable-length source coding scheme which employs turbo codes for data compression. Although the scheme offers low compression rates and lends itself to joint source-channel coding, it suffers from a large delay in the encoding phase. The delay is imposed by several tentative encoding-decoding procedures performed at the encoder to search for the minimum compression length. In this work, we apply machine learning to provide a highly accurate estimate of the proper compression length. The encoder starts its search from this estimated length, thus the delay of turbo source coding will decrease considerably. The preliminary results show a four-fold reduction in the encoding delay at the expense of a negligible increase in the compression rate. [ABSTRACT FROM AUTHOR]

Cache-enabled UAVs are widely used as edge servers to provide on-demand content services for ground users. Most of prior works deploy UAVs based on user locations and explore the benefits of UAV caching under static content library. Motivated by this observation, we further consider heterogeneous user activity level and dynamic content library. We formulate a joint optimization problem of UAV deployment and content placement to minimize the average request delay, which is proved to be NP-hard. To tackle this problem efficiently, we decompose this optimization problem into two sub-problems, UAV deployment problem and content placement problem. Specifically, we first jointly consider user activity level and user locations for UAV deployment using weighted K-means method. After the UAV deployment, we propose a Q-learning algorithm to learn the content placement directly, rather than estimating the content popularity first, which is not effective when content library is dynamically changing. The simulation results show that the proposed algorithm outperforms the benchmark algorithms when dynamic content library and heterogeneous user activity level are considered. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicles (UAVs) have gained momentum as one of the potential solutions in 5 G networks. Indeed, using UAVs as Aerial Base Stations (ABS) to assist the traditional cellular infrastructure and/or extend its coverage represents a high-potential flexible and cost-effective approach to provide on-demand communications in these new generations of networks. Yet, their effective deployment brings out many challenges, including their optimal 3D placement, coverage optimization, backhaul constraints, etc. Hence, we tackle these challenges by proposing a new framework for 3D positioning of an ABS swarm in order to extend the coverage of ground base stations (GBS). Unlike existing work that ignore ABS’s limited backhaul capacity and how it restraints the number of users that can be served, we consider a multi-hop backhaul scheme that allows ABSs to remain connected to the core network through the GBSs directly, or other deployed ABSs. Under this setup, we aim to maximize the number of served UEs, by optimizing the ABS’s placement, jointly with their association with UEs and backhauling base stations. Besides, our framework, named ASF for Adaptive Social Spider Optimization based framework, uses machine learning techniques to predict the users’ mobility and enable ABSs to adjust their position according to their spatial distribution. Simulations show that ASF framework significantly improves the cellular network’s coverage and provides access to 92% of mobile users, as compared to other benchmark schemes that only serve 79% and 58% of users. [ABSTRACT FROM AUTHOR]

A key task in Internet of Things (IoTs) networks is determining the active time of a set of devices or set covers to monitor static targets. This task, however, requires the battery level of devices. However, in practice, it is impractical to obtain an accurate battery level or channel state information from all devices, especially in large-scale networks. To this end, we present a number of approaches to construct set covers. We first propose a Two-Phase Algorithm (TPA) that requires devices to first determine their probability of being active in each time slot. This probability is then used by a Hybrid Access Point (HAP) to construct set covers. We then introduce learning approaches based on Gibbs and Thompson sampling. The Gibbs sampling based algorithm, aka GB, allows a sink/gateway to learn the best set cover to use over time. Similarly, our Thompson sampling solutions, namely TS-Random and TS-CB, construct set covers iteratively based on the probability that a device successfully monitors static targets. The numerical results show that GB performs better than TS-CB initially but has similar performance to TS-CB in the long term. [ABSTRACT FROM AUTHOR]

Proliferation of 5G devices and services has driven the demand for wide-scale enhancements ranging from data rate, reliability, and compatibility to sustain the ever increasing growth of the telecommunication industry. In this regard, this work investigates how machine learning technology can improve the performance of 5G cell and beam index search in practice. The cell search is an essential function for a User Equipment (UE) to be initially associated with a base station, and is also important to further maintain the wireless connection. Unlike the former generation cellular systems, the 5G UE faces with an additional challenge to detect suitable beams as well as the cell identities in the cell search procedures. Herein, we propose and implement new channel-learning schemes to enhance the performance of 5G beam index detection. The salient point lies in the use of machine learning models and softwarization for practical implementations in a system level. We develop the proposed channel-learning scheme including algorithmic procedures and corroborative system structure for efficient beam index detection. We also implement a real-time operating 5G testbed based on the off-the-shelf Software Defined Radio (SDR) platform and conduct intensive experiments with commercial 5G base stations. The experimental results indicate that the proposed channel-learning schemes outperform the conventional correlation-based scheme in real 5G channel environments. [ABSTRACT FROM AUTHOR]

Link adaptation (LA) is an adaptive transmission technique that determines the modulation and coding scheme (MCS) based on channel-state information. In LA, an accurate estimation of the link performance is required to optimally determine the MCS level. In this correspondence, a high-accuracy machine-learning (ML)-aided link-level performance-prediction method for coded multiple-input–multiple-output (MIMO) systems is proposed. The basic concept of this scheme is to apply the ML model to train the relation between the inputs, such as the channel matrix and signal-to-noise ratio, and the output of the block-error rate (BLER). Specifically, we predict the index of the quantized BLER value using a random forest classifier. The simulation results show that the proposed scheme is able to accurately predict the link performance of MIMO systems and outperforms the conventional link performance-prediction schemes. [ABSTRACT FROM AUTHOR]

Aggressive driving is one of the main causes of fatal crashes. Correctly identifying aggressive driving events still represents a challenge in the literature. Furthermore, datasets available for testing the proposed approaches have some limitations since they generally (a) include only a few types of events, (b) contain data collected with only one device, and (c) are generated in drives that did not fully consider the variety of road characteristics and/or driving conditions. The main objective of this work is to compare the performance of several state-of-the-art algorithms for aggressive driving event detection (belonging to anomaly detection-, threshold- and machine learning-based categories) on multiple datasets containing sensors data collected with different devices (black-boxes and smartphones), on different vehicles and in different locations. A secondary objective is to verify whether smartphones could replace black-boxes in aggressive/non-aggressive classification tasks. To this aim, we propose the AD $^2$ (Aggressive Driving Detection) dataset, which contains (i) data collected using multiple devices to evaluate their influence on the algorithm performance, (ii) geographical data useful to analyze the context in which the events occurred, (iii) events recorded in different situations, and (iv) events generated by traveling the same path with aggressive and non-aggressive driving styles, in order to possibly separate the effects of driving style from those of road characteristics. Our experimental results highlighted the superiority of machine learning-based approaches and underlined the ability of smartphones to ensure a level of performance similar to that of black-boxes. [ABSTRACT FROM AUTHOR]

Vehicular fog computing (VFC) pushes the cloud computing capability to the distributed fog nodes at the edge of the Internet, enabling compute-intensive and latency-sensitive computing services for vehicles through task offloading. However, a heterogeneous mobility environment introduces uncertainties in terms of resource supply and demand, which are inevitable bottlenecks for the optimal offloading decision. Also, these uncertainties bring extra challenges to task offloading under the oblivious adversary attack and data privacy risks. In this article, we develop a new adversarial online learning algorithm with bandit feedback based on the adversarial multi-armed bandit theory, to enable scalable and low-complexity offloading decision making. Specifically, we focus on optimizing fog node selection with the aim of minimizing the offloading service costs in terms of delay and energy. The key is to implicitly tune the exploration bonus in the selection process and the assessment rules of the designed algorithm, taking into account volatile resource supply and demand. We theoretically prove that the input-size dependent selection rule allows to choose a suitable fog node without exploring the sub-optimal actions, and also an appropriate score patching rule allows to quickly adapt to evolving circumstances, which reduce variance and bias simultaneously, thereby achieving a better exploitation-exploration balance. Simulation results verify the effectiveness and robustness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

This study considers the simultaneous optimization problem of the transmit beamforming at the access point and the reflecting beamforming at the intelligent reflecting surface (IRS) in an IRS-assisted multiuser downlink system. This joint optimization problem is nonconvex and challenging due to the intricate coupling of transmit and reflecting beamforming variables and the highly nonconvex constant modulus constraints. All the known solutions apply the alternating optimization framework to decouple the joint optimization problem into two problems. Then, these problems are optimized individually with different optimization methods in an alternating manner. However, such an alternative procedure may cause performance degradation. On the basis of the cross-entropy (CE) framework, which was developed initially for machine learning applications, we propose a machine learning-inspired algorithmic framework for simultaneously optimizing transmit and reflecting beamforming in an IRS-assisted wireless system. Extensive simulation results reveal that the proposed CE-based algorithms significantly perform better than the state-of-the-art test algorithms for various system configurations. [ABSTRACT FROM AUTHOR]

The sensitivity to blockages is a key challenge for millimeter wave and terahertz networks in 5G and beyond. Since these networks mainly rely on line-of-sight (LOS) links, sudden link blockages highly threaten the reliability of the networks. Further, when the LOS link is blocked, the network typically needs to hand off the user to another LOS basestation, which may incur critical time latency, especially if a search over a large codebook of narrow beams is needed. A promising way to tackle the reliability and latency challenges lies in enabling proaction in wireless networks. Proaction allows the network to anticipate future blockages, especially dynamic blockages, and initiate user hand-off beforehand. This article presents a complete machine learning framework for enabling proaction in wireless networks relying on visual data captured, for example, by red-green-blue (RGB) cameras deployed at the base stations. In particular, the article proposes a vision-aided wireless communication solution that utilizes bimodal machine learning to perform proactive blockage prediction and user hand-off. This is mainly achieved via a deep learning algorithm that learns from visual and wireless data how to predict incoming blockages. The predictions of this algorithm are used by the wireless network to proactively initiate hand-off decisions and avoid any unnecessary latency. The algorithm is developed on a vision-wireless dataset generated using the ViWi data-generation framework. Experimental results on two basestations with different cameras indicate that the algorithm is capable of accurately detecting incoming blockages more than ${\sim} 90\%$ of the time. Such blockage prediction ability is directly reflected in the accuracy of proactive hand-off, which also approaches 87%. This highlights a promising direction for enabling high reliability and low latency in future wireless networks. [ABSTRACT FROM AUTHOR]