Logo

Publikacije (259)

Nazad
Chao-Yang Chen, Dingrong Tan, Pei Li, Juan Chen, Guan Gui, B. Adebisi, H. Gačanin, Fumiyuki Adachi

This article focuses on the parameter estimation problem in wireless sensor networks (WSNs) under adversarial attacks, considering the complexities of sensing and communication in challenging environments. In order to mitigate the impact of these attacks on the network, we propose a novel AP-DLMS algorithm with adaptive threshold attack detection and malicious punishment mechanism. The adaptive threshold is constructed using the observation matrix and network topology to detect the location of malicious attacks, while the standard reference estimation is designed to obtain the estimated deviation of each node. To mitigate the impact of data tampering on network performance, we introduce the honesty factor and punishment factor to combine the weights of normal nodes and malicious nodes respectively. Additionally, we propose a new probabilistic random attack model. Simulations are conducted to investigate the influence of key parameters in the adaptive threshold on the performance of the proposed AP-DLMS algorithm, and the mean square performance of the algorithm is analyzed under various attack models. The results demonstrate that the proposed algorithm exhibits strong robustness in adversarial networks, and the proposed attack model effectively demonstrates the impact of attacks.

Yuexia Zhang, Ying Zhou, Siyu Zhang, Guan Gui, B. Adebisi, H. Gačanin, Hikmet Sari

Limited edge server resources and uneven distribution of traffic density in vehicular networks result in problems such as unbalanced network load and high task processing latency. To address these issues, we proposed an efficient caching and offloading resource allocation (ECORA) strategy in vehicular social networks. First, to improve the utilization of vehicular idle resources, a collaborative computation and storage resource allocation mechanism was designed using mobile social similarity. Next, with the optimization objective of minimizing the average task processing delay, we studied the combined resource allocation optimization problem and decoupled it into two sub-problems. For the service caching subproblem, we designed a stable matching algorithm by mobile social connections to dynamically update the cache resource allocation scheme for improving the task unloading efficiency. For the task offloading subproblem, a discrete cuckoo search algorithm based on differential evolution was designed to adaptively select the best task offloading scheme, which minimized the average task processing delay. Simulation results revealed that the ECORA strategy outperformed the resource allocation strategy based on particle swarm optimization and genetic algorithm, and reduced the average task processing delay by at least 7.59%. Meanwhile, the ECORA strategy can achieve superior network load balancing.

Haitao Zhao, Zhi-Hua Kong, Shengnan Shi, Hao Huang, Yiyang Ni, Guan Gui, H. Gačanin, H. Sari et al.

This article proposes a new framework of aerial reconfigurable intelligent surface (ARIS) enhancing the nonorthogonal multiple access (NOMA) system. The base station (BS) transmits superimposed signals to multiple users with different channel gains through ARIS which can flexibly change channel conditions and perform intelligent NOMA operations. It ensures that our system can perform well in providing services to multiple users simultaneously. In this system, the placement of the unmanned aerial vehicle (UAV) is jointly optimized along with the AIRS passive beam and the multiuser power allocation in order to maximize the communication sum rate. Since the joint optimization problem is nonconvex and coupled, it is hence disintegrated into three subproblems and it is solved alternately through the successive convex approximation (SCA). Moreover, semi definite programming (SDP) is used to deal with the rank one constraint of RIS reflection matrix and comparisons are made using particle swarm optimization (PSO). The numerical results show that the proposed ARIS-NOMA framework can achieve better sum rate performance than traditional NOMA with fixed RIS and OMA-ARIS.

Yue Yin, Guan Gui, Miao Liu, H. Gačanin, H. Sari, Fumiyuki Adachi

To provide seamless wireless coverage, the air-to-ground (A2G) heterogeneous wireless network is considered as one of the most promising solutions. In this article, we develop a novel A2G communication-caching-charging (3C) integrated network based on non-orthogonal multiple access (NOMA). As a significant participant of A2G network, unmanned aerial vehicle (UAV), which harvests energy from the base station (BS) with the aid of wireless power transfer (WPT), is utilized as content server to cache files and serve users. To be specific, we first propose a resource allocation strategy to enhance the quality of service (QoS) of ground users. The goal is to minimize the transmission latency of ground users, which is decomposed into sub-problems, such as user pairing, files' power allocation and users' power allocation. Firstly, we propose a NOMA user pairing algorithm based on K-means to deploy UAVs and pair users. Then, the closed-form solution for files' power allocation with the goal of maximizing the duration for energy harvesting is formulated. Finally, we apply the genetic algorithm (GA) to obtain power allocation factors to increase users' rate and the reminder time of content delivery phase is utilized for energy harvesting. Simulation results validate the advantage of the proposed strategy in reducing user delay than benchmark schemes.

Hao Gu, Jun Yang, Guan Gui, H. Gačanin

In this article, we propose a few-shot indoor position method based on Triplet Matchnet, which transforms coordinate positioning into channel state information (CSI) similarity matching problem. Triplet loss is designed to train and learn hidden correspondence between CSI features and physical space positions, with emphasis on minimizing distance or angle-based triplet loss. Then, according to pre-trained network with best similarity match, a similarity score map of CSI with unknown coordinates is constructed to predict position precisely. Experimental results show that angle-based triplet loss can obtain more accurate CSI fingerprint similarity matching accuracy. Compared with existing methods, experiment results confirm that our proposed method can achieve excellent positioning performance with few-shot datasets.

Chengkun Wang, Xue Fu, Yu Wang, Guan Gui, H. Gačanin, H. Sari, Fumiyuki Adachi

Specific emitter identification (SEI) is a potential physical layer authentication technology, which is one of the most critical complements of upper layer authentication. Radio frequency fingerprint (RFF)-based SEI is to distinguish one emitter from each other by immutable RF characteristics from electronic components. Due to the powerful ability of deep learning (DL) to extract hidden features and perform classification, it can extract highly separative features from massive signal samples, thus enabling SEI. Considering the condition of limited training samples, we propose a novel few-shot SEI (FS-SEI) method based on interpolative metric learning (InterML) which gets rid of the dependence on auxiliary dataset. Specifically, InterML is designed to mine more implicit samples in the sample space to improve generalization, and constrain the feature distance in the feature space to improve discriminability. The proposed InterML-based FS-SEI method is evaluated on a real-world Wi-Fi dataset. The simulation results show that the proposed method achieves better identification performance, higher feature discriminability and more stable performance than five latest FS-SEI methods. In the 10 shot scenario, the identification accuracy of InterML is 91.48%, compared to the comparison methods, the accuracy is improved by 0.62%–31.29%.

Jinlong Sun, Yibin Zhang, Guan Gui, Haitao Zhao, H. Gačanin, H. Sari

To establish more intelligent cellular networks for future ubiquitous access and heterogeneous devices, we need to obtain channel state information (CSI) in a more agile and economical manner, especially for frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) architectures. Unlike conventional CSI feedback or limited feedback methods, we can predict downlink CSI by leveraging channel reciprocity between uplink and downlink. The downlink CSI prediction can be formulated as a data-driven deep learning task, however, there exist isolated data silos and online adaptation problem for the offline trained neural network-based models. In this article, we propose an interacting federated and transfer learning (IFTL) based framework for downlink CSI prediction and online update, where several factors including asynchrony of different clients are considered, and light heterogeneity of diverse cells can be tolerated. Both model-level and link-level simulations are conducted under standardized FDD massive MIMO scenarios. The results outline promising prospect and potential of the utilization of federated learning and transfer learning in physical layer of wireless communications.

Yang Peng, Changbo Hou, Yibin Zhang, Yun Lin, Guan Gui, H. Gačanin, Shiwen Mao, Fumiyuki Adachi

Radio-frequency fingerprint (RFF), which comes from the imperfect hardware, is a potential feature to ensure the security of communication. With the development of deep learning (DL), DL-based RFF identification methods have made excellent and promising achievements. However, on one hand, existing DL-based methods require a large amount of samples for model training. On the other hand, the RFF identification method is generally less effective with limited amount of samples, while the auxiliary data set and the target data set often needs to have similar data distribution. To address the data-hungry problems in the absence of auxiliary data sets, in this article, we propose a supervised contrastive learning (SCL)-based RFF identification method using data augmentation and virtual adversarial training (VAT), which is called “SCACNN.” First, we analyze the causes of RFF, and model the RFF identification problem with augmented data set. A nonauxiliary data augmentation method is proposed to acquire an extended data set, which consists of rotation, flipping, adding Gaussian noise, and shifting. Second, a novel similarity radio-frequency fingerprinting encoder (SimRFE) is used to map the RFF signal to the feature coding space, which is based on the convolution, long short-term-memory, and a fully connected deep neural network (CLDNN). Finally, several secondary classifiers are employed to identify the RFF feature coding. The simulation results show that the proposed SCACNN has a greater identification ratio than the other classical RFF identification methods. Moreover, the identification ratio of the proposed SCACNN achieves an accuracy of 92.68% with only 5% samples.

Zhengran He, Xixi Zhang, Yu Wang, Yun Lin, Guan Gui, H. Gačanin

Wi-Fi-based passive sensing is considered as one of the promising sensing techniques in advanced wireless communication systems due to its wide applications and low deployment cost. However, existing methods are faced with the challenges of low sensing accuracy, high computational complexity, and weak model robustness. To solve these problems, we first propose a robust channel state information (CSI)-based Wi-Fi passive sensing method using attention mechanism deep learning (DL). The proposed method is called as convolutional neural network (CNN)-ABLSTM, a combination of CNNs and attention-based bi-directional long short-term memory (LSTM). Specifically, CSI-based Wi-Fi passive sensing is devised to achieve the high precision of human activity recognition (HAR) due to the fine-grained characteristics of CSI. Second, CNN is adopted to solve the problems of computational redundancy and high algorithm complexity which are often occurred by machine learning (ML) algorithms. Third, we introduce an attention mechanism to deal with the weak robustness of CNN models. Finally, simulation results are provided to confirm the proposed method in three aspects, high recognition performance, computational complexity, and robustness. Compared with CNN, LSTM, and other networks, the proposed CNN-ABLSTM method improves the recognition accuracy by up to 4%, and significantly reduces the calculation rate. Moreover, it still retains 97% accuracy under the different scenes, reflecting a certain robustness.

Yuxin Ji, Yu Wang, Haitao Zhao, Guan Gui, H. Gačanin, H. Sari, Fumiyuki Adachi

The communications between vehicle-to-vehicle (V2V) with high frequency, group sending, group receiving and periodic lead to serious collision of wireless resources and limited system capacity, and the rapid channel changes in high mobility vehicular environments preclude the possibility of collecting accurate instantaneous channel state information at the base station for centralized resource management. For the Internet of Vehicles (IoV), it is a fundamental challenge to achieve low latency and high reliability communication for real-time data interaction over short distances in a complex wireless propagation environment, as well as to attenuate and avoid inter-vehicle interference in the region through a reasonable spectrum allocation. To solve the above problems, this paper proposes a resource allocation (RA) method using dueling double deep Q-network reinforcement learning (RL) with low-dimensional fingerprints and soft-update architecture (D3QN-LS) while constructing a multi-agent model based on a Manhattan grid layout urban virtual environment, with communication links between V2V links acting as agents to reuse vehicle-to-infrastructure (V2I) spectrum resources. In addition, we extend the amount of transmitted data in our work, while adding scenarios where spectrum resources are relatively scarce, i.e. the number of V2V links is significantly larger than the amount of spectrum, to compensate for some of the shortcomings in existing literature studies. We demonstrate that the proposed D3QN-LS algorithm leads to a further improvement in the total capacity of V2I links and the success rate of periodic secure message transmission in V2V links.

Jiaxi Liu, Si Chen, Guan Gui, H. Gačanin, Hikmet Sari, Fumiyuki Adachi

Vehicular ad hoc network (VANETs) improves road safety and efficiency by organizing vehicles and infrastructure to provide a platform for application deployment. The availability of vehicles and infrastructure is critical to the operation of applications. Accurate failure detector (FD) has been one of the fundamental components for maintaining high availability in VANETs. However, it is hard to find the vehicle failure accurately and timely due to the dynamic nature of VANETs caused by the high mobility of vehicles and communications link failures. Therefore, it is important to achieve an accurate FD which can cope with the high mobility of VANETs. In this paper, we propose a dead reckoning based FD, called DR-FD. It can predict the mobility of vehicle accurately and avoid the impact of link failures on the detection results by the cooperation between vehicles. Experimental results are provided to confirm that the proposed DR-FD method can achieve at most 20% reduction in detection time, 30% improvement in mistake rate and 20% improvement in overhead.

Yue Yin, Guan Gui, H. Gačanin, Hikmet Sari

To provide seamless wireless coverage, the framework integrating the air network and the ground heterogeneous network has attracted extensive attentions. In this work, we develop a non-orthogonal multiple access (NOMA) assisted air-to-ground (A2G) communication-caching-charging (3C) integrated network. Specifically, we propose a resource allocation strategy to minimize the transmission latency of ground users. Since the formulated problem is difficult to solve directly, it is decomposed into three sub-problems, user pairing, user power allocation and file power allocation. Firstly, we propose a user clustering and pairing strategy according to the distance and channel gain. Secondly, the closed-form solution for the power allocation of files to maximize the duration for energy harvesting is derived. Thirdly, we apply genetic algorithm (GA), which can search for the global optimal solution, to obtain the power allocation factors for users to maximize the rate. Finally, simulations evaluate the superiority of the developed network and the proposed strategy in reducing user delay.

Hao Huang, Yun Lin, Guan Gui, H. Gačanin, H. Sari, F. Adachi

Unsupervised learning (UL) is widely used in the wireless resource allocation problems due to its lower computational complexity and better performance compared with traditional optimization algorithms. Since wireless resource allocation problems usually have several constraints, primal-dual learning based UL framework are widely adopted. However, the primal-dual learning approach has the problem of oscillation around the constraint threshold while training and there may be serious constraint violations when deployment. In addition, although the output of the neural network can also be restricted to the feasible region by the penalty function method, the optimality of such training methods cannot be guaranteed. In this article, we combine the primal dual learning method with the penalty function method and propose a regularized unsupervised learning (RUL) framework to enhance the robustness of the primal-dual learning based UL framework. In the proposed RUL framework, we use regularization techniques to improve the robustness of primal-dual learning by reducing the risk of constraint violations while training. A quadratic penalty term is introduced into the Lagrangian function of the wireless optimization problem where the constraints can be equivalent to equality constraints to form its augmented Lagrangian function. In the simulation, we give a simple point to point power optimization problem as an example to show that the proposed RUL can improve the robustness of constraint convergence, and can also accelerate training speed.

Hao Huang, Guan Gui, H. Gačanin, C. Yuen, H. Sari, F. Adachi

Millimeter wave (mmWave) systems need beam management to establish and maintain reliable links. This complex and time-consuming process seriously affects communication efficiency. Benefiting from data-driven technology in deep learning, the beam can be predicted from the waveform without coordination between transceivers. By passively listening enough waveforms that are transmitted from the base station (BS) to other receivers, the BS can predict which beam is suitable for transmitting in the downlink. However, training such a waveform learning neural network usually requires a large number of labeled training samples. This is a huge challenge, because it is difficult for the receiver to get the precise signal parameters from the transmitter in advance in the non-cooperative mmWave system. As a result, the limited samples may cause overfitting and seriously restrict the performance. Although the data augmentation technology can improve the performance under limited samples, existing data augmentation methods are mostly based on strong prior knowledge which cannot further exploit the potential characteristics of data in the real environment. This paper proposes a mixed regularization training method for training the beam prediction neural network under limited training samples. Specifically, data augmentation is implemented in the data pre-processing procedure with prior knowledge and then the signal splicing strategy is proposed in the training procedure. In order to mine the time correlation characteristics of signals, the cyclic time shift (CTS) based data augmentation method is proposed in the data augmentation step. The simulation results show that our proposed deep regularized waveform learning method needs less training samples under the same performance. Moreover, the proposed method can achieve best performance compared with existing data augmentation methods.

Amna Kopic, Kenan Turbic, H. Gačanin

This paper provides a comprehensive study on the learning models' power violation, sum-rate performance while taking into consideration power constraint, and computational efficiency in terms of training and execution times over a dynamic wireless channel. We propose a reward shaping method and modify learning models with the output scaling strategy to enforce them to fully respect the power constraints while optimizing the sum-rate performance. The proposed approach reaches close-to-optimal accuracy, i.e., up to 99.15%, while satisfying the predefined power constraint of the base station. Moreover, learning models are shown to be more computationally efficient compared to the traditional algorithm. However, solving the power allocation problem within the Orthogonal Frequency Division Multiplexing (OFDM) symbol duration of $16.7\mu \mathrm{s}$ is a remaining challenge.

Nema pronađenih rezultata, molimo da izmjenite uslove pretrage i pokušate ponovo!

Pretplatite se na novosti o BH Akademskom Imeniku

Ova stranica koristi kolačiće da bi vam pružila najbolje iskustvo

Saznaj više