In 5G era, it is expected to achieve wireless network coverage including offshore areas. Modeling of marine wireless channels is the basis of constructing a marine communication system. In this paper, a communication scene between an unmanned aerial vehicle (UAV) and a boat is simulated to study the marine wireless channel. Firstly, an improved spatial partitioning ray tracing algorithm is proposed to track the propagation path of electromagnetic waves at sea surface. Secondly, a mobile channel is simulated and modeled based on the track results. Finally, a loss measurement is carried out in the coastal waters based on the simple wireless channel loss measuring platform, and a path loss propagation model is built. Then we compare the actual measurement data with the simulation results and find that the two are have good consistency, which further verifies the reliability of the simulation.

Modulation recognition has been long investigated in the literature, however, the performance could be severely degraded in multipath fading channels especially for high-order Quadrature Amplitude Modulation (QAM) signals. This could be a critical problem in the broadband maritime wireless communications, where various propagation paths with large differences in the time of arrival are very likely to exist. Specifically, multiple paths may stem from the direct path, the reflection paths from the rough sea surface, and the refraction paths from the atmospheric duct, respectively. To address this issue, we propose a novel blind equalization-aided deep learning (DL) approach to recognize QAM signals in the presence of multipath propagation. The proposed approach consists of two modules: A blind equalization module and a subsequent DL network which employs the structure of ResNet. With predefined searching step-sizes for the blind equalization algorithm, which are designed according to the set of modulation formats of interest, the DL network is trained and tested over various multipath channel parameter settings. It is shown that as compared to the conventional DL approaches without equalization, the proposed method can achieve an improvement in the recognition accuracy up to 30% in severe multipath scenarios, especially in the high SNR regime. Moreover, it efficiently reduces the number of training data that is required.

As an alternative to satellite communications, multi-hop relay networks can be deployed for maritime long-distance communications. Distinct from terrestrial environment, marine radio signals are affected by many factors, e.g., weather conditions, evaporation ducting, and ship rocking caused by waves. To ensure the data transmission reliability, the block Markov superposition transmission (BMST) codes, which are easily configurable and have predictable performance, are applied in this study. Meanwhile, the physical-layer network coding (PNC) scheme with spatial modulation (SM) is adopted to improve the spectrum utilization. For the BMST-SM-PNC system, we propose an iterative algorithm, which utilizes the channel observations and the a priori information from BMST decoder, to compute the soft information corresponding to the XORed bits constructed by the relay node. The results indicate that the proposed scheme outperforms the convolutional coded SM-PNC over fast-fading Rician channels. Especially, the performance can be easily improved in high spatial correlation maritime channel by increasing the memory m.

This paper studies sampled-data consensus control of a collection of unmanned surface vehicles (USV) operating in network environments with fading channels and time-varying transmission delay. The channel fading is modeled as each independent stochastic process whose probability distribution is known. By considering the effects of channel fading and transmission delay from sampler to the controller, a new MUSV system model is formulated in the framework of network. With the novel established model, stability analysis is given at first, then the sampled-data consensus controller is designed, which also extends to the robust control with wave-induced disturbance. The effectiveness of the presented method is demonstrated by numerical simulation.

Unmanned surface vehicle (USV) is currently a hot research topic in maritime communication network (MCN), where denoising and semantic segmentation of maritime images taken by USV have been rarely studied. The former has recently researched on autoencoder model used for image denoising, but the existed models are too complicated to be suitable for real-time detection of USV. In this paper, we proposed a lightweight autoencoder combined with inception module for maritime image denoising in different noisy environments and explore the effect of different inception modules on the denoising performance. Furthermore, we completed the semantic segmentation task for maritime images taken by USV utilizing the pretrained U-Net model with tuning, and compared them with original U-Net model based on different backbone. Subsequently, we compared the semantic segmentation of noised and denoised maritime images respectively to explore the effect of image noise on semantic segmentation performance. Case studies are provided to prove the feasibility of our proposed denoising and segmentation method. Finally, a simple integrated communication system combining image denoising and segmentation for USV is shown.

How to explore and exploit the full potential of artificial intelligence (AI) technologies in future wireless communications such as beyond 5G (B5G) and 6G is an extremely hot inter-disciplinary research topic around the world. On the one hand, AI empowers intelligent resource management for wireless communications through powerful learning and automatic adaptation capabilities. On the other hand, embracing AI in wireless communication resource management calls for new network architecture and system models as well as standardized interfaces/protocols/data formats to facilitate the large-scale deployment of AI in future B5G/6G networks. This paper reviews the state-of-art AI-empowered resource management from the framework perspective down to the methodology perspective, not only considering the radio resource (e.g., spectrum) management but also other types of resources such as computing and caching. We also discuss the challenges and opportunities for AI-based resource management to widely deploy AI in future wireless communication networks.

Novel centralized base station architectures integrating computation and communication functionalities have become important for the development of future mobile communication networks. Therefore, the development of dynamic high-speed interconnections between baseband units (BBUs) and remote radio heads (RRHs) is vital in centralized base station design. Herein, dynamic high-speed switches (HSSs) connecting BBUs and RRHs were designed for a centralized base station architecture. We analyzed the characteristics of actual traffic and introduced a switch traffic model suitable for the super base station architecture. Then, we proposed a data-priority-aware (DPA) scheduling algorithm based on the traffic model. Lastly, we developed the dynamic HSS model based on the OPNET platform and the prototype based on FPGA. Our results show that the DPA achieves close to 100% throughput with lower latency and provides better run-time complexity than iOCF and HE-iSLIP, thereby demonstrating that the proposed switch system can be adopted in centralized base station architectures.

Channel estimation is a well-known challenge for wireless orthogonal frequency division multiplexing (OFDM) communication systems with massive antennas on high speed rails (HSRs). This paper investigates this problem and design two practicable uplink and downlink channel estimators for orthogonal frequency division multiplexing (OFDM) communication systems with massive antenna arrays at base station on HSRs. Specifically, we first use pilots to estimate the initial angle of arrival (AoA) and channel gain information of each uplink path through discrete Fourier transform (DFT), and then refine the estimates via the angle rotation technique and suggested pilot design. Based on the uplink angel estimation, we design a new downlink channel estimator for frequency division duplexing (FDD) systems. Additionally, we derive the Cramér-Rao lower bounds (CRLBs) of the AoA and channel gain estimates. Finally, numerical results are provided to corroborate our proposed studies.

This paper applies the repetition index scheme (RIS) to the channel identification of cyclic prefixed (CP) multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems with virtual carriers (VCs) in the environment of the number of receive antennas being no less than that of transmit antennas. The VCs will cause a rank deficiency problem in computing the subspace information. With the subcarrier mapping matrix, the received signal is simplified to remove the rank deficiency. We use the RIS scheme to generate many times of equivalent symbols so the channel identification can converge with few received OFDM blocks. The RIS scheme will convert the white noise into non-white noise. With the Cholesky factorization, a noise whitening technique is developed to turn the non-white noise back to white noise. We further analyze the necessary conditions of identifiability of channel estimation. Simulations are performed to show the superiority of the proposed method.

Unmanned Aerial Vehicle (UAV) equipped with uniform linear array has been applied to multiple emitters localization. Meanwhile, nested linear array enables to enhance localization resolution and achieve under-determined Direction of Arrival (DOA) estimation. In this paper, we propose a new system structure for emitters localization that combines the UAV with nested linear array, which is capable of significantly increasing the positioning accuracy of interested targets. Specifically, a localization scheme is designed to obtain the paired two-dimensional DOA (2D-DOA, i.e. azimuth and elevation angles) estimates of emitters by nested linear array with UAV. Furthermore, we propose an improved DOA estimation algorithm for emitters localization that utilizes Discrete Fourier Transform (DFT) method to obtain coarse DOA estimates, subsequently, achieve the fine DOA estimates by sparse representation. The proposed algorithm has lower computational complexity because the coarse DOA estimates enable to shrink the range of over-complete dictionary of sparse representation. In addition, compared to traditional uniform linear array, improved 2D-DOA estimation performance of emitters can be obtained with a nested linear array. Extensive simulation results testify the effectiveness of the proposed method.

This paper presents our investigation into a 220 GHz multicarrier high-speed communication system based on solid state transceivers. The proposed system has eased the demand of high sampling rate analog-to-digital converter (ADC) by providing several signal carriers in microwave band and converting them to 220 GHz channel. The system consists of a set of 220 GHz solid-state transceiver with 2 signal carriers, two basebands for 4 GSPS ADCs. It has achieved 12.8 Gbps rate real-time signal transmission using 16QAM modulation over a distance of 20 m without any other auxiliary equipment or test instruments. The baseband algorithm overcomes the problem of frequency difference generates by non-coherent structure, which guarantees the feasibility of long-distance transmission application. Most importantly, the proposed system has already carried out multi-channel 8K video parallel transmission through switch equipment, which shows the multicarrier high-speed communication system in submillimeter wave has great application prospects. To the best of the authors’ knowledge, this is the first all-solid-state electronics multicarrier communication system in submillimeter and terahertz band.

The network is a major platform for implementing new cyber-telecom crimes. Therefore, it is important to carry out monitoring and early warning research on new cyber-telecom crime platforms, which will lay the foundation for the establishment of prevention and control systems to protect citizens’ property. However, the deep-learning methods applied in the monitoring and early warning of new cyber-telecom crime platforms have some apparent drawbacks. For instance, the methods suffer from data-distribution differences and tremendous manual efforts spent on data labeling. Therefore, a monitoring and early warning method for new cyber-telecom crime platforms based on the BERT migration learning model is proposed. This method first identifies the text data and their tags, and then performs migration training based on a pre-training model. Finally, the method uses the fine-tuned model to predict and classify new cyber-telecom crimes. Experimental analysis on the crime data collected by public security organizations shows that higher classification accuracy can be achieved using the proposed method, compared with the deep-learning method.

Publish/subscribe paradigm is often adopted to create the communication infrastructure of the Internet of Things (IoT) for many clients to access enormous real-time sensor data. However, most current publish/subscribe middlewares are based on traditional ossified IP networks, which are difficult to enable Quality of Service (QoS). How to design the next generation publish/subscribe middleware has become an urgent problem. The emerging Software Defined Networking (SDN) provides new opportunities to improve the QoS of publish/subscribe facilities for delivering events in IoT owing to its customized programmability and centralized control. We can encode event topics, priorities and security policies into flow entries of SDN-enabled switches to satisfy personalized QoS needs. In this paper, we propose a cross-layer QoS enabled SDN-like publish/subscribe communication infrastructure, aiming at building an IoT platform to seamlessly connect IoT services with SDN networks and improving the QoS of delivering events. We first present an SDN-like topic-oriented publish/subscribe middleware architecture with a cross-layer QoS control framework. Then we discuss prototype implementation, including topic management, topology maintenance, event routing and policy management. In the end, we use differentiated services and cross-layer access control as cross-layer QoS scenarios to verify the prototype. Experimental results show that our middleware is effective.

As the cyber security has attracted great attention in recent years, and with all kinds of tools’ (such as Network Agent, VPN and so on) help, traditional methods of tracking users like log analysis and cookie have been not that effective. Especially for some privacy sensitive users who changed their browser configuration frequently to hide themselves. The Browser Fingerprinting technology proposed by Electronic Frontier Foundation (EFF) gives a new approach of tracking users, and then our team designed an enhanced fingerprint dealing solution based on browser fingerprinting technology. Our enhanced solution plays well in recognizing the similar fingerprints, but it is not that efficient. Nowadays we improve the algorithm and propose a high-performance, efficient Browser Fingerprint Recognition Model. Our new model reforms the fingerprint items set by EFF and propose a Fingerprint Tracking Algorithm (FTA) to deal with collected data. It can associate users with some browser configuration changes in different periods of time quickly and precisely. Through testing with the experimental website built on the public network, we prove the high-performance and efficiency of our algorithm with a 20% time-consuming decrease than ever.

In view of the fact that news can generate derivative topics when it spreads through micro-blogs, a two-layer coupled SEIR public opinion propagation model is proposed in this paper. The model divides the process of public opinion propagation into two layers: the original topic layer and the derived topic layer. Messages are transmitted separately by the SEIR model in the two topic layers, which are independent and interactive. The influence of the topic derivation rate on the propagation trend is established by solving for the equilibrium point and propagation threshold. Further, we establish the relationship between the original topic and the derived topic by simulation. This paper uses the Baidu index to demonstrate the correctness of the model. The relationship between the derived topic and the original topic is verified by adjusting the parameters by the control variable method. The results show that the proposed model is consistent with the propagation of actual public opinion.

Recently, initiatives to integrate Internet of Things (IoT) technologies into smart buildings have attracted extensive attention for improving the performance of buildings and the comfort of occupants. However, the amount of data generated by IoT devices remains a challenge to the building management systems (BMSs) in terms of intensity and complexity. Different from cloud computing and edge computing, we propose a computation sharing architecture in smart buildings to incentivize idle computing devices (ICDs, sellers) to offload computational tasks for the BMS (buyer). In this paper, we design a hierarchical game model, consisting of a Stackelberg game and a Cournot game, to achieve a dynamic increase in computational capacity for the BMS. To guarantee the utility of BMS and ICDs, the Stackelberg game model is built to analyze the interactions between BMS and ICDs. Then, the Cournot game model is presented to formulate the internal competition among multiple ICDs. Under the premise of the subgame perfect Nash equilibrium, the BMS can quote the optimal pricing strategy, and the ICDs can share the corresponding optimal amount of computing resources. Finally, the simulation results show that the BMS’s computational capacity is enhanced on-demand, and each participant in the game obtains maximal utility.

Stock price forecasting is an important issue and interesting topic in financial markets. Because reasonable and accurate forecasts have the potential to generate high economic benefits, many researchers have been involved in the study of stock price forecasts. In this paper, the DWT-ARIMA-GSXGB hybrid model is proposed. Firstly, the discrete wavelet transform is used to split the data set into approximation and error parts. Then the ARIMA (0, 1, 1), ARIMA (1, 1, 0), ARIMA (2, 1, 1) and ARIMA (3, 1, 0) models respectively process approximate partial data and the improved xgboost model (GSXGB) handles error partial data. Finally, the prediction results are combined using wavelet reconstruction. According to the experimental comparison of 10 stock data sets, it is found that the errors of DWT-ARIMA-GSXGB model are less than the four prediction models of ARIMA, XGBoost, GSXGB and DWT-ARIMA-XGBoost. The simulation results show that the DWT-ARIMA-GSXGB stock price prediction model has good approximation ability and generalization ability, and can fit the stock index opening price well. And the proposed model is considered to greatly improve the predictive performance of a single ARIMA model or a single XGBoost model in predicting stock prices.