Proceedings of the 2nd International Conference on Networks, Communications and Intelligent Computing (NCIC 2024)

Table of Contents

1. Communication

   1. Frontmatter

   2. A Optimization Study of Communication Systems Based on Dijkstra Algorithm and Particle Swarm Optimization (PSO)

      Yuhan Feng

      Abstract

      In recent years, with the widespread adoption of fiber-optic communication, the development of wireless communication technologies, advancements in interference management, and the innovative application of transmission technologies, signal transmission technology has been continuously evolving in various fields, playing a crucial role in providing strong technical support for societal development and progress. Firstly, the distribution of communication system base stations was optimized in this paper, with Dijkstra algorithm being utilized to optimize the shortest transmission paths between different base stations. Secondly, Particle Swarm Optimization (PSO) was applied to optimize the shortest transmission paths between the base stations and terminal devices. Finally, MATLAB was employed to simulate and analyze both Dijkstra algorithm and PSO, resulting in the identification of the shortest transmission paths between base stations and between base stations and terminal devices under predefined conditions. Through a comparative simulation analysis, the feasibility and effectiveness of the optimization model proposed in this paper were verified, thereby laying a solid foundation for future optimization designs.

   3. Phase Aware Based Channel Estimation for Uplink Cell-Free Massive MIMO over Rician Fading Channel

      Birhanu Dessie Ayalew, Zenebe Melesew Yetneberk, Yibltal Abebaw Molla, Tong-Xing Zheng, Isayiyas Nigatu Tiba

      Abstract

      One of the key advancements in wireless communication, particularly in 5G and 6G networks, is cell-free massive multiple-input multiple-output (CF M-MIMO). This technology uses a large number of distributed antennas to serve multiple users simultaneously, providing higher spectral efficiency (SE), improved coverage, and better interference control compared to traditional cellular networks. However, achieving efficient channel estimation with low computational complexity remains a challenge. Several algorithms have been developed to address these challenges, with the phase-aware minimum mean square error (PA-MMSE) estimator standing out as a high-performance option. Although effective, the PA-MMSE estimator is limited by its high computational complexity. To overcome these challenges, this paper introduces a phase-aware element-wise MMSE (PA-EW-MMSE) estimator, which incorporates QR decomposition (where Q is an orthogonal matrix and R is an upper triangular matrix) along with a user-side precoding matrix. The proposed estimator is evaluated in terms of uplink (UL) SE using MMSE combining. Additionally, energy efficiency (EE) and area throughput are calculated from SE. Simulation results demonstrate that the proposed PA-EW-MMSE estimator significantly reduces computational complexity while delivering superior SE, EE, and area throughput compared to existing methods.

   4. Integrated Sensing and Communication Air Interface Design and Performance Evaluation

      Lifang Cao, Lingtong Meng, Wei Deng, Li Zhang, Tianming Jiang, Liang Liu, Lei Cao, Jinghua Kuang, Songhe Lu

      Abstract

      Integrated Sensing and Communication (ISAC), regarding as an important 5G-A and 6G (Radio Communication Technology (02) 2021, J. Beijing Univ. Posts Telecommun, (04)2021, Theor. Technol. Integr. 6G Commun. Sens Control. Decis, 38(1), 22–38 (2023) technical aspect, has currently met a break though from academic research to industrial implementation. The development of this technology marks a significant transition from theoretical research to practical application, paving the way for the intelligentization of future communication networks. This paper first outlines the air interface design scheme for ISAC in three typical scenarios of low-altitude airspace, waterway and sea area, through three steps: analysis and design of sensing waveform, transmission time slot for sensing signals, and sensing waveform parameters. Secondly, the paper gives out the lab test results of the ISAC air interface design scheme. Finally, it briefly introduces the three aspects that still need to be considered and solved for further commercial use: reducing system overhead, improving sensing performance, and reducing network interference.

   5. Max-Min Fair Energy Efficiency Optimization for STAR-RIS-Aided ISAC Systems

      Shuang Zhang, Wanming Hao, Gangcan Sun, Zhengyu Zhu

      Abstract

      Underlying the near-field scenario, this paper investigates the communication energy efficiency (EE) of the integrated sensing and communications (ISAC) systems which aided by simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS). Aiming to achieve the purpose of maximizing the minimum (max-min) communication EE while satisfying the target minimum illumination power requirement, the maximum transmission power budget and adhering to the hardware limitations of the STAR-RIS, the dual-functional base station transmit and STAR-RIS beamforming matrices undergo a joint optimization process. The formulated max-min optimization problem exhibits non-convexity stemming from the intricate interplay and high degree of coupling within the optimization variables involved. So as to resolve this problem, the fractional programming method is first leveraged to convert the objection function into a more tractable structure, and then the original max-min problem is transformed into an equivalent maximization problem via bringing in the auxiliary variable. Next, an alternating optimization framework is introduced to decouple the newly rewritten maximization problem into two sub-problems for alternatively optimizing until convergence. Finally, the outcomes from the simulations are given to confirm the advantages and effectiveness of the scheme we have introduced.

   6. A Multi-layer LSTM-Based Channel State Estimator in OFDM Wireless Systems

      Zhenjie Deng, Chunhui Wu, Chen Bian

      Abstract

      A novel multi-layer LSTM-based approach for signal detection and channel estimation for OFDM wireless systems is proposed in this paper. Unlike conventional methods such as Minimum Mean-Square Error (MMSE), Least Squares (LS), and Fully-Connected Neural networks (FCN), the multi-layer LSTM model leverages its capability to capture temporal dependencies and sequential patterns in the received signal, enabling more accurate signal detection and Channel State Information (CSI) estimation in an end-to-end manner. We also evaluate our proposed model through extensive simulations, focusing on its robustness in various scenarios, including varying numbers of pilots, different cyclic prefix (CP) lengths, and a combination of reduced pilots and CP. Furthermore, we examine the impact of mismatches between offline training and online deployment environments, where channel conditions differ between training and real-time operation. Simulation results indicate that our approach consistently achieves superior performance in terms of BER compared to LS, MMSE, and FCN. Our model also shows strong resilience to mismatched deployment environments, maintaining robust performance even when the channel characteristics during deployment deviate from those in training.

   7. A Joint PTS and IMM Scheme for PAPR Reduction in OFDM-IM Systems

      Yi-Hang Ma, Si-Yu Zhang, Ruo-Yan Li, Jie-Yu Cheng, Xiao-Yan Tian, Bo Yang

      Abstract

      To address the high peak-to-average power ratio (PAPR) problem in orthogonal frequency division multiplexing with index modulation (OFDM-IM) systems, this paper proposes a novel PAPR reduction approach called the joint partial transmit sequence and index modulation mapping (J-IMM-PTS) scheme. The J-IMM-PTS method operates in two stages: the first stage applies index modulation mapping (IMM) rules to achieve an initial reduction in PAPR, while the second stage employs the partial transmit sequence (PTS) technique to further process signals that still exhibit high PAPR. A threshold mechanism is introduced to decide whether the PTS stage should be executed, enabling a balance between PAPR reduction performance and computational complexity. Simulation results demonstrate that the proposed J-IMM-PTS scheme achieves superior PAPR reduction compared to the traditional IMM method while also reducing computational complexity.

   8. A Conflict Resolution Study for the Sensor Scheduling Problem in a Space Situation Awareness System

      Houwu Peng, Jingfeng Tian

      Abstract

      As the space environment becomes increasingly complex, the demand for space situational awareness using space-based optical sensor networks is becoming more urgent. Existing centralized and distributed sensor scheduling methods cannot meet the dynamic and time-sensitive demands for space target observation . The multi-master sensor scheduling approach based on regional grouping is a feasible solution meeting this need, but conflicts may arise when multiple masters make task allocation decisions simultaneously. To resolve conflicts in the task allocation process, we developed a post-allocation conflict resolution method based on the contract net with confirmation protocol, and a pre-allocation conflict resolution method based on the contract net with preselection protocol. Additionally, we have developed two heuristic preselection rules: the revenue-priority rule and the scarcity-priority rule. Experimental results show that the combination of the contract net with preselection protocol with the revenue-priority rule has the lowest communication cost and the highest allocation success rate, making it the most recommended conflict resolution method.

   9. Research on Multi-domain Resource Joint Allocation Algorithm Based on Deep Reinforcement Learning

      Hengyi Zhang, Xuehua Li, Shuo Chen

      Abstract

      In response to the declining quality of user service in cell-free massive MIMO networks due to an increase in communication traffic, this paper explores the multi-domain resource management problem utilizing deep reinforcement learning. The resource management issue is formulated as a total transmission rate maximization problem, constrained by various hardware conditions while considering the distinct characteristics of access point (AP) devices and user service quality requirements. For efficient resource allocation across multiple domains, we introduce a deep reinforcement learning-based approach. Furthermore, this paper demonstrates the effective collaboration among multiple APs through a training mechanism designed to promote cooperation among the agents. Simulation results indicate that the proposed multi-domain joint resource allocation algorithm significantly improves system spectral efficiency when compared to existing resource allocation algorithms in cell-free massive MIMO system.

   10. High-Accuracy Action Recognition in Practical WiFi Systems: Platform Implementation, Dataset Construction, and Algorithm Design

       Congyu Li, Zhongyuan Zhao, Jinlong Zhang, Yang Li, Mingfeng Xu

       Abstract

       WiFi-based action recognition has become increasingly powerful due to rapid advancements in deep learning, especially for applications in smart homes, health monitoring, and security. However, existing studies frequently lack detailed guidelines for platform setup and dataset construction, and they seldom discuss the impact of window length and latency on recognition accuracy. To address these gaps, this study explores the implementation of platforms and the construction of datasets, incorporating movement sequences of varying levels of action completeness to simulate different recognition latencies. We propose a high-accuracy algorithm, named CNN-ResNet-BiLSTM (C-R-BL), which significantly improves recognition accuracy while ensuring timely responses. To validate the effectiveness and superiority of the proposed algorithm, we conduct ablation and comparative experiments. Results indicate that the algorithm achieves accuracy rates ranging from 93.8% to 96.0% under low-latency conditions, demonstrating significant performance enhancements. This study provides a practical guide for new researchers and emphasizes the importance of these factors in WiFi-based action recognition.

   11. Segmented Double Parity Check Aided Successive Cancellation List Flip Decoding Algorithm of Polar Codes for Satellite Communication

       Xiaojun Zhang, Junshuo Huo, Yue Qiu, Shuguang Liu, Jian Gao

       Abstract

       Satellite communication systems have garnered significant attention in recent years as essential frameworks for transmission. Given the numerous interferences and detection issues in the space communication environment, satellite covert communications often employ short codes for channel coding, such as polar codes. To improve the performance of the Successive Cancellation List Bit-Flip (SCLF) algorithm for polar codes, this paper introduces a method that integrates a threshold strategy with segmented parity check (PC) checks to reduce the average flip numbers. The method sets thresholds for Rate-1 and FI nodes to better identify unreliable positions. To further reduce flips, two PC bits are added after each segment of information bits, enabling early termination of erroneous decoding processes. Simulation results demonstrate that the proposed algorithm improves both decoding accuracy and lowers the average flip numbers. For the polar code P(1024, 512) with list size L = 4 and maximum flips \(T _\textit{max}\) = 40, the new algorithm achieves a 0.13dB gain over SCLF at BLER = 10\(^{\textbf {-4}}\). Furthermore, at SNR = 2dB, the Segmented Double Parity Check(SDPC) SCLF algorithm reduces the average flips by 34.3\(\%\) compared to General-SCLF.

   12. Physical Layer Encryption Method Based on Modulation Constellation Rotation in Secure Communication Systems

       Siheng Zhao, Lu Tian, Zhan Xu, Yulong Wang, Yuanmu Wang, Huiqing Xiao

       Abstract

       Improving confidentiality is a major issue in many wireless transmission systems. Physical layer security techniques are often used to improve confidentiality from eavesdroppers. In this paper, we propose a secure communication method based on physical layer encryption to ensure the security of transmitted data. We adjust the modulation method and phase of the transmitted signal based on the conventional encrypted signal. The adjustment is jointly determined by the encryption key and the front-end signaling information. The proposed method has almost no bit error rate (BER) performance loss under different signal-to-noise ratios (SNR) compared to conventional communication methods. While, the method can realize eavesdropping-proof high-security communication with low complexity.

   13. A Communication and Positioning Method for Nano-satellite Clusters Applied in Deep-space Exploration

       Mingchuan Yang, Changlin Du, Fang Lu

       Abstract

       More and more nano-satellites (≤10 kg) are being sent into deep space to carry out exploration missions. Due to their limited resources, nano-satellites have limited capabilities and single functionality. However, a cluster composed of multiple nano-satellites can effectively break through the limitations of individual ones and perform more complex tasks. Wireless network and positioning system are the core technology of nano-satellite clusters, which need to meet communication distance requirements within tens to hundreds of kilometers of satellites group, provide the position of each satellite within the cluster to support formation flying, and meet real-time requirements of multiple satellites collaborating on tasks. A hierarchical network architecture based on routing technology has been designed, and a relative positioning method based on optical angle measurement and radio ranging has been introduced. By modifying the data link layer and network layer protocols, a wireless network with both network capacity and real-time performance has been achieved. With the help of network, the time deviation of each satellite in the cluster can be controlled within 5ms, and the positioning accuracy can reach 98m@50km.

   14. Research on Semantic Compression Methods in Semantic Communication System

       Bohui Wang, Chunhua Zhu, Yanning Yang

       Abstract

       Semantic communication can effectively improve the efficiency of data transmission by extracting the deeper meanings of information, addressing the issue of the rapidly increasing data transmission volumes in the communication industry. Semantic compression is one of the key technologies that determine the performance of semantic communication system. This study investigates semantic compression methods within the semantic communication system and constructs a frequency domain compressed semantic communication system tailored for image classification tasks, and compares it with the compression method based on feature map weights. Experimental results demonstrate that the two semantic compression methods can significantly reduce data transmission volumes while maintaining high classification accuracy. Under the compression ratio of 60% and SNR greater than 0, the difference of classification accuracy before and after semantic compression is within 5%, and the proposed frequency-domain compression method has better anti-noise performance. When SNR is less than 0, the frequency domain compression method has higher classification accuracy.

   15. Multi-frequency Channel Measurement and Characterization in Dense Urban Scenario

       Shilong Xie, Mi Yang, Xuejian Zhang, Jingya Yang, Yunlong Lu, Guoyu Ma

       Abstract

       Communication in dense urban area has consistently attracted significant attention from both academia and industry. It is an essential component for the related wireless communication system by measuring and analyzing wireless channel across various frequency bands. Measuring and analyzing wireless channel in dense urban environments is far more complex and poses significant challenges. Therefore, we conducted measurements and analyzed the channel characteristics of vehicle-to-infrastructure (V2I) communication channel. This paper presents the measurement activities of channels in dense urban environments and compares key channel characteristics under different link conditions, such as power path loss (PL). We researched the Rician power delay profile (PDP) under different channel bandwidths, and Rician K-factor at different carrier frequencies ranging from 0.69 to 5.9 GHz, and also conducted extensive analysis of the characteristics of shadow fading (SF). Additionally, a statistical analysis of the decorrelation distance of SF was also performed, that as the channel bandwidth increases, the decorrelation distance also increases.

   16. Enabling RIS-Aided Wideband ISAC Systems: A Signal Processing Approach

       Sitong Li, Zhouyuan Yu, Xiaoling Hu, Chenxi Liu, Xiqing Liu

       Abstract

       Reconfigurable intelligent surface (RIS) has been recognized as an efficient solution to realize integrated sensing and communications (ISAC) by dynamically reconfiguring wireless channels, improving signal quality, and mitigating issues such as signal attenuation and blockages, especially in high-frequency millimeter-wave band. However, traditional sensing signal processing methods are only applicable for narrowband systems. Due to the wideband effects that ISAC signals significantly varies across different frequencies, sensing signal processing methods have to be newly designed in order to fulfill the potential of RIS-aided ISAC systems. To address this issue, in this paper, we propose a wideband signal processing approach for velocity and range estimation in RIS-aided ISAC systems, where we flatten the frequency property of ISAC signals through sub-band division. Specifically, we first employ a discrete Fourier transform (DFT)-based method to initialize the Doppler shift and time delay of the target. Then, we propose a sub-band division method, based on which we solve the maximum likelihood estimation problem by iteratively optimizing Doppler shift, time delay, as well as the frequency-domain amplitudes on multiple sub-bands. Simulation results demonstrate that the proposed wideband signal processing method significantly outperforms the traditional narrowband signal processing approaches in terms of velocity and range estimation accuracy, especially with high SNR and proper sub-band division.

   17. Multi-UAV Cooperative Search for Moving Targets: A Deep Reinforcement Learning Method

       Xueying Qian, Gaoqing Shen, Lei Lei, Yufeng Chen

       Abstract

       Unmanned aerial vehicles (UAVs), due to their affordability and flexibility, are extensively utilized in target search tasks. However, the complexity and scale of search task search scenarios pose challenges for multi-UAV cooperative search of moving targets. This paper establishes a system model for multi-UAV cooperative search of moving targets to address these challenges. At the same time, the detection performance of the sensor varies with the altitude of the UAV, which is usually ignored in previous studies. A new target probability map update method, based on a revisit time compensation mechanism, is proposed to enhance the UAVs’ ability to capture moving targets. Subsequently, a height-hierarchical adaptive multi-agent deep reinforcement learning algorithm (HHARL) is introduced, allowing UAV swarms to adapt to sensor performance changes and environmental conditions, while also developing an optimized and dynamic search strategy. Finally, a series of experimental results verify the effectiveness of the proposed HHARL algorithm.

   18. Measurements and Characterization for Vehicle-to-Infrastructure Channels in Urban Scenarios at 5.9 GHz

       Fangzhou Ye, Mi Yang, Bo Ai, Yi Gong, Xuejian Zhang, Shuaiqi Gao, Chenlong Wang, Ruisi He

       Abstract

       Globally, the 5.9 GHz frequency band is widely adopted for Internet of Vehicles (IoV) applications. This paper presents V2I channel measurements at 5.9 GHz in urban environments. Using measurement data, we extract key channel characteristics, including large-scale and small-scale fading. We analyzed statistical properties of these parameters and compared the effects of different transmitter antenna heights on channel characteristics. The results show that as antenna height increases, path loss decreases and multipath effects weaken, but reflections and interference from buildings become more significant. The findings of this paper are valuable for designing and optimizing communication systems, particularly in determining optimal base station heights in urban environments.

   19. Outage Probability of ASTARS-NOMA Uplink Networks

       Xinning Guo, Xinwei Yue, Hongxu Jin, Xianli Gong, Peng Yang

       Abstract

       The active simultaneously transmitting and reflecting surface (ASTARS) has attracted significant academic interest for its ability to alleviate multiplicative fading and reshape the full-space electromagnetic environment. In this paper, we propose to use ASTARS to support non-orthogonal multiple access (NOMA) in uplink communications. By considering both perfect and imperfect successive interference cancellation (pSIC/ipSIC), we establish novel closed-form and asymptotic expressions for the outage probability in ASTARS-NOMA uplink network. Additionally, the system throughput of ASTARS-NOMA uplink networks is evaluated under delay-limited transmission mode.Numerical results indicate that: (i) The outage probability of ASTARS-NOMA uplink networks is superior to that of ASTARS-assisted orthogonal multiple access (OMA) uplink networks, and (ii) The system throughput of ASTARS-NOMA uplink networks exceeds that of other benchmark schemes.

   20. Dynamic 3-Dimensional Deployment of Unmanned Aerial Vehicle Base Stations in Indoor-Outdoor-Hybrid Urban Scenarios

       Lin Cheng, Wenjun Wu, Zhiqiang Dan, Yang Sun

       Abstract

       To extend the coverage of traditional terrestrial communication networks and serve more diverse application scenarios, employing unmanned aerial vehicles (UAV) as aerial base stations has emerged as a viable solution. However, due to the mobility of users and the dynamic nature of UAV base stations (UAV-BSs), the optimal UAV-BS deployment problem is dynamic and complex. In this paper, the dynamic location adjustment problem of UAV-BS in an urban scenario is studied. At each time step, the locations adjustment problem is modeled as a particle swarm optimization (PSO) problem, in which the position of a particle represents a specific value of change in locations of all the UAV-BSs. The improved particle swarm optimization (IPSO) algorithm incorporating simulated annealing principle is adopted to search for the better positions of particles, and then, the locations of UAV-BSs are dynamically adjusted to improve the communication quality. The movement of users and the complex wireless channel in urban scenario are simulated. Results show that the proposed PSO model and the IPSO algorithm can effectively achieve dynamic deployment of UAV-BS. The proposed algorithm exhibits superior performance in practice.

   21. Distance Difference Prediction-Based V2V Multicast Cluster Transmission Mechanism Using Interacting Multiple Model Kalman Filter

       Chunze Jia, Peng Wang, Yufang Zhang, Ruyu Xu, Chen Chen, Zhigang Lv, Mianmian Dong

       Abstract

       In Vehicular Ad-hoc Networks (VANETs), increasing service demand complicates vehicle network control. Clustering management simplifies this control and enhances spectrum resource utilization. This paper introduces a distance difference prediction-based Vehicle-to-Vehicle (V2V) multicast cluster transmission mechanism using an interacting multiple model Kalman filter, termed DP-IMMK. It predicts distance differences between vehicles by considering three distinct movement statuses and clusters vehicles based on V2V transmission distance and multicast performance. Information is transmitted within clusters via V2V multicast, and cluster maintenance is managed by setting clustering factors and predicting vehicle movement statuses. Simulation results indicate a prediction error of less than 1.81%. Compared to geographical static clustering algorithms, this mechanism improves system energy efficiency by 23.61%.

   22. DRASN-DynaRose Attack Surface Management for Network Security Analysis and Enforcement

       Zuojun Dai, Xuesong Wang, Yuping Wang, Shiqian Wang

       Abstract

       Enterprises face increasingly cybersecurity challenges due to expanding digital infrastructures and complex IT environments. Existing attack surface management methods lack practical method and fail to account for asset importance, and are insufficient as guidance on cybersecurity efforts. To address this issue, we propose the DynaRose Attack Surface Management (DRASM) framework. Firstly in DRASM, a practical asset vulnerability priority rating method, DynaRose Vulnerability Priority Rating (DRVPR) that considers exploitability and cumulative vulnerability effects without requiring extensive data, is proposed. Secondly, we introduced an attack impacting assessment method based on asset value, allowing impact assessments from the asset owner's perspective. Furthermore, an objective attack surface scoring method for enterprise networks is developed, along with attack surface reduction methods considering budget constraints. Simulation results demonstrate that the proposed methods effectively reduce the attack surface and enhance network security with limited budgets. The DRASM offers a comprehensive framework for enterprises to assess and mitigate risks, aligning security efforts with asset value and operational priorities.

   23. Research and Application of Satellite Communication Intelligent Scheduling System Based on Work Order Management

       Yuan Zhang, Tong Lin, Pengfei Xie, Tao Wei, Tong Gao, Wenzhi Si

       Abstract

       With the increasing demand for satellite communication in emergency rescue, important activities, and remote areas, traditional satellite communication link scheduling methods are unable to meet the requirements of rapid response and efficient resource utilization. This study proposes an intelligent satellite communication scheduling system based on work order management. This system combines automated intelligent scheduling algorithms with work order management technology, which can accurately schedule resources and achieve rapid dynamic adjustment of satellite communication links to ensure communication stability and efficiency.

   24. Ultra-Accurate Terahertz Indoor Localization with User Micro-mobility

       Yanran Sun, Chuang Yang, Renzhi Yuan, Mugen Peng

       Abstract

       With the development of the sixth generation (6G) of wireless cellular systems, localization-based service has obtained more and more attention. Terahertz (THz) band with its ultra-broad bandwidth can provide low latency and centimeter-level high accuracy for indoor localization. In the meanwhile, with its narrow beam intrinsic property, the performance of the THz system will be highly affected by user micro-mobility such as shakes and rotations, which means the original THz localization methods may all fail without consideration of micro-mobility. To solve the problem, in this work, we proposed an ultra-accuracy THz indoor localization method, by adding the user equipment (UE) micro-mobility model to the original CSI-based localization model. Simulation results show that our methods provided a better localization performance, and the accuracy is within 5cm. With a new angle measurement, the localization system can reflect the real-time position and direction of the control unit in the scenario of industrial Internet-of-Things (IoT).

   25. Joint Transceiver Beamforming Design for UAV-Assisted Full-Duplex ISAC

       Yuanshuo Gang, Yuexia Zhang

       Abstract

       Unmanned aerial vehicle (UAV) has become ideal platform for integrated sensing and communication (ISAC) due to its low-cost deployment and strong line-of-sight capabilities, meeting the demands for high-quality communication and precise sensing in 6G wireless networks. However, the beamforming design in UAV-assisted ISAC system suffers due to the half-duplex (HD) communication mode, leading to reduced system efficiency. To address this issue, this paper studies a UAV-assisted full-duplex (FD) ISAC system. This system utilizes a dual FD communication and radar transceiver architecture at the UAV, not only allowing it to reuse the same time and frequency resources for communication with both uplink (UL) and downlink (DL) users but also enabling it to detect target and process echo signal, aiming to maximize the transmission sum rate for both UL and DL users. Furthermore, a joint transceiver beamforming design algorithm is proposed. Initially, an equivalent communication model for sensing SINR is derived to establish its rate expression. Subsequently, an augmented weighted minimum mean squared error method is used to iteratively solve the problem through alternating iterations. Simulation results demonstrate that, compared to traditional HD ISAC, FD ISAC can effectively enhance the rate performance.

   26. A Multi-bit Flipping Algorithm of Polar Code Based on Dynamic Flipping Matrix

       Shuguang Liu, Xiaowen Han, Junshuo Huo, Xiaojun Zhang

       Abstract

       The belief propagation (BP) algorithm is inherently parallel with low latency. Nevertheless, especially in high SNR, the error correction capability of BP is uncompetitive. To lower the block error rate (BLER), this study proposes a multi-bit flipping algorithm based on dynamic flipping matrix. The polarized channel’s transmission error probability is analyzed and the most unreliable channels are chosen as the static flipping positions. When conventional BP decoding encounters failure, We determine the dynamic positions by selecting the log-likelihood ratio (LLR) with the smallest absolute value. Finally we combine the static positions and dynamic positions to construct a dynamic flipping matrix. The numerical results show that compared with the bit-flipping BP (BFBP)-CS-\({\omega ^3}\), with the assistance of the dynamic flipping matrix, the proposed bit-flipping BP has a performance gain of 0.13 dB at BLER \( = \) \( {10^{-3}}\). Compared with the BFBP-CS-\({\omega ^2}\), the complexity is reduced by 22.27% at Eb/N0\( = \)3 dB.

   27. Research on UAV Attitude Adjustment Strategy for Forest Fire Monitoring

       Yongju Xian, Wenguang Tan, Xiaobo Zhou, Wenbo Wang

       Abstract

       UAV has been widely used in forest fire monitoring because of its small size, simple structure and simple operation. Due to the complex environment in the forest fire scene, the UAV needs to make attitude adjustment to reduce the influence of these factors when performing tasks. Meanwhile, the optimization of energy consumption should be considered due to the limited carrying energy of the UAV. Therefore, this paper discusses the UAV attitude adjustment strategy based on energy consumption optimization in the forest fire scene, establishes the UAV energy consumption model, and puts forward the energy model optimization problem combined with the UAV attitude adjustment. The optimization problem is transformed into Markov decision process, and the Deep Q network (DQN) enhancement algorithm is used to realize the effective attitude adjustment of UAV. The simulation results show that the proposed scheme can effectively realize the UAV monitoring task under the circumstance of forest fire environment with limited energy.

   28. Metamaterial Inspired Millimeter-Wave Antenna Arrays for 5G Wireless Applications

       Moti Beyene Gole, Isayiyas Nigatu Tiba, Zenebe Melesew Yetneberk, Mulugeta Tegegn Gemeda, Tong-Xing Zheng

       Abstract

       Fifth-generation (5G) wireless communication systems utilize millimeter-wave (mm-wave) frequency bands to achieve high data rate transmission. To meet stringent system requirements, high-performance antenna arrays are essential. This paper proposes and analyzes the design and performance of single-element, \(2\times 1\), and \(4\times 1\) metamaterial-inspired millimeter-wave antenna (MIA) arrays. The antennas are designed using Rogers 5880 substrate with a dielectric constant of 2.2 and a thickness of 0.35 mm, optimized for a center frequency of 38 GHz. The simulated performance metrics for the single, \(2\times 1\), and \(4\times 1\) MIA arrays include return loss (−82.95 dB, −67.1 dB, −69.12 dB), bandwidth (1.971 GHz, 2.278 GHz, 4.704 GHz), gain (7.36 dBi, 9.11 dBi, 11.4 dBi), and total efficiency (95.55%, 94.01%, 95.87%). Compared to previous designs, this work shows improved performance through metamaterial integration on both the radiator and ground plane of microstrip patch antennas (MPAs). This metamaterial configuration enhances fringing fields at the MPA edges, improving radiation efficiency and reducing surface wave loss. The proposed MIA arrays address limitations of traditional MPAs, making them well-suited for 5G communication demands.

   29. mmWave-Based High-Capacity Beam Management in UAV-Aided Maritime Communication Networks

       Xueyan Cao, Jun Cui, Fei Xu

       Abstract

       Unmanned aerial vehicle (UAV)-aided maritime communication networks (MCNs) face low throughput and transmission efficiency challenges. We first characterize a millimeter wave (mmWave) UAV-aided MCN to enhance network performance and implement dynamic beam management to address device mobility and time-varying channels. We propose a small-timescale mmWave beamforming sub-problem utilizing a normalized least mean square adaptable beamforming scheme to capacity maximization alongside a large-timescale beam tracking sub-problem that integrates a Kalman filter for state prediction and a non-blind minimum variance distortionless response algorithm for beam reconstruction. Numerical results demonstrate the effectiveness of mmWave beamforming in enhancing capacity, improving mobility prediction, and optimizing joint dynamic beam management.

   30. Equivalent Modeling and Impedance Characteristics of RS-485 Interface Circuit Under Pulse Conditions

       Jian Huang, Jiarun Lu

       Abstract

       RS-485 as a widely used serial communication interface, the current research mainly focuses on the level of serial communication, and the impedance characteristics of the interface circuit are seldom studied. Based on the physical characteristics of RS-485 interface, this paper establishes an equivalent circuit model under high-altitude electromagnetic pulse (HEMP) coupling by analyzing the circuit composition and coupling mechanism of the normal signal circuit of RS-485 interface circuit and the signal circuit under HEMP coupling. Moreover, the port voltage and current of the RS-485 interface under the coupling of the pulse source and HEMP are obtained respectively through experiments. Combined with the Space simulation model, the real equivalent impedance of the signal circuit under HEMP coupling is finally obtained by adjusting the values of resistance, capacitance and inductance, which provides a reference for determining the equivalent impedance of various serial communication interface circuits. Lay the foundation for subsequent protective measures .

   31. Mine Safety Monitoring System Based on EtherCAT Communication

       Jianfei Li, Yue Fan, Fuyu Zhou, Zongmin Zhao

       Abstract

       In modern industrial and mining environments, real-time monitoring systems are crucial for ensuring safety and improving efficiency. However, traditional communication methods are often affected by interference, long-distance transmission, and latency, which impact data stability and reliability. To address these issues, this paper proposes an EtherCAT-based master–slave field monitoring system designed for mine environments. The system provides a more efficient solution for real-time data transmission by implementing a mine-specific EtherCAT data transmission protocol. The slave hardware is based on the STM32F405 microcontroller, which reduces development costs and deployment difficulty. The master system software is developed using TwinCAT software to leverage the high-speed and deterministic communication advantages of EtherCAT, overcoming real-time data transmission challenges in underground environments. Experimental results show that the system significantly improves monitoring response speed and data reliability while reducing power consumption, offering an efficient solution for mine safety.

   32. Lightened, Customize-supported Keyword Spotting on Microcontroller Units

       Zeyu Xiao, Jie Ji, Jinyang Tu, Weijian Xu

       Abstract

       Keyword Sporting (KWS) is an algorithm used to detect specific keywords within audio stream. It is usually adopted to trigger further interactions between users and devices with specific keywords or directly act as an input to directly operating the device. However, the mainstream methods of KWS caused inconvenience or problems to users, such as latency caused by network problem or high cost for calculate device. It turns out to be cost-effective and fast-responded if KWS is able to run on a Microcontroller Unit (MCU), which is network-free and cheaper than commonly-used System on Chips (SoCs). In this paper, we proposed and lightened a convolutional neural network Based on Resnet, lightened the model until it can be successfully deployed on an MCU. Additionally, we adopted Rnnoise speech enhancement algorithm to denoise the input signal, purified the input of network under Mel Frequency Cepstral Coefficient (MFCC) domain, and significantly improved the performance of our model. With only 993.8KiB Flash memory required (needed 4.5MB before model quantization and structure improvement) on STM32H753ZIT6, our model can reach an average of 92.7% with 10 users to record 10 sound files each as input to extract features. The accuracy is even possible to increase further if the number of users is decreased.

   33. Trajectory Planning for UAV Data Collection in Forest Fire Scenarios

       Yongju Xian, Zhou Wang, Hongzhe Shen

       Abstract

       The rapid development of unmanned aerial vehicle (UAV) technology has greatly expanded the application scope of the Internet of Things (IoT). Particularly, within forest fire scenarios characterized by the absence of communication infrastructure, the lifespan of ground nodes becomes unpredictable, and the operational environment for UAV becomes increasingly challenging and complex. It is imperative to adopt a trajectory planning methodology for UAV data collection missions, which not only facilitates prompt data acquisition but also ensures the operational safety of the UAV. In response to these challenges, this paper introduces the concept of unit data value for nodes and presents a trajectory planning algorithm for UAV data collection, grounded in the Double Deep Q-Network (DDQN) framework. The primary objective of this algorithm is to maximize the value of the data gathered during the UAV's flight cycle, while simultaneously ensuring the promptness of data acquisition and optimizing the UAV's flight trajectory for safety. In comparison with the baseline algorithms, namely Dueling DQN and DDQN, the novel approach presented in this study demonstrates substantial enhancements in performance across multiple dimensions, including convergence speed, overall data collection efficiency, success rate in planning safe trajectories, and rate of collecting high-value data.

   34. Virtual Beacon Assisted Visible Light Positioning Algorithm Based on Multi-antenna

       Jiangyi Hao, Yang Yang, Zhiyu Zhu, Wuxia Hu, Wenxuan Pan

       Abstract

       Visible light positioning (VLP) is known for its high positioning accuracy and low cost. However, traditional VLP systems typically require multiple light-emitting diode (LED) beacons for accurate location estimation, which limits their application, especially in scenarios with sparse LED layouts. This paper proposes a virtual beacon-assisted VLP (VB-VLP) algorithm based on multi-antenna. To tackle the challenges mentioned before, one of the beacons is implemented as a virtual beacon, and a camera is utilized for enhanced accuracy in locating the target. In this system, several LED beacons are installed in the ceiling, and a user equipped with a camera attempts to determine their position by capturing images of these LED beacons. VB-VLP consists of an offline virtual beacon construction stage and an online localization stage. During the online stage, a positioning algorithm effectively matches real-time visual information with the virtual beacon to achieve accurate localization. Simulation results indicate that VB-VLP can achieve a positioning accuracy of 91% within approximately 10 cm. Moreover, VB-VLP demonstrates robust performance across various LED radii and levels of pixel noise.

   35. Simultaneous Signal and Energy Transfer Mechanism for Near-Field Magnetic Induction Communication Based on SWIPT Time Switching

       Jiahao Ge, Yufang Zhang, Peng Wang, Xinhang Lu, Haoqi Wei, Chen Chen

       Abstract

       In high-conductivity media, near-field magnetic information transmission exhibits the advantages of low loss and strong anti-interference capability. Based on this advantage, this paper proposes a Near-Field Simultaneous Wireless Information and Power Transfer (NF-SWIPT) system. Using a time-switching SWIPT method, the system achieves simultaneous information and power transfer via the magnetic field. Simulations show that when the signal-to-noise ratio (SNR) is 35 dB, the NF-SWIPT system increases bandwidth efficiency by a factor of six and improves energy transmission efficiency by \(10^4\) times compared to traditional electromagnetic wave-based SWIPT systems.

   36. Research on Integrated Sensing and Communication Continuous Networking and Interference Solution

       Yongli Zhang, Jianfeng Wei, Wei Deng, Li Zhang, Liang Liu, Wufeng Kong, Jinghua Kuang, Hanning Wang, Yahui Xue

       Abstract

       Integrated Sensing and Communication (ISAC) is a mobile communication network superimposed on sensing capability that senses the position and speed of a moving target while performing communication. Compared with the traditional radar, ISAC has the advantages of ubiquity, seamlessness, and scale, and has been identified by international organizations as one of the three new core capabilities of 5G-A/6G, which can be used in many scenarios, such as the national low-altitude economy, security management, and social governance. Nevertheless, in the process of engineering from theory, ISAC still faces many challenges, how to realize the continuous coverage of the communication and sensing, and how to improve the performance of the network under the complex interference environment are the difficult problems that need to be solved urgently. In this paper, we start from the link difference between sensing and communication network, give the link budget theoretical formula of sensing network, further analyze the interference sources and characteristics of sensing network, and put forward the low-cost continuous coverage network structure as well as the interference solution, and finally give the preliminary validation results of the field test, so as to provide the theoretical basis and practical guidance for the further development of the sensing network technology and industry.

   37. Greedy Belief Propagation Algorithm for Low-Complexity LDPC Decoding

       Yimo Zhen, Jinhui Chen, Zhan Xu, Ruxin Zhi

       Abstract

       In this paper, we propose a greedy belief propagation (BP) algorithm in LDPC (Low Density Parity Check) decoding for reducing processing complexity at mobile terminals. In this algorithm, we implement the greedy algorithm in BP decoding for the optimization procedure. Its performance is evaluated and compared with the conventional BP algorithm in terms of mean bit error rate and average time per iteration. Our simulation results show that its performance is close to that of the conventional BP algorithm while its complexity is lower. The greedy BP algorithm can be used for cost and power consumption reduction at mobile terminals, which would be helpful for mobile IoT (Internet of Things) networks.

   38. Interference Characterization for Cooperative ISAC Cellular Networks

       Xiaozhou Zhang, Lincong Han, Yahui Xue, Jing Dong, Jing Jin, Qixing Wang

       Abstract

       This paper characterizes the inter-base station interference of cooperative integrated sensing and communication (ISAC), which is considered as one of the key technologies in the sixth-generation mobile communication system (6G). First, a cooperative ISAC cellular system model is presented. Then, the inter-base station interference is analyzed and evaluated for two types of sensing targets. Based on the evaluation results, the principle for the interference management due with the inter-base station interference that suits for high frequency and low frequency systems is respectively proposed to ensure high detection probability and improve sensing accuracy. A ring networking scheme is proposed to further improve the sensing accuracy. The performances are verified through simulations.

   39. Beamforming Design for SWIPT Internet of Vehicle Aided by IRS

       Yuanyuan Gu, Lei Zhang, Yu Wang, Siqi Bi, Zhongfang Hu, Desheng Wang

       Abstract

       This paper studies a joint active and passive beamforming design method of IRS-assisted MISO downlink vehicular-SWIPT communication system. To maximize the received energy of the vehicle terminal, the optimization is subject to constraints on total transmit power, signal to interference plus noise ratio (SINR), and IRS phase shift. The resulting non-convex optimization problem with coupled variables, is addressed through an alternate iterative approach that employs semidefinite relaxation and first-order Taylor expansion. The results demonstrate significant performance improvement with the proposed algorithm over the benchmark methods.

   40. Low Complexity Optimized LLR-BP Algorithm for LDPC-Hadamard Codes

       Xiaoyu Zhang, Jiachi Li, Zehao Li, Lichun Yang, Yi Gong, Zhan Xu

       Abstract

       Low-Density Parity-Check (LDPC) codes are critical for enhancing error correction in communication systems, making them a key enabler of reliable, high-speed data transmission, and a foundational technology in the development of the 6th Generation Mobile Communication Technology (6G) networks. However, traditional LDPC codes exhibit reduced error-correction efficiency in highly noisy or complex communication environments, especially at very low Signal-to-Noise Ratio (SNR). This paper proposes a low code rate scheme using LDPC-Hadamard codes, with Hadamard code constraints imposed at the check nodes. A Progressive Edge-Growth (PEG) algorithm is employed to simplify the coding process. Additionally, this paper proposes the Log-Likelihood Ratio Belief Propagation (LLR-BP) algorithm to reduce the computational complexity of the decoding process. Simulation results indicate that LDPC codes achieve a Bit Error Rate (BER) of \(10^{-5}\) at a lower SNR of \(0.3\,\text {dB}\), in contrast to LDPC-Hadamard codes, which require an SNR of \(-0.2\,\text {dB}\). The results demonstrate the performance improvement of LDPC-Hadamard codes in BPSK modulation is \(0.5\,\text {dB}\) superior than that of LDPC codes.

   41. AI Enhanced Communication and Computing Based on Cache-at-RIS Systems

       Zhenjiang Li

       Abstract

       Reconfigurable Intelligent Surfaces (RIS) represent a breakthrough in wireless communication, enhancing signal quality and network coverage through intelligent wave manipulation. However, traditional RIS systems face challenges in dynamic environments and high-latency scenarios. This study introduces a novel Cache-at-RIS framework, integrating caching capabilities with a Transformer-based predictive caching mechanism. The Transformer model leverages its self-attention mechanism to analyze user request patterns, accurately predicting future demands and optimizing cache management. By dynamically adjusting RIS parameters and preloading frequently requested data, the framework significantly reduces latency and improves achievable rates, particularly in high-frequency bands and dense user environments. Key findings demonstrate the superiority of Cache-at-RIS in supporting ultra-low latency applications, such as AR/VR and autonomous driving, while also reducing energy consumption. This work advances the integration of intelligent communication and edge computing, offering a scalable and efficient solution for next-generation 6G networks.

   42. A Semantic Communication-Based Video Conferencing System

       Qi Wang, Caili Guo, Chuanhong Liu, Zirui Guo, Yang Yang

       Abstract

       In recent years, the surge in demand for remote work has increased the bandwidth requirements of video conferencing systems. While conventional video encoding standards perform well in high bandwidth environments, their quality and performance degrade significantly in low bandwidth and low bit rate conditions. To address this issue, semantic communication technology can be introduced, which reduces bandwidth demand by extracting and transmitting the semantic information of the video. Although extensive theoretical research has been conducted on semantic feature extraction and reconstruction for video, existing methods struggle with poor reconstruction quality during large head movements in practical applications. In this paper, we propose a semantic communication-based video conferencing system that improves the user experience in practical applications by introducing a preprocessing mechanism for video frames with large head pose. Additionally, we design and implement a testing platform to validate the system’s performance. First, we develop the system model and design a preprocessing module for video frames with large head pose. Then, we build a testing platform and conduct performance evaluations on the proposed system. Experimental results demonstrate that the proposed system successfully resolves the poor reconstruction issue during head movements in semantic video conferencing, while reducing the average bandwidth requirements by three-quarters compared to traditional video conferencing solutions .

   43. Large Scale Model-Aided Digital MIMO Semantic Communication in Smart Grid

       Ruchao Tan, Tian Cai, Hua Wang, Hui Xiao, Jianjun Xu, Xin Tu

       Abstract

       The significant increase in data volume generated by smart grid devices presents challenges for traditional power grid communication systems. Semantic communication offers a promising approach by extracting relevant features from the source information. However, existing large-scale model-based semantic communication systems often overlook the common MIMO channel conditions prevalent in power grid environments. To address this issue, we propose a Large Scale Model-aided Digital MIMO semantic communication system in Smart Grid (LSM-MIMO-SCSG), where the transmitter utilizes the LSM as the semantic encoder to extract domain-specific knowledge for smart grid applications and a semantic decoder is performed to accomplish smart grid task. Besides, a robust compression mechanism using vector quantization through the MIMO channel is proposed to quantize the extracted features into indices with a pretrained codebook. To optimize the semantic encoder/decoder and codebook design, a two-stage training strategy on a smart grid fault classification dataset is proposed. Experimental results show that our proposed LSM-MIMO-SCSG can achieve 34.92% classification accuracy and reduce 99.56% transmission symbols at most compared with the traditional methods.

   44. Evolutionary-Based Adaptive Clustered Federated Learning for Wireless Traffic Prediction

       Ziyi Li, Yuchen Zhuang, Yu Wang, Yanlin Fan, Shangjing Lin, Lei Sun, Zhongbo Bi

       Abstract

       Wireless traffic prediction is of great significance to operators in network construction, wireless resources management and user experiences improvement. We develop a hierarchical clustered Federated Learning (FL) framework for wireless traffic prediction. Base stations with similar traffic distributions are grouped into clusters. Within each cluster, the central server continues to form sub-clusters which helps in mitigating the impact of non-IID data by addressing it within more homogeneous clusters. Furthermore, the sub-cluster formation process is modeled as an optimal federation formation problem, which is a NP-hard problem. The evolutionary-based heuristic approach (PSO-GA) are proposed to search for the intra-cluster optimal federation structures (including the number of the federations, as well as the members in each federations). Extensive experiments are conducted using real-world mobile traffic dataset to show that the two evolutionary-based FL outperforms previous state-of-the-art methods in terms of convergence rate as well as prediction accuracy.

   45. Collaborate Heterogeneous Resource Scheduling for AI Inference Based on Distributed Model Training in ECFN Enabled NG-RAN

       Chonghan Zhou, Xin Wang, Jing Jiang

       Abstract

       As demand for artificial intelligence (AI) inference surges, traditional networks face significant challenges in computational and bandwidth resources. AI inference based on distributed model training can leverage parallel computing across multiple nodes to enhance training efficiency and model performance for subsequent real-time and accurate AI inference tasks. This paper mainly focuses on the collaborative scheduling issue of heterogeneous resources for AI inference services in Edge Computing First Network (ECFN) enabled NG-RAN. To address the issue, a mathematical model is proposed with the goal of minimizing transmission bandwidth usage rate, computing resource usage rate, backlog of AI inference subtasks, while maximizing the number of successfully sent AI inference subtasks. Moreover, we develop a heuristic algorithm called collaborate heterogeneous resource scheduling algorithm based on greedy strategy (CHRS-GS) in an efficient manner. Simulation results demonstrate that our proposed heuristic algorithm surpasses benchmark methods significantly achieving better performance in resource utilization, service success rates, and backlog minimization, reducing 21.4% joint optimization objectives, and approaching the optimal solution with an error of 3.1%.

   46. Satellite Semantic Communication MIMO System for Smart Grids

       Ruchao Tan, Tian Cai, Ziyang Xiao, Qiang Liu, Delin Fu, Jun Lan

       Abstract

       The integration of renewable energy sources into smart grids has accelerated their evolution towards greater intelligence. However, as grids expand, traditional terrestrial communication networks face significant challenges, especially in remote areas with poor coverage. Satellite communication offers a potential solution but is limited by bandwidth and real-world channel conditions, such as Multiple-Input Multiple-Output (MIMO) channels. To address these issues, we propose a Satellite Semantic Communication MIMO system for Smart Grids (SSC-MIMO-SG). This system leverages the BeiDou satellite’s Regional Short Message Communication (RSMC) and a DNN-based semantic encoder to efficiently compress image data, reducing bandwidth usage. The system’s end-to-end training adapts semantic features to BD satellite MIMO channels, improving transmission reliability. Experimental results demonstrate that, compared to traditional methods, SSC-MIMO-SG significantly enhances PSNR performance under low SNR conditions, while both methods exhibit similar PSNR performance under high SNR conditions; MS-SSIM is improved by 28.53%; data transmission volume is increased by 71.43%; and communication latency is reduced by 88.47%.

   47. Study on the Generation of APD Received Optical Signal Under Turbulence Disturbance with Exponential Weibull Distribution

       Xiaoying Ding, Xin Zhao, Xinyao Wang, Chenyan Shu

       Abstract

       In order to analyze the performance of atmospheric optical communication systems under aperture averaging effect by Monte Carlo, a method is proposed to simulate the received optical signal of exponential Weibull distribution APD with specified temporal autocorrelation affected by turbulent disturbance. This method first uses the autoregressive (AR) model to generate Gaussian random samples with specified time autocorrelation characteristics, and then uses the inverse transformation method to convert these autocorrelated Gaussian random samples into random samples that obey the APD exponential Weibull distribution. Through simulation experiments, we found that the generated signal matches the specified time autocorrelation function in terms of time autocorrelation performance. The simulation results show that the proposed method can effectively simulate the time-domain optical signal received by the APD with exponential Weibull distribution affected by turbulence disturbance.

   48. Robust Identification of Communication Radiation Source Individuals Based on Transfer Learning

       Xingyuan Han, Jiayi Yao, Bowei Liang, Jiawen Chen, Ziyi Yang, Dawei Chen, Xuhui Ding

       Abstract

       This paper proposes a transfer learning-based communication radiation source individual identification algorithm to mitigate the practical limitations of deep learning-based communication radiation source identification technology and address the performance degradation of deep learning networks in complex and dynamic electromagnetic environments. This algorithm constructs a new metric function founded on feature fusion and designs a subdomain alignment loss function to quantify the discrepancy in the distribution of source and target domain data in the feature space. By integrating the subdomain alignment loss function into the network training process, this method can effectively reduce the variability in the data distribution. Furthermore, a transfer learning strategy based on the model parameters is introduced to accelerate the training process of the model. The experimental results demonstrate that the proposed algorithm exhibits superior classification performance.

   49. Frequency Detection of Crossing Fresnel Boundaries Based on IoT Signals

       Yan Wang, Hui Zhao, Zhiwei Yu, Peng Wang

       Abstract

       The Fresnel zone has been critical in advancing Integrated Sensing and Communication technologies, significantly enhancing the accuracy of observing changes in Non-Line-of-Sight paths. With the widespread deployment of Internet of Things (IoT) devices, leveraging IoT signals in conjunction with the Fresnel zone for sensing research has become increasingly feasible. As a result, this paper proposes an Enhanced channel estimation and Channel impulse response-based Fresnel boundary crossing frequency Estimation (ECFE) method based on IoT signals. This approach focuses on improving sensing performance in IoT scenarios. The repetitive transmission characteristics of IoT signals are leveraged to enhance the accuracy of Channel State Information estimation. The narrow bandwidth of IoT signals allows for more precise monitoring of channel dynamics from the Channel Impulse Response perspective, and integrating information across all subcarriers further improves the accuracy of dynamic path change detection. Simulation results demonstrate that the ECFE method performs robustly under various Signal-to-Noise Ratio conditions, providing reliable Fresnel Boundary Crossing Frequency estimation. This method shows significant potential for IoT applications, providing more reliable prior information for tasks such as path prediction and object localization.

   50. Multi-loss Learning Based Residual Convolutional Recurrent Neural Network for Automatic Modulation Classification

       Shuo Chang, Sai Huang, Zheng Yang, Weiwei Jiang, Han Zhang, Shaoshuai Fan

       Abstract

       Automatic Modulation Classification (AMC) is to recognize the modulation type of received signal, which can be used to ensure the wireless security. In this paper, a residual convolutional recurrent neural network (RCRNN) is proposed to make classification, where two cues amplitude/phase (AP) and in-phase/quadrature (IQ) are used together, which has a better classification performance than using only one of them. In addition, a novel shrinkage loss is utilized to optimize distances among different modulations, where the inner products of intra-class are increased with respect to inter-class. Numerical results suggest that our proposed method has made a superior performance.

   51. Joint Beamforming and Power Allocation Technology in Integrated Terrestrial-Satellite Network

       Weidong Xue, Liang Han, Qian Xiong, Yingqi Yang, Shici Li, Lin Zhang

       Abstract

       This work investigates the joint beamforming and power allocation scheme of terrestrial-satellite network in high-speed railway scenario, where, base stations (BS) and satellite work together to provide universally available communication service for ground users. Firstly, based on the historical travel information of high-speed railway, such as deterministic direction, known speed, and predictable trajectory, we propose a phase-based beamforming design to compensate for the Doppler effect and improve the system total capacity performance. Combing the phase-based beamforming design with the BS’s maximum ratio transmission (MRT) beamforming and the satellite’s zero forcing beamforming (ZFBF). Secondly, considering the performance of the satellite, we maximize the overall system capacity, ensuring compliance with the satellite's baseline capacity requirements. Then Lagrange sub-gradient joint power allocation algorithm is derived to improve the users’ signal-to-noise ratio (SNR) and maximize the total system capacity. Finally, the effectiveness of the proposed algorithm is assessed through simulation-based validation. The simulation outcomes substantiate that, in comparison to the greedy algorithm, the power allocation strategy introduced in this study enhances the system capacity by approximately 25% .

   52. Optimizing Movable Time Modulated Arrays for Low Radar Cross Section

       Yue Ma, Kefeng Guo, Ruiqian Ma, Zhi Lin, Ruoyu Zhang, Wen Wu

       Abstract

       For radar systems, minimizing the radar cross section (RCS) of the antenna diminishes the likelihood of its detection by adversaries. In this paper, we investigate the movable time modulated array (MTMA) and propose an optimization method that effectively reduces the RCS while ensuring the beamwidth and sidelobe level (SLL). Genetic algorithms with a novel parameter updating strategies are used to solve the optimization problem. The on/off time of the RF switch of the MTMA as well as the position of the array element are used as optimization variables. Ultimately, simulation results validate the proposed approach. The findings of the numerical simulations indicate that the proposed method can be utilized to minimize the RCS of the MTMA while ensuring that the beamwidth and SLL performance are maintained.