最新刊期
卷 41 ， 期 6 ， 2025
- 摘要：Artificial intelligence (AI), with its powerful capabilities in reasoning, learning, and self-correction, has become a key technology for addressing complex problems and is widely applied in cutting-edge scientific and technological fields. As the core infrastructure of modern information society, mobile communication networks face increasing challenges in their construction, management, and optimization due to their complexity. The open systems interconnection reference model (OSI-RM), with its layered structure, enables the modularization and standardization of network functions, providing a fundamental theoretical framework for the design and implementation of mobile communication networks and guiding the interoperability of multiple-protocols and multi-device systems. From the perspective of OSI-RM, the current applications of AI technologies across different layers of mobile communication networks were systematically reviewed, and the roles of AI in addressing complex issues in mobile communication networks were analyzed. Furthermore, it was highlighted that some AI technologies demonstrated potential for cross-layer applications, breaking the limitations of single-layer approaches, and offering new directions for advancing the research and application of AI in mobile communication networks.关键词：artificial intelligence;OSI-RM;mobile communication8697|8878|0更新时间：2025-06-28
Review
- 摘要：Efficient deep joint source-channel coding (DeepJSCC) is a key technology for enabling semantic communication in band-width-constrained scenarios. However, in resource-limited environments such as vehicular networks or unmanned aerial vehicles, existing methods struggle to adapt to the dynamic characteristics of multiple-input multiple-output (MIMO) channels and are challenging to deploy due to their large model size. To address these issues, a lightweight DeepJSCC framework (VxLJSCC) was proposed. A semantic extraction network based on extended long short-term memory was proposed to achieve a lightweight, high quality semantic feature extraction. Then, MIMO-channel state information (CSI) prediction was employed to address the performance degradation caused by CSI aging in semantic communication systems. Finally, to adapt the semantic information to the time-varying quality of MIMO channels, a channel adaptive module was designed. This module assigns appropriate transmission subchannels and time slots to different features based on their importance, thereby enhancing the semantic accuracy of image reconstruction. Simulation results show that, compared to the best method DeepJSCC-MIMO, VxLJSCC saves up to 61.67% in model storage and 77.86% in computational cost, while still providing up to 2.972 dB channel gain.关键词：joint source-channel coding;semantic communication;channel state information;MIMO;image transmission;feature allocation8494|574|0更新时间：2025-06-28
- 摘要：To address the high Doppler frequency shift and thus achievable rate limitation caused by rapid movement of the train, an orthogonal time frequency space (OTFS) multiple access transmission scheme was proposed based on the delay division multiple access and Doppler division multiple access techniques for the multi-user uplink in high-speed railway scenario. Firstly, a multi-user system model for OTFS multiple access was established based on the high-speed rail scenario. Secondly, the serial interference cancellation was applied to the uplink transmission at the base station to eliminate the interference by using the signal difference between the multiple users and achieve the correct detection of the user signals. Finally, the closed-form expression for the achievable rate was derived based on the mutual information theorem and the nature of the trace operation. Simulation results show that the proposed scheme has better performance of resources allocation and resistance to Doppler shift than the traditional multiple-access transmission scheme, which meets the achievable rate requirement of uplink vehicle-to-infrastructure communication in high-speed scenarios.关键词：OTFS;multi-user;multiple access transmission;achievable rate196|455|0更新时间：2025-06-28
- 摘要：UAV swarm assistance communication system can improve the existing wireless communication network, enhance the system service quality and coverage. However, the open characteristics of wireless channels make drone communication systems extremely vulnerable to eavesdropped by illegal users. A safe communication algorithm for UAVs based on cooperative beamforming was proposed. To maximize the confidentiality of the system, the relative position and energy of each drone in the swarm, as well as the overall movement of the swarm and the beam of the antenna array, were comprehensively considered. Since this optimization problem was characterized by highly coupled non-convex terms, the initial problem was decomposed into two sub-problems and a cyclic iterative successive convex approximation algorithm was designsed to solve it through Taylor expansion and convex relaxation. Simulation results show that the optimization scheme proposed can effectively improve the system confidentiality rate, realize physical layer secure communication, and achieve better results compared with other comparison algorithms.关键词：UAV communication;virtual antenna array;cooperative beamforming;secure communication222|489|0更新时间：2025-06-28
- 摘要：The low earth orbit (LEO) satellite has advantages of the low launch cost, the short transmission delay, the small link loss and the high data rate. But the Doppler effect caused by high-speed satellite and the short TT&C (telemetry, tracking and command) time caused by random service lead to the difficulty of the high-accuracy parameter estimation for spread spectrum signal with large Doppler frequency shift. A high-accuracy parameter estimation algorithm for spread spectrum signal based on interpolated correct pseudo-code phase and carrier frequency was proposed. Firstly, the comparative detection with correlation integral peak and adaptive detection threshold was employed to acquire correlation integral peak/side-peak and its pseudo-code phase/carrier frequency index. Then, the trigonometric geometry relationship of pseudo-code autocorrelation was applied to interpolate the correct pseudo-code phase, and the parabola fitting method of correlation integral peak was used to interpolate the correct carrier frequency. The experiments and analysis verify that the proposed algorithm can achieve the pseudo-code phase estimation accuracy better than 0.05 chip and the carrier frequency estimation accuracy better than 50 Hz with ±25 kHz carrier Doppler frequency shift, and significantly improve the pseudo-code phase and carrier frequency estimation accuracy of high dynamic spread spectrum signal in LEO satellite TT&C systems.关键词：LEO satellite;spread spectrum signal;parameter estimation;interpolated correction;parabola fitting198|474|0更新时间：2025-06-28
- 摘要：In order to solve the problems of large energy consumption, and poor performance gain of RIS in the traditional reconfigurable intelligent surface (RIS)-assisted integrated sensing and communication (ISAC) system, the sub-connected active reconfigurable intelligent surface (ARIS) was considered to be introduced into the ISAC system. The system energy efficiency was maximized by optimizing the beamform for dual-function base station, the phase shift matrix of sub-connected ARIS and the vector of amplification factors for sub-connected ARIS under the user’s minimum signal to interference plus noise ratio and the constraint of radar detection power. An algorithm based on fractional programming (FP) theory, alternating optimization (AO) technique, and successive convex approximation (SCA) technique was proposed to deal with the non-convex problem. The simulation results show that the algorithm has good convergence and the sub-connected ARIS-assisted ISAC system can significantly improve the energy efficiency of the system compared to the fully connected ARIS-assisted ISAC system.关键词：millimeter wave;integrated sensing and communication system;active reconfigurable intelligent surface;sub-connected125|345|0更新时间：2025-06-28
- 摘要：The current unsupervised pedestrian re-identification algorithms using residual networks can only extract rough global features, but it can’t adequately reflect subtle local features. In addition, the pseudo labels generated by clustering methods introduce noise, which will affect the performance of feature discrimination. A dual branch guided contrastive learning method was proposed. Firstly, an effective feature extraction method was introduced, which divided the extracted features into global branches and local branches to improve the utilization of local information. Secondly, the consistency between global and local features was proposed to refine the pseudo labels for global feature prediction, utilizing the complementary relationship between local and global features, thereby effectively reducing the noise generated by pseudo label clustering. Finally, a contrastive learning module was proposed to perform contrastive learning on refined labels and improve the robustness of the model. The experimental results on the Market1501, DukeMTMC-ReID, and MSMT17 datasets validate the effectiveness of the proposed method.关键词：unsupervised pedestrian re-identification;global feature;local feature;label refinement;contrastive learning119|228|0更新时间：2025-06-28
- 摘要：With the advent of the era of big data, the effective representation and analysis of high-level data has become a major challenge. Based on this, the application of tensor decomposition technology in multi-clustering algorithms was focused on especially for the processing of large multi-source heterogeneous datasets. The tensor train (TT) method was studied and improved in depth, which had significantly improved its performance in multi-clustering tasks by introducing a new optimization strategy. The innovations were mainly reflected in two aspects: firstly, a new tensor decomposition framework was proposed, which effectively reduced the storage cost and improved the computational efficiency by optimizing the objective function; secondly, the improved tensor decomposition technique was applied to three main multi-clustering algorithms, including self-weighted multi-view clustering (SwMC), latent multi-view subspace clustering (LMSC), and multi-view subspace clustering with intactness-aware similarity (MSC IAS), which significantly improved the accuracy and efficiency of clustering. To validate the effectiveness of the proposed methodology, comprehensive experiments were conducted on seven real-world datasets, including assessments of key metrics such as accuracy (ACC), normalized mutual information (NMI), and purity. Experimental results show that the proposed method has significant advantages in extracting meaningful patterns and improving clustering performance.关键词：tensor;multi-clustering algorithm;tensor decomposition;multi-source heterogeneous data;principal component analysis209|854|0更新时间：2025-06-28
- 摘要：The development of industrial Internet has greatly improved the digital and intelligent level of industrial enterprises. Industrial data assets have become an increasingly important strategic resource and new production factor. How to ensure the security and credibility of industrial data in the whole life cycle from creation, authorization, sharing and income distribution is the primary problem to be solved at present. To this end, based on the design goal of the industrial data asset value transfer system, a blockchain-based framework for trusted ownership confirmation and value transfer of data assets was proposed, a general framework and specific solution with strong applicability and scalability were constructed, and specific solutions and processes were provided to ensure the trustworthiness and controllability of industrial data assets throughout the entire process of ownership confirmation, access, and revenue sharing in an industrial scenario where data was involved from multiple parties and shared multiple times. To solve the contradiction between security and efficiency, a lightweight trusted blockchain model was proposed, which measured the trustworthiness of nodes based on their behavior and status, and provided a dynamic initial value calculation method for nodes and an overall trust value measurement model for trust management. The consensus protocol algorithm of the blockchain system was optimized based on the trustworthiness of nodes, reducing the probability of malicious attacks on nodes while improving the efficiency of system transaction consensus, achieving security and lightweight parallelism of the entire system. Finally, the superiority of this scheme was verified through simulation experiments.关键词：industrial data sharing;blockchain;asset confirmation;value distribution288|1393|0更新时间：2025-06-28
- 摘要：To address the high complexity of network training and improve speech emotion feature extraction, a dual-branch feature extraction model based on DN-ResNet11 and a channel attention residual network (CRNet) was proposed. Firstly, the low-complexity DN-ResNet11 was designed to efficiently extract fused emotional features from spectrograms, enhancing emotion recognition accuracy. Secondly, multiscale guided filtering and the local binary pattern (LBP) algorithm were incorporated to enhance spectrogram details. Finally, the two sets of features were fused for emotion classification, forming a dual-branch weighted fusion model (weighted fusion model based on dual nested residual and channel residual network, WFDN_CRNet), further enhancing emotional representation ability. Experiments on the CASIA, EMO-DB, and IEMOCAP speech emotion datasets show emotion recognition rates of 94.58%, 85.59%, and 65.72%, respectively. The proposed method not only achieves superior emotion recognition rates compared to baseline models such as ResNet18, but also significantly reduces computational cost, demonstrating the model’s effectiveness.关键词：emotion recognition;dual nested residual network;detail enhancement;weighted fusion224|424|0更新时间：2025-06-28
- 摘要：To improve the accuracy and robustness of influential node recognition in diverse complex networks, a deep learning-based recognition method for influential nodes in diverse complex networks was proposed. Firstly, multiple centrality indexes were utilized to evaluate the importance of network topology from different perspectives, the weight of each index in different complex networks was decided adaptively through the learnable weight vector. Secondly, a new Transformer framework that could handle features of different dimensions was proposed. Finally, the Transformer model was exployed to realize hierarchical aggregation of the neighbor information in different distances, so as to extract the contextual information of the neighborhood. Validation experiments were carried on multiple complex network datasets, the results showed that the proposed method achieved a good recognition performance of influential nodes for the complex networks of different scales and different categories, effectively improving the accuracy and robustness of influential node recognition.关键词：complex network;deep learning;self-attention mechanism;centrality measurement;influential node172|453|0更新时间：2025-06-28
- 摘要：Dynamic scene reconstruction holds significant research value in the fields of computer vision and virtual reality. Recent advancements in neural representation technologies have facilitated rapid progress in this task. Over the past four years, methods based on neural radiance fields and 3D Gaussian splatting have been proposed, achieving remarkable results. However, the large number of literature presents a challenge for individuals to comprehensively track comprehensive relevant works. To address this issue, typical work for dynamic scene reconstruction based on neural representation was summarized, categorizing them into methods based on neural radiance fields and 3D Gaussian splatting. Furthermore, representative datasets were highlighted and common evaluation metrics for algorithms were summarized. Finally, the persistent challenges in current methodologies were discussed and potential directions for future development trends were proposed.关键词：dynamic reconstruction;neural representation;neural radiance field;3D Gaussian splatting505|1976|0更新时间：2025-06-28
Research and Development
- 摘要：With the rapid development of 5G, cloud computing, and edge computing, metropolitan area networks (MANs), as critical hubs connecting users and core networks, face multifaceted challenges in bandwidth, latency, and flexibility. Focusing on the broadband remote access server (BRAS), its evolution from traditional closed hardware architectures to control-plane/user-plane (CU) separation was reviewed, and the technological advancements and advantages of the emerging data processing unit (DPU) network interface cards were explored. In particular, the technical solutions and challenges of implementing the BRAS forwarding plane using DPU-based network cards were analyzed in depth, providing theoretical references for operators to build highly resilient and low-latency next-generation MANs.关键词：BRAS;NFV;DPU network interface card;CU separation184|701|0更新时间：2025-06-28
- 摘要：As the core hub of the power grid system, substations undertake the key task of digital transformation of the power grid. The application of digital twin technology in intelligent substations was explored deeply to improve the efficiency of substation operation and maintenance management and equipment fault diagnosis capabilities. Firstly, the basic concepts and application characteristics of digital twin technology were introduced, and the key business requirements for the application of digital twin technology in substations were analyzed. Secondly, the basic architecture of the digital twin model of the substation was built, and the constituent elements of each level of the model were described. The basic data collected from the substation was pre-processed through a data filtering mechanism, and the 3D modeling of the substation was carried out based on the ground model cluster algorithm. The experimental results show that the proposed method significantly improves the accuracy of 3D modeling in substation business scenarios and enhances modeling efficiency. Meanwhile, the constructed model has demonstrated high reliability in equipment fault diagnosis. The application of digital twin technology in substations can effectively enhance the intelligence level of substations and provide strong support for the digital transformation of the power grid.关键词：substation;digital twin;data collection;3D modeling;accuracy;reliability447|1445|0更新时间：2025-06-28
- 摘要：In the telecommunications industry, repeated customer complaints about unresolved or unsatisfactory issues are a common challenge. Manually generating re-investment reports is not only time-consuming and prone to subjectivity but also fails to meet enterprise demands for efficiency and consistency. To address this issue, an automatic report generation method based on an improved Transformer model was proposed. This method introduced emotion embedding, enabling the model to effectively capture dynamic emotional changes in customer interactions and better understand customer attitudes and demands during the dialogue. Additionally, the incorporation of customized position encoding enhanced the model’s ability to perceive complaint time series information, significantly improving the time logic and detailed completeness of the generated content. Experimental results demonstrate that the proposed model achieves BLEU (bilingual evaluation understudy) and ROUGE (recall-oriented understudy for gisting evaluation) scores of 0.352 and 0.482, respectively, outperforming the original Transformer and other baseline models. Moreover, compared to manual efforts, the proposed model improves work efficiency by 89%. The generated reports not only align more accurately with real-world requirements but also exhibit superior performance in semantic detail and time sequence consistency.关键词：telecom customer service;Transformer;re-complaints report;automatic report generation250|504|0更新时间：2025-06-28
Engineering and Application
- Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
- Total Visits：1035510 Visits Today：3559
0