Computer Networks最新文献

{"title":"SMUSAC: Lightweight federated learning framework for SUNETs with tolerance of data loss and node compromise","authors":"Wenhao Cheng ,&nbsp;Xia Feng ,&nbsp;Liangmin Wang ,&nbsp;Zhan Xie ,&nbsp;Liang Wang ,&nbsp;Siben Tian","doi":"10.1016/j.comnet.2025.111626","DOIUrl":"10.1016/j.comnet.2025.111626","url":null,"abstract":"<div><div>Satellite-Assisted Unmanned-System Networks (SUNETs) are emerging network applications that leverage satellites to support ubiquitous data-driven services, such as autonomous underwater vehicles and unmanned aircraft systems. In these applications, transmitting data over external networks poses a risk of privacy leakage. Usually, federated learning is used to prevent the direct leakage of raw data; however, its effectiveness and robustness in SUNETs are constrained due to two key challenges arising from limited bandwidth and unmanned nodes: (a) <em>data loss</em>, some nodes may fail to transmit data back to the server in time; (b) <em>node compromise</em>, unmanned nodes might be controlled by adversaries, even uploading malicious data to the server. To address these challenges, we propose a lightweight federated learning framework, called SMUSAC, which includes three stages: Sparsifying Model, Uploading Signs, and Aggregating with Compensation. Specifically, we design a sign-based updating mechanism for sparsified models, rather than transmitting model parameters or gradients over the communication link. It improves SMUSAC’s tolerance to data loss and node compromise by relying solely on the sign of updates rather than their specific values, while also reducing bandwidth demands. Additionally, an error-compensation mechanism is employed to mitigate the accuracy loss caused by sparsification. We theoretically analyze the convergence of SMUSAC under a non-convex cost function. Simulation results show that SMUSAC exhibits significant resilience under adverse conditions, maintaining stable performance even with 40% of nodes compromised, and outperforms seven baselines across multiple evaluation metrics.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"271 ","pages":"Article 111626"},"PeriodicalIF":4.6,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144886487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Source identification for worm propagation: A graph neural network approach and evaluation on social network and internet datasets","authors":"Qitao Huo,&nbsp;Peng Zhou","doi":"10.1016/j.comnet.2025.111616","DOIUrl":"10.1016/j.comnet.2025.111616","url":null,"abstract":"<div><div>Source identification plays an essential role in the analysis and forensics of worm propagation but unfortunately is quite challenging to solve due to the limited traces and clues left on the observed propagation graphs. State-of-the-art solutions to source identification are mostly based on unsupervised graph induction and reasoning, hence missing the chances to find more trails from additional origins of information for worm tracing. In this paper, we go beyond unsupervised source identification and make perhaps the first attempt to design a supervised solution, to “borrow” outside information to facilitate the detection of the propagation sources. Our basic idea is to apply a graph neural network (GNN) to learn the additional clues (specifically the node state distributions over the graph structures) from a training set of propagation graph samples whose sources are known in advance, hence able to model the mapping relationship between the different node state distributions and the many different nodes as the sources for propagation. This way, we can wisely convert the unsupervised source identification problem to a supervised classification of propagation graphs with the sources as class labels, thereby tracing back the given worm later guided by the similar propagation behaviors found on the sampled propagation graphs. We understand that the direct use of the GNN model is not quite effective in the condition of large graphs since a large number of nodes should be considered individual class labels for classification and accordingly propose a hierarchical improvement. That is, we cluster the nodes from the large graph into several smaller subgraphs (i.e., communities) and then deploy a set of GNN models through a hierarchical architecture for these subgraphs, hence being able to largely reduce the number of class labels for each of the GNN models over this architecture. To evaluate the effectiveness of our solution, we have run extensive source identification experiments using the worm propagation graphs simulated from both the synthetic and social network and Internet datasets. Our results have successfully confirmed a higher identification accuracy (in terms of the length of the shortest path from the identified source to the true one) by our supervised solution compared with the competing counterparts. For the best case, we can improve the identification accuracy up to ten times the magnitude.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"271 ","pages":"Article 111616"},"PeriodicalIF":4.6,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144861200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Maintaining source–destination connectivity in uncertain networks under adversarial attack","authors":"Jianzhi Tang ,&nbsp;Luoyi Fu ,&nbsp;Yu-E Sun ,&nbsp;Xinbing Wang ,&nbsp;He Huang","doi":"10.1016/j.comnet.2025.111607","DOIUrl":"10.1016/j.comnet.2025.111607","url":null,"abstract":"<div><div>This paper investigates the problem of maintaining the connectivity between two vertices, a source and a destination, in an uncertain network under adversarial attack, where a defender preserves crucial links to prevent the source–destination vertex pair from being disconnected by an attacker. In contrast with prior art that mostly focuses on the overall network connectivity, in this work connectivity maintenance is restricted to a pair of selected vertices, which may provide insights into reliable point-to-point connection. We model the network as a random graph where each link carries both an existence probability and a probing cost, and seek to design a defensive strategy that ensures source–destination connectivity under minimum probing expenditure, regardless of adversarial behavior. To this end, we first delve into the computational complexity of the problem by establishing its NP-hardness, and put forth an optimal defensive strategy leveraging dynamic programming. Due to the prohibitive price of attaining optimality, we further design two approximate defensive strategies aimed at pursuing effective defensive performance within polynomial time, in which the first one is a path-based heuristic strategy that iteratively extends a preserved path by probing links with high utility regarding source–destination connectivity, and the second one is a cut-based minimax strategy that prioritizes the links in the minimum potential source–destination cut in order to minimize the possible worst-case loss suffered by the defender with a constant approximation ratio. Extensive experiments conducted on synthetic and real-world network datasets under diverse attacking strategies validate the superiority of the proposed strategies in both effectiveness and robustness over baselines.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"271 ","pages":"Article 111607"},"PeriodicalIF":4.6,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144878781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SCDFL: A Spectral Clustering-based framework for accelerating convergence in Decentralized Federated Learning","authors":"Faisal Alshami ,&nbsp;Lin Yao ,&nbsp;Xin Wang ,&nbsp;Guowei Wu","doi":"10.1016/j.comnet.2025.111615","DOIUrl":"10.1016/j.comnet.2025.111615","url":null,"abstract":"<div><div>Decentralized Federated Learning (DFL) is a popular distributed machine learning framework that facilitates collaboration among multiple clients without dependence on a central server to develop a global model. This architecture faces issues with client convergence, resulting in network congestion and slower convergence during the DFL process. These challenges stem from various communications topologies and the non-independent and non-identically distributed nature of data on terminal devices in real-world scenarios, which affect both model convergence speed and overall terminal performance. Therefore, we propose SCDFL, a federated learning framework that leverages spectral clustering to efficiently and scalably handle client data heterogeneity. SCDFL introduces a novel spectral clustering strategy that focuses on grouping clients based on their characteristics. Key components include reducing the dimensionality of the client data by incremental PCA, which includes high-dimensional model updates or feature vectors, making the clustering process more efficient. Then, a similarity matrix based on the reduced data will be computed to measure client similarity. Utilizing this matrix, we apply spectral clustering to group clients with similar data characteristics. Finally, we apply the aggregation in intra-cluster and inter-cluster to the updated global model. Extensive experiments have been conducted across different topologies, and the results demonstrate that SCDFL achieves higher accuracy, faster convergence, reduced communication overhead, and improved generalization, particularly on complex datasets like MNIST, CIFAR10, and CIFAR100, while efficiently handling data heterogeneity and optimizing resource utilization across various network topologies.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"271 ","pages":"Article 111615"},"PeriodicalIF":4.6,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144886488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EDVFL: An evaluable and decentralized privacy-preserving VFL for secure data sharing in ATM","authors":"Qing Wang,&nbsp;Zhijun Wu,&nbsp;YanRong Lu","doi":"10.1016/j.comnet.2025.111555","DOIUrl":"10.1016/j.comnet.2025.111555","url":null,"abstract":"<div><div>In the realm of civil aviation transport, the exchange of data among various entities opens up new avenues for enhancing both the efficiency of flight operation and the overall service quality. Vertical federated learning (VFL) enables secure sharing by transferring local model instead of raw data, thereby mitigating privacy concerns in data sharing across different entities. However, conventional centralized VFL are highly dependent on coordinators, which pose significant security and privacy risks, including single point of failure and reconstruction attack. Furthermore, the absence of an effective incentive mechanism that aligns with contribution leads to data providers’ reluctance to share their most valuable data, which may degrade the performance of the shared model, ultimately impacting the quality of flight operation. To address these challenges, we have explored the blockchain to develop a VFL-based evaluable and decentralized data sharing architecture EDVFL. Specifically, a tree-structured aggregation based on secret sharing is devised over blockchain for feature distributed stochastic variance reduced gradient (FD-SVRG) to enhance the training efficiency of models and strengthen the system against reconstruction attack. Then, using <span><math><mrow><mi>ρ</mi><mi>−</mi><mi>z</mi><mi>C</mi><mi>D</mi><mi>P</mi></mrow></math></span> differential privacy, we propose a secure Shapley value (SV)-based contribution assessment approach SDPFL. SDPFL can accurately and efficiently assess each participant’s contribution to the global model while protecting privacy. Moreover, based on SDPFL, EDVFL provides a reweighted strategy to enhance the ability of the global model to resist data poisoning in the case of negative participation. Numerical results on real datasets and security and privacy analysis indicate that our proposed EDVFL has enhanced security and high efficiency, which can effectively promote data sharing in ATM.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"271 ","pages":"Article 111555"},"PeriodicalIF":4.6,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144852598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"BTMH: A blockchain-powered trust management system for IoMT in healthcare","authors":"Maroua Akkal ,&nbsp;Sarra Cherbal ,&nbsp;Boubakeur Annane ,&nbsp;Hicham Lakhlef","doi":"10.1016/j.comnet.2025.111589","DOIUrl":"10.1016/j.comnet.2025.111589","url":null,"abstract":"<div><div>The Internet of Things (IoT) has transformed daily life, particularly in healthcare, through the Internet of Medical Things (IoMT), which revolutionizes medical services and enables telemedicine. However, this increased reliance on IoMT devices raises concerns about their reliability, trust, and security, emphasizing the need for secure, decentralized solutions. While Trust Management Systems (TMS) have been developed to address these issues, centralized TMS are vulnerable to single points of failure if compromised. Although decentralized TMS have been explored for IoMT, a scalable solution that balances security, scalability, and performance has yet to be realized. Existing systems often fall short in addressing security threats such as bad-mouthing, ballot stuffing, and whitewashing, leaving trust management exposed. Blockchain-based decentralized approaches offer dynamic management but are still susceptible to vulnerabilities, including attacks on honest nodes and manipulation of trust levels for malicious ones. To overcome these limitations, we propose a Blockchain-powered Trust Management system for IoMT in Healthcare (BTMH), which utilizes a two-chain architecture to separate authentication and trust data management. This design enhances both security and scalability, with one chain dedicated to authentication and the other to trust data management. Our implementation, using Hyperledger Fabric and benchmarking via Hyperledger Caliper, shows that BTMH outperforms existing solutions in trust convergence, throughput, and latency, providing robust protection against security threats while delivering superior performance.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"271 ","pages":"Article 111589"},"PeriodicalIF":4.6,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144863401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large Language Models for computer networking operations and management: A survey on applications, key techniques, and opportunities","authors":"Fan Liu,&nbsp;Behrooz Farkiani,&nbsp;Patrick Crowley","doi":"10.1016/j.comnet.2025.111614","DOIUrl":"10.1016/j.comnet.2025.111614","url":null,"abstract":"<div><div>This survey examines the application of Large Language Models (LLMs) in network operations and management (NO&amp;M). It outlines the transformation in NO&amp;M driven by LLMs, highlighting their potential to address challenges across network design, automation, optimization, and security domains. The paper explores how LLMs enhance traditional methods by automating complex tasks, improving network agility, and providing solutions to emerging network demands. We present our methodology for a systematic literature review and analyze how LLMs complement network technologies, including Software-Defined Networking, Network Function Virtualization, Intent-Based Networking, and Zero-Touch Network. The survey categorizes existing research into key application areas, providing comparisons between LLM-based approaches and traditional methods. We identify current limitations, such as integration with legacy systems, explainability, data privacy, and computational scalability. Additionally, we propose future research directions, including domain-specific efficient architectures, advanced intent-based management, privacy-preserving techniques, integration with next-generation networks, sustainable LLM solutions, cross-domain collaboration frameworks, and ethical considerations. Our findings offer insights for researchers and practitioners aiming to leverage LLMs for intelligent network management in complex and dynamic environments.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"271 ","pages":"Article 111614"},"PeriodicalIF":4.6,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144889940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated BD-RIS and hybrid NOMA/OMA optimization for secure, low-latency vehicular networks","authors":"Abdulbasit A. Darem ,&nbsp;Asma A. Alhashmi ,&nbsp;Abed Saif Ahmed Alghawli ,&nbsp;Amal Alshardan ,&nbsp;Mohammed Burhanur Rehman ,&nbsp;Mukhtar Ghaleb","doi":"10.1016/j.comnet.2025.111609","DOIUrl":"10.1016/j.comnet.2025.111609","url":null,"abstract":"<div><div>To address the dual demands of low-latency and secure offloading in vehicular edge computing networks, we propose a beyond-diagonal RIS (BD-RIS)-assisted hybrid uplink framework. The BD-RIS architecture partitions elements into reflective and transmissive sub-surfaces to simultaneously support roadside units (RSUs) via non-orthogonal multiple access (NOMA) and remote processing units (RPUs) via orthogonal multiple access (OMA). The network topology comprises mobile vehicles, fixed RSUs, a centrally placed BD-RIS, and a remote RPU connected via backhaul. Tasks are dynamically classified into latency-sensitive (NOMA) and delay-tolerant (OMA) streams based on application-specific latency and data-size thresholds derived from quality of service (QoS) requirements. Vehicular mobility is modeled via time-varying positions, with simulations performed under snapshot-based quasi-static Rician fading. A cross-layer optimization problem jointly addresses BD-RIS phase configuration (under orthogonality constraints), user association, and uplink bandwidth allocation to maximize the minimum secrecy rate under mobility-driven channel variations and imperfect successive interference cancellation (SIC). We solve this mixed-integer non-convex problem via a low-complexity block coordinate descent (BCD) algorithm, which decomposes the problem into tractable subproblems using successive convex approximation (SCA). Extensive simulations of the proposed Joint BD-RIS Hybrid MEC-NOMA Offloading (JBD-RIS-HMCO) scheme demonstrate 30%–45% gains in minimum secrecy rate over traditional diagonal RIS and baseline strategies, along with fast convergence and scalability. Sensitivity studies reveal the critical roles of RIS elements, RSU density, and residual SIC interference (<span><math><mi>η</mi></math></span>). These factors significantly impact the trade-off between secure throughput and quality of service (QoS).</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"271 ","pages":"Article 111609"},"PeriodicalIF":4.6,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144863400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Overcoming emergency HTTP/3 DDoS attack detection: A domain adaptation solution with graph neural network","authors":"Jie Yao ,&nbsp;Li Tian ,&nbsp;Ziyi Wei ,&nbsp;Guozi Sun","doi":"10.1016/j.comnet.2025.111611","DOIUrl":"10.1016/j.comnet.2025.111611","url":null,"abstract":"<div><div>Distributed Denial of Service (DDoS) attacks refer to attacks that exhaust the resources of a target system by flooding it with a large volume of invalid data packets. Existing methods for detecting encrypted malicious traffic under traditional protocols, such as HTTP, TCP, and UDP, have shown satisfactory performance in identifying DDoS attacks. However, a new next-generation HTTP protocol, HTTP/3, based on the Quick UDP Internet Connections (QUIC) protocol, has been recently introduced. With the deployment of HTTP/3 on websites, detecting DDoS attacks targeting the HTTP/3 protocol has become increasingly critical. Due to the relatively recent introduction of HTTP/3, collecting a large amount of usable HTTP/3 DDoS attack traffic samples for training classifiers remains a challenge. Leveraging DDoS attack traffic samples from other protocols, such as UDP-FLOOD and HTTP-FLOOD, can enhance the performance of HTTP/3-DDoS classifiers. Unfortunately, the differences in traffic characteristics between protocols weaken the generalization ability of these classifiers. To address this, this paper proposes a Protocol Shared Feature-Aware Network (PSFAN) for detecting authentic HTTP/3-DDoS attack traffic. PSFAN utilizes a small amount of HTTP/3 DDoS attack traffic along with a large volume of DDoS traffic from traditional protocols to effectively classify HTTP/3 traffic. The model comprises three main components: a protocol confuser, a shared feature extractor, and a graph neural network classifier. The shared feature extractor is designed to extract cross-protocol feature representations from traffic data. The protocol confuser functions to minimize protocol-specific discrepancies, guiding the shared feature extractor to learn protocol-invariant feature representations. It works collaboratively with the traffic classifier to learn discriminative traffic classification representations. Our experiments demonstrate that PSFAN performs effectively in addressing urgent HTTP/3 DDoS detection tasks.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"271 ","pages":"Article 111611"},"PeriodicalIF":4.6,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144886561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid IoT network for real-time monitoring of maritime containers","authors":"Oscar Ledesma ,&nbsp;Paula Lamo","doi":"10.1016/j.comnet.2025.111627","DOIUrl":"10.1016/j.comnet.2025.111627","url":null,"abstract":"<div><div>Monitoring and traceability of maritime containers is challenging due to extreme environmental conditions and communication limitations at sea. This work presents an Internet of Things (IoT) architecture integrated with low Earth orbit satellites for real-time maritime container monitoring. Unlike traditional systems that focus solely on geolocation, the proposed solution supports internal condition tracking—such as temperature and door status—through onboard sensors. Two satellite communication models, indirect-to-satellite (ItS) and direct-to-satellite (DtS) along with two random access protocols (pure ALOHA and slotted ALOHA), to assess their energy efficiency, scalability, and communication reliability for LoRaWAN-based container networks are analyzed and compared. To validate the system, simulations of revisit times, visibility windows, and message capacity are detailed, encompassing five realistic maritime scenarios. Finally, a practical feasibility assessment is provided, addressing hardware constraints, energy consumption, satellite link parameters, and regulatory and cybersecurity considerations. The results demonstrate that, with optimal constellation configurations and communication parameters, it is possible to achieve global coverage, low latency, and a scalable capacity to integrate IoT nodes into maritime networks.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"271 ","pages":"Article 111627"},"PeriodicalIF":4.6,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144863396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}