计算机科学最新文献

{"title":"A Taylor Flamingo Shark Optimization–Based Traffic Aware Content Caching Vehicular Social Networks","authors":"Vedha Vinodha D.,&nbsp;Malathy Subramanium","doi":"10.1002/dac.70188","DOIUrl":"https://doi.org/10.1002/dac.70188","url":null,"abstract":"<div>\u0000 \u0000 <p>Vehicular Social Networking (VSN) is an emerging and developing application of the Internet of Vehicles (IoV) that aims to integrate vehicular networks with social networks seamlessly. Nevertheless, unique vehicular network features, namely, high mobility as well as frequent communication interruptions, make content delivery to end users under strict delay constraints very problematic. The Taylor Flamingo Shark Optimization (TFSO) method is introduced to address the limitations of existing caching and routing strategies in VSN under real-time traffic conditions. With the amalgamation of FSA and WSO with the Taylor series, TFSO provides a powerful tool for accurate, delay-aware, and mobility-sensitive content caching, thereby improving content delivery efficiency in VSNs. The proposed optimization-based traffic-aware content caching is implemented using several stages. Initially, the shortest path with the vehicular content provider is found based on the proposed hybrid Flamingo Shark Optimization (FSO). The FSO is devised by using the Flamingo Search Algorithm (FSA) as well as White Shark Optimization (WSO). Subsequently, traffic-aware content recommendations are carried out based on conditional likelihood probability. Additionally, the vehicular distribution managed by the content provider is optimized across the network by using the proposed TFSO, which is devised using the proposed FSO along with the Taylor series concept. Moreover, the effectiveness of the developed TFSO approach is assessed by leveraging metrics including computational cost, delivery delay, and delivery rate. The computational cost recorded value is 1.057, which shows that the algorithm operates with low computational overhead; the delivery delay of TFSO is 0.611 s, which indicates that the system required less time to deliver content to end users in high-mobility scenarios; and the delivery rate is 85.996, which reflects the high success rate of content delivery across the network using 2000 rounds with 150 vehicles.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"38 13","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Design and Analysis of Sunshine-Shaped MIMO Antenna for High Demand in Data Rates and Ultra-Fast Sixth-Generation Wireless Communications Through THz Spectrum Range","authors":"K. V. Vineetha,&nbsp;M. Siva Kumar,&nbsp;P. Durgaprasadarao,&nbsp;Satti Sudha Mohan Reddy,&nbsp;Kokku Aruna Kumari,&nbsp;Lokesh Raju Vysyaaraju,&nbsp;B. T. P. Madhav,&nbsp;Sk Hasane Ahammad,&nbsp;Mahmoud M. A. Eid,&nbsp;Ahmed Nabih Zaki Rashed","doi":"10.1002/dac.70196","DOIUrl":"https://doi.org/10.1002/dac.70196","url":null,"abstract":"<div>\u0000 \u0000 <p>THz antennas, which function at high speeds, frequencies, and data rates, were developed in response to the increased need for high-speed communication equipment. High data transfer is necessary for wireless communication in modern technologies. After 5G, the next generation of wireless technology is called 6G (sixth-generation wireless). Because 6G networks may run at greater frequencies than 5G networks, their capacity and latency will be significantly increased. Allowing communications with a latency of 1 μs is one of the objectives of the 6G internet. This paper introduces a compact and highly efficient sunshine-slotted MIMO antenna designed for 6G and wireless applications. The antenna features a sun-shaped patch and a partial ground layer to improve its overall performance. The proposed antenna operates across 3.6, 4.5, 5.2, and 6.2 THz, respectively, which are used for wireless communication systems. This work presents a MIMO antenna constructed with a low reflection coefficient value of −34, −38, −18, and −23 dB, with an insertion loss of less than −30 dB over the operational frequency. In addition to this, the antenna has a gain value of 8.5–9.2 dBi. The proposed MIMO antenna also has a minimum ECC value of &lt; 0.01; similarly, across the operating frequency, the antenna has a DG value range of 10–11 dB respectively. The proposed antenna has dimensions of 33 × 33 × 100 μm³ using graphene as a conducting layer and silicon as a substrate layer. The suggested antenna can be utilized for high-speed communications because of its high gain and operating frequency applicability.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"38 13","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"IEEE Internet of Things Journal Society Information","authors":"","doi":"10.1109/JIOT.2025.3587570","DOIUrl":"https://doi.org/10.1109/JIOT.2025.3587570","url":null,"abstract":"","PeriodicalId":54347,"journal":{"name":"IEEE Internet of Things Journal","volume":"12 15","pages":"C3-C3"},"PeriodicalIF":8.2,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11096046","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144695514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IEEE Transactions on Information Theory Publication Information","authors":"","doi":"10.1109/TIT.2025.3583663","DOIUrl":"https://doi.org/10.1109/TIT.2025.3583663","url":null,"abstract":"","PeriodicalId":13494,"journal":{"name":"IEEE Transactions on Information Theory","volume":"71 8","pages":"C2-C2"},"PeriodicalIF":2.2,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11095972","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144695537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IEEE Transactions on Cybernetics Information for Authors","authors":"","doi":"10.1109/TCYB.2025.3588439","DOIUrl":"https://doi.org/10.1109/TCYB.2025.3588439","url":null,"abstract":"","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 8","pages":"C4-C4"},"PeriodicalIF":9.4,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11095879","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144695610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Event-Based Integral Sliding-Mode Consensus Control for Networked Multiagent Systems With State Quantization.","authors":"Deyin Yao,Zhifei Zheng,Hongru Ren,Hongyi Li,Yang Shi","doi":"10.1109/tcyb.2025.3586510","DOIUrl":"https://doi.org/10.1109/tcyb.2025.3586510","url":null,"abstract":"This article focuses on the issue of the quantization-based event-triggered integral sliding-mode controller design for networked multiagent systems (MASs) encountering interferences under limited network bandwidth. An integral sliding manifold (ISM) is designed to address the effect of disturbances and ensure the desired dynamic performance of the system. We establish an event-triggered mechanism (ETM) with an exponential decay rate to conserve the limited communication resources. Then, a uniform quantizer is added to quantify the triggered state signals to lessen the network transmission burden caused by the digital network. Combining the designed ETM with a static uniform quantizer, the quantized trigger state signals are sent to decoders through the digital network to construct a quantized ISM. Subsequently, an event-triggered integral sliding-mode controller under quantization technology is developed to ensure the asymptotic average consensus of networked MASs. By testifying that every network agent has a lower positive bound, the viability of the proposed ETM is demonstrated, thereby ensuring the absence of Zeno behavior. Eventually, two simulation examples are proffered to confirm the efficacy of the quantization feedback-based event-triggered SMC methodology.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"144 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144700999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Toward Generalized Entropic Sparsification for Convolutional Neural Networks.","authors":"Tin Barisin, Illia Horenko","doi":"10.1162/neco.a.21","DOIUrl":"https://doi.org/10.1162/neco.a.21","url":null,"abstract":"<p><p>Convolutional neural networks (CNNs) are reported to be overparametrized. The search for optimal (minimal) and sufficient architecture is an NP-hard problem: if the network has $N$ neurons, then there are 2$^{N}$ possibilities to connect them-and therefore 2$^{N}$ possible architectures and 2$^{N}$ Boolean hyperparameters to encode them. Selecting the best possible hyperparameter out of them becomes an $N^{p}$ -hard problem since 2$^{N}$ grows in $N$ faster then any polynomial $N^{p}$. Here, we introduce a layer-by-layer data-driven pruning method based on the mathematical idea aiming at a computationally scalable entropic relaxation of the pruning problem. The sparse subnetwork is found from the pretrained (full) CNN using the network entropy minimization as a sparsity constraint. This allows deploying a numerically scalable algorithm with a sublinear scaling cost. The method is validated on several benchmarks (architectures): on MNIST (LeNet), resulting in sparsity of 55% to 84% and loss in accuracy of just 0.1% to 0.5%, and on CIFAR-10 (VGG-16, ResNet18), resulting in sparsity of 73% to 89% and loss in accuracy of 0.1% to 0.5%.</p>","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":" ","pages":"1-29"},"PeriodicalIF":2.7,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144700387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"A frequent pattern-based coevolutionary framework for multi-component spectral feature selection","authors":"Panpan Zhang ,&nbsp;Jing Rong ,&nbsp;Ye Tian ,&nbsp;Yajie Zhang ,&nbsp;Shangshang Yang ,&nbsp;Xingyi Zhang","doi":"10.1016/j.swevo.2025.102077","DOIUrl":"10.1016/j.swevo.2025.102077","url":null,"abstract":"<div><div>Spectral feature selection plays a crucial role in spectral analysis as it aims to identify the most effective features from the original high-dimensional wavelength variables, thereby enhancing the accuracy of concentration prediction models. In multi-component spectral feature selection (MCSFS) problems, diverse composition and concentration of samples result in complex overlapping peaks and correlations among variables. This complexity poses challenges in finding optimal subsets of features efficiently. To address this issue, this paper proposes a frequent pattern-based coevolutionary framework for solving MCSFS problems. Specifically, the algorithm starts by generating a main population for multi-component spectral feature selection and multiple auxiliary populations for single-component spectral feature selection. Furthermore, it introduces a frequent pattern mining strategy to identify dynamic superior feature combinations and their updated weights in each population, dealing with the complexity of variables to accelerate the search for effective features. The proposed coevolutionary framework facilitates interactions between populations by sharing the identified feature combinations and offspring information, leading to the acquisition of high-quality feature selection results. Experimental results on twelve MCSFS problems, based on three high-dimensional spectral datasets, demonstrate that the proposed algorithm outperforms six state-of-the-art evolutionary algorithms.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"98 ","pages":"Article 102077"},"PeriodicalIF":8.2,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144702682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Mobility-Aware Predictive Split Federated Learning for 6G vehicular networks with ultra-low latency guarantees","authors":"Iftikhar Rasheed ,&nbsp;Hala Mostafa","doi":"10.1016/j.comnet.2025.111553","DOIUrl":"10.1016/j.comnet.2025.111553","url":null,"abstract":"<div><div>The integration of distributed learning in 6G vehicular networks faces significant challenges due to high mobility, stringent latency requirements, and resource constraints at the network edge. This paper proposes MAPSFL, a novel mobility-aware predictive split federated learning framework that seamlessly integrates mobility prediction, dynamic model splitting, and hierarchical learning architectures to enable efficient distributed learning in highly mobile vehicular environments. Our framework employs a predictive mobility model to optimize resource allocation and model splitting decisions while maintaining ultra-low latency guarantees through adaptive compression and selective parameter transmission mechanisms. Theoretical analysis provides convergence guarantees under dynamic network conditions, while extensive experimental results demonstrate that MAPSFL achieves 31% reduction in CPU utilization, 28% lower bandwidth consumption, and 34% reduction in end-to-end training latency compared to state-of-the-art approaches. The proposed work achieved 85% efficiency at large scales of vehicles, i.e. 5000, while ensuring the required latency of 100ms, thus making it particularly suitable for safety-critical vehicular applications. The comprehensive evaluation of the proposed method validates its effectiveness in addressing the challenges of high mobility, resource constraints, and network dynamics in 6G vehicular networks.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"270 ","pages":"Article 111553"},"PeriodicalIF":4.4,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144704134","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":"Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos","authors":"Hadi Alzayer, Zhihao Xia, Xuaner (Cecilia) Zhang, Eli Shechtman, Jia-Bin Huang, Michael Gharbi","doi":"10.1145/3750722","DOIUrl":"https://doi.org/10.1145/3750722","url":null,"abstract":"We propose a generative model that, given a coarsely edited image, synthesizes a photorealistic output that follows the prescribed layout. Our method transfers fine details from the original image and preserve the identity of its parts. Yet, it adapts it to the lighting and context defined by the new layout. Our key insight is that videos are a powerful source of supervision for this task: objects and camera motions provide many observations of how the world changes with viewpoint, lighting, and physical interactions. We construct an image dataset in which each sample is a pair of source and target frames extracted from the same video at randomly chosen time intervals. We warp the source frame toward the target using two motion models that mimic the expected test-time user edits. We supervise our model to translate the warped image into the ground truth, starting from a pretrained diffusion model. Our model design explicitly enables fine detail transfer from the source frame to the generated image, while closely following the user-specified layout. We show that by using simple segmentations and coarse 2D manipulations, we can synthesize a photorealistic edit faithful to the user’s input while addressing second-order effects like harmonizing the lighting and physical interactions between edited objects. Project page and code can be found at https://magic-fixup.github.io","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"20 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144701760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}