计算机科学最新文献

{"title":"Generative Diffusion Model-based Variational Inference for MIMO Channel Estimation","authors":"Zhixiong Chen, Hyundong Shin, Arumugam Nallanathan","doi":"10.1109/tcomm.2025.3556753","DOIUrl":"https://doi.org/10.1109/tcomm.2025.3556753","url":null,"abstract":"","PeriodicalId":13041,"journal":{"name":"IEEE Transactions on Communications","volume":"55 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143757839","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":"Enhancing Automated Vending Machine Product Recognition Through Depth-Guided Regression Refinement","authors":"Jinjin Qian, Chengxu Liu, Yubin Ai, Guoshuai Zhao, Xueming Qian","doi":"10.1109/tii.2025.3545046","DOIUrl":"https://doi.org/10.1109/tii.2025.3545046","url":null,"abstract":"","PeriodicalId":13301,"journal":{"name":"IEEE Transactions on Industrial Informatics","volume":"28 1","pages":""},"PeriodicalIF":12.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143757876","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":"Efficient Spatiotemporal-Structural Masking for Dynamic Human Activity Recognition with Optimized Computation","authors":"Nanfu Ye, Lei Zhang, Di Xiong, Hao Wu, Aiguo Song","doi":"10.1109/jiot.2025.3555985","DOIUrl":"https://doi.org/10.1109/jiot.2025.3555985","url":null,"abstract":"","PeriodicalId":54347,"journal":{"name":"IEEE Internet of Things Journal","volume":"216 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143757886","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":"Scheduling Services in Multi-UAVs IoT Networks","authors":"Athena Forghani, Kwan-Wu Chin, Montserrat Ros","doi":"10.1109/jiot.2025.3556653","DOIUrl":"https://doi.org/10.1109/jiot.2025.3556653","url":null,"abstract":"","PeriodicalId":54347,"journal":{"name":"IEEE Internet of Things Journal","volume":"75 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143757917","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":"ICH-PRNet: a cross-modal intracerebral haemorrhage prognostic prediction method using joint-attention interaction mechanism.","authors":"Xinlei Yu, Ahmed Elazab, Ruiquan Ge, Jichao Zhu, Lingyan Zhang, Gangyong Jia, Qing Wu, Xiang Wan, Lihua Li, Changmiao Wang","doi":"10.1016/j.neunet.2024.107096","DOIUrl":"10.1016/j.neunet.2024.107096","url":null,"abstract":"<p><p>Accurately predicting intracerebral hemorrhage (ICH) prognosis is a critical and indispensable step in the clinical management of patients post-ICH. Recently, integrating artificial intelligence, particularly deep learning, has significantly enhanced prediction accuracy and alleviated neurosurgeons from the burden of manual prognosis assessment. However, uni-modal methods have shown suboptimal performance due to the intricate pathophysiology of the ICH. On the other hand, existing cross-modal approaches that incorporate tabular data have often failed to effectively extract complementary information and cross-modal features between modalities, thereby limiting their prognostic capabilities. This study introduces a novel cross-modal network, ICH-PRNet, designed to predict ICH prognosis outcomes. Specifically, we propose a joint-attention interaction encoder that effectively integrates computed tomography images and clinical texts within a unified representational space. Additionally, we define a multi-loss function comprising three components to comprehensively optimize cross-modal fusion capabilities. To balance the training process, we employ a self-adaptive dynamic prioritization algorithm that adjusts the weights of each component, accordingly. Our model, through these innovative designs, establishes robust semantic connections between modalities and uncovers rich, complementary cross-modal information, thereby achieving superior prediction results. Extensive experimental results and comparisons with state-of-the-art methods on both in-house and publicly available datasets unequivocally demonstrate the superiority and efficacy of the proposed method. Our code is at https://github.com/YU-deep/ICH-PRNet.git.</p>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"184 ","pages":"107096"},"PeriodicalIF":6.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142972996","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":"Data-driven recursive multivariable modeling, operation, and control of active distribution networks with distributed generation","authors":"Diego Feroldi ,&nbsp;Pablo Rullo ,&nbsp;Sair Rodríguez del Portal,&nbsp;Lautaro Braccia ,&nbsp;Patricio Luppi ,&nbsp;David Zumoffen","doi":"10.1016/j.compeleceng.2025.110241","DOIUrl":"10.1016/j.compeleceng.2025.110241","url":null,"abstract":"<div><div>This paper addresses the challenges arising from the increasing integration of distributed generation into active distribution networks (ADNs), focusing on their modeling, operation, and control. Data-driven recursive multivariable modeling, capable of capturing both static and dynamic interactions in real time, has emerged as a promising solution. By utilizing the extensive data generated by modern grid infrastructure, this approach enhances network model accuracy and improves operational efficiency and control strategies. This paper strengthens the connection between Process Systems Engineering (PSE) and power systems, traditionally underexplored in this domain. By integrating PSE principles, particularly data-driven and control allocation methodologies, into the modeling, operation, and control of ADNs, this work optimizes power system performance. Three Recursive Partial Least Squares (RPLS) methodologies—sample-wise, block-wise, and moving-window—are rigorously compared regarding estimation/prediction characteristics and convergence speed. This novel analysis challenges the assumption of instantaneous model adaptation, emphasizing the importance of carefully considering convergence periods for effective monitoring, control, and optimization. The paper proposes and analyzes three control structures integrated into an RPLS-based supervisory strategy for voltage regulation at ADN nodes: (1) decentralized control, (2) control allocation with measurement combination, and (3) optimization-based centralized control. Different integration formats are evaluated based on the controller technology used: (a) simple setpoint updates, (b) full ADN model adaptation to recalculate controller matrices, and (c) full model adaptation for updating the optimization formulation. Simulation results were obtained using the IEEE 33-bus test system. The results reveal a trade-off between the complexity and performance benefits of each control strategy. Although no strategy proves definitively superior, the latter two show more promising overall prospects.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110241"},"PeriodicalIF":4.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143738039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"SiamYOLOv8: a rapid conditional detection framework for one-shot object detection","authors":"Matthieu Desmarescaux,&nbsp;Wissam Kaddah,&nbsp;Ayman Alfalou,&nbsp;Isabelle Badoc","doi":"10.1007/s10489-025-06513-2","DOIUrl":"10.1007/s10489-025-06513-2","url":null,"abstract":"<div><p>Deep learning networks typically require vast amounts of labeled data for effective training. However, recent research has introduced a challenging task called One-Shot Object Detection, which addresses scenarios where certain classes are novel and unseen during training and represented by only a single labeled example. In this paper, we propose a novel One-Shot Object Detection model applicable to Conditional Detection without over-training on novel classes. Our approach leverages the strengths of YOLOv8 (You Only Look Once v8), a popular real-time object detector. Specifically, we incorporate a Siamese network and a matching module to enhance One-Shot Object Detection capabilities. Our proposed model, SiamYOLOv8, enables exploration of new applications without being limited by its training data. To evaluate the performance, we introduce a novel methodology for using the Retail Product Checkout (RPC) dataset “(https://github.com/MatD3mons/Conditional-Detection-datasets/tree/main/RPC)”, and extend our evaluation using the Grozi-3.2k dataset “(https://github.com/MatD3mons/Conditional-Detection-datasets/tree/main/GROZI-3.2k)”. In such contexts, new products often lack sufficient data for continuous Deep Learning methods, making individual case identification difficult. Our model outperforms SOTA models, achieving a significant performance improvement of 20.33% increase in Average Precision (+12.41 AP) on the Grozi-3.2k dataset and 25.68% increase (+17.37 AP) on the RPC dataset.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740748","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":"Energy Efficient Dual Index Multicarrier M-Ary Cyclic Shifted Chaotic Vector Shift Keying System","authors":"G. Bavatharani,&nbsp;T. Laxmikandan,&nbsp;T. Manimekalai","doi":"10.1002/ett.70123","DOIUrl":"https://doi.org/10.1002/ett.70123","url":null,"abstract":"<div>\u0000 \u0000 <p>Chaotic signals are highly suitable for spread spectrum communication due to their inherent anti-jamming and anti-interference properties. Chaos-based multicarrier systems meet the increasing demands for high spectral efficiency, energy efficiency, secure, and reliable communication. However, the transmission of reference signals in these systems negatively impacts both spectral and energy efficiency. In this work, we enhance the energy efficiency of chaos-based multicarrier systems by employing index modulation with dual indexing on carriers, combined with cyclic-shifted chaotic signals. This approach not only improves energy efficiency but also reduces hardware complexity by utilizing a subset of subcarriers. Semi-analytical expressions for bit error rate (BER) over AWGN (additive white Gaussian noise) and multipath fading channels have been derived and validated through simulations. Comparative analysis reveals that the proposed system achieves significant improvement in BER performance and offers gain in energy efficiency up to a 2.5 dB over existing chaotic multicarrier systems and reduced hardware complexity in addition.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"36 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143741401","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":"Securing Tomorrow of Next-Generation Technologies with Biometrics, State-of-The-Art Techniques, Open Challenges, and Future Research Directions","authors":"Muhammad Adil ,&nbsp;Ahmed Farouk ,&nbsp;Aitizaz Ali ,&nbsp;Houbing Song ,&nbsp;Zhanpeng Jin","doi":"10.1016/j.cosrev.2025.100750","DOIUrl":"10.1016/j.cosrev.2025.100750","url":null,"abstract":"&lt;div&gt;&lt;div&gt;In the recent past, the increasing use of online applications, from simple food orders to complex banking services, has highlighted the need for strong and reliable network security measures. Traditional password-based authentication schemes have proven vulnerable to various cyber threats, including password guessing, keylogging, phishing, and credential theft, etc. To address these challenges, the research community has turned its attention to biometric technologies as a promising solution for Next-Generation Technologies security. These biometrics technologies use the physiological and behavioral characteristics of humans to verify or confirm their identity in many NGTs such as smartphones, computers, banking systems, and border control systems, etc. However, these NGTs faces several key challenges in the context of biometric systems. This is because the biometrics features change a lot with age, or once someone passes away, compared to the collected data when the person was alive. Therefore, these systems face multidirectional challenges. First, the attackers can use different techniques to compromise the security of an application. Secondly, the disparities inherent in biometric technologies pose significant challenges to their effective implementation because they rely on specific human features such as irises, fingerprints, and faces, etc. Considering that, we conducted a comprehensive survey over the past decade. This survey aimed to identify both the strengths and weaknesses of existing biometric techniques used in NGTs, with the goal of setting the path for future research that can enhance the security of these technologies. Furthermore, it is crucial to address the question of why this paper is necessary, given the presence of several survey papers on the same topic. To answer this question, our work offers several unique contributions based on the undermentioned factors: (i:) Firstly, it familiarizes the reader with the taxonomy of biometrics, followed by enabling technologies and use cases in the context of NGTs, which are ignored in most published papers. (ii:) Secondly, it meticulously examines the reliability of mostly used biometric authentication techniques by highlighting their strong and weak aspects to underscore the research gaps. (iii:) Thirdly, our paper thoroughly explores the requirements of biometric technologies in the context of NGTs to support the literature arguments regarding their inefficiency in meeting the demands of emerging technologies. Moreover, this work provides insights into both the achievements made thus far and the areas that still require attention to enhance the reliability of biometric systems. (iv:) Fourthly, it highlights the open challenges that current biometric methods struggle to overcome in futuristic technologies. (v:) Lastly, we propose research directions with the aim of addressing the highlighted open challenges and maintaining the trust of all stakeholders in biometric technolog","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"57 ","pages":"Article 100750"},"PeriodicalIF":13.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143738598","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":"PrGChain: A privacy-preserving blockchain-enabled energy trading system","authors":"Ahmed-Sami Berkani ,&nbsp;Hamouma Moumen ,&nbsp;Saber Benharzallah ,&nbsp;Mohand Tahar Kechadi ,&nbsp;Ahcène Bounceur","doi":"10.1016/j.compeleceng.2025.110289","DOIUrl":"10.1016/j.compeleceng.2025.110289","url":null,"abstract":"<div><div>The integration of blockchain, Internet of Things devices, and distributed energy resources is revolutionizing peer-to-peer energy trading by enabling decentralized, efficient, and transparent transactions. However, existing solutions face challenges related to privacy, interoperability, and scalability. This paper presents PrGChain, a privacy-preserving blockchain-enabled energy trading framework within the smart grid, incorporating a decentralized ZKOracle to securely connect blockchain networks with off-chain energy data sources.</div><div>The proposed ZKOracle employs zero-knowledge proofs to verify energy data without exposing sensitive information, ensuring compliance with privacy regulations, while leveraging a distributed network of oracle nodes for enhanced reliability and interoperability. To improve security and efficiency, PrGChain utilizes smart contracts, decentralized applications (dApps), and leverages stablecoins to mitigate cryptocurrency volatility.</div><div>Performance evaluations demonstrate that our system achieves improved decentralization and privacy without sacrificing efficiency. This is particularly true when deployed on Layer 2 blockchain networks like Polygon, where transaction latency and costs are significantly reduced.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110289"},"PeriodicalIF":4.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143737773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}