检索结果-内蒙古大学图书馆

Predictive ISAC Beamforming Using LoRA-Transformer LSTM Integrated with GNN in Ultra-Dense D2D mmWave Networks

IEEE Transactions on Vehicular Technology 2025年

作者： Liu, Haochen Bi, Jia Li, Bohan Xiang, Luping Yang, Xin Zhang, Zhaolin Wang, Ling Northwestern Polytechnical University School of Electronics and Information Xi'an710019 China Rutherford Appleton Laboratory Scientific Computing Department STFC DidcotOX11 0QX United Kingdom Ocean University of China Faculty of Information Science and Engineering Qingdao266100 China Nanjing University State Key Laboratory of Novel Software Technology Nanjing210008 China School of Intelligent Software and Engineering Suzhou China

Effective beamforming is crucial in ultra-dense device-to-device (D2D) mmWave networks to reduce interference and optimize communication. However, current methods often struggle to balance high data rates with minimal signaling overhead, especially with imperfect channel state information (CSI). This paper introduces a machine learning-assisted beamforming design tailored for integrated sensing and communication (ISAC), combining an efficient Low-Rank Adaptation Blocked LSTM Transformer with Message Passing Graph Neural Network that is called as LoRA_BLT-MPGNN. The LoRA_BLT component provides a key advantage by efficiently capturing both temporal and spatial patterns through fixed-weight updates during training and low-rank approximation for fine-tuning, significantly reducing computational complexity without sacrificing accuracy. Using historical channel data, the method implicitly captures channel characteristics and directly predicts the beamforming matrix for the subsequent time slot, minimizing signaling overhead while maximizing the achievable sum rate. Our research and simulation results show that the proposed predictive beamforming design maintains robust sensing performance and achieves a sum rate closely approaching the upper bound achievable with perfect CSI. Additionally, the incorporation of MPGNNs enables efficient modeling and learning of complex inter-node relationships, making the approach adaptable to networks of varying sizes and densities. Simulations further demonstrate that the LoRA_BLT-MPGNN model can be generalized across different network densities and coverage areas, reducing computational complexity by approximately 32× in terms of Tensor Floating Point Operations (TFLOPs) compared to conventional methods while maintaining high performance. © 2025 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Privacy Enhanced Edge-AI Healthcare Devices Authentication: A Federated Learning Approach

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Ahmed, Syed Thouheed Kaladevi, A.C. Kumar, V. Vinod Shankar, Achyut Alqahtani, Fayez REVA University School of Computing and Information Technology India Vellore Institute of Technology School of Computer Science Engineering Vellore632014 India Bennett University School of Computer Science Engineering and Technology Uttar Pradesh Greater Noida201310 India King Saud University College of Computer and Information Sciences Software Engineering Department Riyadh12372 Saudi Arabia

Medical devices connected via internet are open to cyber-attacks, hence the privacy preservation of the user and the devices plays an important role. In this paper, Medical Edge-devices privacy enhanced technique based on the federated learning principles is proposed on the distributed coordination of devices and computational system. The technique generates a dedicated token via Centralized Authentication Authority (CAA) for the active users at the local Federated Learning (FL) cum training model. Further the technique introduces dual layer validation of tokens via Authentication Authority Valuation Layer (AAVL) and Centralized Server Firewall Authentication Layer (CSFAL). The purpose of these layers is to optimize the active and inactive tokens, assigning tokens and revoking the inactive tokens from the user groups via distributed federated learning model. The technique is validated on 1500 edge devices of IoT/IoMT on 5 clusters servers of global model. The technique has demonstrated an accuracy of 96% in training and optimizing the IoMT device operations via privacy policies proposed in this paper. © 1975-2011 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Clouds

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年

作者： Yang, Chuanxiang Zhou, Yuanfeng Wei, Guangshun Ma, Long Hou, Junhui Liu, Yuan Wang, Wenping The School of Software Shandong University Jinan250100 China The Department of Computer Science City University of Hong Kong Hong Kong The College of Computing and Data Science Nanyang Technological University Singapore The Department of Computer Science and Engineering Texas A&M University College StationTX77843 United States

As commonly used implicit geometry representations, the signed distance function (SDF) is limited to modeling watertight shapes, while the unsigned distance function (UDF) is capable of representing various surfaces. However, its inherent theoretical shortcoming, i.e., the non-differentiability at the zero-level set, would result in sub-optimal reconstruction quality. In this paper, we propose the scaled-squared distance function (S2DF), a novel implicit surface representation for modeling arbitrary surface types. S2DF does not distinguish between inside and outside regions while effectively addressing the non-differentiability issue of UDF at the zero-level set. We demonstrate that S2DF satisfies a second-order partial differential equation of Monge-Ampere-type, allowing us to develop a learning pipeline that leverages a novel Monge-Ampere regularization to directly learn S2DF from raw unoriented point clouds without supervision from ground-truth S2DF values. Extensive experiments across multiple datasets show that our method significantly outperforms state-of-the-art supervised approaches that require ground-truth surface information as supervision for training. The code will be publicly available at https://***/chuanxiang-yang/S2DF. © 2025 IEEE. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

ChatGPT, Let Us Chat Sign Language: Experiments, Architectural Elements, Challenges and Research Directions

ChatGPT, Let Us Chat Sign Language: Experiments, Architectur...

引用

International Symposium on Networks, Computers and Communications (ISNCC)

作者： Nada Shahin Leila Ismail Department of CS and Software Engineering Intelligent Distributed Computing and Systems (INDUCE) Lab College of IT National Water and Energy Center UAE University Al-Ain UAE CLOUDS lab School of Computing and Information Systems The University of Melbourne Melbourne Australia

ChatGPT is a language model based on Generative AI. Existing research work on ChatGPT focused on its use in various domains. However, its potential for Sign Language Translation (SLT) is yet to be explored. This paper addresses this void. Therefore, we present GPT's evolution aiming a retrospective analysis of the improvements to its architecture for SLT. We explore ChatGPT's capabilities in translating different sign languages in paving the way to better accessibility for deaf and hard-of-hearing community. Our experimental results indicate that ChatGPT can accurately translate from English to American (ASL), Australian (AUSLAN), and British (BSL) sign languages and from Arabic Sign Language (ArSL) to English with only one prompt iteration. However, the model failed to translate from Arabic to ArSL and ASL, AUSLAN, and BSL to Arabic. Consequently, we present challenges and derive insights for future research directions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using transformers and Bi-LSTM with sentence embeddings for prediction of openness human personality trait

引用

PeerJ Computer Science 2025年 11卷 1-42页

作者： Naz, Anam Khan, Hikmat Ullah Alsahfi, Tariq Alhajlah, Mousa Alshemaimri, Bader Daud, Ali Department of Information Technology University of Sargodha Punjab Sargodha Pakistan Department of Information Systems and Technology College of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia Applied of Computer Science College King Saud University Riyadh Saudi Arabia Software Engineering Department College of Computing and Information Sciences King Saud University Riyadh Saudi Arabia Faculty of Resilience Rabdan Academy Abu Dhabi United Arab Emirates

Understanding human personality traits is significant as it helps in decision making related to consumers’ behavior, career counselling, team building and top candidates’ selection for recruitment. Among various traits, openness is essential as it shows both diverse aspects of sensitive nature or intuitive nature. The individuals having a sensing nature tends to be more practical and prefer to focus on concrete information whereas the users having intuitive trait type is characterized by a focus on abstract ideas, creative thinking and future-oriented perspectives. In this research work, we aim to explore diverse natural language processing (NLP) based features and apply state of the art deep learning algorithms for openness trait prediction. Using standard Myers-Briggs Type Indicator (MBTI) dataset, we propose the use of the latest deep features of sentence embeddings which captures contextual semantics of the content to be used with deep learning models. For comparison, we explore textual features of Frequency-Inverse Document (TF-IDF) and parts of speech (POS) tagging with machine learning models and deep features of word2vec and global vectors for word representation (GloVe) with deep learning models. The comprehensive empirical analysis reveals that TF-IDF used with gradient boosting achieves high accuracy of 90% whereas, the deep feature of sentence embeddings when used and with deep model bidirectional long short-term memory (Bi-LSTM) achieves 90.5% accuracy. The best results have been achieved using the latest Transformer-based DistilBERT, which achieves the highest accuracy of 92% outperforming the existing studies in relevant literature. Subjects Human-Computer Interaction, Artificial Intelligence, Data Mining and Machine Learning, Natural Language and Speech © 2025 xxxx

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

MRLATO: An Adaptive Task Offloading Mechanism Based on Meta Reinforcement Learning in Edge computing Environment

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Zhang, Peiying Liu, Jiamin Guizani, Maher Wang, Jian Kumar, Neeraj Tan, Lizhuang Qingdao Institute of Software College of Computer Science and Technology Qingdao266580 China Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software Qingdao266580 China Ministry of Education Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Jinan250014 China University of Texas Arlington Computer Science and Engineering Department TX United States College of Science Qingdao266580 China Thapar University Department of Computer Science and Engineering Patiala147004 India Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan250014 China

Traditional cloud computing models struggle to meet the requirements of latency-sensitive applications when processing large amounts of data. As a solution, Multi-access Edge computing (MEC) extends computing resources to the edge of the network to reduce processing delays and improve user experience. However, in dynamically changing edge computing environments, effective decision making on whether to offload tasks to edge servers remains a core challenge. For this purpose, we propose MRLATO, an adaptive task offloading mechanism based on Meta Reinforcement Learning (MRL), which exploits a large amount of a priori knowledge of different tasks to achieve fast adaptation. The task offloading process is modelled as multiple Markov Decision Processes (MDPs) and solved using a Sequence to Sequence (Seq2Seq) neural network integrating multi-head attention and recursive task sequencing. It is shown by the experimental results that the proposed method has the lowest latency in all experimental settings and the convergence efficiency is improved by 14.06% compared to the traditional Deep Reinforcement Learning (DRL) algorithm. This research fully demonstrates the significant benefits of the deep integration of MRL with the edge computing domain, providing new optimisation ideas for task offloading decisions. © 1967-2012 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Identifying Dna-Binding Proteins Using Local Features Dpc-Pssm and Ab-Pssm with Primary Sequences Based on 2dcnn

SSRN

引用

SSRN 2024年

作者： Sikander, Rahu Rahu, Ali Ghulam Rahu, Mujeeb -Ur-Rehman Center for Computing Research Department of Computer Science and Software Engineering Jinnah University for Women Karachi Pakistan Information Technology Centre Sindh Agriculture University Sindh Tandojam Pakistan School of Information and Communication Engineering Guilin University of Electronic Technology Guilin China

DBPs, also known as DNA-binding proteins, play a crucial role in the evolutionary and genetic mechanisms of humans. Understanding the features of DNA-binding peptides might develop our comprehension of protein roles inside cellular genetic processes. Investigation on predicting the function of DNA-binding proteins can advance the study of drug proteins and facilitate the development of computer-assisted medications. Deep learning methods have become the major approach for protein prediction in recent years. While current approaches can yield impressive expect performance, further research is necessary to enhance this performance. This work proposed the prediction of DNA-binding proteins using two-dimensional Convolutional Neural Network (CNN) named 2DCNN-DBP. The prominent characteristics are obtained through innovative techniques, specifically position specific scoring matrix-dipeptide composition dipeptide composition (PSSM-DPC), Second, we employed Average Block novel approach to representing proteins using position-specific scoring matrices (AB-PSSM) in images. The DPC-PSSM feature extraction approach achieved a prediction accuracy of 0.9309% for the validation set, which is notably superior to the AB-PSSM. Based on the analysis, DPC-PSSM shown superior performance compared to the other two feature selection approaches in classification using 2DCNN. Specifically, AB-PSSM attained a higher accuracy level of 73.50% using independent test datasets and a training dataset accuracy score of 87.52%. The results demonstrate the superior performance of our innovative predictor compared to previous studies. Utilizing PSSM-DPC could lead to the development of more effective therapeutic approaches for the treatment of life-threatening diseases. © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

SpaceCube GHOST: A Resilient Processor for Low-Power, High-Reliability Space computing

SpaceCube GHOST: A Resilient Processor for Low-Power, High-R...

引用

IEEE Conference on Aerospace

作者： Noah Perryman Nicholas Franconi Gary Crum Christopher Wilson Alan D. George Department of Electrical and Computer Engineering NSF Center for Space High-Performance and Resilient Computing (SHREC) University of Pittsburgh Pittsburgh PA Science Data Processing Branch Code 587 Software Engineering Division NASA Goddard Space Flight Center Greenbelt MD

There is a direct need for high-visibility NASA missions that provide significant scientific impact or have a high mission class using completely radiation-hardened (rad-hard) electronics solutions, to enable artificial intelligence (AI) applications in harsh environments despite severe size, weight, and power (SWaP) constraints. For these missions, where current state-of-the-art solutions are too power-demanding or are incapable of surviving the intended radiation environment, an alternative rad-hard processing architecture that can leverage the control-flow capabilities of scalar processors while also incorporating the hardware-acceleration capabilities of an FPGA is of significant value. Therefore, in this research, we propose a miniaturized (3.5 in. × 3.5 in. form factor) processor card featuring the GR740 quad-core rad-hard processor and the CertusPro-NX-RT radiation-tolerant FPGA, called the SpaceCube GR740 Host for Onboard Science and Telemetry (GHOST) architecture. The card will be designed to conform to the NASA Goddard Space Flight Center (GSFC) CubeSat Card Specification (CS2), which provides a common template to build new 1U CubeSat-sized cards compatible with a variety of other avionics designs. The GR740 features a fault-tolerant quad- processor LEON4FT SPARC V8 integer unit with a 7-stage pipeline and 4×4 KiB instruction and data caches. To extend the capabilities of the GR740, the CertusPro-NX-RT, a low-power radiation-tolerant FPGA, was combined to create a hybrid system architecture, providing the benefits of a programmable logic fabric. The GHOST architecture supports high-reliability, general-purpose processing and system monitoring via the GR740 while simultaneously increasing the AI-based application performance via a combination of the GR740 and CertusPro-NX-RT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Commercial Dishes Can Be My Ladder: Sustainable and Collaborative Data Offloading in LEO Satellite Networks

arXiv

引用

arXiv 2025年

作者： Chou, Yi Ching Chen, Long Wang, Hengzhi Wang, Feng Fang, Hao Zhao, Haoyuan Zhang, Miao Fan, Xiaoyi Liu, Jiangchuan School of Computing Science Simon Fraser University Canada College of Computer Science and Software Engineering Shenzhen University China Department of Computer and Information Science The University of Mississippi United States Jiangxing Intelligence Inc. Shenzhen China

Low Earth Orbit (LEO) satellite networks, characterized by their high data throughput and low latency, have gained significant interest from both industry and academia. Routing data efficiently within these networks is essential for maintaining a high quality of service. However, current routing strategies, such as bent-pipe and inter-satellite link (ISL) routing, have their unique challenges. The bent-pipe strategy requires a dense deployment of dedicated ground stations, while the ISL-based strategy can negatively impact satellite battery lifespan due to increased traffic load, leading to sustainability issues. In this paper, we propose sustainable collaborative offloading, a framework that orchestrates groups of existing commercial resources like ground stations and 5G base stations for data offloading. This orchestration enhances total capacity, overcoming the limitations of a single resource. We propose the collaborator group set construction algorithm to construct candidate groups and the collaborator selection and total payment algorithm to select offloading targets and determine payments no less than the costs. Extensive real-world-based simulations show that our solution significantly improves energy consumption, satellite service life, and end-to-end latency. Copyright © 2025, The Authors. All rights reserved.

关键词： Satellite links

来源：评论

学校读者我要写书评

暂无评论

Debiasing Graph Representation Learning based on Information Bottleneck

arXiv

引用

arXiv 2024年

作者： Zhang, Ziyi Ouyang, Mingxuan Lin, Wanyu Lan, Hao Yang, Lei The School of Software Engineering South China University of Technology Guangzhou China The Hong Kong Polytechnic University Hong Kong The Department of Computing The Hong Kong Polytechnic University Hong Kong The Department of Computer Science and Technology Tsinghua University Beijing China

—Graph representation learning has shown superior performance in numerous real-world applications, such as finance and social networks. Nevertheless, most existing works might make discriminatory predictions due to insufficient attention to fairness in their decision-making processes. This oversight has prompted a growing focus on fair representation learning. Among recent explorations on fair representation learning, prior works based on adversarial learning usually induce unstable or counterproductive performance. To achieve fairness in a stable manner, we present the design and implementation of GRAFair, a new framework based on a variational graph auto-encoder. The crux of GRAFair is the Conditional Fairness Bottleneck, where the objective is to capture the trade-off between the utility of representations and sensitive information of interest. By applying variational approximation, we can make the optimization objective tractable. Particularly, GRAFair can be trained to produce informative representations of tasks while containing little sensitive information without adversarial training. Experiments on various real-world datasets demonstrate the effectiveness of our proposed method in terms of fairness, utility, robustness, and stability. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：