检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Chuang Sun, Geng Li, Jiahui Wang, Jiacheng Zhang, Ruichen Niyato, Dusit Mao, Shiwen Quek, Tony Q.S. Computer Science and Technology Jilin University Changchun130012 China Singapore University of Technology and Design Singapore487372 Singapore College of Computer Science and Technology Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Department of Electrical and Computer Engineering Auburn University AuburnAL36849 United States Information System Technology and Design Pillar Singapore University of Technology and Design Singapore487372 Singapore

An integration of satellites and terrestrial networks is crucial for enhancing performance of next generation communication systems. However, the networks are hindered by the long-distance path loss and security risks in dense urban environments. In this work, we propose a satellite-terrestrial covert communication system assisted by the aerial active simultaneous transmitting and reflecting reconfigurable intelligent surface (AASTAR-RIS) to improve the channel capacity while ensuring the transmission covertness. Specifically, we first derive the minimal detection error probability (DEP) under the worst condition that the Warden has perfect channel state information (CSI). Then, we formulate an AASTAR-RIS-assisted satellite-terrestrial covert communication optimization problem (ASCCOP) to maximize the sum of the fair channel capacity for all ground users while meeting the strict covert constraint, by jointly optimizing the trajectory and active beamforming of the AASTAR-RIS. Due to the challenges posed by the complex and high-dimensional state-action spaces as well as the need for efficient exploration in dynamic environments, we propose a generative deterministic policy gradient (GDPG) algorithm, which is a generative deep reinforcement learning (DRL) method to solve the ASCCOP. Concretely, the generative diffusion model (GDM) is utilized as the policy representation of the algorithm to enhance the exploration process by generating diverse and high-quality samples through a series of denoising steps. Moreover, we incorporate an action gradient mechanism to accomplish the policy improvement of the algorithm, which refines the better state-action pairs through the gradient ascent. Simulation results demonstrate that the proposed approach significantly outperforms important benchmarks, and also validate the performance and practicality under different algorithm parameters and environment settings. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Integrated Conflict Management for UAM with Strategic Demand Capacity Balancing and Learning-based Tactical Deconfliction

arXiv

引用

arXiv 2023年

作者： Chen, Shulu Evans, Antony Brittain, Marc Wei, Peng The Department of Electrical and Computer Engineering George Washington University WashingtonDC20052 United States System Design for Airbus UTM at Acubed An Airbus Innovation Center SunnyvaleCA94086 United States The Technical Staff MIT Lincoln Laboratory LexingtonMA02421 United States The Department of Mechanical and Aerospace Engineering George Washington University WashingtonDC20052 United States

Urban air mobility (UAM) has the potential to revolutionize our daily transportation, offering rapid and efficient deliveries of passengers and cargo between dedicated locations within and around the urban environment. Before the commercialization and adoption of this emerging transportation mode, however, aviation safety must be guaranteed, i.e., all the aircraft have to be safely separated by strategic and tactical deconfliction. Reinforcement learning has demonstrated effectiveness in the tactical deconfliction of en route commercial air traffic in simulation. However, its performance is found to be dependent on the traffic density. In this project, we propose a novel framework that combines demand capacity balancing (DCB) for strategic conflict management and reinforcement learning for tactical separation. By using DCB to precondition traffic to proper density levels, we show that reinforcement learning can achieve much better performance for tactical safety separation. Our results also indicate that this DCB preconditioning can allow target levels of safety to be met that are otherwise impossible. In addition, combining strategic DCB with reinforcement learning for tactical separation can meet these safety levels while achieving greater operational efficiency than alternative solutions. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Harmony in the brain: A narrative review on the shared neural substrates of emotion regulation and creativity

Brain Organoid and Systems Neuroscience Journal

引用

Brain Organoid and systems Neuroscience Journal 2024年 2卷 81-91页

作者： A.I. Ladas T. Gravalas C. Katsoridou C.A. Frantzidis Department of Psychology CITY College University of York Europe Campus 24 Proxenou Koromila st Thessaloniki 54622 Greece School of Computer Science University of Lincoln Lincoln Brayford Pool LN6 7TS United Kingdom Laboratory of Medical Physics and Digital Innovation Biomedical Engineering and Aerospace Neuroscience (BEAN) School of Medicine Faculty of Health Sciences Aristotle University of Thessaloniki Thessaloniki Greece

The contribution of creativity in overall well-being through regulating emotions has sparkled research interest in employing artistic interventions recently for the improvement of mental health. Although the behavioural links between emotion regulation and creativity have been established, the neural networks reflecting these relations are yet to be investigated. In this mini review, we describe the neural underpinnings of all forms of creativity and of the emotion regulation strategies. Given the complexity of both of these constructs, we separate creativity in its various forms and report the regions and the neural networks involved. Similarly, we distinguish between the differential emotion regulation strategies and describe the relevant brain areas and networks. We then proceed to a critical exploration of common regions of interest and of neural pathways among these important functions. The studies included in this review point towards certain brain regions that are shared among creativity and affective control, such as the prefrontal cortex, the anterior cingulate cortex, the dorsolateral prefrontal cortex, the medial temporal lobe and the inferior parietal lobule. The common neural networks of emotion regulation and creativity mainly focus on the default mode, the executive control and the salience networks. We then suggest a shared neural mechanism that may underlie emotion regulation and creativity, involving both control and affective processing. Drawing on the limitations of the studies reviewed, directions for future research are suggested that could significantly inform the field.

关键词： Emotion regulation Neural substrates Creativity Common neural pathways

来源：评论

学校读者我要写书评

暂无评论

Bandwidth-Efficient Two-Server ORAMs with O(1) Client Storage

arXiv

引用

arXiv 2025年

作者： Wang, Wei Zhang, Xianglong Xu, Peng Chen, Rongmao Yang, Laurence Tianruo School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Jinyinhu Laboratory Wuhan430040 China School of Computer National University of Defense Technology Changsha410073 China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou450001 China Department of Computer Science St. Francis Xavier University AntigonishNSB2G 2W5 Canada

Oblivious RAM (ORAM) allows a client to securely retrieve elements from outsourced servers without leakage about the accessed elements or their virtual addresses. Two-server ORAM, designed for secure two-party RAM computation, stores data across two non-colluding servers. However, many two-server ORAM schemes suffer from excessive local storage or high bandwidth costs. To serve lightweight clients, it is crucial for ORAM to achieve concretely efficient bandwidth while maintaining O(1) local storage. Hence, this paper presents two new client-friendly two-server ORAM schemes that achieve practical logarithmic bandwidth under O(1) local storage, while incurring linear symmetric key computations. The core design features a hierarchical structure and a pairwise-area setting for the elements and their tags. Accordingly, we specify efficient read-only and write-only private information retrieval (PIR) algorithms in our schemes to ensure obliviousness in accessing two areas respectively, so as to avoid the necessity of costly shuffle techniques in previous works. We empirically evaluate our schemes against LO13 (TCC’13), AFN17 (PKC’17), and KM19 (PKC’19) in terms of both bandwidth and time cost. The results demonstrate that our schemes reduce bandwidth by approximately 2 ∼ 4× compared to LO13, and by 16 ∼ 64× compared to AFN17 and KM19. For a database of size 214 blocks, our schemes are over 64× faster than KM19, while achieving similar performance to LO13 and AFN17 in the WAN setting, with a latency of around 1 second. Copyright © 2025, The Authors. All rights reserved.

关键词： Virtual addresses

来源：评论

学校读者我要写书评

暂无评论

Statistical Analysis of Intrinsic High-Frequency Characteristic Fluctuation of Emerging Silicon Gate-All-Around Nanosheet (NS) MOSFETs at Sub-3-nm Nodes

Statistical Analysis of Intrinsic High-Frequency Characteris...

引用

IEEE Electron Devices Technology and Manufacturing Conference (EDTM)

作者： Sekhar Reddy Kola Yiming Li Min-Hui Chuang Kazuhiko Endo Seiji Samukawa Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Institute of Communications Engineering Department of Electronics and Electrical Engineering Institute of Biomedical Engineering Center for mm Wave Smart Radar System and Technologies National Yang Ming Chiao Tung University Hsinchu Taiwan Institute of Fluid Science Tohoku University 2-1-1 Katahira Aoba-ku Sendai Japan National Institute of Advanced Industrial Science and Technology Tsukuba Japan

In recent years, the GAA NS Si MOSFET has been explored as a leading technology. However, the intrinsic parameters of GAA NS Si MOSFETs are affected to varying degrees by various fluctuation sources, Statistically independent and identically distributed $(iid)$ assumptions on the aforementioned random variables overestimate the variability of high-frequency characteristics, compared with considering all fluctuation factors simultaneously. Notably, the random nanosized metal grains dominates the variations of voltage gain, cut-off frequency, and 3dB frequency because the random work functions strongly alter the channel surface potential.

关键词： MOSFET Fluctuations Statistical analysis Gallium arsenide Cutoff frequency Metals Logic gates

来源：评论

学校读者我要写书评

暂无评论

Mixture of Experts for Network Optimization: A Large Language Model-enabled Approach

arXiv

引用

arXiv 2024年

作者： Du, Hongyang Liu, Guangyuan Lin, Yijing Niyato, Dusit Kang, Jiawen Xiong, Zehui Kim, Dong In The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China The School of Automation Guangdong University of Technology Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Optimizing various wireless user tasks poses a significant challenge for networking systems because of the expanding range of user requirements. Despite advancements in Deep Reinforcement Learning (DRL), the need for customized optimization tasks for individual users complicates developing and applying numerous DRL models, leading to substantial computation resource and energy consumption and can lead to inconsistent outcomes. To address this issue, we propose a novel approach utilizing a Mixture of Experts (MoE) framework, augmented with Large Language Models (LLMs), to analyze user objectives and constraints effectively, select specialized DRL experts, and weigh each decision from the participating experts. Specifically, we develop a gate network to oversee the expert models, allowing a collective of experts to tackle a wide array of new tasks. Furthermore, we innovatively substitute the traditional gate network with an LLM, leveraging its advanced reasoning capabilities to manage expert model selection for joint decisions. Our proposed method reduces the need to train new DRL models for each unique optimization problem, decreasing energy consumption and AI model implementation costs. The LLM-enabled MoE approach is validated through a general maze navigation task and a specific network service provider utility maximization task, demonstrating its effectiveness and practical applicability in optimizing complex networking systems. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Survey on Indoor Visible Light Positioning systems: Fundamentals, Applications, and Challenges

arXiv

引用

arXiv 2024年

作者： Zhu, Zhiyu Yang, Yang Chen, Mingzhe Guo, Caili Cheng, Julian Cui, Shuguang The Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China The Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China The Faculty of Applied Science School of Engineering The University of British Columbia KelownaBCV1V 1V7 Canada The Chinese University of Hong Kong Shenzhen518172 China

The growing demand for location-based services in areas like virtual reality, robot control, and navigation has intensified the focus on indoor localization. Visible light positioning (VLP), leveraging visible light communications (VLC), becomes a promising indoor positioning technology due to its high accuracy and low cost. This paper provides a comprehensive survey of VLP systems. In particular, since VLC lays the foundation for VLP, we first present a detailed overview of the principles of VLC. Then, we provide an in-depth overview of VLP algorithms. The performance of each positioning algorithm is also compared in terms of various metrics such as accuracy, coverage, and orientation limitation. Beyond the physical layer studies, the network design for a VLP system is also investigated, including multi-access technologies, resource allocation, and light-emitting diode (LED) placements. Next, the applications of the VLP systems are overviewed. Finally, this paper outlines open issues, challenges, and opportunities for the research field. In a nutshell, this paper constitutes the first holistic survey on VLP from state-of-the-art studies to practical uses. Copyright © 2024, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

SRoUDA: Meta Self-training for Robust Unsupervised Domain Adaptation

arXiv

引用

arXiv 2022年

作者： Zhu, Wanqing Yin, Jia-Li Chen, Bo-Hao Liu, Ximeng Fujian Province Key Laboratory of Information Security of Network System Fuzhou350108 China College of Computer Science and Big Data Fuzhou University Fuzhou350108 China Department of Computer Science and Engineering Yuan Ze University Taiwan

As acquiring manual labels on data could be costly, unsupervised domain adaptation (UDA), which transfers knowledge learned from a rich-label dataset to the unlabeled target dataset, is gaining increasing popularity. While extensive studies have been devoted to improving the model accuracy on target domain, an important issue of model robustness is neglected. To make things worse, conventional adversarial training (AT) methods for improving model robustness are inapplicable under UDA scenario since they train models on adversarial examples that are generated by supervised loss function. In this paper, we present a new meta self-training pipeline, named SRoUDA, for improving adversarial robustness of UDA models. Based on self-training paradigm, SRoUDA starts with pre-training a source model by applying UDA baseline on source labeled data and taraget unlabeled data with a developed random masked augmentation (RMA), and then alternates between adversarial target model training on pseudo-labeled target data and fine-tuning source model by a meta step. While self-training allows the direct incorporation of AT in UDA, the meta step in SRoUDA further helps in mitigating error propagation from noisy pseudo labels. Extensive experiments on various benchmark datasets demonstrate the state-of-the-art performance of SRoUDA where it achieves significant model robustness improvement without harming clean accuracy. Code is available at https://***/VisionFlow/SRoUDA main. Copyright © 2022, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Aligning Learning Materials and Assessment with Course Learning Outcomes in MOOCs Using Data Mining Techniques 8th

Aligning Learning Materials and Assessment with Course Learn...

引用

8th International Workshop on Combinations of Intelligent Methods and Applications, CIMA 2018 held in conjunction with the 30th IEEE International Conference on Tools with Artificial Intelligence, IEEE ICTAI 2018

作者： Ewais, Ahmed Awad, Mohammed Hadia, Khetam Department of Computer Science Arab American University Jenin Palestine Department of Computer System Engineering Arab American University Jenin Palestine Laboratory Department of Computer Science Vrije Universiteit Brussel Brussels Belgium

ISBN: (纸本)9789811519178

Massive open online courses (MOOCs) are considered as a new trend in the domain of e-learning. They provide a platform for supporting learners from different places and at any time with highly scalable and interesting learning experience. As a result, this led to continuous increase in the rate of learners with different knowledge, background, and skills. Therefore, supporting learners with adapted courses’ materials and assessments based on learning outcomes is considered as a crucial concept for enhancing MOOCs. This paper presents a framework for delivering learning materials and generating assessments based on intended learning outcomes (ILOs) using both support vector machine (SVM) and fuzzy logic algorithm. The SVM is mainly used to classify learning materials according to learning outcomes. On the other hand, the fuzzy logic algorithm is mainly used to generate examinations and quizzes automatically based on learners’ achievements and scores. Accordingly, the proposed framework can be used to enable learners to achieve learning outcomes by following adapted learning materials and automatically generated examinations. To validate the proposed framework, a prototype was developed and evaluated. The results of classifying both learning materials and assessment show interesting results. For instance, the results of classification process for learning materials were related to a number of factors such as accuracy rate for SVM classifier which was 71.5%, the weighted average for TP rate = 0.715, FN rate = 0.285, FP rate = 0.028, TN rate = 0.972, precision = 0.738, recall = 0.715, F-measure = 0.678, and finally ROC area = 0.939. In addition, fuzzy logic technique provided promising results to deliver examinations with a difficulty levels that are compatible with the current level of the learner depending on his grade point average (GPA). © 2020, Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Moroccan Water Information system: Exploratory study system Literature Review 2020

Moroccan Water Information System: Exploratory study System ...

引用

4th International Conference on Geo-IT and Geospatial Technologies and Water Resources in Mediterranean Region, GEOIT4W 2020

作者： Hicham, Jamil Aniss, Moumen Bouabid, Mansouri Natural Resources Geoscience Laboratory Ibn Tofail University Kenitra Morocco System Engineering Laboratory Department of Computer Science Logistics and Mathematics ENSA Kenitra Morocco

ISBN: (纸本)9781450375788

The Kingdom of Morocco is committed to meeting the challenges of the water sector in the country to ensure sustainable and balanced socio-economic development throughout the territory through integrated management of its mobilizable resources and different uses. The water sector is today an important component of Morocco's government strategy;its management is the vector of the national economy. The emergence of new computer technologies is an important area for ensuring this management through large water information systems exploiting very large and diversified databases (Big data). This article will present the state of the art of water information systems in Morocco through surveys carried out with the various actors at the level of the department of Water as well as the hydraulic basins agencies. © 2020 ACM.

关键词： Big data

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：