检索结果-内蒙古大学图书馆

International Conference on advanced Robotics and Mechatronics (ICARM)

作者： XingLin Li Xinde Li Chuanfei Hu Huaping Liu School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China Nanjing Center for Applied Mathematics Nanjing China Southeast University Shenzhen Research Institute Shenzhen China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Given the difficulty of recognizing ambiguous emotions in facial expression recognition tasks, we propose a visual-language model named CAER-CLIP to address this challenge. The proposed CAER-CLIP standed for Context-Aware Emotion Recognition (CAER), and were incorporated structure of the Contrastive Language–Image Pre-training (CLIP) model as promising alternative to classifier. There are two parts in CAER-CLIP model. In the visual part, facial expressions and contextual information of the image are simultaneously extracted to obtain the final feature embeddings, which are then used as a learnable “class” token for text-image pairing with desired module. In the textual part, we use text labels for emotion recognition classes as input. The outputs were merged to participate the comparative study to generated parameters of the model. The experiments demonstrate the effectiveness of the proposed method and show that our CAER-CLIP outperforms the state-of-the-art results on the CAER benchmark. The ablation experiment verified the effectiveness of both the classifier-based and text-based (ours without classifier) models, demonstrating that our method with the CAER-CLIP structure performed better, and the incorporation of a text encoder in the deep network model architecture effectively enhancing recognition accuracy.

关键词： Training Emotion recognition Visualization Accuracy Text recognition Face recognition Benchmark testing Feature extraction Data mining Context modeling

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Based Scheduling Strategy in Blockchain Payment Channel Networks

引用

IEEE/ACM Transactions on Networking 2024年

作者： Ren, Zhe Wang, Zihao Li, Xinghua Miao, Yinbin Li, Zhuowen Liu, Ximeng Han, Lei Deng, Robert H. Xidian University State Key Laboratory of Integrated Services Networks The School of Cyber Engineering Xi'an710071 China Ministry of Education Engineering Research Center of Big Data Security Xi'an710071 China Fuzhou University College of Mathematics and Computer Science Fuzhou350108 China Fuzhou University Fujian Provincial Key Laboratory of Information Security of Network Systems Fuzhou350116 China Beijing Institute of Computer Technology and Application Beijing100000 China Singapore Management University School of Information Systems Singapore178902 Singapore

With the popularity of blockchains, low transaction throughput has become a significant bottleneck in applications such as cryptocurrencies. Payment channel networks (PCNs) have received attention as a way to improve throughput. However, due to the difficulty of predicting future transactions for nodes, the transactions are prone to failure when the channel balances do not meet required conditions. It has been shown that increasing buffers (queues) in PCNs can increase the success rate of transactions and throughput. Nevertheless, there is no effective transaction scheduling strategy in buffers when transaction values are flexible and variable. To solve this problem, we first formulate the Scheduling Problem in PCNs (named PSP), and then prove it is NP-hard. We design a neural network solver based on the Sequence to Sequence (Seq2Seq) architecture and train the solver using the reinforcement learning method. With the solver, we first give two scheduling strategies to maximize transaction throughput, and then design a PCN simulator for performance evaluation. Extensive experiments are conducted to show the superiority and various performances of our proposal and illustrate that our proposal can get a significant advantage in terms of the transaction throughput compared to the existing works. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Quantum Linear System Solvers: A Survey of Algorithms and Applications

arXiv

引用

arXiv 2024年

作者： Morales, Mauro E.S. Pira, Lirandë Schleich, Philipp Koor, Kelvin Costa, Pedro C.S. An, Dong Aspuru-Guzik, Alán Lin, Lin Rebentrost, Patrick Berry, Dominic W. Joint Center for Quantum Information and Computer Science University of Maryland United States Centre for Quantum Software and Information University of Technology Sydney Australia Centre for Quantum Technologies National University of Singapore Singapore Department of Computer Science University of Toronto Canada Vector Institute for Artificial Intelligence Toronto Canada ContinoQuantum Sydney Australia Beijing International Center for Mathematical Research Peking University Beijing China Department of Chemistry University of Toronto Canada Canadian Institute for Advanced Research Toronto Canada Acceleration Consortium Toronto Canada Department of Chemical Engineering & Applied Chemistry University of Toronto Toronto Canada Department of Materials Science & Engineering University of Toronto Toronto Canada Lebovic Fellow Canadian Institute for Advanced Research Toronto Canada Department of Mathematics University of California Berkeley United States Applied Mathematics and Computational Research Division Lawrence Berkeley National Laboratory Berkeley United States Department of Computer Science National University of Singapore Singapore School of Mathematical and Physical Sciences Macquarie University Sydney Australia

Solving linear systems of equations plays a fundamental role in numerous computational problems from different fields of science. The widespread use of numerical methods to solve these systems motivates investigating the feasibility of solving linear systems problems using quantum computers. In this work, we provide a survey of the main advances in quantum linear systems algorithms, together with some applications. We summarize and analyze the main ideas behind some of the algorithms for the quantum linear systems problem in the literature. The analysis begins by examining the Harrow-Hassidim-Lloyd (HHL) solver. We note its limitations and reliance on computationally expensive quantum methods, then highlight subsequent research efforts which aimed to address these limitations and optimize runtime efficiency and precision via various paradigms. We focus in particular on the post-HHL enhancements which have paved the way towards optimal lower bounds with respect to error tolerance and condition number. By doing so, we propose a taxonomy that categorizes these studies. Furthermore, by contextualizing these developments within the broader landscape of quantum computing, we explore the foundational work that have inspired and informed their development, as well as subsequent refinements. Finally, we discuss the potential applications of these algorithms in differential equations, quantum machine learning, and many-body physics. © 2024, CC BY.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Improved Particle Swarm Optimization Algorithm for EIT Image Reconstruction

Improved Particle Swarm Optimization Algorithm for EIT Image...

引用

IEEE SSD International Multi-Conference on systems, Signals and Devices

作者： Oumayma Kahouli Mariem Hafsa Hiba Hellara Imed Eddine Bennour Najoua Essoukri Ben Amara Olfa Kanoun Department of Computer Science National Engineering School of Sousse University of Sousse Sousse Tunisia Laboratory of Advanced Technology and Intelligent Systems National Engineering School of Sousse Laboratory of Measurement and Sensor Technology Technische Universität Chemnitz Chemnitz Germany Laboratory of Signals Systems Artificial Intelligence and Networks Digital Research Center of Sfax University of Sfax Tunisia

Electrical Impedance Tomography (EIT) is a clinical imaging technique that gained a lot of attention because it is a non-invasive and radiation-free method. To obtain an inner image of the domain under study, a specific number of electrodes is attached to the surface of the object, then through a pair of electrodes, a low alternative current is injected. Potentials produced by this injection are measured with the remaining electrodes. Based on these boundary voltages measurements, the inner conductivity can be inferred, thus the image is reconstructed. The focus of this paper is to overcome the major weakness of the EIT image reconstruction technique, which is the low spatial resolution of the reconstructed images caused by the non-linearity of EIT inverse problem. This paper considers this problem, an optimization problem that is solved using the Particle Swarm Optimization (PSO) meta-heuristic. A variant of the standard PSO is proposed and validated, first on a circular mesh composed of 686 triangles then on a lung mesh composed of 2707 triangles.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Excitatory and Inhibitory Balance for High Learning Performance in Spiking Neural Networks with Long-Tailed Synaptic Weight Distributions

Optimal Excitatory and Inhibitory Balance for High Learning ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ibuki Matsumoto Sou Nobukawa Tomoki Kurikawa Nobuhiko Wagatsuma Yusuke Sakemi Takashi Kanamaru Nina Sviridova Kazuyuki Aihara Graduate School of Information and Computer Science Chiba Institute of Technology Chiba Japan Department of Complex and Intelligent Systems Future University Hakodate Hokkaido Japan Department of Information Science Toho University Chiba Japan Research Center for Mathematical Engineering Chiba Institute of Technology Chiba Japan School of Advanced Engineering Kogakuin University Tokyo Japan Department of Intelligent Systems Tokyo City University Tokyo Japan International Research Center for Neurointelligence The University of Tokyo Tokyo Japan

Excitatory/inhibitory (E/I) balance is significantly associated with cognitive function. Its imbalance impairs cognitive function, particularly in patients with psychiatric disorders. Recent physiological and modeling findings show that excitatory postsynaptic potentials (EPSPs) have a long-tailed distribution and contribute to the generation of spontaneous activity. Moreover, this spontaneous activity and its response to the external stimulus significantly alternate under the different E/I balance. However, the effects of the E/I balance under long-tailed EPSPs at the functional level remain unknown. Hence, to elucidate this relationship, we constructed a reservoir computing (RC) model generating the long-tailed distribution of EPSPs and investigated the effect of the E/I balance on the learning performance of RC in the memory capacity (MC) task, which measures how correctly delayed input signals can be reproduced. The results revealed that an appropriate E/I balance maximized the MC. This high MC was realized by recurrent spike propagation under long-tailed EPSPs. These findings contribute to the understanding of the effect of the E/I balance in physiologically relevant neural networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy grid management system with anomaly detection and Q-learning decision modules

引用

computers and Electrical engineering 2023年第1期107卷

作者： Syu, Jia-Hao Srivastava, Gautam Fojcik, Marcin Cupek, Rafal Lin, Jerry Chun-Wei Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Department of Mathematics and Computer Science Brandon University Brandon Canada Research Center for Interneural Computing China Medical University Taichung Taiwan Department of Computer Science and Math Lebanese American University Beirut Lebanon Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Bergen Norway Department of Distributed Systems and Informatic Devices Silesian University of Technology Gliwice Poland

Stability and security issues in energy management have become widespread research topics, in which artificial intelligence techniques are often embedded in management systems to efficiently manage the smart grid. In this paper, we propose an energy grid management system with anomaly detection and Q-learning decision modules (EMSAD). The anomaly detection module is a multitask learning network that simultaneously classifies suppliers and predicts actual supply quantities. The Q-learning decision module then determines the operating reserve and subsidies to manage the energy grid. Experimental results show that the proposed anomaly detection module has an excellent performance in classifying malicious suppliers with F1-scores from 73.3% to 100.0%. The robustness evaluation also shows that EMSAD maintains high performance even in unseen environments without fine-tuning. Thus, the simulation results demonstrate the security, efficiency, transferability, and robustness of the proposed EMSAD in smart grid energy management. © 2023 Elsevier Ltd

关键词： Energy management

来源：评论

学校读者我要写书评

暂无评论

Over-the-air Wireless Federated Learning Model for Generative AI

引用

IEEE Network 2025年

作者： Zheng, Jie Niyato, Dusit Zhang, Haijun Du, Hongyang Wang, Jiacheng Kang, Jiawen Xiong, Zehui Northwest University State-Province Joint Engineering and Research Center of Advanced Networking and Intelligent Information Services School of Information Science and Technology Shaanxi 710127 China Nanyang Technological University School of Computer Science and Engineering Singapore639798 Singapore University of Science and Technology Beijing Institute of Artificial Intelligence Beijing100083 China University of Hong Kong Department of electrical and electronic engineering Hong Kong Hong Kong Guangdong University of Technology Automation of School Guangzhou510006 China Singapore University of Technology and Design Pillar of Information Systems Technology and Design Singapore

Generative artificial intelligence (GenAI) technologies represent an important advancement in the field of AI, particularly for their capabilities in text and image generation. Over-the-air wireless federated learning (OA-WFL) can utilize the wireless waveform superposition property to achieve efficient model aggregation, thereby providing support for GenAI training and deployment. Therefore, this article investigates the support of OA-WFL for GenAI, focusing on potential applications and specific examples. We first discuss the OA-WFL and GenAI models, emphasizing their functionalities and the potential benefits arising from their interaction. We then explore its application in various GenAI scenarios, including large-scale edge device content generation, efficient distributed training of GenAI models, and reduction of bandwidth requirements and device load. Next, a framework is proposed to apply OA-WFL to diffusion models, such as those used in image generation, and validate its effectiveness through simulation results. Finally, we discuss prospective research directions for the application of OA-WFL for GenAI. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

BG-GAN: Generative AI Enable Representing Brain Structure-Function Connections for Alzheimer's Disease

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Zhou, Tong Ding, Chen Jing, Changhong Liu, Feng Hung, Kevin Pham, Hieu Mahmud, Mufti Lyu, Zhihan Qiao, Sibo Wang, Shuqiang Tsang, Kim-Fung Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen518055 China University of Chinese Academy of Sciences Beijing100864 China Stevens Institute of Technology Department of Systems and Enterprises United States Hong Kong Metropolitan University School of Science and Technology Hong Kong Hong Kong VinUniversity College of Engineering and Computer Science VinUni-Illinois Smart Health Center Viet Nam King Fahd University of Petroleum and Minerals Interdisciplinary Research Center for Biosystems and Machines Department of Information and Computer Science SDAIA-KFUPM Joint Research Center for AI Dhahran Saudi Arabia Uppsala University Department of Game Design Faculty of Arts Sweden Tiangong University School of Software Tianjin300387 China

The relationship between brain structure and function is critical for revealing the pathogenesis of brain disorders, including Alzheimer's disease (AD). However, mapping brain structure to function connections is a very challenging task. In this work, a bidirectional graph generative adversarial network (BG-GAN) is proposed to represent brain structure-function connections. Specifically, by designing a module incorporating inner graph convolution network (InnerGCN), the generators of BG-GAN can employ features of direct and indirect brain regions to learn the mapping function between the structural domain and the functional domain. Besides, a new module named Balancer is designed to counterpoise the optimization between generators and discriminators. By introducing the Balancer into BG-GAN, both the structural generator and functional generator can not only alleviate the issue of mode collapse but also learn complementarity of structural and functional features. Experimental results using Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset show that both generated structure and function connections can improve the identification accuracy of AD. The experimental findings suggest that the relationship between brain structure and function is not a complete one-to-one correspondence. They also suggest that brain structure is the basis of brain function, and the strong structural connections are majorly accompanied by strong functional connections. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

ON THE SIZE DISTRIBUTION OF THE FIXED-LENGTH LEVENSHTEIN BALLS WITH RADIUS ONE

arXiv

引用

arXiv 2022年

作者： Wang, Geyang Wang, Qi Department of Electronic and Computer Engineering Institute for Systems Research University of Maryland College ParkMD20742 United States Department of Computer Science and Engineering National Center for Applied Mathematics Shenzhen Southern University of Science and Technology Nanshan District Guangdong Shenzhen518055 China

The fixed-length Levenshtein (FLL) distance between two words x, y ∈ Znm is the smallest integer t such that x can be transformed to y by t insertions and t deletions. The size of a ball in the FLL metric is a fundamental yet challenging problem. Very recently, Bar-Lev, Etzion, and Yaakobi explicitly determined the minimum, maximum and average sizes of the FLL balls with radius one, respectively. In this paper, based on these results, we further prove that the size of the FLL balls with radius one is highly concentrated around its mean by Azuma's *** Codes 94B50, 05D40 © 2022, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Privacy-Preserving ML for IoT: Cluster-Based Split Federated Learning Scheme for Non-IID Data

Efficient Privacy-Preserving ML for IoT: Cluster-Based Split...

引用

Cyber Security in Networking Conference (CSNet)

作者： Mohamad Arafeh Mohamad Wazzeh Hakima Ould-Slimane Chamseddine Talhi Azzam Mourad Hadi Otrok Department of Software and IT engineering Ecole de Technologie Superieure (ETS) Montreal Canada Department of Mathematics and Computer Science Universite de Quebec a Trois-Rivieres (UQTR) Canada Division of Science New York University Abu Dhabi UAE Department of CSM Cyber Security Systems and Applied AI Research Center Lebanese American University Beirut Lebanon Department of EECS Center of Cyber-Physical Systems (C2PS) Khalifa University Abu Dhabi UAE

This paper proposes a scheme addressing the challenges of integrating privacy-preserving distributed machine learning in the Internet of Things (IoT) context while improving the efficiency of the learning process and accelerating the convergence of the model. Specifically, it addresses the presence of non-independent and identically distributed (Non-IID) data and device heterogeneity, which occurs during parallel training and are common characteristics of IoT environments. In this context, SplitFed is a privacy-preserving technique that combines Federated Learning (FL) and Split Learning (SL) to enable fast and privacy-preserving model training on IoT devices. Through parallelism, FL allows fast and parallel model training. Furthermore, SL enables weak devices to train models through model splitting. However, SplitFed suffers from the increasing convergence time due to the FL parallelism introducing Non-IID and stragglers issues. In this paper, we aim to address the aforementioned problems by proposing a clustering parallelization scheme. As such, similar clients are combined based on their weight divergence and considered a single FL unit addressing the Non-IID problem. Moreover, to improve time efficiency and overcome the stragglers' presence, we offer a second clustering stage that separates clients by efficiency and uses FedAsync for model aggregation.

关键词：

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：