检索结果-内蒙古大学图书馆

Low-rank Adaptation Method for Wav2vec2-based Fake Audio Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Chenglong Yi, Jiangyan Zhang, Xiaohui Tao, Jianhua Xu, Le Fu, Ruibo University of Science and Technology of China Hefei China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences China School of Computer and Information Technology Beijing Jiaotong University China Department of Automation Tsinghua University China

Self-supervised speech models are a rapidly developing research topic in fake audio detection. Many pre-trained models can serve as feature extractors, learning richer and higher-level speech features. However,when fine-tuning pre-trained models, there is often a challenge of excessively long training times and high memory consumption, and complete fine-tuning is also very expensive. To alleviate this problem, we apply low-rank adaptation(LoRA) to the wav2vec2 model, freezing the pre-trained model weights and injecting a trainable rank-decomposition matrix into each layer of the transformer architecture, greatly reducing the number of trainable parameters for downstream tasks. Compared with fine-tuning with Adam on the wav2vec2 model containing 317M training parameters, LoRA achieved similar performance by reducing the number of trainable parameters by 198 times. Copyright © 2023, The Authors. All rights reserved.

关键词： Fake detection

Petri net modeling and lagrangian relaxation approach to vehicle scheduling in 300mm semiconductor manufacturing

学校读者我要写书评

暂无评论

Petri net modeling and lagrangian relaxation approach to veh...

IEEE International Conference on Robotics and automation (ICRA)

作者： Da-Yin Liao MuDer Jeng MengChu Zhou Department of Information Management National Chi Nan University Nantou Taiwan Department of Electrical Engineering National Taiwan Ocean University Keelung Taiwan Laboratory of Complex Systems and Intelligence Science Institute of Automation CAS Beijing China Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark USA

Instead of making decisions with fast but local dispatching functions, the increasing computing power and up-to-moment information provisioning have made possible real-time vehicle scheduling in an automated material handling environment in 300mm semiconductor manufacturing. To our best knowledge, this paper is the first work to adopt the scheduling approach to solve the 300mm vehicle transportation problems. We adopt Petri nets to model the coupling dynamics among transport jobs and OHT vehicles in an intrabay loop. The congestion phenomenon among OHT vehicles is captured. The OHT scheduling problem is then formulated into an integer programming problem whose goal is to efficiently allocate OHT vehicles to jobs such that average job delivery time is minimized. A solution methodology that combines Lagrangian relaxation and the surrogate subgradient methods [13] is developed. To reduce computational efforts in solving each subproblem optimally, an approximation method is developed to solve for subproblems. A heuristic algorithm is developed to adjust the dual solution to a feasible schedule. Numerical results demonstrate that our solution methodology can generate good schedules within a reasonable amount of computation time for realistic problems. Compared to a popular vehicle dispatching rule, our approach can achieve 25.6% improvements on the average delivery time in our realistic test cases.

关键词： Lagrangian functions Vehicles Job shop scheduling Virtual manufacturing Semiconductor device manufacture Processor scheduling Dispatching computer aided manufacturing Materials handling Manufacturing automation

Fusion of Mixture of Experts and Generative Artificial Intelligence in Mobile Edge Metaverse

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Guangyuan Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Jamalipour, Abbas Mao, Shiwen Kim, Dong In The College of Computing and Data Science The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The College of Computing and Data Science Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The Department of Electrical and Computer Engineering Auburn University Auburn United States The School of Electrical and Computer Engineering University of Sydney Australia The Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

In the digital transformation era, Metaverse offers a fusion of virtual reality (VR), augmented reality (AR), and web technologies to create immersive digital experiences. However, the evolution of the Metaverse is slowed down by the challenges of content creation, scalability, and dynamic user interaction. Our study investigates an integration of Mixture of Experts (MoE) models with Generative Artificial Intelligence (GAI) for mobile edge computing to revolutionize content creation and interaction in the Metaverse. Specifically, we harness an MoE model's ability to efficiently manage complex data and complex tasks by dynamically selecting the most relevant experts running various sub-models to enhance the capabilities of GAI. We then present a novel framework that improves video content generation quality and consistency, and demonstrate its application through case studies. Our findings underscore the efficacy of MoE and GAI integration to redefine virtual experiences by offering a scalable, efficient pathway to harvest the Metaverse's full potential. © 2024, CC BY.

关键词： Augmented reality

The applied principles of EEG analysis methods in neuroscience and clinical neurology

学校读者我要写书评

暂无评论

Military Medical Research 2024年第6期11卷 907-941页

作者： Hao Zhang Qing-Qi Zhou He Chen Xiao-Qing Hu Wei-Guang Li Yang Bai Jun-Xia Han Yao Wang Zhen-Hu Liang Dan Chen Feng-Yu Cong Jia-Qing Yan Xiao-Li Li School of Systems Science Beijing Normal UniversityBeijing 100875China College of Electrical and Control Engineering North China University of TechnologyBeijing 100041China School of Automation Science and Engineering South China University of TechnologyGuangzhou 510641China Department of Psychology the State Key Laboratory of Brain and Cognitive Sciencesthe University of Hong KongHong Kong SAR 999077China HKU-Shenzhen Institute of Research and Innovation Shenzhen 518057GuangdongChina Department of Health Technology and Informatics the Hong Kong Polytechnic UniversityHong Kong SAR 999077China Department of Rehabilitation Medicine the First Afliated Hospital of Nanchang UniversityNanchang 330006China Rehabilitation Medicine Clinical Research Center of Jiangxi Province Nanchang 330006China Beijing Key Laboratory of Learning and Cognition School of PsychologyCapital Normal UniversityBeijing 100048China School of Communication Science Beijing Language and Culture UniversityBeijing 100083China Institute of Electrical Engineering Yanshan UniversityQinhuangdao 066004HebeiChina School of Computer Science Wuhan UniversityWuhan 430072China School of Biomedical Engineering Faculty of Electronic Information and Electrical EngineeringDalian University of TechnologyDalian 116081LiaoningChina Guangdong Artifcial Intelligence and Digital Economy Laboratory(Guangzhou) Guangzhou 510335China.

Electroencephalography(EEG)is a non-invasive measurement method for brain *** to its safety,high resolution,and hypersensitivity to dynamic changes in brain neural signals,EEG has aroused much interest in scientific research and medical *** article reviews the types of EEG signals,multiple EEG signal analysis methods,and the application of relevant methods in the neuroscience feld and for diagnosing neurological ***,3 types of EEG signals,including time-invariant EEG,accurate event-related EEG,and random event-related EEG,are ***,5 main directions for the methods of EEG analysis,including power spectrum analysis,time-frequency analysis,connectivity analysis,source localization methods,and machine learning methods,are described in the main section,along with diferent sub-methods and effect evaluations for solving the same ***,the application scenarios of different EEG analysis methods are emphasized,and the advantages and disadvantages of similar methods are *** article is expected to assist researchers in selecting suitable EEG analysis methods based on their research objectives,provide references for subsequent research,and summarize current issues and prospects for the future.

关键词： Electroencephalogram analysis methods Applied principles Neuroscience Diagnosis Neurological diseases

Pointwise Logic on Completely Distributive Lattices and Approximate Reasoning

学校读者我要写书评

暂无评论

Pointwise Logic on Completely Distributive Lattices and Appr...

International Conference on Fuzzy systems and Knowledge Discovery (FSKD)

作者： Yalin Zheng Guang Yang Jing Zheng Jinsheng Xing State Key Laboratory for Intelligent Technology and Systems Department of Automation Faculty of Information Science and Technology Tsinghua University Beijing China Research Center of Intelligent Information Technology Department of Computer Science and Technology Faculty of Software Dongguan University of Science and Technology Dongguan China Research Center of Dongguan Economy Department of Economy and Commerce Dongguan University of Science and Technology Dongguan China Faculty of Mathematics and Computer Science Shanxi Normal University Linfen China Research Center of System Engineering Faculty of Electronic and Information Engineering Xi'an Jiaotong University Xi'an China

In this paper, we propose the basic framework of point- wise topological logic on completely distributive lattices and explore approximate reasoning in it. The logic of this paper is based on pointwise characterization, therefore the pointwise conception is pervasive. We explore approximate reasoning in abstract logical framework Fl on completely distributive lattice L. We propose the structure of point- wise topological logic F TL , the structure of matching function sigma. and the structure of matching neighborhood group. We investigate approximate reasoning in pointwise topological logic F TL with matching function sigma, develop pointwise topological algorithm of simple approximate reasoning, introduce the essential characteristics of this scheme.

关键词： Lattices Fuzzy logic computer science Knowledge engineering Fuzzy systems information technology Laboratories Intelligent systems automation information science

When Large Language Model Agents Meet 6G Networks: Perception, Grounding, and Alignment

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Minrui Niyato, Dusit Kang, Jiawen Xiong, Zehui Mao, Shiwen Han, Zhu Kim, Dong In Letaief, Khaled B. The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore The Department of Electrical and Computer Engineering Auburn University AuburnAL36849-5201 United States The Department of Electrical and Computer Engineering University of Houston HoustonTX77004 United States The Department of Computer Science and Engineering Kyung Hee University Seoul446-701 Korea Republic of The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of Hong Kong

AI agents based on multimodal large language models (LLMs) are expected to revolutionize human-computer interaction and offer more personalized assistant services across various domains like healthcare, education, manufacturing, and entertainment. Deploying LLM agents in 6G networks enables users to access previously expensive AI assistant services via mobile devices democratically, thereby reducing interaction latency and better preserving user privacy. Nevertheless, the limited capacity of mobile devices constrains the effectiveness of deploying and executing local LLMs, which necessitates offloading complex tasks to global LLMs running on edge servers during long-horizon interactions. In this article, we propose a split learning system for LLM agents in 6G networks leveraging the collaboration between mobile devices and edge servers, where multiple LLMs with different roles are distributed across mobile devices and edge servers to perform user-agent interactive tasks collaboratively. In the proposed system, LLM agents are split into perception, grounding, and alignment modules, facilitating inter-module communications to meet extended user requirements on 6G network functions, including integrated sensing and communication, digital twins, and task-oriented communications. Furthermore, we introduce a novel model caching algorithm for LLMs within the proposed system to improve model utilization in context, thus reducing network costs of the collaborative mobile and edge LLM agents. © 2024, CC BY.

关键词： Learning systems

Modal regression based structured low-rank matrix recovery for multi-view learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xu, Jiamiao Wang, Fangzhao Peng, Qinmu You, Xinge Wang, Shuo Jing, Xiao-Yuan Philip Chen, C.L. School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute China State Key Laboratory of Software Engineering School of Computer Wuhan University China Department of Computer and Information Science Faculty of Science and Technology University of Macau 99999 China Dalian Maritime University Dalian116026 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080 China

Low-rank Multi-view Subspace Learning (LMvSL) has shown great potential in cross-view classification in recent years. Despite their empirical success, existing LMvSL based methods are incapable of well handling view discrepancy and discriminancy simultaneously, which thus leads to the performance degradation when there is a large discrepancy among multi-view data. To circumvent this drawback, motivated by the block-diagonal representation learning, we propose Structured Low-rank Matrix Recovery (SLMR), a unique method of effectively removing view discrepancy and improving discriminancy through the recovery of structured low-rank matrix. Furthermore, recent low-rank modeling provides a satisfactory solution to address data contaminated by predefined assumptions of noise distribution, such as Gaussian or Laplacian distribution. However, these models are not practical since complicated noise in practice may violate those assumptions and the distribution is generally unknown in advance. To alleviate such limitation, modal regression is elegantly incorporated into the framework of SLMR (term it MR-SLMR). Different from previous LMvSL based methods, our MR-SLMR can handle any zero-mode noise variable that contains a wide range of noise, such as Gaussian noise, random noise and outliers. The alternating direction method of multipliers (ADMM) framework and half-quadratic theory are used to efficiently optimize MR-SLMR. Experimental results on four public databases demonstrate the superiority of MR-SLMR and its robustness to complicated noise. Copyright © 2020, The Authors. All rights reserved.

关键词： Gaussian noise (electronic)

Energy Efficiency Optimization for Full-Duplex D2D Communications Underlaying Distributed Antenna systems

学校读者我要写书评

暂无评论

IEEE Transactions on Green Communications and Networking

IEEE Transactions on Green Communications and Networking 2024年

作者： Liu, Zhan Liao, Zhiyuan Li, Chunquan Zhang, Zhijun Yu, Junzhi Liu, P.X. Hunan University of Humanities Science and Technology School of Information Loudi417000 China Nanchang University School of Information Engineering Nanchang330031 China Jiangxi Provincial Key Laboratory of Intelligent Systems and Human-Machine Interaction Nanchang330031 China South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics College of Engineering Beijing100871 China Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada

In this paper, we investigate the total system energy efficiency (EE) of full-duplex (FD) device-to-device (D2D) communications underlaying distributed antenna systems (DAS), where remote access units (RAUs), D2D users (DUs), and cellular users (CUs) are all capable of FD operation. Specifically, we jointly optimize subcarrier assignment and power allocation under the quality of service (QoS) requirements of CUs and DUs and the maximum power constraints of RAUs, CUs, and DUs. In addition, we propose a novel spectrum sharing strategy that allows each subcarrier to be assigned to multiple CUs and/or multiple D2D pairs (DPs) for flexibility. To solve the formulated non-convex optimization problem, we first employ fractional programming to transform the objective function in the optimization problem from the fractional form into the equivalent subtractive form. Then, an efficient iterative resource allocation algorithm is proposed, which needs to solve an inner problem in each iteration. After relaxing the variables and introducing penalty factors, the non-convex inner problem is transformed into a convex problem through the successive convex approximation (SCA) method and solved by iterative algorithm. Simulation results demonstrate that the proposed algorithm can considerably improve the system EE compared to other benchmark schemes. Furthermore, the proposed spectrum sharing strategy is superior to the existing sharing strategies. © 2017 IEEE.

关键词： Convex optimization

A Full Dive into Realizing the Edge-enabled Metaverse: Visions, Enabling Technologies,and Challenges

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Minrui Ng, Wei Chong Lim, Wei Yang Bryan Kang, Jiawen Xiong, Zehui Niyato, Dusit Yang, Qiang Shen, Xuemin Sherman Miao, Chunyan The School of Computer Science and Engineering Nanyang Technological University Singapore Alibaba Group Alibaba-NTU Joint Research Institute Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore The Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Webank China The Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada

Dubbed "the successor to the mobile Internet", the concept of the Metaverse has grown in popularity. While there exist lite versions of the Metaverse today, they are still far from realizing the full vision of an immersive, embodied, and interoperable Metaverse. Without addressing the issues of implementation from the communication and networking, as well as computation perspectives, the Metaverse is difficult to succeed the Internet, especially in terms of its accessibility to billions of users today. In this survey, we focus on the edge-enabled Metaverse to realize its ultimate vision. We first provide readers with a succinct tutorial of the Metaverse, an introduction to the architecture, as well as current developments. To enable ubiquitous, seamless, and embodied access to the Metaverse, we discuss the communication and networking challenges and survey cutting-edge solutions and concepts that leverage next-generation communication systems for users to immerse as and interact with embodied avatars in the Metaverse. Moreover, given the high computation costs required, e.g., to render 3D virtual worlds and run data-hungry artificial intelligence-driven avatars, we discuss the computation challenges and cloud-edge-end computation framework-driven solutions to realize the Metaverse on resource-constrained edge devices. Next, we explore how blockchain technologies can aid in the interoperable development of the Metaverse, not just in terms of empowering the economic circulation of virtual user-generated content but also to manage physical edge resources in a decentralized, transparent, and immutable manner. Finally, we discuss the future research directions towards realizing the true vision of the edge-enabled Metaverse. © 2022, CC BY.

关键词： Blockchain