检索结果-内蒙古大学图书馆

SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognition

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lei, Mengqi Wu, Yihong Li, Siqi Zheng, Xinhu Wang, Juan Gao, Yue Du, Shaoyi BNRist THUIBCS BLBCI School of Software Tsinghua University Beijing100084 China Department of Mechanical Engineering Taiyuan University of Technology Taiyuan030024 China Guangzhou China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Department of Ultrasound the Second Affiliated Hospital of Xi’an Jiaotong University Xi’an China Department of Ultrasound the Second Affiliated Hospital Xi’an Jiaotong University China State Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China

Visual recognition relies on understanding both the semantics of image tokens and the complex interactions among them. Mainstream self-attention methods, while effective at modeling global pair-wise relations, fail to capture high-order associations inherent in real-world scenes and often suffer from redundant computation. Hypergraphs extend conventional graphs by modeling high-order interactions and offer a promising framework for addressing these limitations. However, existing hypergraph neural networks typically rely on static and hard hyperedge assignments, leading to excessive and redundant hyperedges with hard binary vertex memberships that overlook the continuity of visual semantics. To overcome these issues, we present Soft Hypergraph Neural Networks (SoftHGNNs), which extend the methodology of hypergraph computation, to make it truly efficient and versatile in visual recognition tasks. Our framework introduces the concept of soft hyperedges, where each vertex is associated with hyperedges via continuous participation weights rather than hard binary assignments. This dynamic and differentiable association is achieved by using the learnable hyperedge prototype. Through similarity measurements between token features and the prototype, the model generates semantically rich soft hyperedges. By using these soft hyperedges as the medium for message aggregation and dissemination, SoftHGNN models various high-order semantic relationships within visual features. To further enhance efficiency when scaling up the number of soft hyperedges, we incorporate a sparse hyperedge selection mechanism that activates only the top-k important hyperedges, along with a load-balancing regularizer to ensure adequate and balanced hyperedge utilization. Experimental results across three tasks on five datasets demonstrate that SoftHGNN efficiently captures high-order associations in visual scenes, achieving significant performance improvements. The source code of our framework is availa

关键词： computer vision

Recognition of patient groups with sleep related disorders using bio-signal processing and deep learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jarchi, Delaram Andreu-Perez, Javier Kiani, Mehrin Vysata, Oldrich Kuchynka, Jiri Prochazka, Ales Sanei, Saeid Smart Health Technologies Group School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom Embedded and Intelligent Systems Laboratory School of Computer Science and Electronics University of Essex ColchesterCO4 3SQ United Kingdom Department of Computing and Control Engineering University of Chemistry and Technology in Prague Prague 6166 28 Czech Republic Department of Neurology Faculty of Medicine in Hradec Králové Charles University Hradec Králové500 05 Czech Republic Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Prague 6160 00 Czech Republic School of Science and Technology Nottingham Trent University NottinghamNG11 8NS United Kingdom

Accurately diagnosing sleep disorders is essential for clinical assessments and treatments. Polysomnography (PSG) has long been used for detection of various sleep disorders. In this research, electrocardiography (ECG) and electromayography (EMG) have been used for recognition of breathing and movement-related sleep disorders. Bio-signal processing has been performed by extracting EMG features exploiting entropy and statistical moments, in addition to developing an iterative pulse peak detection algorithm using synchrosqueezed wavelet transform (SSWT) for reliable extraction of heart rate and breathing-related features from ECG. A deep learning framework has been designed to incorporate EMG and ECG features. The framework has been used to classify four groups: healthy subjects, patients with obstructive sleep apnea (OSA), patients with restless leg syndrome (RLS) and patients with both OSA and RLS. The proposed deep learning framework produced a mean accuracy of 72% and weighted F1 score of 0.57 across subjects for our formulated four-class problem. © 2021, CC BY-NC-ND.

关键词： Wavelet transforms

A multi-objective deep reinforcement learning algorithm for spatio-temporal latency optimization in mobile IoT-enabled edge computing networks

学校读者我要写书评

暂无评论

Simulation Modelling Practice and Theory 2025年 143卷

作者： Khoshvaght, Parisa Haider, Amir Rahmani, Amir Masoud Gharehchopogh, Farhad Soleimanian Anka, Ferzat Lansky, Jan Hosseinzadeh, Mehdi Institute of Research and Development Duy Tan University Da Nang Viet Nam School of Engineering & Technology Duy Tan University Da Nang Viet Nam Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura140401 India Department of AI and Robotics Sejong University Seoul05006 Korea Republic of Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Department of Computer Engineering Ur. C. Islamic Azad University Urmia Iran Fatih Sultan Mehmet Vakif University Istanbul Turkey Department of Computer Science and Mathematics Faculty of Economic Studies University of Finance and Administration Prague Czech Republic Pattern Recognition and Machine Learning Laboratory School of Computing Gachon University Seongnam Korea Republic of

The rapid increase in Mobile Internet of Things (IoT) devices requires novel computational frameworks. These frameworks must meet strict latency and energy efficiency requirements in Edge and Mobile Edge Computing (MEC) systems. Spatio-temporal dynamics, which include the position of edge servers and the timing of task schedules, pose a complex optimization problem. These challenges are further exacerbated by the heterogeneity of IoT workloads and the constraints imposed by device mobility. The balance between computational overhead and communication challenges is also a problem. To solve these issues, advanced methods are needed for resource management and dynamic task scheduling in mobile IoT and edge computing environments. In this paper, we propose a Deep Reinforcement Learning (DRL) multi-objective algorithm, called a Double Deep Q-Learning (DDQN) framework enhanced with Spatio-temporal mobility prediction, latency-aware task offloading, and energy-constrained IoT device trajectory optimization for federated edge computing networks. DDQN was chosen for its optimize stability and reduced overestimation in Q-values. The framework employs a reward-driven optimization model that dynamically prioritizes latency-sensitive tasks, minimizes task migration overhead, and balances energy efficiency across devices and edge servers. It integrates dynamic resource allocation algorithms to address random task arrival patterns and real-time computational demands. Simulations demonstrate up to a 35 % reduction in end-to-end latency, a 28 % improvement in energy efficiency, and a 20 % decrease in the deadline-miss ratio compared to benchmark algorithms. © 2025 Elsevier B.V.

关键词： Resource allocation

Task-informed fidelity management for speeding up robotics simulation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Tallavajhula, Abhijeet Schoisengeier, Adrian Kim, Sung-Kyun Vemula, Anirudh Lister, Levi Salzman, Oren National Robotics Engineering Center Carnegie Mellon University Jet Propulsion Laboratory California Institute of Technology Robotics Institute Carnegie Mellon University Computer Science Department Technion-Israel Institute of Technology

Simulators are an important tool in robotics that is used to develop robot software and generate synthetic data for machine learning algorithms. Faster simulation can result in better software validation and larger amounts of data. Previous efforts for speeding up simulators have been performed at the level of simulator building blocks, and robot systems. Our key insight, motivating this work, is that further speedups can be obtained at the level of the robot task. Building on the observation that not all parts of a scene need to be simulated in high fidelity at all times, our approach is to toggle between high- and low-fidelity states for scene objects in a task-informed manner. Our contribution is a framework for speeding up robot simulation by exploiting task knowledge. The framework is agnostic to the underlying simulator, and preserves simulation fidelity. As a case study, we consider a complex material-handling task. For the associated simulation, which contains many of the characteristics that make robot simulation slow, we achieve a speedup that can be up to three times faster than high fidelity without compromising on the quality of the results. We also demonstrate that faster simulation allows us to train better policies for performing the task at hand in a short period of time. A video summarizing our contributions can be found at https://***/PEzypDyqc3o. Copyright © 2019, The Authors. All rights reserved.

关键词： Simulators

F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Wenhao Jin, Bo Wang, Xiangfeng Yan, Junchi Zha, Hongyuan School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai201804 China School of Computer Science and Technology Key Laboratory of Mathematics and Engineering Applications Ministry of Education East China Normal University Shanghai200062 China Department of Computer Science and Engineering Key Laboratory of Artificial Intelligence Ministry of Education Shanghai Jiao Tong University Shanghai200240 China

Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractical in complicated applications due to non-interactivity between agents, the curse of dimensionality, and computation complexity. Hence, several decentralized MARL algorithms are motivated. However, existing decentralized methods only handle the fully cooperative setting where massive information needs to be transmitted in training. The block coordinate gradient descent scheme they used for successive independent actor and critic steps can simplify the calculation, but it causes serious bias. This paper proposes a flexible fully decentralized actor-critic MARL framework, which can combine most of the actor-critic methods and handle large-scale general cooperative multi-agent settings. A primal-dual hybrid gradient descent type algorithm framework is designed to learn individual agents separately for decentralization. From the perspective of each agent, policy improvement and value evaluation are jointly optimized, which can stabilize multi-agent policy learning. Furthermore, the proposed framework can achieve scalability and stability for the large-scale environment. This framework also reduces information transmission by the parameter sharing mechanism and novel modeling-other-agents methods based on theory-of-mind and online supervised learning. Sufficient experiments in cooperative Multiagent Particle Environment and StarCraft II show that the proposed decentralized MARL instantiation algorithms perform competitively against conventional centralized and decentralized methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Gradient methods

Perovskite superlattices with efficient carrier dynamics

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Xu, Sheng Lei, Yusheng Li, Yuheng Lu, Chengchangfeng Yan, Qizhang Gong, Huaxin Zhang, Song Zhou, Jiayun Zhang, Ruiqi Chen, Yimu Tsai, Hsinhan Gu, Yue Hu, Hongjie Lo, Yu-Hwa Nie, Wanyi Lee, Taeyoon Luo, Jian Yang, Kesong Jang, Kyung-In Department of Nanoengineering University of California San Diego La Jolla CA92093-0448 United States Department of Chemical Engineering Stanford University StanfordCA94305 United States Department of Electrical and Computer Engineering University of California San Diego La Jolla CA92093 United States Material Science and Engineering Program University of California San Diego La Jolla CA92093-0418 United States Los Alamos National Laboratory Los AlamosNM87545 United States School of Electrical and Electronic Engineering Yonsei University Seoul03722 Korea Republic of Department of Bio and Brain Engineering Korea Institute of Science and Technology Korea Republic of Department of Robotics Engineering Daegu Gyeongbuk Institute of Science and Technology Daegu42988 Korea Republic of Department of Bioengineering University of California San Diego La Jolla CA92093-0412 United States

Compared with their three-dimensional counterparts, low-dimensional metal halide perovskites with periodic inorganic/organic structures have shown promising stability and hysteresis-free electrical performance, which paves the way for next-generation optoelectronic devices. However, when integrated in devices, they have relatively limited efficiencies because devices usually require carrier transport through the film thickness direction. In conventionally grown single crystals, the carrier transport in the thickness direction is hindered by the insulating organic spacers. In addition, the strong quantum confinement from the organic spacers limits the generation and transport of free carriers. The carrier dynamics is further compromised by the presence of grain boundaries in polycrystals. Here, we report a low-dimensional metal halide perovskite superlattice with efficient carrier transport in three dimensions by epitaxial growth. Epitaxy on a slightly lattice-mismatched substrate compresses the organic spacers in the superlattice, which weakens the quantum confinement and further improves carrier dynamics. The performance of a low-dimensional perovskite superlattice solar cell has been certified under the quasi-steady state for the first time. Moreover, the device shows an unusually high open-circuit voltage, due to a unique intra-band exciton relaxation mechanism. © 2021, CC BY.

关键词： Grain boundaries

Trajectory tracking of optimal social distancing strategies with application to a CoVid-19 scenario

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Di Lauro, Francesco Kiss, István Zoltán Rus, Daniela Santina, Cosimo Della Department of Mathematics School of Mathematical and Physical Sciences University of Sussex FalmerBrightonBN1 9QH United Kingdom MIT Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology CambridgeMA United States Cognitive Robotics Department Delft University of Technology DelftCD2628 Netherlands Oberpfaffenhofen Germany

This letter proposes the use of nonlinear feedback control to produce robust and reactive social distancing policies that can be adapted in response to an epidemic outbreak. A trajectory tracking algorithm is proposed, and its effectiveness is analytically proven when acting on a low-dimensional approximation of the epidemics. Means of mapping the inputs and output of this controller to a more realistic epidemic model of an explicit network of contacts is introduced. The strategy is tested with extensive simulations in a Covid-19 inspired scenario, with particular focus on the case of Codogno - a small city in Northern Italy that has been among the most harshly hit by the pandemic. The proposed algorithm generates dramatic reductions in the number of infected people, while maintaining a total level of social distancing close to the nominal optimum. Copyright © 2020, The Authors. All rights reserved.

关键词： Approximation algorithms

Optimizing Multi-class Fleet Compositions for Shared Mobility-as-a-Service

学校读者我要写书评

暂无评论

Optimizing Multi-class Fleet Compositions for Shared Mobilit...

International Conference on Intelligent Transportation

作者： Alex Wallar Wilko Schwarting Javier Alonso-Mora Daniela Rus Computer Science and Artificial Intelligence Laboratory of the Massachusetts Institute of Technology Cambridge MA USA Department of Cognitive Robotics Delft University of Technology Delft Netherlands

Mobility-as-a-Service (MaaS) systems are transforming the way society moves. The introduction and adoption of pooled ride-sharing has revolutionized urban transit with the potential of reducing vehicle congestion, improving accessibility and flexibility of a city's transportation infrastructure. Recently developed algorithms can compute routes for vehicles in realtime for a city-scale volume of requests, as well as optimize fleet sizes for MaaS systems that allow requests to share vehicles. Nonetheless, they are not capable of reasoning about the composition of a fleet and their varying capacity classes. In this paper, we present a method to not only optimize fleet sizes, but also their multi-class composition for MaaS systems that allow requests to share vehicles. We present an algorithm to determine how many vehicles of each class and capacity are needed, where they should be initialized, and how they should be routed to service all the travel demand for a given period of time. The algorithm maximizes utilization while reducing the total number of vehicles and incorporates constraints on wait- times and travel-delays. Finally, we evaluate the effectiveness of the algorithm for multi-class fleets with pooled ride-sharing using 426,908 historical taxi requests from Manhattan and 187,243 downtown Singapore. We show fleets comprised of vehicles with smaller capacities can reduce the total travel delay by 10% in Manhattan whereas larger capacity fleets in downtown Singapore contribute to a 9% reduction in the total waiting time.

关键词： Delays Schedules Automobiles Quality of service Urban areas Optimization

Localizing dexterous surgical tools in X-ray for image-based navigation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Gao, Cong Unberath, Mathias Taylor, Russell Armand, Mehran Department of Computer Science Johns Hopkins University Laboratory for Computational Sensing and Robotics Johns Hopkins University Johns Hopkins University Applied Physics Laboratory Department of Orthopaedic Surgery Johns Hopkins Hospital