检索结果-内蒙古大学图书馆

Multi-Granularity Distribution Alignment for Cross-Domain Crowd Counting

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society 2025年 PP卷 PP页

作者： Xian Zhong Lingyue Qiu Huilin Zhu Jingling Yuan Shengfeng He Zheng Wang Wuhan University of Technology Sanya Science and Education Innovation Park Sanya 572025 China Nanyang Technological University Rapid-Rich Object Search Lab School of Electrical and Electronic Engineering 639798 Singapore Wuhan University of Technology Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan 430070 China Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan 430070 China Singapore Management University School of Computing and Information Systems 188065 Singapore Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan 430072 China

Unsupervised domain adaptation enables the transfer of knowledge from a labeled source domain to an unlabeled target domain, and its application in crowd counting is gaining momentum. Current methods typically align distributions across domains to address inter-domain disparities at a global level. However, these methods often struggle with significant intra-domain gaps caused by domain-agnostic factors such as density, surveillance angles, and scale, leading to inaccurate alignment and unnecessary computational burdens, especially in large-scale training scenarios. To address these challenges, we propose the Multi-Granularity Optimal Transport (MGOT) distribution alignment framework, which aligns domain-agnostic factors across domains at different granularities. The motivation behind multi-granularity is to capture fine-grained domain-agnostic variations within domains. Our method proceeds in three phases: first, clustering coarse-grained features based on intra-domain similarity; second, aligning the granular clusters using an optimal transport framework and constructing a mapping from cluster centers to finer patch levels between domains; and third, re-weighting the aligned distribution for model refinement in domain adaptation. Extensive experiments across twelve cross-domain benchmarks show that our method outperforms existing state-of-the-art methods in adaptive crowd counting. The code will be available at https://***/HopooLinZ/MGOT.

关键词： crowd counting distribution alignment multi-granularity optimal transport unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

smart decentralised energy management

Smart decentralised energy management

引用

CIRED 2020 Berlin Workshop (CIRED 2020)

作者： Stefan Werner Thomas Walter Christian Wiezorek Christian Backe Miguel Bande Firvida Thomas Vögele Peter Conradi Samrat Bose Enrique Kremers Easy Smart Grid GmbH (ESG) Karlsruhe Germany Technical University of Berlin (TUB) Department of Electrical Engineering and Computer Sciences Berlin Germany German Research Center for Artificial Intelligence (DFKI) Robotics Innovation Center Bremen Germany ALL4IP Technologies Darmstadt Germany European Institute for Energy Research (EIFER) Department of Complex Systems Research Karlsruhe Germany

The German–Finnish research project FUture smart Energy shows, how flexible devices, consuming or producing electricity in electric grids, can be self-organised in a fully decentralised way, using autonomous algorithms integrated with the devices' controllers. By shifting operation time, existing flexible devices are hereby utilised as ‘virtual batteries’, providing high storage capacity and power. To gain sufficient flexibility, a large number of devices like combined heat and power generators, heat pumps (HP), heaters, coolers, charging stations, pumps, household appliances and industrial plants, has to be coordinated. This results in a high system complexity for which the evaluated method provides an easy, resilient, cyber-secure and cost-effective solution. This novel technology uses a new market approach for electric energy systems. A real-time price signal is generated directly out of grid state variables, like frequency, voltage, power or current, and broadcast to the flexible devices. Without a need for central control, the flexible devices react like a natural swarm to the price signal. The system is easily and highly scalable, as adding and removing flexibilities does not imply adapting a central control system. The system can be operated parallel or in addition to existing energy markets.

关键词： Internet of Things smart power grids energy management systems decentralised control power distribution control decision making pricing

来源：评论

学校读者我要写书评

暂无评论

Multi-segment Soft Robot Control via Deep Koopman-based Model Predictive Control

arXiv

引用

arXiv 2025年

作者： Lv, Lei Liu, Lei Bao, Lei Sun, Fuchun Dong, Jiahong Zhang, Jianwei Shan, Xuemei Sun, Kai Huang, Hao Luo, Yu Department of Computer Science and Technology Tsinghua University China School of Biomedical Engineering Tsinghua University China Beijing Soft Robot Tech Co. Ltd. China School of Clinical Medicine Tsinghua University China Department of Informatics University of Hamburg Germany School of Mechanical Engineering and Automation Beihang University China Huawei Noah’s Ark Lab Hong Kong Shanghai Research Institute for Intelligent Autonomous Systems Tongji University China

Soft robots, compared to regular rigid robots, as their multiple segments with soft materials bring flexibility and compliance, have the advantages of safe interaction and dexterous operation in the environment. However, due to its characteristics of high dimensional, nonlinearity, time-varying nature, and infinite degree of freedom, it has been challenges in achieving precise and dynamic control such as trajectory tracking and position reaching. To address these challenges, we propose a framework of Deep Koopman-based Model Predictive Control (DK-MPC) for handling multi-segment soft robots. We first employ a deep learning approach with sampling data to approximate the Koopman operator, which therefore linearizes the high-dimensional nonlinear dynamics of the soft robots into a finite-dimensional linear representation. Secondly, this linearized model is utilized within a model predictive control framework to compute optimal control inputs that minimize the tracking error between the desired and actual state trajectories. The real-world experiments on the soft robot "Chordata" demonstrate that DK-MPC could achieve high-precision control, showing the potential of DK-MPC for future applications to soft robots. More visualization results can be found at https://***/DKMPC/. © 2025, CC BY.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

SYNAPSE: An international roadmap to large brain imaging

引用

Physics Reports 2023年第1期999卷 1-60页

作者： Stampfl, Anton P.J. Liu, Zhongdong Hu, Jun Sawada, Kei Takano, H. Kohmura, Yoshiki Ishikawa, Tetsuya Lim, Jae-Hong Je, Jung-Ho Low, Chian-Ming Teo, Alvin Tok, Eng Soon Tan, Tin Wee Ban, Kenneth Libedinsky, Camilo Tan, Francis Chee Kuan Chen, Kuan-Peng Yang, An-Cheng Chuang, Chao-Chun Chen, Nan-Yow Shih, Chi-Tin Lee, Ting-Kuo Yang, De-Nian Lai, Hsu-Chao Shuai, Hong-Han Cheng, Chang-Chieh Ching, Yu-Tai Li, Chia-Wei Charng, Ching-Che Lo, Chung-Chuan Chiang, Ann-Shyn Recur, Benoit Petibois, Cyril Cheng, Chia-Liang Chen, Hsiang-Hsin Yang, Shun-Min Hwu, Yeukuang Rojviriya, Catleya Rugmai, Supagorn Rujirawat, Saroj Margaritondo, Giorgio Australian Nuclear Science and Technology Organization Lucas Heights 2234 NSW Australia Henan university of Technology Zhengzhou China Shanghai Institute of Applied Physics Chinese Academy of Science Shanghai China RIKEN SPring-8 Center Hyogo 679-5148 Japan Pohang Accelerator Laboratory Pohang University of Science and Technology Pohang Gyeongbuk 37673 South Korea Department of Materials Science and Engineering Pohang University of Science and Technology Gyeongbuk Pohang 37673 South Korea Department of Pharmacology Department of Anaesthesia and Healthy Longevity Research Programme Yong Loo Lin School of Medicine National University of Singapore Singapore School of Chemical and Life Sciences Nanyang Polytechnic Singapore eMaGIC-Lab Department of Physics National University of Singapore Singapore National Supercomputing Center Singapore Department of Psychology The N1 Institute for Health National University of Singapore Singapore Institute of Molecular and Cell Biology A*STAR Singapore Department of Anaesthesia National University Hospital National University Health System Singapore National Center for High-Performance Computing Hsinchu Taiwan Department of Physics Tunghai University Taichung Taiwan Department of Physics National Tsing Hua University Hsinchu Taiwan Institute of Information Science Academia Sinica Taipei Taiwan Department of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Information Technology Service Center National Yang Ming Chiao Tung University Hsinchu Taiwan National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Life Science National Tsing Hua University Hsinchu Taiwan Institute of Systems Neuroscience and Brain Research Center National Tsing Hua University Hsinchu Taiwan Institute of Physics Academia Sinica Taipei Taiwan Department of Physics National Dong Hwa University

Since 2020, synchrotron radiation facilities in several Asia-Pacific countries have been collaborating in a major project called “SYNAPSE” (Synchrotrons for Neuroscience: an Asia-Pacific Scientific Enterprise). They use x-ray imaging to attack in a coordinated fashion one of the major issues in modern science: the structure of animal and human brains, including neurons and connections. The objective is to develop Google-like maps also including detailed structural and functional information for selected regions of interest. The sheer mass of data needed for the objective poses huge problems for the acquisition, processing, storage and use of images. In order to complete the task within a reasonable time, the key element of the SYNAPSE strategy is the parallel and coordinated work of several facilities on the same specimens. This article reviews different aspects of the enterprise, including the foundations of synchrotron radiation, coherence and of its role in advanced imaging, electron accelerators, x-ray optics and detectors. This will provide the foundation for an extensive presentation of the different components of SYNAPSE, with an overview of results already obtained within the consortium. © 2022

关键词： Brain mapping Phase contrast Radiology Supercomputing Synchrotron X-rays

来源：评论

学校读者我要写书评

暂无评论

Intelligent reflecting surface aided MISO uplink communication network: Feasibility and power minimization for perfect and imperfect CSI

arXiv

引用

arXiv 2020年

作者： Liu, Yang Zhao, Jun Li, Ming Wu, Qingqing School of Information and Communication Engineering Dalian University of Technology Dalian China School of Computer Science and Engineering Nanyang Technological University Singapore National Mobile Communications Research Laboratory Southeast University Nanjing210096 China State Key Lab. of Internet of Things for Smart City University of Macau Macau China

In this paper, we consider the weighted sum-power minimization under quality-of-service (QoS) constraints in the multi-user multi-input-single-output (MISO) uplink wireless network assisted by intelligent reflecting surface (IRS). We perform a comprehensive investigation on various aspects of this problem. First, when users have sufficient transmit powers, we present a new sufficient condition guaranteeing arbitrary information rate constraints. This result strengthens the feasibility condition in existing literature. Then, we design novel penalty dual decomposition (PDD) based and nonlinear equality constrained alternative direction method of multipliers (neADMM) based solutions to tackle the IRS-dependent-QoS-constraints, which effectively solve the feasibility check and power minimization problems. Besides, we further extend our proposals to the cases where channel status information (CSI) is imperfect and develop an online stochastic algorithm that satisfy QoS constraints stochastically without requiring prior knowledge of CSI errors. Extensive numerical results are presented to verify the effectiveness of our proposed algorithms. © 2020, CC BY.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Accurately predicting anticancer peptide using an ensemble of heterogeneously trained classifiers

引用

Informatics in Medicine Unlocked 2023年 42卷

作者： Azim, Sayed Mehedi Sabab, Noor Hossain Nuri Noshadi, Iman Alinejad-Rokny, Hamid Sharma, Alok Shatabda, Swakkhar Dehzangi, Iman Center for Computational and Integrative Biology Rutgers University Camden 08102 NJ United States Department of Computer Science and Engineering United International University Plot 2 United City Madani Avenue BaddaDhaka 1212 Bangladesh Department of Bioengineering University of California Riverside 92507 CA United States BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering The University of New South Wales (UNSW Sydney) Sydney NSW 2052 Australia UNSW Data Science Hub UNSW Sydney Sydney NSW 2052 Australia Health Data Analytics Program AI-enabled Processes Research Centre Macquarie University Sydney 2109 Australia Institute for Integrated and Intelligent Systems Griffith University Brisbane Australia Laboratory for Medical Science Mathematics RIKEN Center for Integrative Medical Sciences Yokohama 230-0045 Japan Department of Computer Science Rutgers University Camden 08102 NJ United States

The use of therapeutic peptides for the treatment of cancer has received tremendous attention in recent years. Anticancer peptides (ACPs) are considered new anticancer drugs which have several advantages over chemistry-based drugs including high specificity, strong tumor penetration capacity, and low toxicity level for normal cells. Due to the rise of experimentally verified bioactive peptides, several in silico approaches became imperative for the investigation of the characteristics of ACPs. In this paper, we proposed a new machine learning tool named iACP-RF that uses a combination of several sequence-based features and an ensemble of three heterogeneously trained Random Forest classifiers to accurately predict anticancer peptides. Experimental results show that our proposed model achieves an accuracy of 75.9% which outperforms other state-of-the-art methods by a significant margin. We also achieve 0.52, 75.6%, and 76.2% in terms of Matthews Correlation Coefficient (MCC), Sensitivity, and Specificity, respectively. iACP-RF as a standalone tool and its source code are publicly available at: https://***/MLBC-lab/iACP-RF. © 2023 The Authors

关键词： Anticancer peptides Ensemble learning Feature extraction Heterogeneous classifiers Machine learning Random Forest

来源：评论

学校读者我要写书评

暂无评论

Configurable Phase Transitions in a Topological Thermal Material

引用

Physical Review Letters 2021年第10期127卷 105901-105901页

作者： Guoqiang Xu Ying Li Wei Li Shanhui Fan Cheng-Wei Qiu Department of Electrical and Computer Engineering National University of Singapore Kent Ridge 117583 Republic of Singapore Interdisciplinary Center for Quantum Information State Key Laboratory of Modern Optical Instrumentation ZJU-Hangzhou Global Scientific and Technological Innovation Center Zhejiang University Hangzhou 310027 China International Joint Innovation Center Key Lab. of Advanced Micro/Nano Electronic Devices & Smart Systems of Zhejiang The Electromagnetics Academy at Zhejiang University Zhejiang University Haining 314400 China GPL Photonics Laboratory State Key Laboratory of Applied Optics Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences Changchun 130033 China Department of Electrical Engineering and Ginzton Laboratory Stanford University Stanford California 94305 USA

Diffusive nature of thermal transportation fundamentally restricts topological characteristics due to the absence of a sufficient parametric space with complex dimensionalities. Here, we create an orthogonal advection space with two advective pairs to reveal the unexplored topological transitions in thermal material. We demonstrate four types of configurable thermal phases, including the nontrivial dynamic-equilibrium distribution, nonchiral steplike π-phase transition, and another two trivial profiles related to the anti-parity-time symmetry nature. Our findings provide a recipe for realizing a topologically robust thermal system under arbitrary perturbations.

关键词： Diffusion Heat transfer Topological insulators Topological phase transition Metamaterials Topological materials

来源：评论

学校读者我要写书评

暂无评论

RISCuer: A Reliable Multi-UAV Search and Rescue Testbed

arXiv

引用

arXiv 2020年

作者： Abdelkader, Mohamed Fiaz, Usman A. Toumi, Noureddine Mabrok, Mohamed A. Shamma, Jeff S. Lab King Abdullah University of Science & Technology Thuwal Saudi Arabia Department of Electrical & Computer Engineering Institute for Systems Research University of Maryland College ParkMD United States Group for Research in Decision Analysis Polytechnique Montreal QC Canada Department of Mathematics School of Engineering Australian College of Kuwait Kuwait

We present the Robotics Intelligent systems & Control (RISC) lab multiagent testbed for reliable search and rescue and aerial transport in outdoor environments. The system consists of a team of three multirotor unmanned aerial vehicles (UAVs), which are capable of autonomously searching, picking up, and transporting randomly distributed objects in an outdoor field. The method involves vision based object detection and localization, passive aerial grasping with our novel design, GPS based UAV navigation, and safe release of the objects at the drop zone. Our cooperative strategy ensures safe spatial separation between UAVs at all times and we prevent any conflicts at the drop zone using communication enabled consensus. All computation is performed onboard each UAV. We describe the complete software and hardware architecture for the system and demonstrate its reliable performance using comprehensive outdoor experiments, and by comparing our results with some recent, similar works. Copyright © 2020, The Authors. All rights reserved.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Heat Transfer with Linear Conductive Metamaterials

arXiv

引用

arXiv 2022年

作者： Su, Yishu Li, Ying Qi, Minghong Guenneau, Sebastien Li, Huagen Xiong, Jian Center for Composite Materials and Structures Harbin Institute of Technology Harbin150001 China Interdisciplinary Center for Quantum Information State Key Laboratory of Modern Optical Instrumentation ZJU-Hangzhou Global Scientific and Technological Innovation Center Zhejiang University Hangzhou310027 China International Joint Innovation Center Key Lab. of Advanced Micro/Nano Electronic Devices & Smart Systems of Zhejiang The Electromagnetics Academy of Zhejiang University Zhejiang University Haining314400 China UMI 2004 Abraham de Moivre-CNRS Imperial College London LondonSW7 2AZ United Kingdom Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

Asymmetric heat transfer systems, often referred to as thermal diodes or thermal rectifiers, have garnered increasing interest due to their wide range of application possibilities. Most of those previous macroscopic thermal diodes either resort to nonlinear thermal conductivities with strong temperature dependence that may be quite limited by or fixed in natural materials or rely on active modulation that necessitated auxiliary energy payloads. Here, we establish a straightforward strategy of passively realizing asymmetric heat transfer with linear conductive materials. The strategy also introduces a new interrogative perspective on the design of asymmetric heat transfer utilizing nonlinear thermal conductivity, correcting the misconception that thermal rectification is impossible with separable nonlinear thermal conductivity. The nonlinear perturbation mode can be versatilely engineered to produce an effective and wide-ranging perturbation in the heat conduction, which imitates and bypasses intrinsic thermal nonlinearity constraints set by naturally occurring counterparts. Independent experimental characterizations of surface thermal radiation and thermal convection verified that the heat exchange between a graded linear thermal metamaterial and the ambient can be tailored to achieve macroscopic asymmetric heat transfer. Our work is envisaged to inspire conceptual models for heat transfer control, serving as a robust and convenient platform for advanced thermal management, thermal computation, and heat transport. © 2022, CC BY.

关键词： Thermal conductivity

来源：评论

学校读者我要写书评

暂无评论

Guaranteed Convergence of Training Convolutional Neural Networks via Accelerated Gradient Descent

Guaranteed Convergence of Training Convolutional Neural Netw...

引用

Annual Conference on Information Sciences and systems (CISS)

作者： Shuai Zhang Meng Wang Sijia Liu Pin-Yu Chen Jinjun Xiong Dept. of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy NY USA MIT-IBM Watson AI Lab Cambridge MA USA IBM Thomas J. Watson Research Center NY USA

ISBN: (数字)9781728140858

ISBN: (纸本)9781728188317

In this paper, we study the linear regression problem of training an one-hidden-layer non-overlapping convolutional neural networks (ConvNNs) with the rectified linear unit (ReLU) activation functions. Given a set of training data that contains the inputs (feature vectors) and outputs (labels), the outputs are assumed to be generated from a ConvNN with unknown weights, and our goal is to recover the ground-truth weights by minimizing a non-convex optimization problem whose object function is the empirical loss function. We have proved that if the inputs belong to Gaussian distribution, then the optimization problem can be solved by accelerated gradient descent (AGD) algorithm with a well-designed initial point and enough samples, and the iterates via AGD algorithm converge linearly to the ground-truth weights.

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：