检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Pu, L.I. Xiaoyan, Y.U. Peng, Hao Xian, Yantuan Wang, Linqin Li, S.U.N. Zhang, Jingyun Philip, S.Y.U. Faculty of Information Engineering and Automation Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Kunming650500 China School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China School of Cyber Science and Technology Beihang University No. 37 Xue Yuan Road Haidian District Beijing100191 China School of Control and Computer Engineering North China Electric Power University Beijing102206 China Department of Computer Science University of Illinois at Chicago ChicagoIL60607 United States

Social Event Detection (SED) aims to identify significant events from social streams, and has a wide application ranging from public opinion analysis to risk management. In recent years, Graph Neural Network (GNN) based solutions have achieved state-of-the-art performance. However, GNN-based methods often struggle with missing and noisy edges between messages, affecting the quality of learned message embedding. Moreover, these methods statically initialize node embedding before training, which, in turn, limits the ability to learn from message texts and relations simultaneously. In this paper, we approach social event detection from a new perspective based on Pre-trained Language Models (PLMs), and present RPLM (Relational prompt-based Pre-trained Language Models for Social Event Detection). We first propose a new pairwise message modeling strategy to construct social messages into message pairs with multi-relational sequences. Secondly, a new multi-relational prompt-based pairwise message learning mechanism is proposed to learn more comprehensive message representation from message pairs with multi-relational prompts using PLMs. Thirdly, we design a new clustering constraint to optimize the encoding process by enhancing intra-cluster compactness and inter-cluster dispersion, making the message representation more distinguishable. We evaluate the RPLM on three real-world datasets, demonstrating that the RPLM model achieves state-of-the-art performance in offline, online, low-resource, and long-tail distribution scenarios for social event detection tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Reduced Network Cumulative Constraint Violation for Distributed Bandit Convex Optimization under Slater’s Condition

arXiv

引用

arXiv 2024年

作者： Zhang, Kunpeng Yi, Xinlei Ding, Jinliang Cao, Ming Johansson, Karl H. Yang, Tao State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Department of Control Science and Engineering College of Electronics and Information Engineering Tongji University Shanghai201800 China Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen GroningenAG 9747 Netherlands Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures Stockholm10044 Sweden

This paper studies the distributed bandit convex optimization problem with time-varying inequality constraints, where the goal is to minimize network regret and cumulative constraint violation. To calculate network cumulative constraint violation, existing distributed bandit online algorithms solving this problem directly use the clipped constraint function to replace its original constraint function. However, the use of the clipping operation renders Slater’s condition (i.e, there exists a point that strictly satisfies the inequality constraints at all iterations) ineffective to achieve reduced network cumulative constraint violation. To tackle this challenge, we propose a new distributed bandit online primal–dual algorithm. If local loss functions are convex, we show that the proposed algorithm establishes an O(T max{c,1−c})network regret bound and an O(T 1−c/2) network cumulative constraint violation bound, where T is the total number of iterations and c ∈ (0, 1) is a user-defined trade-off parameter. When Slater’s condition holds, the network cumulative constraint violation bound is reduced to O(T 1−c). In addition, if local loss functions are strongly convex, for the case where strongly convex parameters are unknown, the network regret bound is reduced to O(T1−c), and the network cumulative constraint violation bound is O(T1−c/2) and O(T1−c) without and with Slater’s condition, respectively. For the case where strongly convex parameters are known, the network regret bound is further reduced to O)(log(T)), and the network cumulative constraint violation bound is reduced to O(log(T)T) and O(log(T)) without and with Slater’s condition, respectively. To the best of our knowledge, this paper is among the first to establish reduced (network) cumulative constraint violation bounds for (distributed) bandit convex optimization with time-varying constraints under Slater’s condition. Finally, a numerical example is provided to verify the theoretical results. Copyright © 2

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Manufacturing Process Selection Using Graph Neural Networks: A Novel Approach to CAD Model Semantic Segmentation

Manufacturing Process Selection Using Graph Neural Networks:...

引用

Artificial Intelligence and Intelligent Manufacturing (AIIM), International Symposium on

作者： Shuai Niu Yishu Cai Feng Li Yibo Li Xiaomeng Tong School of Automation Science and Electrical Engineering Beihang University (BUAA) Beijing China Department of computer science University of Liverpool Liverpool United Kingdom AVIC Shenyang Aircraft Corporation Shenyang China State Key Laboratory of Precision Manufacturing for Extreme Service Performance Central South University Changsha China

ISBN: (数字)9798331541729

ISBN: (纸本)9798331541736

Manufacturing process selection, as a core element in the manufacturing workflow, plays a crucial role in improving processing efficiency and manufacturing quality. However, due to the fragmented, experience-based, and often outdated nature of processing knowledge, current process selection methods heavily rely on human intervention. To address these challenges, this study proposes an innovative approach that reframes manufacturing process selection as a graph-based semantic segmentation task. Building on this concept, we introduce a graph neural network-based method for manufacturing process selection, capable of effectively identifying processing methods in CAD models. This method discretely samples the topological faces and edges of CAD models, storing them as node and edge attributes in an attributed adjacency graph. Finally, we design experiments to validate the effectiveness and accuracy of this method in identifying manufacturing processes. Experimental results demonstrate that representing 3D CAD models with attributed adjacency graphs effectively captures the geometric and topological relationships between different faces of the model. This method can accurately identify corresponding manufacturing processes at the topological face level of CAD models, offering a novel approach to automated process selection.

关键词： Solid modeling Manufacturing processes Accuracy Three-dimensional displays Semantic segmentation Buildings System integration Graph neural networks Manufacturing Faces

来源：评论

学校读者我要写书评

暂无评论

More task-balanced Class-Incremental Learning

More task-balanced Class-Incremental Learning

引用

Youth Academic Annual Conference of Chinese Association of automation (YAC)

作者： Junzhi Chen Tian Wang Deyuan Liu Jian Wang Yao Fu Hichem Soussi School of Automation Science and Electrical Engineering Beihang University Beijing China Institute of Artificial Intelligence SKLSDE Beihang University Zhongguancun Laboratory Beijing China School of Computer Science Wuhan University Wuhan China Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences Changchun China Laboratory of Computer Science and Digital Society University of Technology of Troyes Troyes France

Although deep learning has achieved high performance on many tasks, neural networks suffer from catastrophic forgetting in incremental learning scenarios. Class-Incremental Learning focuses on the scenario where new category data continuously arrives. PASS (Prototype Augmentation and Self-Supervised) is a classic method that does not require storing old exemplars. Based on PASS, we propose three improvement measures from the perspective of making the new and old tasks more balanced. Firstly, we propose a balanced prototype replay (Balanced PR) strategy to make the image number of new and old categories that the model head encounters more balanced. Secondly, at the feature knowledge distillation (FKD) stage, we assign different weights to the incoming data based on the confidence of the old model, which is named Focal FKD. The goal is to minimize interference with learning new task data while preserving the representation capability of the model backbone on old data. Thirdly, we combine FKD with weight regularization on the model backbone. In the feature space, FKD is beneficial for preserving the positions of the old categories while weight regularization helps to separate the new and old categories well. Experiments on the benchmark indicate that there has been obvious improvement in the performance of PASS after our modifications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Denoising Diffusion Model-Based Channel Estimation in IRS-Assisted ISAC Systems

Denoising Diffusion Model-Based Channel Estimation in IRS-As...

引用

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Lan Yi Jiansong Miao Tao Zhang Zhenhui Yuan Jiawen Kang Dusit Niyato Beijing Laboratory of Advanced Information Networks Beijing University of Posts and Telecommunications Beijing China School of Software Engineering Beijing Jiaotong University Beijing China School of Engineering University of Warwick UK School of Automation Guangdong University of Technology Guangzhou China School of Computer Science and Engineering Nanyang Technological University Singapore Singapore

ISBN: (数字)9798350390643

ISBN: (纸本)9798350390650

In Integrated Sensing and Communications (ISAC) systems assisted by Intelligent Reflecting Surfaces (IRS), precise channel estimation is crucial for optimal system performance and maximizing the potential benefits. The estimation problem, however, becomes intricate due to complex channel coupling and specific environmental conditions. This paper addresses these challenges by formulating channel estimation as a denoising problem and proposing a novel diffusion-based framework. This approach mitigates the impact of ill-posedness, which is typically problematic for general neural network (NN)-based techniques. By modeling the joint distribution and sampling from the learned posterior distribution, we accurately recover the channel coefficients from noisy pilot-based observations. Simulation results demonstrate significant performance improvements of the proposed method compared to both least-squares and NN-based benchmarks. Moreover, thanks to the carefully designed architecture and residual prediction strategy, the number of sampling steps in the diffusion reverse process is greatly reduced, enabling real-time CSI acquisition.

关键词： Wireless communication System performance Noise reduction Channel estimation Signal processing algorithms Estimation Artificial neural networks Integrated sensing and communication Prediction algorithms Diffusion models

来源：评论

学校读者我要写书评

暂无评论

Stimulated Emission Depletion (STED) Magnetic Particle Imaging

arXiv

引用

arXiv 2024年

作者： Jia, Guang Bian, Zhongwei Li, Tianshu Bai, Shi Hu, Chenxing Zhao, Lixuan Gao, Peng Li, Tanping Hui, Hui Tian, Jie School of Computer Science and Technology Xidian University Shaanxi Xi’an China School of Biological Science and Medical Engineering Beihang University Beijing China School of Information Science and Engineering Shenyang University of Technology Liaoning Shenyang China School of Physics Xidian University Shaanxi Xi’an China CAS Key Laboratory of Molecular Imaging Institute of Automation Chinese Academy of Sciences Beijing China

Magnetic particle imaging (MPI) is an in-vivo imaging method to detect magnetic nanoparticles for blood vessel imaging and molecular target imaging. Compared with conventional molecular imaging devices (such as nuclear medicine imaging PET and SPECT), magnetic nanoparticles have longer storage periods than radionuclides without ionizing radiation. MPI has higher detection sensitivity compared with MRI. To accurately locate molecular probes in living organisms, high-resolution images are needed to meet the requirements of precision medicine. The spatial resolution of the latest domestic and international MPI equipment is 1-6 mm and has not yet met the requirements of medical imaging detection. We previously studied the spatial encoding technology based on pulsed square wave stimulation, which significantly improved the image resolution along the field free line (FFL) direction. This study proposes an innovative idea of high-resolution MPI based on stimulated emission depletion (STED) of magnetic nanoparticle signals. The stimulated emission was implemented by using cosine stimulation on FFL-based MPI scanner systems. The STED signal was generated by adding an offset magnetic field parallel to the FFL, which may form a donut-shaped focal spot or a regular Gaussian focal spot depending on the offset field strength. Focal spot modulation techniques and deconvolution algorithms were developed to improve image resolution. Copyright © 2024, The Authors. All rights reserved.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

Research Progress in Cell Classification Detection Based on Deep Learning

Research Progress in Cell Classification Detection Based on ...

引用

IEEE International Conference on Cyber Technology in automation, Control, and Intelligent Systems

作者： Dongze Gai Chuang Zhang Yiwei Zhang Jiaduo Guo Qi Zhang Hengshen Qin Dan Dang School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China School of Mechanical Engineering Shenyang Jianzhu University Shenyang China School of Science Shenyang Jianzhu University Shenyang China

ISBN: (数字)9798331506056

ISBN: (纸本)9798331506063

This paper reviews the application of deep learning in cell classification detection, highlights the importance of convolutional neural networks in image analysis, and discusses the application of image preprocessing, feature extraction and deep learning models. Despite the progress made by deep learning techniques in improving cell classification accuracy, challenges such as data quality, model generalization and interpretability remain. This article suggests future research directions, including combining medical knowledge with deep learning and developing multimodal learning to improve the accuracy and efficiency of cell detection. Meanwhile, this article also explores the potential of label-free cell classification methods combining optically induced optically-induced dielectrophoresis (ODEP) techniques with deep learning to achieve cell classification without labeling, providing a new perspective on cell analysis. optically induced.

关键词： Deep learning YOLO Biomedical optical imaging Accuracy Image analysis Optical imaging Feature extraction Labeling Image preprocessing Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Filling Deterministic Approximate Gap in Denoising Diffusion Probabilistic Models with Energy

Filling Deterministic Approximate Gap in Denoising Diffusion...

引用

Youth Academic Annual Conference of Chinese Association of automation (YAC)

作者： Ge Kan Tian Wang Deyuan Liu Jian Wang Yao Fu Hichem Snoussi School of Automation Science and Electrical Engineering Beihang University Beijing China Institute of Artificial Intelligence SKLSDE Beihang University Zhongguancun Laboratory Beijing China School of Computer Science Wuhan University Wuhan China Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences Changchun China Laboratory of Computer Science and Digital Society University of Technology of Troyes Troyes France

Diffusion probabilistic models (DPMs) have shown the best generative quality and admit impressive likelihood meanwhile. However, its variants take very long generative processes during sampling, because of the small noise scale assumption, say, sets the variance of the forward diffusion kernel to be very small. Under which, the generative denoising processes are of tractable Gaussian form. To shorten the generative process, we explore the non-Gaussian reverse kernel under the large noise scale assumption and analysis the deterministic approximate gap of Gaussian denoising process. To fill the gap, we enhance the standard DPM with conditional energy and introduce variantional sampler to construct tractable generative process. The new probabilistic model, termed denoising diffusion energy-based model (DDEBM), are trained with two stage adversarial optimization. Experiments show our models demonstrate competitive generative performance with only four steps.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ag2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representations

Ag2Manip: Learning Novel Manipulation Skills with Agent-Agno...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Puhao Li Tengyu Liu Yuyang Li Muzhi Han Haoran Geng Shu Wang Yixin Zhu Song-Chun Zhu Siyuan Huang National Key Laboratory of General Artificial Intelligence Beijing Institute for General Artificial Intelligence (BIGAI) Department of Automation Tsinghua University Institute for Artificial Intelligence Peking University University of California Los Angeles School of Electronics Engineering and Computer Science Peking University

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Autonomous robotic systems capable of learning novel manipulation tasks are poised to transform industries from manufacturing to service automation. However, current methods (e.g., VIP and R3M) still face significant hurdles, notably the domain gap among robotic embodiments and the sparsity of successful task executions within specific action spaces, resulting in misaligned and ambiguous task representations. We introduce Ag2Manip (Agent-Agnostic representations for Manipulation), a framework aimed at addressing these challenges through two key innovations: (1) an agent-agnostic visual representation derived from human manipulation videos, with the specifics of embodiments obscured to enhance generalizability; and (2) an agent-agnostic action representation abstracting a robot’s kinematics to a universal agent proxy, emphasizing crucial interactions between end-effector and object. Ag2Manip has been empirically validated across simulated benchmarks, showing a 325% performance increase without relying on domain-specific demonstrations. Ablation studies further underline the essential contributions of the agent-agnostic visual and action representations to this success. Extending our evaluations to the real world, Ag2Manip significantly improves imitation learning success rates from 50% to 77.5%, demonstrating its effectiveness and generalizability across both simulated and real environments.

关键词： Visualization Technological innovation Service robots Navigation Transforms Kinematics Manufacturing Robots Intelligent robots Videos

来源：评论

学校读者我要写书评

暂无评论

Improved Sliding Window Smoothing for Video Temporal Action Segmentation and Recognition

Improved Sliding Window Smoothing for Video Temporal Action ...

引用

Chinese automation Congress (CAC)

作者： Ce Li Yihan Tian Longshuai Sheng Junzhi Chen Tian Wang Xianlong Wei Computer Science and Technology China University of Mining & Technology Beijing Peking University Beijing China Computer Science and Technology China University of Mining & Technology Beijing Beijing China School of Automation Science and Electrical Engineering Beihang University Beijing China Zhongguancun Laboratory Institute of Artificial Intelligence SKLSDE Beihang University Beijing China

Despite substantial research on human action segmentation in videos to determine the type and timing of activities, the topic is still unresolved because of the dearth of large-scale annotation data in video analysis applications. Supervised video action segmentation employs a number of temporal convolutional network (TCN) models to address this problem. The process is still difficult, because of the intricate temporal duration division of the movements in the videos. In order to create a soft and flexible video partition, we incorporate an improved sliding window smoothing (ISWS) technique into a TCN baseline model in this study. When screening the target video segmentation sequence, our research method carefully selects three discriminative frames and cleverly integrates them into the adaptive sliding window to more specifically optimize the smoothing effect of the entire prediction sequence. It is particularly worth noting that we implement a doubling penalty mechanism when the window slides to the wrong category position. In order to learn the resultants of effective and ineffective segmentation paths, we designed a new loss function to smooth the candidate frames of the segmentation points in the sliding window using the ISWS scheme. So that our method can increase the receptive field of video segmentation effectively to gain the optimal action segmentation. Experiments on the breakfast, 50salads, and GTEA datasets demonstrate that our method significantly improved the frame accuracy for action segmentation in videos when compared to the state-of-the-art techniques.

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：