检索结果-内蒙古大学图书馆

16th International Conference on Genetic and Evolutionary computing, ICGEC 2024

作者： Zhang, Tiancong Weng, Shaowei Chu, Shu-Chuan Nguyen, Trong-The Dao, Thi-Kien School of Computing and Information Science Fuzhou Institute of Technology Fuzhou350506 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China College of Computer Science and Engineering Shandong University of Science and Technology Qing-dao266590 China University of Information Technology Ho Chi Minh City700000 Viet Nam

ISBN: (纸本)9789819615346

The development of effective drug therapies is a complex and multifaceted problem involving various biological, chemical, and computational challenges. Traditional drug development methods are often time-consuming and costly, necessitating innovative approaches. Multi-objective genetic algorithms (MOGAs) have emerged as a powerful tool for optimizing drug design by simultaneously considering multiple conflicting objectives, such as efficacy, safety, and cost. This paper reviews the application of MOGAs in drug discovery, highlighting their principles, advantages, and case studies, and discussing future directions in the field. Enhancing MOGAs in drug discovery are also outlined, emphasizing the integration with machine learning, advancements in computational infrastructure, and the potential for personalized medicine. The paper concludes by affirming the significant promise of MOGAs in accelerating the development of safe and effective drug therapies, thereby addressing critical needs in modern pharmacology. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Drug discovery

来源：评论

学校读者我要写书评

暂无评论

Taking Myopic Best Response Against the Hedge Algorithm 42

Taking Myopic Best Response Against the Hedge Algorithm

引用

42nd Chinese Control Conference, CCC 2023

作者： Guo, Xinxiang Mu, Yifen School of Mathematical Sciences University of Chinese Academy of Sciences Beijing China Academy of Mathematics and Systems Science The State Key Laboratory of Scientific and Engineering Computing Chinese Academy of Sciences Beijing China Academy of Mathematics and Systems Science The Key Laboratory of Systems and Control Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789887581543

With the rapid development of artificial intelligence (AI), the game between the human and machine/AI becomes more and more common. The related theoretical analysis becomes significant and necessary, which however is still rare. This problem involves evolution analysis and optimal control of dynamic game systems driven by learning algorithms. In this paper, we consider a finitely repeated two-player zero-sum game. We study the dynamic evolution process of the game system, in which one player employs the Hedge algorithm and the other player takes the myopic best response. By the updating formula of the Hedge algorithm, we define a quantity called the state and construct the State Transition Triangle Graph (STTG). Then, we prove that the game system is periodic after o(T) stages. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Ultrafast Online Clutter Filtering for Ultrasound Microvascular Imaging

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Chen, Yinran Fang, Baohui Li, Huaying Huang, Lijie Luo, Jianwen Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen361005 China Tsinghua University School of Biomedical Engineering Beijing100084 China

Spatiotemporal clutter filtering via robust principal component analysis (rPCA) has been widely used in ultrasound microvascular imaging. However, the performance of the rPCA clutter filtering highly relies on low-rank modeling for tissue signals and sparse modeling for blood flow signals. Moreover, current rPCA clutter filters are typically based on static processing and have to access a batch of beamformed frames for optimization. This prevents these filters from ultrafast realization. This paper adopts the iteratively reweighted least squares (IRLS) rPCA framework to model tissue and blood flow signals for improved clutter filtering. More importantly, the static IRLS-rPCA filter is upgraded to a spatiotemporal-constrained online method to instantaneously extract blood flow signals from the ongoing beamformed frame. Simulations and in-vivo experiments on a contrast-enhanced rat kidney and a contrast-free human liver demonstrated that the IRLS-rPCA clutter filter achieves higher sensitivity, contrast-to-noise ratio (CNR), and signal-to-noise ratio (SNR) than other rPCA methods. Particularly, the static IRLS-rPCA clutter filter obtains more than 2 dB improvements in CNR over the compared methods in the human liver dataset. The proposed online clutter filter achieves comparable image quality to the static version and processing time of 0.028 ± 0.004 seconds per frame. The corresponding acceleration factor of the online clutter filter over all the tested methods is more than 20. © 2025 IEEE.

关键词： Radar clutter

来源：评论

学校读者我要写书评

暂无评论

Precise Analysis of Covariance Identifiability for Activity Detection in Grant-Free Random Access

arXiv

引用

arXiv 2024年

作者： Luo, Shengsong Ma, Junjie Xu, Chongbin Wang, Xin the Department of Communication Science and Engineering Fudan University Shanghai200433 China The State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

We consider the identifiability issue of maximum-likelihood based activity detection in massive MIMO-based grant-free random access. An intriguing observation by Chen et al. [1] indicates that the identifiability undergoes a phase transition for commonly-used random user signatures as L2, N and K tend to infinity with fixed ratios, where L, N and K denote the user signature length, the total number of users, and the number of active users, respectively. In this letter, we provide a precise analytical characterization of the phase transition based on a spectral universality conjecture. Numerical results demonstrate excellent agreement between our theoretical predictions and the empirical phase transitions. Copyright © 2024, The Authors. All rights reserved.

关键词： Maximum likelihood

来源：评论

学校读者我要写书评

暂无评论

DiffLoc: Diffusion Model for Outdoor LiDAR Localization

DiffLoc: Diffusion Model for Outdoor LiDAR Localization

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wen Li Yuyang Yang Shangshu Yu Guosheng Hu Chenglu Wen Ming Cheng Cheng Wang Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen University School of Computer Science and Engineering Nanyang Technological University Oosto

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Absolute pose regression (APR) estimates global pose in an end-to-end manner, achieving impressive results in learn-based LiDAR localization. However, compared to the top-performing methods reliant on 3D-3D correspondence matching, APR's accuracy still has room for improvement. We recognize APR's lack of robust features learning and iterative denoising process leads to suboptimal results. In this paper, we propose DiffLoc, a novel framework that formulates LiDAR localization as a conditional generation of poses. First, we propose to utilize the foundation model and static-object-aware pool to learn robust features. Second, we incorporate the iterative denoising process into APR via a diffusion model conditioned on the learned geometrically robust features. In addition, due to the unique nature of diffusion models, we propose to adapt our models to two additional applications: (1) using multiple inferences to evaluate pose uncertainty, and (2) seamlessly introducing geometric constraints on denoising steps to improve prediction accuracy. Extensive experiments conducted on the Oxford Radar RobotCar and NCLT datasets demonstrate that DiffLoc outperforms better than the state-of-the-art methods. Especially on the NCLT dataset, we achieve 35% and 34.7% improvement on position and orientation accuracy, respectively. Our code is released at https://***/liw95/DiffLoc.

关键词： Location awareness Representation learning Laser radar Accuracy Uncertainty Noise reduction Predictive models

来源：评论

学校读者我要写书评

暂无评论

Adaptive energy-preserving algorithms for guiding center system

引用

Plasma Science and Technology 2023年第4期25卷 11-22页

作者：朱贝贝刘健张嘉炜祝爱卿唐贻发 Department of Applied Mathematics School of Mathematics and PhysicsUniversity of Science and Technology BeijingBeijing 100083Peopleʼs Republic of China School of Nuclear Science and Technology University of Science and Technology of ChinaHefei 230026Peopleʼs Republic of China Advanced algorithm Joint Lab Shandong Computer Science CenterQilu University of TechnologyJinan 250014Peopleʼs Republic of China The State Key Laboratory of Scientific and Engineering Computing The Institute of Computational Mathematics and Scientific/Engineering ComputingAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190Peopleʼs Republic of China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049Peopleʼs Republic of China

We develop two types of adaptive energy preserving algorithms based on the averaged vector field for the guiding center dynamics,which plays a key role in magnetized *** adaptive scheme is applied to the Gauss Legendre’s quadrature rules and time stepsize respectively to overcome the energy drift problem in traditional energy-preserving *** new adaptive algorithms are second order,and their algebraic order is carefully *** results show that the global energy errors are bounded to the machine precision over long time using these adaptive algorithms without massive extra computation cost.

关键词： guiding center system energy-preserving methods adaptive energy conservation

来源：评论

学校读者我要写书评

暂无评论

iTA: Inferring Traffic Accident Hotspots with Vehicle Trajectories and Road Environment Data 19

iTA: Inferring Traffic Accident Hotspots with Vehicle Trajec...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Gao, Jiannan Wang, Yigao Jiang, Zhihan Zhu, Hang Zhong, Qiyue Fan, Xiaoliang Chen, Longbiao Wang, Cheng Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen China The University of Hong Kong Faculty of Engineering Department of Electrical and Electronic Engineering Hong Kong

ISBN: (纸本)9798350346558

Traffic accidents, like rear-end collisions and vehicle-to-pedestrian accidents, bringing serious threats to traffic management and people's lives and property. Existing methods rely on historical traffic accident data and are not suitable for expanding cities. Against this background, we propose a framework to infer urban traffic accident hotspots by vehicle trajectory data and heterogeneous data. Firstly, we extract parking events from vehicle trajectories leveraging a map matching algorithm and obtain the parking hotspots under different weather and time periods by semantic segmentation and clustering. Secondly, we extract three sets of contextual features of parking hotspots, i.e., road names, POIs, and traffic flow. Finally, leveraging a graphical convolutional network, we build a model to infer whether a parking hotspot is a traffic accident hotspot based on contextual features. We evaluate our model leveraging real datasets in Xiamen. Results prove that our model accurately infers traffic accident hotspots in Xiamen with F1-Score of 0.794. © 2022 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Adaptive OrderWENO Reconstructions for the Semi-Lagrangian Finite Difference Scheme for Advection Problem

引用

Communications in Computational Physics 2021年第6期30卷 67-96页

作者： Jiajie Chen Xiaofeng Cai Jianxian Qiu Jing-Mei Qiu Department of Mathematical Sciences University of DelawareNewarkDE19717USA School of Mathematical Sciences and Fujian Provincial Key Laboratory of Mathematical Modeling and High-Performance Scientific Computing Xiamen UniversityXiamenFujian 361005P.R.China

We present a new conservative semi-Lagrangian finite difference weighted essentially non-oscillatory scheme with adaptive *** is an extension of the conservative semi-Lagrangian(SL)finite difference WENO scheme in[Qiu and Shu,JCP,230(4)(2011),pp.863-889],in which linear weights in SL WENO framework were shown to not exist for variable coefficient ***,the order of accuracy is not optimal from reconstruction *** this paper,we incorporate a recent WENO adaptive order(AO)technique[Balsara et al.,JCP,326(2016),pp.780-804]to the SL WENO *** new scheme can achieve an optimal high order of accuracy,while maintaining the properties of mass conservation and non-oscillatory capture of solutions from the original SL *** positivity-preserving limiter is further applied to ensure the positivity of ***,the scheme is applied to high dimensional problems by a fourth-order dimensional *** demonstrate the effectiveness of the new scheme by extensive numerical tests on linear advection equations,the Vlasov-Poisson system,the guiding center Vlasov model as well as the incompressible Euler equations.

关键词： Semi-Lagrangian weighted essentially nonoscillatory WENO adaptive order reconstruction finite difference mass conservation Vlasov-Poisson incompressible Euler

来源：评论

学校读者我要写书评

暂无评论

STk: A Scalable Module for Solving Top-k Problems 38

STk: A Scalable Module for Solving Top-k Problems

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Xia, Hanchen Liu, Weidong Mao, Xiaojun School of Mathematical Sciences Shanghai Jiao Tong University Shanghai China Ministry of Education Key Lab of Artificial Intelligence Shanghai Jiao Tong University Shanghai China Ministry of Education Key Laboratory of Scientific and Engineering Computing Shanghai Jiao Tong University Shanghai China RoyalFlush AI Research Institute Hangzhou China

The cost of ranking becomes significant in the new stage of deep learning. We propose STk, a fully differentiable module with a single trainable parameter, designed to solve the Top-k problem without requiring additional time or GPU memory. Due to its fully differentiable nature, STk can be embedded end-to-end into neural networks and optimize the Top-k problems within a unified computational graph. We apply STk to the Average Top-k Loss (ATk), which inherently faces a Top-k problem. The proposed STk Loss outperforms ATk Loss and achieves the best average performance on multiple benchmarks, with the lowest standard deviation. With the assistance of STk Loss, we surpass the state-of-the-art (SOTA) on both CIFAR-100-LT and Places-LT leaderboards. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study on Improved YOLOv7-based Algorithm for Detecting Crack Defects in Ancient Buildings 24

Study on Improved YOLOv7-based Algorithm for Detecting Crack...

引用

3rd International Conference on Computer, Artificial Intelligence and Control engineering, CAICE 2024

作者： Fang, Tianke Hui, Zhenxing Rey, William P Xie, Zhiying Yang, Aihua He, Yuanrong School of Information Technology Mapua University Manila1200 Philippines Big Data Institute of Digital Natural Disaster Monitoring in Fujian Xiamen University of Technology Xiamen Fujian361024 China School of Computing and Information Engineering Xiamen University of Technology Xiamen Fujian361024 China School of Information Media Zhangzhou Vocational College of Science and Technology Zhangzhou Fujian363200 China Hunan Key Laboratory of Remote Sensing Monitoring of Ecological Environment Dongting Lake Area Changsha Hunan410004 China

ISBN: (纸本)9798400716942

In the protection and restoration work of ancient buildings, the detection and analysis of the cracks and defects of the exterior walls of ancient buildings is a crucial task. In this paper, an improved YOLOv7 algorithm is proposed to detect the defects of ancient external walls, aiming to achieve efficient and accurate detection of the defects of ancient external walls. The method involves preprocessing the image using a rectangle clipping algorithm, graying the image using the maximum method, and denoising the image with a median filter. Next, the image is labeled using the LabelImg tool, and the data is split into training, validation, and test sets. During model training, a CBAM-Net module is inserted after several CBS modules in the backbone network, the GIOU loss function is replaced by CIOU, and feature task extraction is performed. The realized attention mechanism is added to the Yolov7 model. The results show that the mAP value of crack detection after the improved algorithm reaches 81.2%. In contrast to the initial YOLOv7 algorithm, the precision of the model has been boosted to 87.2%, exhibiting a 6.0% enhancement in accuracy and an 85.2% improvement in recall rate. The improved YOLOv7 crack detection algorithm reduces network calculation and improves crack classification and recognition ability. This approach is crucial in safeguarding ancient buildings as it enables varying levels of maintenance depending on the severity of cracks. © 2024 ACM.

关键词： Attention mechanism Deep learning Defect detection Image processing YOLOv7

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：