检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ma, Xinghua Fang, Xinyan Zou, Mingye Luo, Gongning Wang, Wei Wang, Kuanquan Qiu, Zhaowen Gao, Xin Li, Shuo Faculty of Computing Harbin Institute of Technology Harbin China Computational Bioscience Research Center King Abdullah University of Science and Technology Thuwal Saudi Arabia Faculty of Computing Harbin Institute of Technology Shenzhen China College of Computer and Control Engineering Northeast Forestry University Harbin China Department of Computer and Data Science Case Western Reserve University Cleveland United States Department of Biomedical Engineering Case Western Reserve University Cleveland United States

ISBN: (纸本)157735897X

Coronary Artery Disease (CAD) poses a significant threat to cardiovascular patients worldwide, underscoring the critical importance of automated CAD diagnostic technologies in clinical practice. Previous technologies for lesion assessment in Coronary CT Angiography (CCTA) images have been insufficient in terms of interpretability, resulting in solutions that lack clinical reliability in both network architecture and prediction outcomes, even when diagnoses are accurate. To address the limitation of interpretability, we introduce the Trusted Lesion-Assessment Network (TLA-Net), which provides a clinically reliable solution for multi-view CAD diagnosis: (1) The causality-informed evidence collection constructs a causal graph for the diagnostic process and implements causal interventions, preventing confounders’ interference and enhancing the transparency of the network architecture. (2) The clinically-aligned uncertainty integration hierarchically combines Dirichlet distributions from various views based on clinical priors, offering confidence coefficients for prediction outcomes that align with physicians’ image analysis procedures. Experimental results on a dataset of 2,618 lesions demonstrate that TLA-Net, supported by its interpretable methodological design, exhibits superior performance with outstanding generalization, domain adaptability, and robustness. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Statistical Scintillation Indices in Polar Ionospheric Climatology

Statistical Scintillation Indices in Polar Ionospheric Clima...

引用

Radio science Meeting (AT-AP-RASC), URSI Atlantic and Asia Pacific

作者： Ishita Gulati Jyoti Kumar Atul Oleg V Kravchenko Satnam Dlay Newcastle University United Kingdom Indian Institute of Geomagnetism Navi Mumbai India Federal Research Center Computer Science and Control RAS Moscow Russian Federation

It has been established that polar cap patches are capable of triggering phase scintillation via various convective instabilities such as Gradient Drift, Gravitational Interchange, Current Convective, and Kelvin-Helmholtz Instabilities coupled with turbulent plasma processes in the cold and warm approximation. These multiple instabilities provide a qualitative density peaking mechanism which ultimately leads to the formation of highly dense and coherent nonlinear structures such as polar patches and auroral blobs at high latitudes. It is important to note that the nonlinear evolution of these polar patches/blobs and their associated plasma number density in-homogeneities are primarily controlled by dominant magnetospheric (inertial) or ionospheric (collisional) current systems. Moreover, intense observational studies on the trans-polar movement of these polar patches/blobs and their associated morphology further classify these structures as Type 1 and Type 2 blobs depending upon their density estimates and ionisation sources. In this study, a correlation between inherent polar patches plasma parameters and phase scintillation metrics is discussed in terms of Total Electron Content (TEC) and ROTI measurements at a localised region Ny-Alesund [78.93 ◦ N, 11.86 ◦ E], Svalbard which is more sensitive to the polar patch mobilisation driven by dayside polar cusp dynamics. Moreover, it is concluded that phase scintillation studied in terms of TEC and ROTI local estimations could be used as proxies for the polar ionosphere.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cooperation Strategy for Optimal Motion of Aerial and Ground Vehicles

Cooperation Strategy for Optimal Motion of Aerial and Ground...

引用

Mediterranean Conference on control and Automation (MED)

作者： Tamás Hegedűs Dániel Fényes Balázs Németh Péter Gáspár Institute for Computer Science and Control (SZTAKI) Eötvös Loránd Research Network (ELKH) Kende u. 13-17 Budapest Hungary Department of Control for Transportation and Vehicle Systems Budapest University of Technology and Economics Stoczek u. 2 Budapest Hungary

In this paper, a route selection algorithm is proposed for aerial and ground vehicle cooperative control. The main goal is to determine a feasible trajectory for a drone, which satisfies several limitations. Moreover, during the route selection, the flight time is also minimized to increase the efficiency of the entire system. The route selection is performed by a graph-based method, which is evaluated for different initial conditions. Then, the proposed algorithm determines the trajectories for the drone, and the predefined limitations are also considered. The method is validated in a MATLAB-based simulation environment, in which the whole algorithm is implemented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning with Success Induced Task Prioritization

arXiv

引用

arXiv 2022年

作者： Nesterova, Maria Skrynnik, Alexey Panov, Aleksandr Moscow Institute of Physics and Technology Moscow Russia AIRI Moscow Russia Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Moscow Russia

Many challenging reinforcement learning (RL) problems require designing a distribution of tasks that can be applied to train effective policies. This distribution of tasks can be specified by the curriculum. A curriculum is meant to improve the results of learning and accelerate it. We introduce Success Induced Task Prioritization (SITP), a framework for automatic curriculum learning, where a task sequence is created based on the success rate of each task. In this setting, each task is an algorithmically created environment instance with a unique configuration. The algorithm selects the order of tasks that provide the fastest learning for agents. The probability of selecting any of the tasks for the next stage of learning is determined by evaluating its performance score in previous stages. Experiments were carried out in the Partially Observable Grid Environment for Multiple Agents (POGEMA) and Procgen benchmark. We demonstrate that SITP matches or surpasses the results of other curriculum design methods. Our method can be implemented with handful of minor modifications to any standard RL framework and provides useful prioritization with minimal computational overhead. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

research and Analysis of the Method for Measuring the Moisture Content of Cottonmaterials at Ultrahigh Frequencies

Research and Analysis of the Method for Measuring the Moistu...

引用

Automatics and Informatics (ICAI), International Conference

作者： Palvan I. Kalandarov Khasan E. Turkmenov Shakhnoza R. Ubaydullayeva Nikola N. Nikolov Mariela I. Alexandrova Department “Automation and control of technology process in production” «Tashkent institute of irrigation and agricultural mechanization engineers» National Research University Tashkent Uzbekistan Department of Automation Faculty of Computer Science and Automation Technical University of Varna Varna Bulgaria

The article provides a theoretical analysis of the ultrahigh frequency (microwave) method of humidity measurement, discusses the problems of instrumentation of the method in question, and proposes a scheme of an experimental installation. Bulk cotton materials were selected as the objects of research. The electromagnetic wave radiation is analyzed during measurement and the evaluation of electrophysical characteristics requires the study of the functional dependence of the amplitude and phase shift on the mass ratio of humidity, mathematical models for various bulk cotton materials describing the joint effect of humidity, material density on the attenuation and phase shift of the passing wave are obtained.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Syntax-based data augmentation for Hungarian-English machine translation

arXiv

引用

arXiv 2022年

作者： Nagy, Attila Nanys, Patrick Konrád, Balázs Frey Bial, Bence Ács, Judit Department Of Automation And Applied Informatics Budapest University Of Technology And Economics Hungary Institute For Computer Science And Control Eötvös Loránd Research Network

We train Transformer-based neural machine translation models for Hungarian-English and English-Hungarian using the Hunglish2 corpus. Our best models achieve a BLEU score of 40.0 on Hungarian-English and 33.4 on English-Hungarian. Furthermore, we present results on an ongoing work about syntax-based augmentation for neural machine translation. Both our code and models are publicly available. © 2022, CC BY.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Risk-Sensitive Reinforcement Learning with Exponential Criteria

arXiv

引用

arXiv 2022年

作者： Noorani, Erfaun Mavridis, Christos N. Baras, John S. Department of Electrical and Computer Engineering the Institute for Systems Research University of Maryland College Park United States Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

While reinforcement learning has shown experimental success in a number of applications, it is known to be sensitive to noise and perturbations in the parameters of the system, leading to high variability in the total reward amongst different episodes on slightly different environments. To introduce robustness, as well as sample efficiency, risk-sensitive reinforcement learning methods are being thoroughly studied. In this work, we provide a definition of robust reinforcement learning policies and formulate a risk-sensitive reinforcement learning problem to approximate them, by solving an optimization problem with respect to a modified objective based on exponential criteria. In particular, we study a model-free risk-sensitive variation of the widely-used Monte Carlo Policy Gradient algorithm, and introduce a novel risk-sensitive online Actor-Critic algorithm based on solving a multiplicative Bellman equation using stochastic approximation updates. Analytical results suggest that the use of exponential criteria generalizes commonly used ad-hoc regularization approaches, improves sample efficiency, and introduces robustness with respect to perturbations in the model parameters and the environment. The implementation, performance, and robustness properties of the proposed methods are evaluated in simulated experiments. © 2022, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent survey method of rice diseases and pests using AR glasses and image-text multimodal fusion model

引用

computers and Electronics in Agriculture 2025年 237卷

作者： Chen, Xiangfu Yang, Baojun Liu, Yongjian Feng, Zelin Lyu, Jun Luo, Ju Wu, Jian Yao, Qing Liu, Shuhua School of Computer Science and Technology Zhejiang Sci-Tech University Hangzhou310018 China State Key Laboratory of Rice Biology and Breeding China National Rice Research Institute Hangzhou311401 China School of Information and Control Keyi College of Zhejiang Sci-Tech University Hangzhou310018 China School of Information Science and Engineering Zhejiang Sci-Tech University Hangzhou310018 China

The timely and accurate detection of the occurrence types and dynamics of rice diseases and insect pests in the field is a fundamental requirement for effective scientific prevention and control. Currently, survey methods rely heavily on the expertise and experience of surveyors, leading to challenges such as limited data traceability, high labor demands, and low efficiency. The complex environmental conditions in rice fields, coupled with the diversity of pests and diseases—many of which coexist and exhibit significant intraspecies variation and interspecies similarities—further complicate detection efforts. When identification models are trained using only a limited set of image samples, they often suffer from poor generalization, undermining the accuracy of pest and disease forecasts. To overcome these challenges, a rapid, efficient, and precise intelligent survey method using AR glasses and image-text multimodal fusion model to detect rice pests and diseases was proposed. The AR glasses have advantages of wearable, hands-free, voice-control functions, which is very convenient to collect rice images in paddy fields. An image-text multimodal fusion model with two stages, RDP-Detector, was developed to improve the detection accuracy rates of rice pest and disease lesions in the images. In the first stage, the improved YOLOv5X model with AF-FPN, Decoupled Head and Soft-NMS post-processing achieved improvements in detection ability. In the second stage, text modalities are introduced, and Prompt tuning is used to perform transfer learning for downstream tasks on the basis of the CLIP model. To improve the accuracy of pest detection, the detection boxes with low confidence in the first stage are subjected to reidentification in the second stage. Compared with the state of the art models, the RDP-Detector achieved an precision, recall, and mAP of 82.3 %, 86.5 %, and 87.4 %, respectively, on the detection of seven rice pests and diseases. Compared with the object detect

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Safe vehicle motion design with learning for moving in environment with uncertainties ⁎

引用

IFAC-PapersOnLine 2024年第4期58卷 228-233页

作者： Dénes Tompos Balázs Németh Tamás Hegedűs Vu Van Tan Péter Gáspár Institute for Computer Science and Control (SZTAKI) Hungarian Research Network (HUN-REN) Kende u. 13-17. 1111 Budapest Hungary Department of Control for Transportation and Vehicle Systems Budapest University of Technology and Economics Stoczek u. 2. 1111 Budapest Hungary Department of Automotive Mechanical Engineering Faculty of Mechanical Engineering University of Transport and Communications 3 Cau Giay Street 100000 Hanoi Vietnam

In this paper a motion profile design for unmanned aerial vehicles is proposed which method is able to guarantee safe collision-free motion. The motivations of the work are provided by the uncertainties of covered areas by the vehicles, and also the need of high performance fast vehicle motion. The uncertain information on the environment for detecting Conflict areas is processed through clustering and Mahalanobis-distance-based filtering methods. The resulted Conflict areas are involved in the motion design method, which is facilitated through reinforcement learning. This paper shows the application of the method on a drone that moves together with a mobile robot in the same environment. The safe and high performance motion of the drone is illustrated through simulation example.

关键词： Unmanned aerial vehicles safe motion clustering point clouds

来源：评论

学校读者我要写书评

暂无评论

Automation of Technological Processes for controlling Grain Moisture in the Flowu

Automation of Technological Processes for Controlling Grain ...

引用

Automatics and Informatics (ICAI), International Conference

作者： Palvan I. Kalandarov Shakhnoza R. Ubaydullayeva Rano T. Gaziyeva Nikola N. Nikolov Mariela I. Alexandrova Department “Automation and control of technology process in production” «Tashkent institute of irrigation and agricultural mechanization engineers» National Research University Tashkent Uzbekistan Department of Automation Faculty of Computer Science and Automation Technical University of Varna Varna Bulgaria

The paper deals with the problems of grain wounding requires large energy costs, requiring a multi-stage process of grain processing, installation and perfect and reliable automation systems for the storage and processing of raw materials, theoretical and experimental studies and the results of the use of the microwave method in measuring the moisture content of grain and grain materials. The method under consideration is based on the principle of selective absorption of microwave radiation energy by water in materials and its derivatives. By the degree of absorption of radiation, the concentration of moisture is judged. The paper investigates the amplitude and phase methods of the passing wave in free space. The influence of the elastic properties of the material under study on the electrical characteristics of the microwave wave, suggesting fundamentally new ways of measuring the attenuation and phase shift of the electromagnetic wave, including discrete conversion of the signal of the primary converter, which does not require rigid metrological support and the use of a phase shift, is substantiated. Information on the values of the thickness of the material is analyzed in order to correct the influence of this value, consisting of two parameters: the signal of the passing wave, the attenuation and phase shift which characterizes the humidity and the additional signal - the phase wave reflected from the front surface of the materials and carrying information about its thickness.

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：