检索结果-内蒙古大学图书馆

5th International Symposium on Artificial Intelligence for Medicine Science, ISAIMS 2024

作者： Chen, Yulin Luo, Jing Tu, Xinhui College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Hubei Wuhan China College of Computer Science Central China Normal University Hubei Wuhan China

ISBN: (纸本)9798400717826

Recent advancements in large language models have led to significant improvements in various natural language processing tasks, including automated question answering. However, these models still struggle with providing accurate responses to complex biology questions, such as those found in the National College Entrance Examination. To address this issue, researchers have explored retrieval-augmented generation techniques, which incorporate external knowledge sources to enhance answer accuracy. While these methods have shown promise in improving efficiency, they often lack the ability to perform in-depth analysis of complex questions. In response to these limitations, the paper proposes a novel ReAct agent-based question answering method. This method combines biology textbook document libraries with Google search engine capabilities, leveraging the strengths of large language models. By integrating these components, this method can engage in autonomous decision-making and multi-step reasoning, allowing for a more thorough analysis of complex biology questions. Experimental results demonstrate the effectiveness of this new approach. When compared to responses generated directly by ChatGPT and GPT-4o models, the method showed significant improvements in accuracy for biology questions from the National College Entrance Examination. Specifically, the new method achieved accuracy increases of 11.1% and 4.64% over ChatGPT and GPT-4o, respectively. © 2024 Copyright held by the owner/author(s).

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Synthesis of Temporally-Robust Policies for Signal Temporal Logic Tasks using Reinforcement Learning

Synthesis of Temporally-Robust Policies for Signal Temporal ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Siqi Wang Shaoyuan Li Li Yin Xiang Yin Department of Automation and Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China Institute of Systems Engineering Macau University of Science and Technology Taipa China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This paper investigates the problem of designing control policies that satisfy high-level specifications described by signal temporal logic (STL) in unknown, stochastic environments. While many existing works concentrate on optimizing the spatial robustness of a system, our work takes a step further by also considering temporal robustness as a critical metric to quantify the tolerance of time uncertainty in STL. To this end, we formulate two relevant control objectives to enhance the temporal robustness of the synthesized policies. The first objective is to maximize the probability of being temporally robust for a given threshold. The second objective is to maximize the worst-case spatial robustness value within a bounded time shift. We use reinforcement learning to solve both control synthesis problems for unknown systems. Specifically, we approximate both control objectives in a way that enables us to apply the standard Q-learning algorithm. Theoretical bounds in terms of the approximations are also derived. We present case studies to demonstrate the feasibility of our approach.

关键词： Measurement Uncertainty Q-learning Approximation algorithms Robustness Logic Task analysis

来源：评论

学校读者我要写书评

暂无评论

High-Accuracy Pose Estimation for 3D Reconstruction Considering the Manipulator Motion Constraints with an Eye-in-Hand RGB-D Camera 42

High-Accuracy Pose Estimation for 3D Reconstruction Consider...

引用

42nd Chinese control Conference, CCC 2023

作者： Zhou, Yanling Zhang, Xuebo Wang, Runhua Zhang, Shiyong Yuan, Mingxing Yuan, Jing Institute of Robotics and Automatic Information System College of Artificial Intelligence Nankai University Tianjin300350 China Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin300350 China Key Laboratory of Industrial Internet of Things and Networked Control Ministry of Education China

ISBN: (纸本)9789887581543

Three-dimensional(3D) environmental reconstruction of the manipulator workspace is a prerequisite to enable autonomous collision-free path planning and subsequent task execution, wherein the positioning accuracy of the equipped sensor is one key issue to determine the performance of 3D reconstruction. In this paper, an eye-in-hand RGB-D camera is used to complete the manipulator workspace scanning and a novel high-accuracy pose estimation method for 3D reconstruction is proposed, which not only considers the geometric and photometric constraints constructed from the visual information used in traditional methods, but also considers the manipulator motion constraints since the positioning accuracy of the manipulator is usually high. Based on above three constraints, three error functions are constructed respectively and fused with different weights to form an integrated objective function. Then, the problem is converted into solving the least squares problem by the Gaussian Newton nonlinear iterative method, which involves the computation of Jacobian matrices and residuals of the three error functions. To this end, the mathematical derivation of their formulas considering the manipulator motion constraints are given in detail. By qualitative and quantitative experimental comparison with traditional methods, the proposed method can greatly improve the accuracy of pose estimation and 3D reconstruction, which always maintains the error within 3 cm, and show good robustness even in the challenging environments with weak texture or geometric features. (Supplemented video link: https://***/FkFTxssnWms) © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Initial Alignment Method for SINS of UAV Based on Digital Filter Pretreatment

Initial Alignment Method for SINS of UAV Based on Digital Fi...

引用

2021 China Automation Congress, CAC 2021

作者： Yang, Wenbo Xu, Jie Li, Shaoyuan Wang, Jianjun Wang, Zhifeng Department of Automation Shanghai Polytechnic University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China

ISBN: (纸本)9781665426473

The two-stage method, which is divided into coarse alignment and fine alignment, is a traditional initial alignment method for SINS (Strapdown inertial navigation system, SINS). First, the coarse alignment is carried out based on the transformation relationship between the geographic information of the earth and the output of inertial measurement unit, and then the fine alignment is carried out based on optimal estimation. However, this method can mainly solve the alignment problem under angular interference. Aiming at in-motion alignment for SINS of UAVs (Unmanned aerial vehicle, UAV) under linear interference, this paper introduced the idea of digital filter and designed the digital filter by analyzing the frequency characteristic of useful signal. Then the reference velocity information is filtered to realize isolation of linear interference at specific frequency. Thus, the in-motion alignment problem under the combined action of angular interference and linear interference is effectively solved. Finally, numerical simulation results show the effectiveness of the above method. © 2021 IEEE

关键词： Digital filters

来源：评论

学校读者我要写书评

暂无评论

Distributed Short-Term Load Forecasting for Interconnecting Power systems

Distributed Short-Term Load Forecasting for Interconnecting ...

引用

2021 China Automation Congress, CAC 2021

作者： Guan, Yaonan Li, Dewei Xi, Yugeng Department of Automation Shanghai Jiao Tong University China Key Laboratory of System Control and Information Processing Ministry of Education of China China

ISBN: (纸本)9781665426473

The social factors which exert an important influence on the load variations are difficult to adopt in centralized load forecasting models. A distributed short-term load forecasting method is proposed in this paper to compensate for the lack of social factors in load forecasting of the interconnecting power system network. In this method, we focus on the influence of social factors rather than the elements themselves. First, a classification method is proposed to arrange systems into several functional groups according to their load curve feature. Second, the interactions between systems are introduced into the model to represent social factors' influence on systems. Finally, experiments are conducted to verify the advantage of the proposed model. © 2021 IEEE

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds

arXiv

引用

arXiv 2023年

作者： Peng, Chensheng Wang, Guangming Lo, Xian Wan Wu, Xinrui Xu, Chenfeng Tomizuka, Masayoshi Zhan, Wei Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai Jiao Tong University China Mechanical Systems Control Laboratory University of California Berkeley United States

Point clouds are naturally sparse, while image pixels are dense. The inconsistency limits feature fusion from both modalities for point-wise scene flow estimation. Previous methods rarely predict scene flow from the entire point clouds of the scene with one-time inference due to the memory inefficiency and heavy overhead from distance calculation and sorting involved in commonly used farthest point sampling, KNN, and ball query algorithms for local feature aggregation. To mitigate these issues in scene flow learning, we regularize raw points to a dense format by storing 3D coordinates in 2D grids. Unlike the sampling operation commonly used in existing works, the dense 2D representation 1) preserves most points in the given scene, 2) brings in a significant boost of efficiency, and 3) eliminates the density gap between points and pixels, allowing us to perform effective feature fusion. We also present a novel warping projection technique to alleviate the information loss problem resulting from the fact that multiple points could be mapped into one grid during projection when computing cost volume. Sufficient experiments demonstrate the efficiency and effectiveness of our method, outperforming the prior-arts on the FlyingThings3D and KITTI dataset. Our source codes will be released on https://***/IRMVLab/DELFlow. © 2023, CC BY.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Towards DDIs Identification by Knowledge Graph with BiRW and Back Aggregation

Towards DDIs Identification by Knowledge Graph with BiRW and...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Yin, Zhuang Lin, Xiaoli Zhang, Xiaolong Wuhan University of Science and Technology Hubei Key Laboratory of Intelligent Information Processing and Real-time Industrial System School of Computer Science and Technology Wuhan China

ISBN: (纸本)9781665468190

Effective identification of potential drug-drug interactions (DDIs) can prevent adverse effects caused by DDIs to a certain extent. This paper proposes the new hybrid method for predicting DDIs, which is called BiRW-KGBAN that combines bidirectional random walk and back aggregation based on knowledge graph. BiRW-KGBAN first constructs two knowledge graph KG-DrugBank and KG-KEGG that integrate data related to drugs. Then, an improved sampling method based on bidirectional random walk (BiRW) is used to sample the neighborhood information of drugs, including directly connected entities, related semantic relations and potential information. In addition, the path with drug as the center node is also extracted. Finally, two improved back aggregation model KGBAN1 and KGBAN2 are used to obtain the final embedded representation of the drugs. The experiments show that, compared with other existing methods, our method could obtain the higher-order topological information and the deeper potential neighborhood information of drugs, and has great improvements in DDIs prediction. The case study also shows that the proposed method has the potential for actual DDIs prediction. © 2022 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Early Forest Fire Recognition Method Based on C-GhostNet Network 5

Early Forest Fire Recognition Method Based on C-GhostNet Net...

引用

5th International Symposium on Autonomous systems, ISAS 2022

作者： Li, Mengna Zhang, Youmin Mu, Lingxia Xin, Jing Yu, Ziquan Jiao, Shangbin Liu, Han Xie, Guo Yi, Yingmin Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Shaanxi Xi'an710048 China Concordia University Industrial and Aerospace Engineering Department of Mechanical MontrealQCH3G 1M8 Canada Nanjing University of Aeronautics and Astronautics College of Automation Engineering Nanjing211106 China Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an Shaanxi 710048 China

ISBN: (纸本)9781665487085

Early forest fire image recognition plays an important role in timely fire fighting. This paper proposes an early forest fire recognition method based on C-GhostNet network. The C-GhostNet network is an improved version of GhostNet, which mainly consists of a series of c-ghost bottlenecks, each c-ghost bottleneck mainly consists of two c-ghost modules. Through the concat operation and channel shuffle, the c-ghost module establishes the relationship between the input data and the output features generated by the original ghost module, so that GhostNet network has the ability to capture contextual features. The experimental results show that the C-GhostNet network achieves better recognition performance than GhostNet without introducing additional computational load, and the running speed reaches about 20FPS, which basically realizes real-time recognition. In addition, like GhostN et, the C-GhostNet network is also a lightweight network. © 2022 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Robust Adatpive Sliding Mode Tracking control for an AUV

Robust Adatpive Sliding Mode Tracking Control for an AUV

引用

2021 China Automation Congress, CAC 2021

作者： Zheng, Jiaqi Yu, Wenbin Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781665426473

In our work, the research on trajectory tracking with time-varying disturbances is investigated via robust adaptive sliding mode control (RASMC). We first design a nonsingular sliding mode surface for tracking error system and show that the sliding mode surface is continuous. Then, since the underwater environment is very complex and the AUV's mathematical model is strongly nonlinear and highly coupled with uncertainties, we propose the robust adaptive law to ensure the superior robust performance of AUV system. The obtained results suggest that the proposed controller can reduce chattering and tracking error by designing a nonsingular sliding mode surface. © 2021 IEEE

关键词： Environmental regulations

来源：评论

学校读者我要写书评

暂无评论

Light Field Compression Based on Implicit Neural Representation

arXiv

引用

arXiv 2024年

作者： Wang, Henan Zhu, Hanxin Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

Light field, as a new data representation format in multimedia, has the ability to capture both intensity and direction of light rays. However, the additional angular information also brings a large volume of data. Classical coding methods are not effective to describe the relationship between different views, leading to redundancy left. To address this problem, we propose a novel light field compression scheme based on implicit neural representation to reduce redundancies between views. We store the information of a light field image implicitly in an neural network and adopt model compression methods to further compress the implicit representation. Extensive experiments have demonstrated the effectiveness of our proposed method, which achieves comparable rate-distortion performance as well as superior perceptual quality over traditional methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Redundancy

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：