检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Electrical, Automation and computer engineering, ICEACE 2024

作者： Bian, Lu Xia, Weimin Tan, Yuanpeng Zhao, Miao State Grid Corporation Limited Beijing China State Grid Zhongxing Property Beijing Co. Ltd Beijing China China Electric Power Research Institute Limited Beijing China North China Electric Power University School of Control and Computer Engineering Beijing China

ISBN: (纸本)9798350368208

This paper delves into an obstacle detection algorithm that utilizes object recognition to enhance the precision of identifying small objects. By extending the YOLOv5s model with an additional layer dedicated to detecting small targets, we achieve multi-scale detection capabilities, thereby bolstering the recognition prowess for small obstacle targets. At the same time, the deformable convolution DCNv2 is combined to make full use of its ability to capture the features of small targets with large shape changes. To address the issue of redundant bounding boxes, we incorporate the Soft-NMS algorithm, which proficiently mitigates the inadvertent removal of bounding boxes, thereby enhancing both the accuracy and trustworthiness of the detection outcomes. Experimental findings underscore the remarkable performance improvement of the proposed algorithm, particularly in tasks involving the detection of small targets. © 2024 IEEE.

关键词： Obstacle detectors

来源：评论

学校读者我要写书评

暂无评论

On final opinions of the Friedkin-Johnsen model over random graphs with partially stubborn community

arXiv

引用

arXiv 2024年

作者： Wang, Lingfei Xing, Yu Johansson, Karl H. Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology with Digital Futures Stockholm Sweden

This paper studies the formation of final opinions for the Friedkin-Johnsen (FJ) model with a community of partially stubborn agents. The underlying network of the FJ model is symmetric and generated from a random graph model, in which each link is added independently from a Bernoulli distribution. It is shown that the final opinions of the FJ model will concentrate around those of an FJ model over the expected graph as the network size grows, on the condition that the stubborn agents are well connected to other agents. Probability bounds are proposed for the distance between these two final opinion vectors, respectively for the cases where there exist non-stubborn agents or not. Numerical experiments are provided to illustrate the theoretical findings. The simulation shows that, in presence of non-stubborn agents, the link probability between the stubborn and the non-stubborn communities affect the distance between the two final opinion vectors significantly. Additionally, if all agents are stubborn, the opinion distance decreases with the agent stubbornness. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Docking to a Specific Person of an Autonomous Mobile Manipulator Using UWB Positioning and RGB-D Camera

Docking to a Specific Person of an Autonomous Mobile Manipul...

引用

International Conference on Advanced Robotics and Intelligent Systems (ARIS)

作者： Kai-Tai Song Yu-Yun Huang Shu-Huan Deng Yuan-Shuo Hsieh Institute of Electrical and Control Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

In this paper, a novel navigation method is proposed to dock a mobile manipulator in front of a specific person by combining the ultra-wideband (UWB) positioning system with image-based motion control. The UWB is used for a longer distance human identification and positioning. As the robot approaches the target person, face recognition and face pose estimation are used for close docking control the person. The experimental results show that the average error of docking to a person is 5.2° in orientation and 8.48cm in distance. The integrated experimental results demonstrate that the autonomous mobile manipulator can navigate to a target person and handover an object to the person.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Optimization of the Interior Permanent Magnet Synchronous Motor for Electric Vehicles

Multi-objective Optimization of the Interior Permanent Magne...

引用

China International Electrical and Energy Conference (CIEEC)

作者： Changchuang Huang Baoqaun Kou Xiaokun Zhao Electrical Engineering and Automation Harbin Institute of Technology Heilongjiang China Computer and Control Engineering Northeast Forestry University Heilongjiang China

Permanent magnet synchronous motors (PMSMs) are widely used in various fields due to their high efficiency, high power factor and small volume. In this paper, a segmented permanent magnet interior permanent magnet synchronous motor (IPMSM) is proposed and optimized. First, the topology of the IPMSM is introduced. Second, multi-objective optimization is performed by non-dominated sorting genetic algorithm-II (NSGA-II) using rotor structure parameters as optimization variables, saliency ratio as constraint, electromagnetic torque and constant-power speed range as objective functions. Then, the electromagnetic characteristics of the initial IPMSM and the optimized IPMSM are analyzed and compared. The results show that the torque and constant-power speed range of the optimized motor are improved, which verifies the validity of the optimization method. The proposed motor is suitable for electric vehicles, which require large torque at low speeds and wide constant-power speed range at high speeds.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Risk-Averse Learning with Delayed feedback

arXiv

引用

arXiv 2024年

作者： Wang, Siyi Wang, Zifan Johansson, Karl H. Hirche, Sandra Department of Electrical and Computer Engineering Technical University of Munich Munich80333 Germany Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden

In real-world scenarios, the impacts of decisions may not manifest immediately. Taking these delays into account facilitates accurate assessment and management of risk in real-world environments, thereby ensuring the efficacy of strategies. In this paper, we investigate risk-averse learning using Conditional Value at Risk (CVaR) as risk measure, while incorporating delayed feedback with unknown but bounded delays. We develop two risk-averse learning algorithms that rely on one-point and two-point zeroth-order optimization approaches, respectively. The regret achieved by the algorithms is analyzed in terms of the cumulative delay and the number of total samplings. The results suggest that the two-point risk-averse learning achieves a smaller regret bound than the one-point algorithm. Furthermore, the one-point risk-averse learning algorithm attains sublinear regret under certain delay conditions, and the two-point risk-averse learning algorithm achieves sublinear regret with minimal restrictions on the delay. We provide numerical experiments on a dynamic pricing problem to demonstrate the performance of the proposed algorithms. © 2024, CC0.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging GPT-4 Capabilities for Developing Context-Aware, Personalized Chatbot Interfaces in E-commerce Customer Support Systems 10

Leveraging GPT-4 Capabilities for Developing Context-Aware, ...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Santosh, Kathari Kholmukhamedov, Timur Kumar, M. Sandeep Aarif, Mohd Muda, Iskandar Bala, B Kiran Cmr Institute of Technology Bengaluru Department of Mba Bengaluru India Turin Polytechnic University In Tashkent Automatic Control and Computer Engineering Department Tashkent Uzbekistan Publishing Global Research Network Noida India Universitas Sumatera Utara Medan Indonesia K.Ramakrishnan College of Engineering Department of Artificial Intelligence and Data Science Trichy India

ISBN: (纸本)9798350353068

In the realm of e-commerce customer support, the adoption of chatbots is on the rise, driven by a quest for heightened user interactions. This study introduces an inventive approach harnessing the advanced capabilities of GPT-4 to construct chatbot interfaces that are both context-aware and personalized. The main aim of this work is to revolutionize ecommerce customer support by developing intelligent and adaptable chatbot interfaces that are context-aware, personalized, and significantly enhance user experiences. Existing chatbot models struggle with context retention and personalization, limiting effectiveness in dynamic e-commerce environments despite the promise of automation. This innovative approach leverages GPT-4's robust language processing, integrating it with user profiling systems for personalized responses grounded in user preferences and historical interactions. The method gives, diverse e-commerce dataset undergoes collection and pre-processing, followed by fine-tuning GPT-4 with an emphasis on context-awareness and personalized responses. The model is seamlessly integrated with e-commerce backend systems for real-time information, multimodal input support caters to varied user preferences. Results exhibit a significant 95% accuracy improvement, affirming the chatbot's enhanced ability to comprehend user queries. By integrating personalization and advanced context retention, this study enhances user engagement, paving way for revolutionary intelligent and adaptable chatbot interfaces in ecommerce customer support. © 2024 IEEE.

关键词： Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Convergent Approaches to AI Explainability for HEP Muonic Particles Pattern Recognition

引用

Computing and Software for Big Science 2023年第1期7卷 1-18页

作者： Maglianella, Leandro Nicoletti, Lorenzo Giagu, Stefano Napoli, Christian Scardapane, Simone Department of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome Rome Italy Department of Physics Sapienza University of Rome Rome Italy Institute for Systems Analysis and Computer Science Italian National Research Council Rome Italy Department of Computational Intelligence Electronics and Telecommunications Czestochowa University of Technology Czestochowa Poland Department of Information Engineering Electronics and Telecommunications Sapienza University of Rome Rome Italy

Neural networks are commonly defined as ‘black-box’ models, meaning that the mechanism describing how they give predictions and perform decisions is not immediately clear or even understandable by humans. Therefore, Explainable Artificial Intelligence (xAI) aims at overcoming such limitation by providing explanations to Machine Learning (ML) algorithms and, consequently, making their outcomes reliable for users. However, different xAI methods may provide different explanations, both from a quantitative and a qualitative point of view, and the heterogeneity of approaches makes it difficult for a domain expert to select and interpret their result. In this work, we consider this issue in the context of a high-energy physics (HEP) use-case concerning muonic motion. In particular, we explored an array of xAI methods based on different approaches, and we tested their capabilities in our use-case. As a result, we obtained an array of potentially easy-to-understand and human-readable explanations of models’ predictions, and for each of them we describe strengths and drawbacks in this particular scenario, providing an interesting atlas on the convergent application of multiple xAI algorithms in a realistic context. © 2023, The Author(s).

关键词： Explainable Artificial Intelligence High-energy physics Intrinsically interpretable Decision Trees Saliency maps methods Tracing gradient descent

来源：评论

学校读者我要写书评

暂无评论

Rethinking Guidance Information to Utilize Unlabeled Samples: A Label Encoding Perspective 41

Rethinking Guidance Information to Utilize Unlabeled Samples...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, Yulong Yao, Yuan Chen, Shuhao Jin, Pengrong Zhang, Yu Jin, Jian Lu, Jiangang Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China College of Control Science and Engineering Zhejiang University Hangzhou China Beijing Teleinfo Technology Company Ltd. China Academy of Information and Communications Technology Beijing China Research Institute of Industrial Internet of Things China Academy of Information and Communications Technology Beijing China

Empirical Risk Minimization (ERM) is fragile in scenarios with insufficient labeled samples.A vanilla extension of ERM to unlabeled samples is Entropy Minimization (EntMin), which employs the soft-labels of unlabeled samples to guide their ***, EntMin emphasizes prediction discriminability while neglecting prediction *** alleviate this issue, in this paper, we rethink the guidance information to utilize unlabeled *** analyzing the learning objective of ERM, we find that the guidance information for labeled samples in a specific category is the corresponding label *** by this finding, we propose a Label-Encoding Risk Minimization (LERM).It first estimates the label encodings through prediction means of unlabeled samples and then aligns them with their corresponding ground-truth label *** a result, the LERM ensures both prediction discriminability and diversity, and it can be integrated into existing methods as a ***, we analyze the relationships between LERM and ERM as well as ***, we verify the superiority of the LERM under several label insufficient *** codes are available at https://***/zhangyl660/LERM. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

HGS-Planner: Hierarchical Planning Framework for Active Scene Reconstruction Using 3D Gaussian Splatting

arXiv

引用

arXiv 2024年

作者： Xu, Zijun Jin, Rui Wu, Ke Zhao, Yi Zhang, Zhiwei Zhao, Jieru Gao, Fei Gan, Zhongxue Ding, Wenchao The Academy for Engineering & Technology Fudan University Shanghai200433 China The Institute of Cyber-Systems and Control College of Control Science and Engineering Zhejiang University Hangzhou310027 China The Department of Computer Science and Engineering Shanghai Jiao Tong University China

In complex missions such as search and rescue, robots must make intelligent decisions in unknown environments, relying on their ability to perceive and understand their surroundings. High-quality and real-time reconstruction enhances situational awareness and is crucial for intelligent robotics. Traditional methods often struggle with poor scene representation or are too slow for real-time use. Inspired by the efficacy of 3D Gaussian Splatting (3DGS), we propose a hierarchical planning framework for fast and high-fidelity active reconstruction. Our method evaluates completion and quality gain to adaptively guide reconstruction, integrating global and local planning for efficiency. Experiments in simulated and real-world environments show our approach outperforms existing real-time methods. Copyright © 2024, The Authors. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Improved Artificial Field Method Based on the Flight Situation Awareness Map in Coaxial Rotor UAV

Improved Artificial Field Method Based on the Flight Situati...

引用

International Conference on Autonomous Unmanned Systems, ICAUS 2021

作者： Wei, Yiran Li, Kewei Deng, Hongbin Pan, Zhenhua Liu, Zhichao Wang, Wei School of Mechatronics Engineering Beijing Institute of Technology Beijing100081 China Beijing Institute of Computer and Electronics Application Beijing China School of Automation Beijing Institute of Technology Beijing China Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (纸本)9789811694912

The use of unmanned aerial vehicle (UAV) has been recognized by the majority of people, and is regarded as a reliable tool to complete some tasks. As for the obstacle avoidance of coaxial rotor UAV (CR-UAV), a flight pattern map (Flight Situation Awareness Map: FSAM) that can sense the flight environment and an integrated control method (Improved Artificial Potential Field: IAPF) based on the common artificial potential field method with appropriate improvements to achieve obstacle avoidance (IAPF). Firstly, we construct the FSAM, which can map the environment information around the UAV on the FSAM. Then, based on the FSAM, the IAPF functions are established to achieve the obstacles avoidance. Cause the artificial potential field (APF) has a characteristic that cannot avoid: the problem of local minima, a rotating potential field is put forward to ensure that the CR-UAV has only one potential equilibrium point at the target point in the environment, and it will improve the ability of CR-UAV to avoid complex obstacles. At the end of this study, through data analysis, the performance of obstacle avoidance and the attitude stability of CR-UAV are good, the simulation results confirm that the approaches proposed in this paper can address the obstacles avoidance successfully. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Unmanned aerial vehicles (UAV)

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：