检索结果-内蒙古大学图书馆

8th International symposium on Computer Science and Intelligent control, ISCSIC 2024

作者： Zhao, Xinyu Liu, Jianxiang Wu, Faguo Zhang, Xiao Institute for Artificial Intelligence Beihang University Beijing China Bejing Advanced Innovation Center for Future Blockchain and Privacy Computing Zhongguancun Laboratory Beijing China Beihang University School of Mathematical Sciences Beijing China Beihang University Beijing China Zhongguancun Laboratory Beijing China

ISBN: (纸本)9798350380286

The use of centralized value networks is an important training method in multi-agent reinforcement learning (MARL). Existing methods usually utilize value decomposition to enable agents to achieve localized learning. However, these methods do not take into account sample efficiency, and the introduction of additional networks will also bring more computational costs. Therefore, it is necessary to introduce the ensemble idea of making full use of the replay buffer. The general ensemble learning approach is to introduce sub-models into the value network, and its application in multi-agent systems is not yet mature. In this paper, we firstly implement a multi-agent ensemble technique with locally shared parameters in the network by introducing a feature-based grouping mechanism. Secondly, we propose random and feature-based grouping principles and design a dimension reduction scheme for action-state space. Finally, our approach was evaluated on the benchmark platform, Multi-Agent Particle Environment (MPE), and compared with baseline algorithms. The results demonstrated that our method exhibited notable advantages in terms of achieving higher scores and converging rapidly. © 2024 ieee.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Learning Dense Visual Object Descriptors to Fold Two-Dimensional Deformable Fabrics 13

Learning Dense Visual Object Descriptors to Fold Two-Dimensi...

引用

13th ieee International Conference on CYBER Technology in automation, control, and Intelligent Systems, CYBER 2023

作者： Cao, Yang Gong, Daoxiong Yu, Jianjun Beijing University of Technology Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing100124 China

ISBN: (纸本)9798350315196

Manipulating two-dimensional fabrics is a significant research field in recent years. Fabric manipulation presents a formidable challenge due to the intricate dynamics and high-dimensional state space inherent in the process, prior research has predominantly relied on robot learning of task-specific strategies as a means to effectively accomplish the corresponding fabric manipulation tasks. In this work, we utilize dense visual object descriptors trained on synthetic RGB images to learn visual representations for two-dimensional fabrics. Based on the learned descriptors, the robot can learn the correspondences of similar fabrics in different configurations. We apply a novel Siamese network architecture to improve the quality of learned descriptors for three types of fabrics, including square fabrics, T-shirts and shorts. By utilizing the learned descriptors, the equivalent actions in an unknown configuration can be computed based on a fabric folding demonstration in an initial configuration. We perform a series of fabric folding tasks in different colors, sizes and shapes. The policy can achieve 87.7% average task success rate across 7 different folding tasks. © 2023 ieee.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Path Planning Based on Improved RRT Algorithm 2

Path Planning Based on Improved RRT Algorithm

引用

2nd International symposium on control Engineering and Robotics, ISCER 2023

作者： Huang, Yanguo Jin, Chao School of Electrical Engineering and Automation Jiangxi University of Technology Ganzhou Jiangxi China

ISBN: (纸本)9798350336405

The traditional path-exploring Random Trees (RRT) algorithm has the defects of low search efficiency and high path curvature. Based on the basic RRT algorithm, target bias strategy and pruning optimization algorithm are adopted to reduce unnecessary blank search and improve the computational speed. By introducing stretch function, the generated path is searched forward along the end node, and the two non-adj acent nodes with no obstacles in the middle are merged to reduce redundant paths. The cubic B-spline function is used to make the path curve smoother. In the matlab simulation environment simulation. Simulation results show that compared with the traditional RRT algorithm, the improved path planning algorithm greatly reduces the length of path planning and the path search time, and verifies the effectiveness of the path planning algorithm. © 2023 ieee.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Threat Detection of Internet of Things Based on Machine Learning 4

Threat Detection of Internet of Things Based on Machine Lear...

引用

4th ieee Annual Flagship India Council International Subsections Conference, INDISCON 2023

作者： Fu, Xinghao School of Automation Engineering University of Electronic Science and Technology of China chengdu China

ISBN: (纸本)9798350333558

The research on threat detection of the Internet of Things based on machine learning aims to find out effective ways or methods that can be used to detect threats and vulnerabilities in Internet of Things devices. This research will help add security features to IoT devices. The main goal of this research is to detect any type of malicious activities that hackers and other network criminals use intelligent gadgets, appliances, etc. The main motivation behind this project is to improve users' trust in Internet of Things devices. This will also help them control their privacy by preventing unauthorized access, which is achieved through such attacks, and provide more secure information sharing between different entities involved in the IoT system. Therefore, if all interested parties can rely on such algorithms, it is to protect our network from any type of network attacks and malicious activities. © 2023 ieee.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Image Segmentation based System for Computing the Shifting of a Tooth 16

Image Segmentation based System for Computing the Shifting o...

引用

16th ieee International symposium on Applied computational intelligence and Informatics, SACI 2022

作者： Stancioi, Cristina-Maria Muresan, Vlad Abrudean, Mihai Clitan, Iulia Unguresan, Mihaela-Ligia Bunta, Olimpia Technical University of Cluj-Napoca Automation Department Cluj-Napoca Romania Technical University of Cluj-Napoca Physics and Chemistry Department Cluj-Napoca Romania University of Medicine and Pharmacy Department of Orthodontics Cluj-Napoca Romania

ISBN: (数字)9781665481250

ISBN: (纸本)9781665481250

The primary goal of this work is to compute the exact position of the teeth in relation to a given anatomical reference using panoramic dental radiography. The complete system was built in such a way that a dental specialist may utilize it to better examine the characteristics of a patient's intraoral configuration. The system was developed with the Matlab work environment and includes a graphical user interface that the doctor may easily operate. Image - processing techniques were utilized during the development to process such an image, and the ones that proved successful will be detailed in this article. Furthermore, another aim of this system is to measure the intensity of each element of the denture, permitting a dental specialist to draw additional vital diagnoses. Some diagnoses can be identified automatically even after the raw image has been pre-processed. As a conclusion, each step executed with the software will aid in the analysis of panoramic dental radiography. © 2022 ieee.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Redundant Constraints Identification Based Acceleration Method for Multi-Stage Robust SCUC Problems 21

Redundant Constraints Identification Based Acceleration Meth...

引用

21st International Conference on Networking, Sensing and control, ICNSC 2024

作者： Zhang, Yuxuan Zhai, Qiaozhu Zhou, Yuzhou Han, Zhihan Qiao, Wei Li, Haozhe School of Automation Science and Engineering Xi'an Jiaotong University Moeklinns Lab Xi'an China

ISBN: (纸本)9798350365221

Security constrained unit commitment (SCUC) problem with uncertainty has become an important research task with the increasing scale of renewable energy access in the power system. Multi-stage robust optimization method has been proved to be effective for solving the UC problem with uncertainty, but it has to deal with the difficulty of excessive computation. The complexity of the UC problem is also increasing due to the rapidly expanding overall size of the power system. A common method to improve the efficiency of solving UC problems is to eliminate redundant security constraints. However, this method is mainly applied to the deterministic UC problems at present. In this paper, a solution framework based on a multi-stage robust optimization method with eliminating redundant security constraints is established. Numerical testing is performed for ieee 24-bus system and 118-bus system. Most of the security constraints are identified as redundant constraints in different scenarios. The computational efficiency is obviously improved after redundant constraints are eliminated. © 2024 ieee.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

IOT Enabled Home automation over Cloud 1

IOT Enabled Home Automation over Cloud

引用

1st International Conference on computational intelligence and Sustainable Engineering Solution, CISES 2022

作者： Gupta, Atul Srivastava, Vivek Choudekar, Pallavi Ruchira, Ruchira Amity University Uttar Pradesh India

ISBN: (数字)9781665480048

ISBN: (纸本)9781665480048

This paper describes the design and development of a home automation system that links its component parts using Wi-Fi technology as the network architecture. Essentially, the proposed system comprises of just two parts. The server (web server), which regulates, coordinates, and keeps an eye on users' homes, is the crucial component because it houses the system's brain. Users and system administrators have local (LAN) and remote (Internet) access to manage and control system code (internet). The system supports a variety of home automation systems, including power management and security components. The suggested technique is more flexible and scalable than current home automation systems. Goal of the work is to utilize easily available electronics modules to implement a cost effective, Compact and efficient home automation project. We made a system which gives service at low cost compared to the cost of the on the market, there are a variety of home automation systems. and it is also very compact. © 2022 ieee.

关键词： automation

来源：评论

学校读者我要写书评

暂无评论

MINER-RRT*: A Hierarchical and Fast Trajectory Planning Framework in 3D Cluttered Environments

引用

ieee TRANSACTIONS ON automation SCIENCE AND ENGINEERING 2025年 22卷 10973-10985页

作者： Wang, Pengyu Tang, Jiawei Lin, Hin Wang Zhang, Fan Wang, Chaoqun Wang, Jiankun Shi, Ling Meng, Max Q. -H. Southern Univ Sci & Technol Shenzhen Key Lab Robot Percept & Intelligence Shenzhen 518055 Peoples R China Southern Univ Sci & Technol Dept Elect & Elect Engn Shenzhen 518055 Peoples R China Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Peoples R China Shandong Univ Sch Control Sci & Engn Jinan 250100 Shandong Peoples R China Southern Univ Sci & Technol Jiaxing Res Inst Jiaxing 314001 Peoples R China Univ Alberta Dept Elect & Comp Engn Edmonton AB T6G 2R3 Canada Chinese Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

Trajectory planning for quadrotors in cluttered environments has been challenging in recent years. While many trajectory planning frameworks have been successful, there still exists potential for improvements, particularly in enhancing the speed of generating efficient trajectories. In this paper, we present a novel hierarchical trajectory planning framework to reduce computational time and memory usage called MINER-RRT*, which consists of two main components. First, we propose a sampling-based path planning method boosted by neural networks, where the predicted heuristic region accelerates the convergence of rapidly-exploring random trees. Second, we utilize the optimal conditions derived from the quadrotor's differential flatness properties to construct polynomial trajectories that minimize control effort in multiple stages. Extensive simulation and real-world experimental results demonstrate that, compared to several state-of-the-art (SOTA) approaches, our method can generate high-quality trajectories with better performance in 3D cluttered environments (https://***/fXuuMRX19q0). Note to Practitioners-The motivation is the problem of planning trajectories for quadrotor autonomous flight in 3D cluttered and complex scenarios such as wild forest exploration and subterranean environment search-and-rescue. Sampling-based path planning methods are suitable for dealing with the complexity of the physical environment but are not convenient for computing dynamics and their differentials. Optimization-based trajectory generation methods are appropriate for handling various high-order constraints but rely on high-quality initial path solutions. Therefore, this paper combines the advantages of the two methods to propose a novel trajectory planning framework that can generate high-quality trajectories for quadrotors faster than many previous algorithms. We conduct numerous simulations and real-world experiments to verify that our method can be effectively deployed in re

关键词： Trajectory Trajectory planning Planning Quadrotors Three-dimensional displays Polynomials Trajectory optimization Splines (mathematics) Resource management Heuristic algorithms Robot trajectory planning sampling-based algorithm deep neural network

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence-based Fault Detection and Diagnosis: Towards Application in a Chemical Process

Artificial Intelligence-based Fault Detection and Diagnosis:...

引用

2023 CAA symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 2023

作者： Liu, Yiqi Li, Zhi Chen, Hongtian The School of Automation Science & Engineering Key Laboratory of Autonomous Systems and Networked Control Ministry of Education South China University of Technology Guangzhou510640 China Shanghai Jiao Tong University Department of Automation Shanghai200240 China

ISBN: (纸本)9798350337754

As the chemical processes become more and more complicated, it is crucial but also difficult to detect and diagnose faults in the system than ever. With the development of machine learning algorithms and cloud computing, to monitor chemical processes completely with the help of big data become true. However, most machine learning methods suffer from unexplainable problem. By employing Explainable Artificial intelligence(XAI) techniques, this paper applies two kinds of unsupervised machine learning methods, One-Class Support Vector Machine and Depth-based Isolation Forest Feature Importance, to detect and diagnosis faults in a chemical process. By combining two different fault explanation methodologies, accuracy and reliability of the fault diagnosis results can be achieved by the validation in a simulated continuous stirred tank reactor. © 2023 ieee.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Incorporating Visual intelligence in Line Following Robots 9

Incorporating Visual Intelligence in Line Following Robots

引用

9th ieee International symposium on Smart Electronic Systems, iSES 2023

作者： Pujara, Dhyanik Naik, Palak Gautam, Riya Mecwan, Akash Institute of Technology Nirma University Electronics and Comminication Department Ahmedabad India

ISBN: (纸本)9798350383249

Line follower robot is a mobile robot that is programmed to detect the path and trace the same. A colored line follower is an improved version of the line follower robot which is able to select the desired line among different colored lines as per the instructions given by the user. Line-following robots have gained significant attention due to their applications in various fields, including industrial automation, transportation, and entertainment. Traditional line-followers use basic infrared sensor-based systems, which restrict their ability to handle complex and dynamic surroundings and also work for either black or white path. In order to improve the robot's ability to navigate and track a colored path, this paper suggests two methods that make use of sophisticated image processing and computer vision algorithms. Open CV and python are used to design the path detection system and a feedback-based control loop mechanism called PID controller is also implemented for robot movement. Out of the two proposed methods, the experimental results demonstrate the effectiveness of IR Analogy Algorithm over Image Warping based algorithm. © 2023 ieee.

关键词： Python

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：