检索结果-内蒙古大学图书馆

24th International Symposium INFOTEH-JAHORINA, INFOTEH 2025

作者： Golić, Anastasija Radović, Mirna University of Novi Sad Faculty of Technical Sciences Department of Computing and Control Engineering Novi Sad Serbia

ISBN: (纸本)9798331515799

This paper evaluates two common methods for trajectory estimation: the Extended Kalman Filter (EKF), the Unscented Kalman Filter (UKF). The EKF and UKF are well-established recursive filtering techniques commonly used for nonlinear state *** performance of these methods is compared through their implementation on a standard trajectory estimation problem, with a focus on assessing their accuracy. © 2025 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Cooperative differential games guidance laws for multiple attackers against an active defense target

引用

Chinese Journal of Aeronautics 2022年第5期35卷 374-389页

作者： Fei LIU Xiwang DONG Qingdong LI Zhang REN School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control LaboratoryBeihang UniversityBeijing 100083China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing 100083China Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education of ChinaChongqing UniversityChongqing 400044China

This paper is concerned with a scenario of multiple attackers trying to intercept a target with active *** types of agents are considered in the guidance:The multiple attackers,the target and the defender,where the attackers aim to pursuit the target from different directions and evade from the defender *** guidance engagement is formulated in the framework of a zero-sum two-person differential game between the two opposing teams,such that the measurements on the maneuver of the target or estimations on the defending strategy of the defender can be *** of the attackers resides in two aspects:redundant interception under the threat of the defender and the relative intercept geometry with the *** miss distances,the relative intercept angle errors and the costs of the agents are combined into a single performance index of the *** formulation enables a unitary approach to the design of guidance laws for the *** minimize the control efforts and miss distances for the attackers,an optimization method is proposed to find the best anticipated miss distances to the defender under the constraint that the defender is endowed with a capture *** simulations with two cases are conducted to illustrate the effectiveness of the proposed cooperative guidance law.

关键词： Active defense Cooperative guidance Differential games Minimum effort optimization Relative intercept angle

来源：评论

学校读者我要写书评

暂无评论

Consensus control of Multi-Agent Systems Using Fault-Estimation-in-the-Loop:Dynamic Event-Triggered Case

引用

IEEE/CAA Journal of Automatica Sinica 2022年第8期9卷 1440-1451页

作者： Yamei Ju Derui Ding Xiao He Qing-Long Han Guoliang Wei Shanghai Key Lab of Modern Optical System the Department of Control Science and EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China Department of Control Science and Engineering University of Shanghai for Science and TechnologyShanghai 200093China School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourneVIC 3122Australia Department of Automation BNRistTsinghua UniversityBeijing 100084China College of Science University of Shanghai for Science and TechnologyShanghai 200093China

The paper develops a novel framework of consensus control with fault-estimation-in-the-loop for multi-agent systems(MASs)in the presence of faults.A dynamic event-triggered protocol(DETP)by adding an auxiliary variable is utilized to improve the utilization of communication ***,a novel estimator with a noise bias is put forward to estimate the existed fault and then a consensus controller with fault compensation(FC)is adopted to realize the demand of reliability and safety of addressed ***,a novel consensus control framework with fault-estimation-in-the-loop is developed to achieve the predetermined consensus performance with the l_(2)-l_(∞)constraint by employing the variance analysis and the Lyapunov stability ***,the desired estimator and controller gains are obtained in light of the solution to an algebraic matrix equation and a linear matrix inequality in a recursive way,***,a simulation result is employed to verify the usefulness of the proposed design framework.

关键词： Consensus control dynamic event-triggered protocol(DETP) fault compensation(FC) fault estimation multi-agent systems(MASs)

来源：评论

学校读者我要写书评

暂无评论

Demonstrating the Potential of Visualization in Education with the Manim Python Library: Examples from Algorithms and Data Structures

Demonstrating the Potential of Visualization in Education wi...

引用

Proceedings of the International Convention MIPRO

作者： Milorad Marković Ivan Kaštelan Department of Computing and Control Engineering Sub-department of Computer Engineering and Communications University of Novi Sad Novi Sad Serbia

ISBN: (数字)9798350382501

ISBN: (纸本)9798350382518

Visualization is a powerful tool for learning and teaching complex concepts, especially in the field of computer science. However, creating effective and engaging visualizations can be challenging and time-consuming for educators and students. This paper demonstrates how the Manim Python library, a free and open-source project for creating mathematical animations, can be used to create visualizations that illustrate algorithms and data structures in an undergraduate course. The paper showcases several examples of visualizations created with the Manim library, and explains how they help the students to understand the logic, behavior, and performance of the algorithms and data structures. The paper also discusses the benefits and limitations of the Manim library, and suggests some directions for future research and development.

关键词： Computer science Education Data visualization Data structures Animation Libraries Mathematics

来源：评论

学校读者我要写书评

暂无评论

Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity

arXiv

引用

arXiv 2024年

作者： Chen, Junkun Mei, Jilin Chen, Liang Zhao, Fangzhou Xing, Yan Hu, Yu Institute of Computing Technology Chinese Academy of Sciences China Beijing Institute of Control Engineering China

Neural networks that are trained on limited category samples often mispredict out-of-distribution (OOD) objects. We observe that features of the same category are more tightly clustered in feature space, while those of different categories are more dispersed. Based on this, we propose using prototype similarity for OOD detection. Drawing on widely used prototype features in few-shot learning, we introduce a novel OOD detection network structure (Proto-OOD). Proto-OOD enhances the representativeness of category prototypes using contrastive loss and detects OOD data by evaluating the similarity between input features and category prototypes. During training, Proto-OOD generates OOD samples for training the similarity module with a negative embedding generator. When Pascal VOC are used as the in-distribution dataset and MS-COCO as the OOD dataset, Proto-OOD significantly reduces the FPR (false positive rate). Moreover, considering the limitations of existing evaluation metrics, we propose a more reasonable evaluation protocol. The code will be released. © 2024, CC BY.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

A review of the approaches for enhancing driver safety through camera-based monitoring

A review of the approaches for enhancing driver safety throu...

引用

Zooming Innovation in Consumer Electronics International Conference (ZINC)

作者： Maksim Egelja Bogdan Pavkovic Computing and Control Engineering Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia

ISBN: (数字)9798350349153

ISBN: (纸本)9798350349160

Road accidents caused by human error continue to result in a rising number of serious injuries and fatalities each year. Automated Driving Assistance Systems (ADAS) offer a promising approach by continuous monitoring of drivers to promptly identify and address unsafe behaviors. A further technical challenge is solely relying on camera sensors to determine crucial human deficiencies such as drowsiness and distraction. In our research, we provide a review of relevant papers from the field of computer vision for driver monitoring. Most of these approaches rely on Machine Learning (ML) algorithms and Convolutional Neural Networks (CNNs) for both image processing and driver state classification. Our findings indicate that Hidden Markov Models (HMMs) and CNNs consistently outperform other techniques in terms of accuracy. In conclusion, we present our perspective on the essential features that a comprehensive driver monitoring system (DMS) should include.

关键词： Computer vision Technological innovation Reviews Hidden Markov models Cameras Sensors Proposals

来源：评论

学校读者我要写书评

暂无评论

A Novel Grades Prediction Method for Undergraduate Students by Learning Explicit Conditional Distribution

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第9期5卷 4837-4848页

作者： Zhang, Na Liu, Ming Wang, Lin Liu, Shuangrong Sun, Runyuan Yang, Bo Zhu, Shenghui Li, Chengdong Yang, Cheng Cheng, Yuhu China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China Shandong Key Laboratory of Intelligent Buildings Technology Jinan250101 China University of Jinan Shandong Provincial Key Laboratory of Network Based Intelligent Computing Jinan250022 China Quan Cheng Laboratory Jinan250100 China Shandong Jianzhu University Shandong Key Laboratory of Intelligent Buildings Technology Jinan250101 China Shandong Jianzhu University School of Information and Electrical Engineering Jinan250101 China Ministry of Education Engineering Research Center of Intelligent Control for Underground Space Xuzhou221116 China

Educational data mining (EDM) offers an effective solution to predict students' course grades in the next term. Conventional grade prediction methods can be viewed as regressing an expectation of the probability distribution of the student's grade, typically called single-value grade prediction. The reliable prediction outcomes of these methods depend on the complete input information related to students. However, next-term grade prediction often encounters the challenge of incomplete input information due to the inaccessibility of future data and the privacy of data. In this scenario, single-value grade prediction struggles to assess students' academic status, as it may not be represented and assessed by relying on a singular expectation value. This limitation increases the risk of misjudgment, and may lead to errors in educational decision-making. Considering the challenge of collecting complete input information, we shift from traditional single-value predictions to forecasting the explicit probability distribution of the course grade. The probability distribution of the grade can assess the students' academic status by providing probabilities corresponding to all possible grade values rather than relying solely on an expectation value, which offers the foundation to support the educators' decision-making. In this article, the course grade distribution prediction (CGDP) model is proposed, aiming to estimate an explicit conditional probability distribution of course grades in the next term. This model can identify at-risk students, offering comprehensive decision-making information for educators and students. To ensure precise distribution predictions, a calibration method is also employed to improve the alignment between predicted and actual probabilities. Experimental results verify the effectiveness of the proposed model in early grade warning for undergraduates, based on real university data. © 2020 IEEE.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Anfis-Stsmc controller Design to Enhance Stability Of Self-Balancing Two-Wheeled Electric Scooter on Uneven Terrain

SSRN

引用

SSRN 2024年

作者： Birhane, Wendwsen Teklay Haile, Endalew Ayenew Department of Electrical Power and Control Engineering School of Electrical Engineering and Computing Adama Science and Technology University Adama Ethiopia

In this work, we design an effective controller for a Segway that can tackle uneven terrain disturbances and parameter variations. Self-balancing is essential for maintaining stability during movement, while effective steering control ensures accurate and responsive direction changes over rough terrain. The study begins with a comprehensive analysis of the interaction between the Segway's mechanical, electrical, and control systems under varying ground conditions. A mathematical model is developed to capture the Segway's behavior in these different scenarios. To enhance control performance, a Super Twisting Sliding Mode controller (STSMC) is designed to manage both balancing and steering. The parameters of the STSMC are optimized using Teaching-Learning-Based Optimization (TLBO). These optimized parameters are then utilized to train an Adaptive Neuro-Fuzzy Inference System (ANFIS) for pitch angle control and a Neural Network (NN) for yaw angle control. The ANFIS-STSMC achieves a settling time of 0.1802 seconds and a rise time of 0.2538 seconds for balance angle control, with no steady-state error. For yaw angle control, the NN controller, trained using STSMC data, achieves a settling time of 0.2994 seconds, a rise time of 0.3495 seconds, and minimal overshoot (0.16\% for balance angle and 0.05\% for direction angle). Performance testing in MATLAB/Simulink demonstrates that the combination of ANFIS-STSMC and NN controllers significantly improves the Segway's stability and steering capability, particularly on uneven terrain. © 2024, The Authors. All rights reserved.

关键词： Steering

来源：评论

学校读者我要写书评

暂无评论

Safety-Critical Defensive Guidance of Autonomous Surface Vehicles for Domain Protection 1

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Kang, Tong Gu, Nan Wang, Dan Peng, Zhouhua Lv, Guanghao School of Marine Electrical Engineering Dalian Maritime University Dalian116026 China Dalian Key Laboratory of Swarm Control and Electrical Technology for Intelligent Ships Dalian116026 China School of Science Computing and Engineering Technologies Swinburne University of Technology MelbourneVIC3122 Australia

ISBN: (数字)9789819733408

ISBN: (纸本)9789819733392

This paper addresses the safety-critical defensive guidance of autonomous surface vehicles (ASVs) concerning the interception of multiple attackers to protect a given domain within an obstacle environment. First, an optimal defensive matching method is proposed, which efficiently assigns multiple defensive ASVs to corresponding attackers. Then, an optimal collision-free defensive guidance law is developed to efficiently intercept an attacker in the presence of stochastic measurement noise. By using the proposed safety-critical defensive guidance method, the defensive ASVs are able to intercept the matched attackers with guaranteed safety. Through the stability analysis, the closed-loop system is practical stochastic input-to-state stability. Simulation results substantiate the effectiveness of the proposed safety-critical defensive guidance for the domain protection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Energy Management Strategy for Fuel Cell Hybrid Emergency Power System based on Deep Reinforcement Learning 4

Energy Management Strategy for Fuel Cell Hybrid Emergency Po...

引用

4th International Symposium on AI, ISAI 2024

作者： Xi, Jingyi Hu, Xiaoyin Xiao, Duo Zhejiang University College of Control Science and Engineering Hangzhou China Hangzhou City University School of Information and Electrical Engineering Hangzhou China Hangzhou City University School of Computer and Computing Science Hangzhou China Hangzhou City University The Academy of Edge Intelligence Hangzhou China

ISBN: (纸本)9798350342482

Addressing the challenges in energy consumption and lifespan of fuel cell hybrid emergency power system, this paper proposes an energy management strategy based on deep reinforcement learning. The strategy aims to holistically balance objectives such as hydrogen consumption of the fuel cell, its lifespan, the stability of the lithium battery's state of charge (SOC), and its degradation. Firstly, we present the system architecture of the fuel cell hybrid emergency power system and establish models for hydrogen consumption and degradation of the fuel cell, as well as the SOC variations and degradation of the lithium battery, upon which a multi-objective reward function is constructed. Subsequently, we adopt the distributional soft actor-critic (DSAC) deep reinforcement learning algorithm, combined with a maximum entropy-based objective function to balance the exploration-exploitation trade-off and incorporated with a distributed value function estimation to alleviate the overestimation of Q-values. Simulation results demonstrate that the proposed strategy can effectively reduce the overall value loss, extend the system's lifespan, and showcase robust adaptability. © 2024 IEEE.

关键词： Deep reinforcement learning

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：