检索结果-内蒙古大学图书馆

IEEE Transactions on Intelligent Vehicles 2023年第9期9卷 1-17页

作者： Lan, Wenxing Li, Dachuan Hao, Qi Zhao, Dezong Tian, Bin Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China James Watt School of Engineering University of Glasgow Glasgow U.K State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences China

The accurate prediction of behaviors of surrounding traffic participants is critical for autonomous vehicles (AV). How to fully encode both explicit (e.g., map structure and road geometry) and implicit scene context information (e.g., traffic rules) within complex scenarios is still challenging. In this work, we propose an implicit scene context-aware trajectory prediction framework (the PRISC-Net, Prediction with Implicit Scene Context) for accurate and interactive behavior forecasting. The novelty of the proposed approach includes: 1) development of a behavior prediction framework that takes advantage of both model- and learning-based approaches to fully encode scene context information while modeling complex interactions;2) development of a candidate path target predictor that utilizes explicit and implicit scene context information for candidate path target prediction, along with a motion planning-based generator that generates kinematic feasible candidate trajectories;3) integration of the proposed target predictor and trajectory generator with a learning-based evaluator to capture complex agent-agent and agent-scene interactions and output accurate predictions. Experiment results based on vehicle behavior datasets and real-world road tests show that the proposed approaches outperform state-of-the-art methods in terms of prediction accuracy and scene context compliance. IEEE

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Bathymetric SLAM Approach Using Multibeam Sonar Toward Polar Region

Bathymetric SLAM Approach Using Multibeam Sonar Toward Polar...

引用

International Conference on Guidance, Navigation and control, ICGNC 2024

作者： Jiao, Zhaonan Chen, Xinshuo Zhao, Shengwu Deng, Zhihong School of Automation Beijing Institute of Technology Beijing 100081 China Engineering Research Center of Navigation Guidance and Control Technology Ministry of Education Beijing China

ISBN: (纸本)9789819622115

This paper proposes a bathymetric simultaneous localization and mapping (SLAM) approach for underwater vehicles to conduct mission in the region with no high-resolution prior seabed terrain map while requires long-endurance autonomous navigation especially in polar region. Because of the rapid attenuation of electromagnetic waves in water mediums and insurmountable defects of regular sonar equipment, satellite navigation and acoustic methodologies are impractical in this scenario. To enhance the performance of navigation this paper chooses multibeam sonar as external sensor to detect the seabed terrain while employs the internal inertial navigation system to provide state information of vehicle to form one integrated navigation solution which not only perceives the position of vehicle but also charts the seabed terrain map of traveled area. The framework consists of multibeam sonar bathymetric method, terrain interpolation, submap processing strategy, path correction technique, and bathymetric SLAM mechanism. By using one real regional seabed terrain map of Arctic Ocean, one deepwater MBS model, and one trajectory of INS, a simulation experiment is conducted and verifies the performance of the proposed approach in detail. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bathymetric SLAM Multibeam Sonar Pose Graph Optimization Submap Processing

来源：评论

学校读者我要写书评

暂无评论

Online Volt-Var control Based on Reinforcement Learning in Active Distribution Systems Considering PV Inverters 5

Online Volt-Var Control Based on Reinforcement Learning in A...

引用

5th International Conference on Power and Energy Technology, ICPET 2023

作者： Gu, Changlei Zhang, Xian Wang, Hong Sayed, Ahmed Rabee Wang, Guibin Harbin Institute of Technology School of Mechanical Engineering and Automation Shenzhen China Electric Power Research Institute China Southern Grid Guangzhou China Shenzhen University College of Mechatronics and Control Engineering Shenzhen China

ISBN: (纸本)9798350339673

Due to the wide deployment of photovoltaic (PV) power generation, voltage stability is facing a severe challenge in the active distribution networks (ADNs). Reinforcement Learning (RL) techniques have been widely adopted in the power system optimal operation and quick control with high-performance achievements. Existing RL algorithms can handle only homogenous control action spaces, i.e., either continuous or discrete actions. However, the voltage control problem has hybrid action spaces. This paper proposes a hybrid soft actor-critic (H-SAC) algorithm for online quick-optimal voltage control. First, the problem is formulated to consider all types of control actions, including the setpoints of PV inverters. Second, it is standardized to be compatible with RL techniques. Third, the fundamental sample-efficient entropy-based maximization SAC algorithm is enhanced to train a policy with hybrid action spaces, where an action selection method is employed to map the continuous output of the actor-network into the integer action spaces. The proposed method is applied to the modified IEEE 33-bus system, where the voltage has been controlled with a very low computational burden. © 2023 IEEE.

关键词： active distribution networks hybrid action spaces Reinforcement Learning Soft Actor-Critic voltage control

来源：评论

学校读者我要写书评

暂无评论

Exploring Deep Learning Methods for computer Vision Applications across Multiple Sectors:Challenges and Future Trends

引用

computer Modeling in engineering & Sciences 2024年第4期139卷 103-141页

作者： Narayanan Ganesh Rajendran Shankar Miroslav Mahdal Janakiraman SenthilMurugan Jasgurpreet Singh Chohan Kanak Kalita School of Computer Science and Engineering Vellore Institute of TechnologyChennai600127India Department of Computer Science and Engineering Koneru Lakshmaiah Education FoundationVaddeswaram522502India Department of Control Systems and Instrumentation Faculty of Mechanical EngineeringVSB-Technical University of OstravaOstrava70800Czech Republic Department of Computer Science and Engineering Vel Tech High Tech Dr.Rangarajan Dr.Sakunthala Engineering CollegeChennai600062India Department of Mechanical Engineering and University Centre for Research&Development Chandigarh UniversityMohali140413India Department of Mechanical Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and TechnologyAvadi600062India

computer vision(CV)was developed for computers and other systems to act or make recommendations based on visual inputs,such as digital photos,movies,and other *** learning(DL)methods are more successful than other traditional machine learning(ML)methods *** techniques can produce state-of-the-art results for difficult CV problems like picture categorization,object detection,and face *** this review,a structured discussion on the history,methods,and applications of DL methods to CV problems is *** sector-wise presentation of applications in this papermay be particularly useful for researchers in niche fields who have limited or introductory knowledge of DL methods and *** review will provide readers with context and examples of how these techniques can be applied to specific areas.A curated list of popular datasets and a brief description of them are also included for the benefit of readers.

关键词： Neural network machine vision classification object detection deep learning

来源：评论

学校读者我要写书评

暂无评论

Virtual Flux-Based Scheme for Passivity Enhancement in MMC-HVDC System 7

Virtual Flux-Based Scheme for Passivity Enhancement in MMC-H...

引用

7th IEEE International Electrical and Energy Conference, CIEEC 2024

作者： Liu, Jiayi Zhang, Hengke Zhao, Bo Gu, Fangning Sun, Mingzhe Liu, Yiqi Zhao, Zheng Teng, Shangfu Northeast Forestry University College of Computer and Control Engineering Harbin China State Grid Economic and Technological Research Institute Co. Ltd. Beijing China

ISBN: (纸本)9798350359558

Inherent control delays pose significant challenges to the stability of the Modular multilevel converter-based high voltage direct current (MMC-HVDC) system, inducing the risk of high-frequency resonances (HFR). This paper provides the virtual flux-based passivity enhancement schemes to remove the influence of the time delay terms. The negative damping risks can be eliminated, improving the system's stability and safety. The impedance modeling and simulation results validate the effectiveness of the approach. © 2024 IEEE.

关键词： System stability

来源：评论

学校读者我要写书评

暂无评论

Adaptive control for Spacecraft Proximity Operations Under Motion Constraints 22

Adaptive Control for Spacecraft Proximity Operations Under M...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Chen, Bin Li, Haoran Shao, Xiaodong Shi, Yongxia Hu, Qinglei Guo, Yabo The School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Beijing Institute of Control Engineering Beijing100094 China Nanyang Technological University Singapore639798 Singapore The 60th Research Institute of CRTC Nanjing210000 China

ISBN: (纸本)9798331527471

This paper addresses the issue of relative position tracking control for spacecraft rendezvous and proximity operations with a freely tumbling target, considering spatial motion constraints, including path and relative velocity limits, as well as mass uncertainty and external disturbances. To handle these challenges, a two-stage operation is proposed to ensure compliance with path constraints. In each stage, the constrained zones are parameterized using geometric features of the space, and corresponding artificial potential functions (APFs) are designed. Based on these APFs, an adaptive tracking controller is developed inside a backstepping control frame that allows the pursuer to reach terminal docking position while respecting the spatial motion constraints. Lyapunov stability analysis shows that the proposed control scheme ensures asymptotic convergence of tracking errors, provided that the APFs avoid local minima. Finally, numerical simulations are performed to validate the efficacy of the proposed control scheme. © 2024 IEEE.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multihead Attention for Enhancing Neural Machine Translation Performance 5th

Dynamic Multihead Attention for Enhancing Neural Machine Tra...

引用

5th International Conference on Trends in Computational and Cognitive engineering, TCCE 2023

作者： Pandey, Mrinal Pandey, Rashmikiran Nazarov, Alexey Department of Radio Engineering and Cybernetics Moscow Institute of Physics and Technology Moscow Russia Federal Research Center Computer Science and Control Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9789819719228

The research paper delves into the realm of "Attention-Based Neural Machine Translation for Multilingual Communication", focusing on the revolutionary impact of attention mechanisms in enhancing cross-language understanding. Through dynamic allocation of focus to pertinent segments of source sequences, attention mechanisms have significantly improved the precision and coherence of translations, playing a pivotal role in multilingual communication. The paper underscores the importance of this technology in addressing the complexities of aligning words across diverse languages and maintaining grammatical accuracy, crucial for effective cross-lingual interactions. The study also presents a visual flowchart outlining the core components of attention-based NMT, encompassing the encoder, decoder, and attention context. Moreover, the paper extrapolates the future trajectory of attention-based NMT, identifying areas for continued exploration and innovation. researchers are urged to refine attention models to cater to intricate linguistic structures, potentially unveiling novel mechanisms that strike a balance between capturing long-range dependencies and computational efficiency. Furthermore, the paper anticipates the integration of attention-based NMT with multimodal inputs, unlocking the potential for comprehensive communication by incorporating visual and auditory cues. These advancements hold the promise of revolutionising multilingual communication, shaping a future where language barriers are transcended in various domains, from global diplomacy to education and beyond. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Robust Divergence Learning for Missing-Modality Segmentation

Robust Divergence Learning for Missing-Modality Segmentation

引用

2024 China automation Congress, CAC 2024

作者： Cheng, Runze Sun, Zhongao Zhang, Ye Li, Chun MSU-BIT-SMBU Joint Research Center of Applied Mathematics Shenzhen MSU-BIT University Shenzhen518172 China Institute of Control Theory and Control Engineering School of Automation Beijing Institute of Technology Beijing100081 China School of Mathematics and Statistics Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9798350368604

Multimodal Magnetic Resonance Imaging (MRI) provides essential complementary information for analyzing brain tumor subregions. While methods using four common MRI modalities for automatic segmentation have shown success, they often face challenges with missing modalities due to image quality issues, inconsistent protocols, allergic reactions, or cost factors. Thus, developing a segmentation paradigm that handles missing modalities is clinically valuable. A novel single-modality parallel processing network framework based on Hölder divergence and mutual information is introduced. Each modality is independently input into a shared network backbone for parallel processing, preserving unique information. Additionally, a dynamic sharing framework is introduced that adjusts network parameters based on modality availability. A Hölder divergence and mutual information-based loss functions are used for evaluating discrepancies between predictions and labels. Extensive testing on the BraTS 2018 and BraTS 2020 datasets demonstrates that our method outperforms existing techniques in handling missing modalities and validates each component’s effectiveness. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Advancing Network Anomaly Detection: Comparative Analysis of Machine Learning Models

Advancing Network Anomaly Detection: Comparative Analysis of...

引用

International Conference on. Cryptology and Network Security with Machine Learning, ICCNSML 2023

作者： Pandey, Rashmikiran Pandey, Mrinal Nazarov, Alexey Department of Radio Engineering and Cybernetics Moscow Institute of Physics and Technology Moscow Russia Federal Research Center Computer Science and Control Russian Academy of Science Moscow Russia

ISBN: (纸本)9789819706402

In the rapidly evolving realm of cyber-security, the detection of network anomalies serves as a pivotal line of defense against a myriad of malicious activities and cyberthreats. This research undertakes the task of enhancing the accuracy and efficacy of network anomaly detection by employing a comparative analysis of various individual machine learning models. The study delves into the performance of distinct models, including Random Forest, Gradient Boosting, AdaBoost, neural networks, and SVM, meticulously scrutinizing their capabilities in detecting network anomalies. The crux of this study lies in its meticulous evaluation of each individual model on the revered NSL-KDD dataset—an established benchmark within the field of network intrusion detection. Through a systematic blend of rigorous mathematical frameworks, precise model implementations, and comprehensive experimental assessments, this research offers a deep understanding of the inner workings of each algorithm. The pivotal aspect of this study revolves around the comprehensive comparative analysis of these standalone models. Going beyond the mere quantifica-tion of accuracy, the exploration delves into aspects of precision, recall, F1-score, and more, shedding light on their diverse facets of performance. With achieved accuracies of 99.2419% for Random Forest, 99.5197% for Gradient Boosting, 86.6044% for AdaBoost, 84.00% for neural networks, and 87.00% for SVM, this research underlines the distinctive attributes and potential of each model in the context of network anomaly detection. As the study unravels the distinct strengths and limitations of each model, it contributes to the broader landscape of cyber-security by providing insights into the efficacy of individual machine learning approaches. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Spatial information considered convolutional neural network for electroencephalogram-based motor imagery classification 3

Spatial information considered convolutional neural network ...

引用

3rd International Conference on Applied Mathematics, Modelling, and Intelligent Computing, CAMMIC 2023

作者： Shi, Hongbing Zhang, Jinhui Pei, Zhongcai School of Automation Science and Electrical Engineering Beihang University Beijing China North Information Control Research Institute Group Co. Ltd. China

ISBN: (数字)9781510667617

ISBN: (纸本)9781510667600

As brain-computer interface (BCI) technology continues to advance in various fields, it has become one of the possible solutions for patients with motor dysfunction who have healthy thinking ability to regain motor ability. The vigorous development of deep learning (DL) provides it with a possible tool to analyze electroencephalogram (EEG) signals. Through analyzing and categorizing EEG signals associated with motor imagery (MI), the system can effectively perceive the patient's motor intentions. Currently, Convolutional Neural Networks (CNN) have exhibited exceptional performance in a variety of fields, including computer vision (CV) and natural language processing (NLP). However, the brain structure has rich spatial information, which was not fully utilized by CNN for MI-EEG signal analysis in the past. This paper introduces SP-CNN, a convolutional neural network that incorporates spatial information from the brain, to address the classification challenge of MI-EEG signals. The experimental findings indicate that this method exhibits stable and robust performance across diverse subjects. © 2023 SPIE.

关键词： Electroencephalography

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：