检索结果-内蒙古大学图书馆

OCEANS

作者： Xueli Sheng Chunyan Sun Qing Ling Jia Lu Jingwei Yin Longxiang Guo Science and Technology on Underwater Acoustic Laboratory Harbin Engineering University College of Underwater Acoustic Engineering Harbin Engineering University Science and Technology on Complex Ship Systems Simulation Laboratory Beijing China

ISBN: (纸本)9781479913084

The passive target tracking problem of multi-sonar belongs to nonlinear problem, and the background noise is not guass noise entirely, so a kind of filtering method which suit for nonlinear and non-guassian system of is needed. In this paper, the interacting multiple model particle filter which combined by particle filter and interacting multiple model is applied in tracking maneuvering target. Combing the particle filter's ability of disposing nonlinear and non-guass problem and the IMM's ability of tracking target's arbitrary maneuvering, the difficulty that traditional filter encounters in tracking maneuvering target under the circumstance of nonlinear and non-guassian can be solved. The interacting multiple model particle filter is simulated in two different model set, the results indicate that, under the case of model matching, this method has good ability in tracking the maneuvering target of nonlinear and non-guassian system.

关键词： Mathematical model Particle filters Target tracking Equations Noise Radar tracking Filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

Influences of driving distraction on professional and non-professional drivers under different traffic conditions

Boletin Tecnico/Technical Bulletin

引用

Boletin Tecnico/Technical Bulletin 2017年第17期55卷 866-875页

作者： Zhang, Hui Qian, Da-Lin Shao, Chun-Fu Zhu, Nuo Key Laboratory for Urban Transportation Complex Systems Theory and Technology Beijing Jiaotong University Beijing100044 China China Academy of Civil Aviation Science and Technology Beijing100028 China

Driver distraction has become one of leading causes of motor-vehicle crashes. Although kinds of driver distraction affection have been studied extensively, little research effort has addressed the different influences on the traffic conditions and driver's profession. To fill this gap, this study aimed to investigate the manner and extent to which driver distraction and driver's proficiency affected driving performance in two traffic conditions. Fifty-three licensed drivers drove the simulator with performed three secondary tasks (baseline, hands-free phone conversation and speech-based texting) in the low-flow scenario and high-flow scenario, respectively. Repeated measure mixed ANOVA was used to analysis the influence of three distraction and two traffic conditions on drivers' vehicle control performance. The results showed that speech-based texting has greater influences than hands-free phone conversation in low-flow condition. Both of secondary tasks can severely undermine drivers' performance in h igh-flow condition. Professional drivers distracted by secondary tasks had a better driving performance than non-professional, such as keep longer headway distance and better lane-keep ing performance. These findings shed some light on the further development of driver d istraction detection technologies and the targeted intervention strategies about driver distraction while driving, especially professional drivers.

关键词： Analysis of variance (ANOVA)

来源：评论

学校读者我要写书评

暂无评论

"Why not looking backward?" a robust two-step method to automatically terminate Bayesian optimization 23

"Why not looking backward?" a robust two-step method to auto...

引用

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Shuang Li Ke Li Wei Li Control and Simulation Center Harbin Institute of Technology China and National Key Laboratory of Modeling and Simulation for Complex Systems China Department of Computer Science University of Exeter Exeter UK

Bayesian Optimization (BO) is a powerful method for tackling expensive blackbox optimization problems. As a sequential model-based optimization strategy, BO iteratively explores promising solutions until a predetermined budget, either iterations or time, is exhausted. The decision on when to terminate BO significantly influences both the quality of solutions and its computational efficiency. In this paper, we propose a simple, yet theoretically grounded, two-step method for automatically terminating BO. Our core concept is to proactively identify if the search is within a convex region by examining previously observed samples. BO is halted once the local regret within this convex region falls below a predetermined threshold. To enhance numerical stability, we propose an approximation method for calculating the termination indicator by solving a bilevel optimization problem. We conduct extensive empirical studies on diverse benchmark problems, including synthetic functions, reinforcement learning, and hyperparameter optimization. Experimental results demonstrate that our proposed method saves up to ≈ 80% computational budget yet is with an order of magnitude smaller performance degradation, comparing against the other peer methods. In addition, our proposed termination method is robust in terms of the setting of its termination criterion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural architecture search for fault diagnosis

arXiv

引用

arXiv 2020年

作者： Li, Xudong Hu, Yang Zheng, Jianhua Li, Mingtao National Space Science Center. CAS University of Chinese Academy of Sciences Beijing China Science and Technology on Complex Aviation System Simulation Laboratory 9236 mailbox Beijing China

Data-driven methods has made great progress in fault diagnosis, especially deep learning method. Deep learning is suitable for processing big data, and has a strong feature extraction ability to realize end-to-end fault diagnosis systems. Due to the complexity and variability of experimental data, some deep learning models are designed to be complex. However, designing neural network architecture requires rich professional knowledge and debugging experience, and a lot of experiments are needed to screen models and hyperparameters, increasing the difficulty of developing deep learning models. Fortunately, neural architecture search (NAS) is developing rapidly, and is becoming one of the next directions for deep learning. Given a search space, NAS can automatically search for the optimal network architecture. In this paper, we proposed a NAS method for fault diagnosis using reinforcement learning. A recurrent neural network is used as an agent to generate the network architecture. The accuracy of the generated network on the validation dataset is fed back to the agent as a reward, and the parameters of the agent are updated through the strategy gradient algorithm. In order to speed up the search process, parameters sharing method is adopted in this paper. We use PHM 2009 Data Challeng gearbox dataset to prove the effectiveness of propsed method, and obtain state-of-the-art results compared with other artificial designed network structures. To authors best knowledge, its the first time that NAS has been applied in fault diagnosis. Copyright © 2020, The Authors. All rights reserved.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

The research on the coverage area of multistatic sonar under various work modes

The research on the coverage area of multistatic sonar under...

引用

OCEANS

作者： Jia Lu Xueli Sheng Qing Ling Jiang Xu Yanyi Yuan College of Underwater Acoustic Engineering Harbin Engineering University Harbin China Science and Technology on Complex Ship Systems Simulation Laboratory Beijing China

Absorption loss which is an important characteristic in the field of underwater acoustic, caused by sea water is often neglected in the research on the coverage area of bistatic sonar, in this article, the coverage area of bistatic sonar considering absorption loss is studied. When multistatic sonar works in different modes, detection criterion varies, so the coverage area can't be considered as the direct sum of coverage area of each bistatic sonar unit. This article discussed the coverage area respect to the most relaxed criterion and the most strict criterion.

关键词： Propagation losses Absorption Sonar detection Receivers Underwater acoustics

来源：评论

学校读者我要写书评

暂无评论

DeepDir: a deep learning approach for API directive detection

引用

science China(Information sciences) 2021年第9期64卷 238-240页

作者： Jingxuan ZHANG He JIANG Shuai LU Ge LI Xin CHEN College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics State Key Laboratory for Novel Software Technology Nanjing University Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education School of Software Dalian University of Technology School of Electronic Engineering and Computer Science Peking University School of Computer Science and Technology Hangzhou Dianzi University

Dear editor,Software developers tend to reuse existing libraries to facilitate their development process and implement certain functionalities by invoking application programming interfaces(APIs) [1]. However, it remains a challenging task for developers to correctly use APIs [2], so they often consult API learning resources [3, 4]. As one of the most important API learning resources,

关键词： Information systems and Communication Service

来源：评论

学校读者我要写书评

暂无评论

An Anomaly Detection Method Based on Adaptive Log and Dual Feature Fusion Analysis for Distributed systems

An Anomaly Detection Method Based on Adaptive Log and Dual F...

引用

Information systems and Computing technology (ISCTech), International Conference on

作者： Yijiang Jia Kefei Li Ping Lu Baodi Xie Huayang Wang Jincai Chen School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan China National Key Laboratory of Modeling and Simulation for Complex Systems Beijing China

In this study, we present a middleware-based approach for detecting anomalies in distributed systems. Our method facilitates the dynamic collection of logs at various levels of detail and incorporates an a priori dictionary-based compression strategy to process and transmit logs, minimizing the performance impact on distributed systems. Additionally, we utilize a dual feature fusion technique to analyze the logs. We evaluate the effectiveness of our approach by performing anomaly detection in a publish/subscribe distributed system and comparing it with existing methods. The results illustrate that our method outperforms other approaches, demonstrating superior performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hazard-evaluation-oriented Moving Horizon Parallel Steering Control for Driver-Automation Collaboration During Automated Driving

引用

IEEE/CAA Journal of Automatica Sinica 2018年第6期5卷 1062-1073页

作者： Hongyan Guo Linhuan Song Jun Liu Fei-Yue Wang Dongpu Cao Hong Chen Chen Lv Partick Chi-Kwong Luk State Key Laboratory of Automotive Simulation and Control and the Department of Con-trol Science and Engineering Jilin University(Campus Nanling)Changchun130025China State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense TechnologyChangsha 410073China Mechanical and Mechatronics Engineering Department at the University ot Waterloo 200 University Avenue West WaterlooONNZL3G1Canada Department of Automotive Engineering Cranfield UniversityBedfordshire MK43 0ALUK School of Water Energy and EnvironmentCranfield UniversityBedfordshire MK43 0ALUK

Prompted by emerging developments in connected and automated vehicles, parallel steering control, one aspect of parallel driving, has become highly important for intelligent vehicles for easing the burden and ensuring the safety of human drivers. This paper presents a parallel steering control framework for an intelligent vehicle using moving horizon *** framework considers lateral stability, collision avoidance and actuator saturation and describes them as constraints, which can blend the operation of a human driver and a parallel steering controller effectively. Moreover, the road hazard and the steering operation error are employed to evaluate the operational hazardous of an intelligent vehicle. Under the hazard evaluation,the intelligent vehicle will be mainly operated by the human driver when the vehicle operates in a safe and stable *** automated steering driving objective will play an active role and regulate the steering operations of the intelligent vehicle based on the hazard evaluation. To verify the effectiveness of the proposed hazard-evaluation-oriented moving horizon parallel steering control approach, various validations are conducted, and the results are compared with a parallel steering scheme that does not consider automated driving situations. The results illustrate that the proposed parallel steering controller achieves acceptable performance under both conventional conditions and hazardous conditions.

关键词： Hazard evaluation intelligent vehicle atera stability moving horizon optimization paralle steering control

来源：评论

学校读者我要写书评

暂无评论

GPIO Based Iterative Learning Control for Manipulators with Time-Varying Disturbances 42

GPIO Based Iterative Learning Control for Manipulators with ...

引用

42nd Chinese Control Conference, CCC 2023

作者： Lu, Huangyuwei Wang, Zuo Sun, Jiankun Xiao, Xi Li, Shihua School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Shenzhen Research Institute Southeast University Shenzhen518063 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Aviation Key Laboratory of Science and Technology on Aero Electromechanical System Integration Nanjing211106 China

ISBN: (纸本)9789887581543

To improve the disturbance rejection ability and repetitive tracking accuracy of manipulators, a composite iterative learning control (ILC) scheme via generalized proportional integral observer (GPIO) is proposed. A high-order polynomial is first employed to model the time-varying disturbances that include unmodeled dynamics, parameter uncertainties and load fluctuations. A GPIO is then designed to estimate the disturbances and high-order time derivatives. By introducing estimations into a PD-type ILC at each iteration, a composite control scheme is obtained, such that the undesirable influence of time-varying disturbances can be effectively attenuated in the repetitive tracking process of manipulators. In this paper, the rigorous stability analysis of the closed-loop system is presented to guarantee that the tracking error exponentially converges to zero as the iteration number tends to infinity. The effectiveness of the proposed control scheme is finally verified by simulation results. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Prompting Large Language Models with Answer Heuristics for Knowledge-Based Visual Question Answering

Prompting Large Language Models with Answer Heuristics for K...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhenwei Shao Zhou Yu Meng Wang Jun Yu Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University China School of Computer Science and Information Engineering Hefei University of Technology China

Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question. Early studies retrieve required knowledge from explicit knowledge bases (KBs), which often introduces irrelevant information to the question, hence restricting the performance of their models. Recent works have sought to use a large language model (i.e., GPT-3 [3]) as an implicit knowledge engine to acquire the necessary knowledge for answering. Despite the encouraging results achieved by these methods, we argue that they have not fully activated the capacity of GPT-3 as the provided input information is insufficient. In this paper, we present Prophet-a conceptually simple framework designed to $prompt$ GPT-3 with answer heuristics for knowledge-based VQA. Specifically, we first train a vanilla VQA model on a specific knowledge-based VQA dataset without external knowledge. After that, we extract two types of complementary answer heuristics from the model: answer candidates and answer-aware examples. Finally, the two types of answer heuristics are encoded into the prompts to enable GPT-3 to better comprehend the task thus enhancing its capacity. Prophet significantly outperforms all existing state-of-the-art methods on two challenging knowledge-based VQA datasets, OK-VQA and A-OKVQA, delivering 61.1% and 55.7% accuracies on their testing sets, respectively.

关键词：

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：