检索结果-内蒙古大学图书馆

A novel dwelling time design method for low probability of intercept in a complex radar network

International Journal of Design and Nature and Ecodynamics 2015年第4期10卷 310-319页

作者： Zhang, Z. Zhu, J. Salous, S. Science and Technology on Electronic Information Control Laboratory China College of Electronic Information JiangSu University of Science and Technology China School of Engineering and Computing Sciences Durham University United Kingdom

To achieve the important tactical requirement of low probability of intercept (LPI) in the complex radar network, dynamically controlling the emission of the radars is very necessary. A novel radar dwelling time control strategy based on an interacting multiple model algorithm is presented in this paper, which controls the dwelling time of radar according to predicted covariance matrix during tracking, taking advantage of the relation model between the dwelling time and the tracking performance. First, the complex radar network is built for target tracking. Secondly, the influence of the dwelling time is considered in the tracking performance of the complex radar network. Finally, a decision will be made after the dwelling time for every radar is obtained by particle swarm optimization, the radar with the smallest dwelling time will be selected to track target. The tracking accuracy and LPI performance are demonstrated in the Monte Carlo simulations. The results are validated through the comparison with other methods. © 2015 WIT Press.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Exploiting Machine Learning and LSTM for Human Activity Recognition: Using Physiological and Biological Sensor Data from Actigraph 25

Exploiting Machine Learning and LSTM for Human Activity Reco...

引用

25th IEEE International Conference on Industrial Technology, ICIT 2024

作者： Oyeleye, Matthew Chen, Tianhua Su, Pan Antoniou, Grigoris School Of Computing And Engineering University Of Huddersfield Department Of Computer Science United Kingdom School Of Control And Computer Engineering North China Electric Power University China

ISBN: (纸本)9798350340266

Human activity recognition involves identifying the daily living activities of an individual through the utilization of sensor attributes and intelligent learning algorithms. The identification of intricate human activities proves to be a labo-rious task, given the inherent difficulty of capturing long-term dependencies and extracting efficient features from unprocessed sensor data. For this purpose, this study aims at recognizing and classifying human activities using physiological and biological sensor data generated by Actigraph, as they can accurately measure moderate-to-vigorous intensity physical which is mostly affected by body composition and also better suited for self-monitoring. We examined the effectiveness of these features by applying prevalent machine learning classifiers and long short-term memory (LSTM) networks on recently publicly available data, which includes accelerometer and heart rate recordings. The results from our experiments showed that LSTM models performed better than conventional ML classifiers with the best result achieving an accuracy of 86.5%. The findings also confirms the significance of the heart rate in accurately classifying and identification of human activity more. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

The windowing effect in cerebral pattern classification: An application to brain computer interface technology

The windowing effect in cerebral pattern classification: An ...

引用

4th IASTED International Conference on Biomedical engineering

作者： Pérez, José Luis Martínez Cruz, Antonio Barrientos Department of Automatic Control Electrical Engineering and Industrial Computing Industrial Engineering School Universidad Politécnica de Madrid Madrid Spain

ISBN: (纸本)0889865787

The Brain Computer Interface technology allows the communication between people and mechanical devices controlled by microprocessors [1] [8]. It translates the human mental activity into device commands. The kernel of this technology is an algorithm that takes samples, filters and classifies the electro-encephalographic signal [2] [3] [4] [5]. In this paper, different types of filtering windows are considered, the main objective is to determine the type of window with best results in the discrimination stage, when the user is thinking about different activities;as secondary result the most relevant features are extracted. With an earlier and better discrimination the classifier would be easier to implement, faster and more reliable[14].

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

V2I Based Environment Perception for Autonomous Vehicles at Intersections

引用

China Communications 2021年第7期18卷 1-12页

作者： Xuting Duan Hang Jiang Daxin Tian Tianyuan Zou Jianshan Zhou Yue Cao Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems&Safety ControlSchool of Transportation Science and EngineeringBeihang UniversityBeijing 100191China School of Cyber Science and Engineering Wuhan UniversityWuhan 430072China

In recent years,autonomous driving technology has made good progress,but the noncooperative intelligence of vehicle for autonomous driving still has many technical bottlenecks when facing urban road autonomous driving challenges.V2I(Vehicle-to-Infrastructure)communication is a potential solution to enable cooperative intelligence of vehicles and *** this paper,the RGB-PVRCNN,an environment perception framework,is proposed to improve the environmental awareness of autonomous vehicles at intersections by leveraging V2I communication *** framework integrates vision feature based on *** normal distributions transform(NDT)point cloud registration algorithm is deployed both on onboard and roadside to obtain the position of the autonomous vehicles and to build the local map objects detected by roadside multi-sensor system are sent back to autonomous vehicles to enhance the perception ability of autonomous vehicles for benefiting path planning and traffic efficiency at the *** field-testing results show that our method can effectively extend the environmental perception ability and range of autonomous vehicles at the intersection and outperform the PointPillar algorithm and the VoxelRCNN algorithm in detection accuracy.

关键词： V2I environmental perception autonomous vehicles 3D objects detection

来源：评论

学校读者我要写书评

暂无评论

System Identification Based on DNNs with Disturbance Observer and Application to Unmanned Aerial Vehicles

System Identification Based on DNNs with Disturbance Observe...

引用

第三十二届中国控制会议

作者： YI Yang ZHENG Weixing YANG Yi GUO Lei Institute of Automation Southeast University School of Computing Engineering and MathematicsUniversity of Western Sydney School of Reliability and Systems Engineering Beihang University Science and Technology on Aircraft Control Laboratory Beihang University

ISBN: (纸本)9781479900305

In this paper,dynamic neural networks(DNNs) are used as the on-line identifier for a class of nonlinear systems with unknown external disturbance and unknown multiple dead zone *** integrating the novel nonlinear disturbance observer with adaptive control algorithms,the parameter coupling problem between unknown dead zone and DNNs can be successfully solved and the multiple disturbances can also be rejected *** the observation error and the identification error can be proved to convergent to ***,by combining with the numerical result of an unmanned aerial vehicle(UAV) model,the effectiveness of theoretical algorithms can be fully verified.

关键词： System identification Dynamic neural networks Disturbance observer Dead zone disturbance Unmanned aerial vehicles

来源：评论

学校读者我要写书评

暂无评论

Generating Adversarial Patterns in Facial Recognition with Visual Camouflage

引用

Journal of Shanghai Jiaotong University (Science) 2024年 1-12页

作者： Bao, Qirui Mei, Haiyang Wei, Huilin Lü, Zheng Wang, Yuxin Yang, Xin Key Laboratory of Social Computing and Cognitive Intelligence of Ministry of Education School of Control Science and EngineeringSchool of Computer Science and Technology Dalian University of Technology Liaoning Dalian116024 China Systems Engineering Institute Academy of Military Sciences Beijing100141 China

Deep neural networks, especially face recognition models, have been shown to be vulnerable to adversarial examples. However, existing attack methods for face recognition systems either cannot attack black-box models, are not universal, have cumbersome deployment processes, or lack camouflage and are easily detected by the human eye. In this paper, we propose an adversarial pattern generation method for face recognition and achieve universal black-box attacks by pasting the pattern on the frame of goggles. To achieve visual camouflage, we use a generative adversarial network (GAN). The scale of the generative network of GAN is increased to balance the performance conflict between concealment and adversarial behavior, the perceptual loss function based on VGG19 is used to constrain the color style and enhance GAN’s learning ability, and the fine-grained meta-learning adversarial attack strategy is used to carry out black-box attacks. Sufficient visualization results demonstrate that compared with existing methods, the proposed method can generate samples with camouflage and adversarial characteristics. Meanwhile, extensive quantitative experiments show that the generated samples have a high attack success rate against black-box models. © 2023, Shanghai Jiao Tong University.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Non-Stop Double Buffering Mechanism for Dataflow Architecture

引用

Journal of Computer Science & Technology 2018年第1期33卷 145-157页

作者： Xu Tan Xiao-Wei Shen Xiao-Chun Ye Da Wang Dong-Rui Fan Lunkai Zhang Wen-Ming Li Zhi-Min Zhang Zhi-Min Tang State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing 100049 China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214125 China Department of Computer Science The University of Chicago Chicago IL 60637 U.S.A.

Double buffering is an effective mechanism to hide the latency of data transfers between on-chip and off-chip memory. However, in dataflow architecture, the swapping of two buffers during the execution of many tiles decreases the performance because of repetitive filling and draining of the dataflow accelerator. In this work, we propose a non-stop double buffering mechanism for dataflow architecture. The proposed non-stop mechanism assigns tiles to the processing element array without stopping the execution of processing elements through optimizing control logic in dataflow architecture. Moreover, we propose a work-flow program to cooperate with the non-stop double buffering mechanism. After optimizations both on control logic and on work-flow program, the filling and draining of the array needs to be done only once across the execution of all tiles belonging to the same dataflow graph. Experimental results show that the proposed double buffering mechanism for dataftow architecture achieves a 16.2% average efficiency improvement over that without the optimization.

关键词： non-stop double buffering dataflow architecture high-performance computing

来源：评论

学校读者我要写书评

暂无评论

Constraining multimodal distribution for domain adaptation in stereo matching

引用

Pattern Recognition 2025年 167卷

作者： Shen, Zhelun Li, Zhuo Wu, Chenming Rao, Zhibo Liu, Lina Dai, Yuchao Zhang, Liangjun Robotics and Autonomous Driving Lab Baidu Research Sunnyvale United States Institute of Computing Technology Chinese Academy of Science China School of Information Engineering Nanchang Hangkong University China Institute of Cyber-Systems and Control Zhejiang University China School of Electronics and Information Northwestern Polytechnical University China

Recently, learning-based stereo matching methods have achieved great improvement in public benchmarks, where soft argmin and smooth L1 loss play core contributions to its success. However, in unsupervised domain adaptation scenarios, we observe that these two operations often yield multimodal disparity probability distributions in target domains, resulting in degraded generalization. In this paper, we propose a novel approach, Constrain Multi-modal Distribution (CMD), to address this issue. Specifically, we introduce uncertainty-regularized minimization and anisotropic soft argmin to encourage the network to produce predominantly unimodal disparity distributions in the target domain, thereby improving prediction accuracy. Experimentally, we apply the proposed method to multiple representative stereo-matching networks and conduct domain adaptation from synthetic data to unlabeled real-world scenes. Results consistently demonstrate improved generalization in both top-performing and domain-adaptable stereo-matching models. The code for CMD will be available at: https://***/gallenszl/CMD. © 2025

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Towards a real-time reference architecture for autonomic systems

Towards a real-time reference architecture for autonomic sys...

引用

ICSE 2007 Workshops: International Workshop on Software engineering for Adaptive and Self-Managing Systems, SEAMS'07

作者： Solomon, Bogdan Ionescu, Dan Litoiu, Marin Mihaescu, Mircea Network Computing and Control Technologies Research Laboratory School of Information Technology and Engineering University of Ottawa IBM CAS Toronto

ISBN: (纸本)0769529739

Autonomic computing aims to embed automation in IT management software such that it can adapt to changes in the configuration, provisioning, protection, and resource utilization variations of the IT infrastructure at run time. It is, therefore, almost natural to consider this control software framework as being designed with control principles in mind. One of the research trends considers autonomic computing as a control system that resolves constraints related to the optimal usage of resources based on external requests made by users or processes in a reactive way. In this paper, a real-time reference architecture is introduced in which components implementing functions of real-time system elements or blocks such as transducers, controllers, and actuators are designed. The architecture of the autonomic computing software also contains components that implement functionalities specific to real-time systems. The transducers, controllers, and actuators are thus connected via real-time pattern components such as concurrency, priority, and reliability patterns. © 2007 IEEE.

关键词： Software architecture

来源：评论

学校读者我要写书评

暂无评论

Enhancing Collaborative and Geometric Multi-Kernel Learning Using Deep Neural Network

引用

Computers, Materials & Continua 2022年第9期72卷 5099-5116页

作者： Bareera Zafar Syed Abbas Zilqurnain Naqvi Muhammad Ahsan Allah Ditta Ummul Baneen Muhammad Adnan Khan Department of Mechatronics and Control Engineering University of Engineering and TechnologyLahore54890Pakistan Department of Information Sciences Division of Science and TechnologyUniversity of EducationLahore54000Pakistan Riphah School of Computing&Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan Department Software Gachon UniversitySeongnam13120Korea

This research proposes a method called enhanced collaborative andgeometric multi-kernel learning (E-CGMKL) that can enhance the CGMKLalgorithm which deals with multi-class classification problems with non-lineardata distributions. CGMKL combines multiple kernel learning with softmaxfunction using the framework of multi empirical kernel learning (MEKL) inwhich empirical kernel mapping (EKM) provides explicit feature constructionin the high dimensional kernel space. CGMKL ensures the consistent outputof samples across kernel spaces and minimizes the within-class distance tohighlight geometric features of multiple classes. However, the kernels constructed by CGMKL do not have any explicit relationship among them andtry to construct high dimensional feature representations independently fromeach other. This could be disadvantageous for learning on datasets with complex hidden structures. To overcome this limitation, E-CGMKL constructskernel spaces from hidden layers of trained deep neural networks (DNN).Due to the nature of the DNN architecture, these kernel spaces not onlyprovide multiple feature representations but also inherit the compositionalhierarchy of the hidden layers, which might be beneficial for enhancing thepredictive performance of the CGMKL algorithm on complex data withnatural hierarchical structures, for example, image data. Furthermore, ourproposed scheme handles image data by constructing kernel spaces from aconvolutional neural network (CNN). Considering the effectiveness of CNNarchitecture on image data, these kernel spaces provide a major advantageover the CGMKL algorithm which does not exploit the CNN architecture forconstructing kernel spaces from image data. Additionally, outputs of hiddenlayers directly provide features for kernel spaces and unlike CGMKL, do notrequire an approximate MEKL framework. E-CGMKL combines the consistency and geometry preserving aspects of CGMKL with the compositionalhierarchy of kernel spaces extracted from DNN hidde

关键词： CGMKL multi-class classification deep neural network multiplekernel learning hierarchical kernel spaces

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：