检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Ding, Zixiang Chen, Yaran Li, Nannan Zhao, Dongbin Chen, C.L. Philip State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China School of Computer Science & Engineering South China University of Technology Guangdong Guangzhou510006 China College of Navigation Dalian Maritime University Dalian116026 China

Different from other deep scalable architecture-based NAS approaches, Broad Neural Architecture Search (BNAS) proposes a broad scalable architecture which consists of convolution and enhancement blocks, dubbed Broad Convolutional Neural Network (BCNN), as the search space for amazing efficiency improvement. BCNN reuses the topologies of cells in the convolution block so that BNAS can employ few cells for efficient search. Moreover, multi-scale feature fusion and knowledge embedding are proposed to improve the performance of BCNN with shallow topology. However, BNAS suffers some drawbacks: 1) insufficient representation diversity for feature fusion and enhancement and 2) time consumption of knowledge embedding design by human experts. This paper proposes Stacked BNAS, whose search space is a developed broad scalable architecture named Stacked BCNN, with better performance than BNAS. On the one hand, Stacked BCNN treats mini BCNN as a basic block to preserve comprehensive representation and deliver powerful feature extraction ability. For multi-scale feature enhancement, each mini BCNN feeds the outputs of deep and broad cells to the enhancement cell. For multi-scale feature fusion, each mini BCNN feeds the outputs of deep, broad and enhancement cells to the output node. On the other hand, Knowledge Embedding Search (KES) is proposed to learn appropriate knowledge embeddings in a differentiable way. Moreover, the basic unit of KES is an over-parameterized knowledge embedding module that consists of all possible candidate knowledge embeddings. Experimental results show that 1) Stacked BNAS obtains better performance than BNAS-v2 on both CIFAR-10 and ImageNet, 2) the proposed KES algorithm contributes to reducing the parameters of the learned architecture with satisfactory performance, and 3) Stacked BNAS delivers a state-of-the-art efficiency of 0.02 GPU days. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An IoT Edge Computing system Architecture and its Application

An IoT Edge Computing System Architecture and its Applicatio...

引用

IEEE International Conference on Networking, Sensing and control

作者： Shichao Chen Qijie Li Hua Zhang Fenghua Zhu Gang Xiong Ying Tang Macau University of Science and Technology The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Macau China Beijing University of Technology The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Beijing Aerospace Smart Manufacturing Technology Development Co. Ltd Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The Engineering Research Center of Intelligent Systems and Technology Institute of Automation and Cloud Computing Center Chinese Academy of Sciences Beijing China Rowan University Glassboro NJ USA Institute of Smart Education Qingdao Academy of Intelligent Industries Qingdao China

ISBN: (数字)9781728168555

ISBN: (纸本)9781728168562

As the number of devices connected to the Internet of things (IoT) surges, the amount of data explodes. Therefore it not only increases the bandwidth load of data transmission but also aggravates the computing and storage load of a cloud platform. At the same time, the traditional computing paradigm centered on cloud computing cannot meet the real-time requirements in many application scenarios. The emergence of edge computing can solve the problems of realtime data processing and network bandwidth occupation in the current IoT scene. In this paper, according to the characteristics of IoT, such as fragmented data, heterogeneous network, and limited energy consumption, the architecture of an IoT edge computing system is constructed to suit better an IoT scene. In addition, the application of edge computing key technologies such as virtualization, edge intelligence, computing offload, collaborative scheduling and micro-services in resource-constrained IoT scenarios is analyzed in detail. Finally, the functions and application of energy consumption monitoring and optimization to a central air-conditioning system are analyzed and summarized, which is a typical application of edge computing in the context of the IoT.

关键词： Energy consumption Processor scheduling Computer architecture Internet of Things Optimization Monitoring Edge computing

来源：评论

学校读者我要写书评

暂无评论

Weakly Aligned Feature Fusion for Multi-modal Object Detection

arXiv

引用

arXiv 2022年

作者： Zhang, Lu Liu, Zhiyong Zhu, Xiangyu Song, Zhan Yang, Xu Lei, Zhen Qiao, Hong The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100086 China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China The Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China The Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong The Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China

To achieve accurate and robust object detection in the real-world scenario, various forms of images are incorporated, such as color, thermal, depth, etc. However, multi-modal data often suffer from the position shift problem, i.e. the image pair is not strictly aligned, making one object has different positions in different modalities. For the deep learning method, this problem makes it difficult to fuse multi-modal features and puzzles the CNN training. In this paper, we propose a general multi-modal detector named Aligned Region CNN (AR-CNN) to tackle the position shift problem. Firstly, a region feature alignment module with adjacent similarity constraint is designed to consistently predict the position shift between two modalities and adaptively align the cross-modal region features. Secondly, we propose a novel RoI jitter strategy to improve the robustness to unexpected shift patterns. Thirdly, we present a new multi-modal feature fusion method, which selects the more reliable feature and suppresses the less useful one via feature re-weighting. Additionally, by locating bounding boxes in both modalities and building their relationships, we provide novel multi-modal labelling named KAIST-Paired. Extensive experiments on 2D and 3D object detection, RGB-T and RGB-D datasets demonstrate the effectiveness and robustness of our method. Copyright © 2022, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Road acceleration spectrum replication on Stewart platform with Three Variable controller

Road acceleration spectrum replication on Stewart platform w...

引用

第三十八届中国控制会议

作者： Hu Xiaoyu Wang Shoukun State Key Laboratory of Intelligent Control and Decision of Complex System School of Automation Beijing Institute of Technology

Comparing to the commonly used hydraulic three-axial shaking tables, multi-degree of freedom shaking systems implemented by Stewart platform have the merits of being portable, easy to install and with high load capacity, but are not well studied because of the inherent nonlinearity and strong coupling of Stewart platform. In order to replicate multi-degree of freedom road acceleration spectrum on Stewart platform, analysis of the system was carried out. Firstly, the system structure was introduced and the linearized platform kinematic equations, at the equilibrium position, were inducted. The models of actuators that drive the platform were simplified and the principles of three variable controller(TVC) were deduced briefly. Finally, MATLAB-Adams co-simulation environment was built to perform multi-degree of freedom road acceleration spectrum replication with TVC. The results show that it can reproduce high accuracy multi-degree of freedom road acceleration spectrum with TVC on Stewart platform.

关键词： Shaking table Stewart platform three variable controller

来源：评论

学校读者我要写书评

暂无评论

A Heuristic Algorithm for Solving Resource Constrained Project Scheduling Problem with Transfer Time under Resource Bundle

A Heuristic Algorithm for Solving Resource Constrained Proje...

引用

第三十八届中国控制会议

作者： Junqi Cai Zhihong Peng School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex System

In this paper we investigate an extension of Resource Constrained Projected Scheduling Problem(RCPSP): the Resource Constrained Project Scheduling Problem with Transfer Time under Resource Bundle. For this complex problem, the use of a parallel scheduling scheme is proposed. Such scheme has been successfully applied to the RCPSP. Introducing transfer time and resource bundle into RCPSP causes two problems, one is the possibility of resources significantly exceed the need of a task, the other is cooperation among unfamiliar members from different team may increase the makespan of the project. In order to deal with the problem, two new concepts are developed: task-related resource weight and collaboration coefficient. Some discussion of such concepts is given of and use them for new heuristic framework we proposed. A computational test is performed and the results show that the new heuristic is very effective in finding better solutions within a very short time.

关键词： RCPSP heuristic algorithm resource bundle transfer time

来源：评论

学校读者我要写书评

暂无评论

Retraction Note: IoT-based 3D convolution for video salient object detection

引用

Neural Computing and Applications 2024年第23期36卷 14621-14621页

作者： Dong, Shizhou Gao, Zhifan Pirbhulal, Sandeep Bian, Gui-Bin Zhang, Heye Wu, Wanqing Li, Shuo Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen Shenzhen China Western University London Canada State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Sun Yat-Sen University Guangzhou China

来源：评论

学校读者我要写书评

暂无评论

Distributed Formation of Autonomous Underwater Vehicles with Unreliable Switching Topologies and Transmission Delays

Distributed Formation of Autonomous Underwater Vehicles with...

引用

第三十九届中国控制会议

作者： Chao Ma Wei Wu Yidao Ji Hang Fu School of Mechanical Engineering University of Science and Technology Beijing State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Automation and Electrical Engineering University of Science and Technology Beijing

This paper investigates the formation problem of autonomous underwater vehicles with unreliable switching communication topologies and time-varying transmission delays. More precisely, the switching topologies contains achievable and unachievable sub-topologies, which can better describe the practical underwater communication environment. By performing model transformation and constructing appropriate multiple Lyapunov-function method, sufficient conditions are established based on admissible edge-dependent average dwell time, such that the desired formation configuration can be achieved with transmission delays. Finally, an illustrative example is given at last to verify the effectiveness of the main results.

关键词： Distributed formation Autonomous underwater vehicles Switching topologies Admissible edge-dependent switching

来源：评论

学校读者我要写书评

暂无评论

Dynamic horizon value estimation for model-based reinforcement learning

arXiv

引用

arXiv 2020年

作者： Wang, Junjie Zhang, Qichao Zhao, Dongbin Zhao, Mengchen Hao, Jianye State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Huawei Noah’s Ark Lab Beijing China

Existing model-based value expansion methods typically leverage a world model for value estimation with a fixed rollout horizon to assist policy learning. However, the fixed rollout with an inaccurate model has a potential to harm the learning process. In this paper, we investigate the idea of using the model knowledge for value expansion adaptively. We propose a novel method called Dynamic-horizon Model-based Value Expansion (DMVE) to adjust the world model usage with different rollout horizons. Inspired by reconstruction-based techniques that can be applied for visual data novelty detection, we utilize a world model with a reconstruction module for image feature extraction, in order to acquire more precise value estimation. The raw and the reconstructed images are both used to determine the appropriate horizon for adaptive value expansion. On several benchmark visual control tasks, experimental results show that DMVE outperforms all baselines in sample efficiency and final performance, indicating that DMVE can achieve more effective and accurate value estimation than state-of-the-art model-based methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Acupoint Detection Based on Deep Convolutional Neural Network

Acupoint Detection Based on Deep Convolutional Neural Networ...

引用

第三十九届中国控制会议

作者： Lingyao Sun Shiying Sun Yuanbo Fu Xiaoguang Zhao State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences University of Chinese Academy of Sciences school of Artificial Intelligence The Department of Acupuncture and Moxibustion Beijing Hospital of Traditional Chinese MedicineCapital Medical UniversityBeijing Key Laboratory of Acupuncture Neuromodulation

As an important component of Traditional Chinese Medicine(TCM),science of acupoint therapy has achieved significant results in clinical practice,but recognizing and positioning acupoints is heavily depends on the skills of *** recent years,researchers have proposed a few methods of automatic acupoints detection and positioning,but most of the methods are still based on manual designed *** this paper,we propose an acupoints detection method based on deep convolutional neural network,and an evaluation method is proposed for acupoint ***'s more,we build an acupoint detection *** are performed and a promising result is achieved.

关键词： convolutional neural network deep learning acupoint detection convolutional pose machine

来源：评论

学校读者我要写书评

暂无评论

Decadal climate variability during the pre-industrial Common Era: characteristics and mechanisms

引用

Science Bulletin 2025年

作者： Ning, Liang Liu, Zhengyu Mann, Michael E. Liu, Jian Yan, Mi Sun, Weiyi Chen, Kefan Qin, Yanmin Wen, Qin State Key Laboratory of Climate System Prediction and Risk Management Nanjing210023 China Key Laboratory for Virtual Geographic Environment Ministry of Education Nanjing210023 China State Key Laboratory Cultivation Base of Geographical Environment Evolution and Regional Response of Jiangsu Province Nanjing210023 China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing210023 China School of Geography Nanjing Normal University Nanjing210023 China Department of Geography The Ohio State University ColumbusOH43210 United States Department of Earth and Environmental Science Annenberg School for Communication University of Pennsylvania PhiladelphiaPA19104 United States Jiangsu Provincial Key Laboratory for Numerical Simulation of Large Scale Complex Systems School of Mathematical Science Nanjing Normal University Nanjing210023 China

In this article, we present a comprehensive review of decadal to multi-decadal climate variability during the Common Era (CE), focusing on their characteristics and mechanisms. We begin by summarizing recent advances in proxy reconstructions that reveal the paleo-evidence of decadal to multi-decadal climate variability during the CE. Decadal to multi-decadal variability has been observed in extensive sets of proxy records in the CE. Despite improvements in proxy records in the type, temporal resolution, and temporal coverage, there remains a lack of clear consistency in the preferred time scales and phases of the variability among different records. The agreements of decadal characteristics between proxy records and model simulations are higher during the periods with strong external forcings, but lower during periods of weak external forcing. We subsequently describe the recent modeling studies on the influences of external forcings and internal variability on decadal to multi-decadal climate variability with associated physical mechanisms, and some emerging research topics. Despite the improved understanding of climate variability and regional climate changes, especially over the eastern Asia summer monsoon region, several inconsistencies still exist, such as the amplitudes of responses to external forcings and relative contributions from external forcings and internal variability. The review ends with perspectives for future directions to reconcile discrepancies of decadal climate variability, such as applications of paleoclimate data assimilation and isotope-enabled transient climate modeling, and implications for projecting future decadal to multi-decadal climate changes and for improving the accuracy of decadal predictions. © 2025 Science China Press

关键词： Global warming

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：