检索结果-内蒙古大学图书馆

ModuleNet: Knowledge-Inherited Neural Architecture Search

IEEE TRANSACTIONS ON CYBERNETICS 2022年第11期52卷 11661-11671页

作者： Chen, Yaran Gao, Ruiyuan Liu, Fenggang Zhao, Dongbin Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Coll Artificial Intelligence Beijing 100049 Peoples R China Chinese Univ Hong Kong Dept Comp Sci & Engn Hong Kong Peoples R China Beijing Inst Technol Coll Automat Beijing 100811 Peoples R China

Although neural the architecture search (NAS) can bring improvement to deep models, it always neglects precious knowledge of existing models. The computation and time costing property in NAS also means that we should not start from scratch to search, but make every attempt to reuse the existing knowledge. In this article, we discuss what kind of knowledge in a model can and should be used for a new architecture design. Then, we propose a new NAS algorithm, namely, ModuleNet, which can fully inherit knowledge from the existing convolutional neural networks. To make full use of the existing models, we decompose existing models into different modules, which also keep their weights, consisting of a knowledge base. Then, we sample and search for a new architecture according to the knowledge base. Unlike previous search algorithms, and benefiting from inherited knowledge, our method is able to directly search for architectures in the macrospace by the NSGA-II algorithm without tuning parameters in these modules. Experiments show that our strategy can efficiently evaluate the performance of a new architecture even without tuning weights in convolutional layers. With the help of knowledge we inherited, our search results can always achieve better performance on various datasets (CIFAR10, CIFAR100, and ImageNet) over original architectures.

关键词： Computer architecture Task analysis Knowledge based systems Microprocessors Statistics Sociology Computational modeling Evaluation algorithm knowledge inherited neural architecture search (NAS)

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Experience Graph with Denoising Autoencoder for Zero-Shot Learning in Visual Cognitive Development 27th

Knowledge-Experience Graph with Denoising Autoencoder for Ze...

引用

27th International Conference on Neural Information Processing

作者： Zhang, Xinyue Yang, Xu Liu, Zhiyong Zhang, Lu Ren, Dongchun Fan, Mingyu Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Meituan Dianping Grp Beijing 100190 Peoples R China

ISBN: (纸本)9783030638221;9783030638238

Visual cognitive development is vital for intelligent robots to handle various types of visual tasks rather than predefined ones. It can transfer the classification ability from an original model to a novel task. However, the high reliance on large amounts of data hinders its development. The energy it costs to adjust to the novel tasks is also a tough problem. Thus we propose a model called knowledge-experience graph (KEG) to imitate the mechanisms of human brains. With the help of social knowledge stored in the knowledge graph, the novel classes can be easily added. The combination of the experience via denoising autoencoder (DAE) also takes the relationship in the visual space into account. With the propagation of information among the graph by graph convolutional network (GCN), KEG generates the classifier of the novel tasks effectively. Experiments show that KEG improves the classification accuracy of novel categories on zero-shot learning and accomplishes visual cognitive development to a certain extent.

关键词： GCN Zero-shot learning Cross-task learning Cognitive development Image classification Denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Efficient Parallel Branch Network With Multi-Scale Feature Fusion for Real-Time Overhead Power Line Segmentation

引用

IEEE SENSORS JOURNAL 2021年第10期21卷 12220-12227页

作者： Gao, Zishu Yang, Guodong Li, En Liang, Zize Guo, Rui Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China State Grid Shandong Elect Power Co Jinan 250001 Peoples R China

Image-based segmentation of overhead power lines is critical for power line inspection. Real-time segmentation helps the inspection robot avoid obstacles or land on the wire during the inspection task. It is challenging for several studies to achieve real-time overhead power line segmentation with high accuracy. In addition, cluttered background brings great difficulties to overhead power lines segmentation. To address these issues, an efficient parallel branch network for real-time overhead power line segmentation is proposed. Our framework combines a context branch that generates useful global information with a spatial branch that preserves high-resolution segmentation details. The asymmetric factorized depth-wise bottleneck (AFDB) module is designed in the context branch to achieve more efficient short-range feature extraction and provide a large receptive field. Furthermore, the subnetwork-level skip connections in the classifier are proposed to fuse long-range features and lead to high accuracy. Experiments demonstrate that our framework achieves more than 90% segmentation accuracy.

关键词： Convolution Feature extraction Image segmentation Inspection Wires Sensors Real-time systems Real-time segmentation lightweight network dilated depth-wise convolution power line inspection

来源：评论

学校读者我要写书评

暂无评论

Environmental monitoring system based on hybrid mode network structure

Environmental monitoring system based on hybrid mode network...

引用

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Li, Zhishuo Yang, Guodong Li, En Liang, Zize Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems 95 Zhongguancun East Road Beijing100190 China Yuquan Road Beijing100049 China

ISBN: (纸本)9781665436786

To achieve large-scale and high bandwidth environmental monitoring, this paper proposes a hybrid network structure based on the ZigBee network and Mesh network, which consists of the backbone network and nodes, branch network and nodes, and monitoring center. Both the backbone network node and branch network node with sensor information collection and wireless communication functions are designed. And a monitoring center is developed to display environmental information in real time. With the hybrid-mode network, the environment monitoring experiments were carried out to verify the feasibility of the system. The results show that compared to traditional environmental monitoring systems, the proposed system has the advantage of strong networking ability, large bandwidth, long transmission distance, and low cost. © 2021 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

MAF-Net: A multi-scale attention fusion network for automatic surgical instrument segmentation?

引用

BIOMEDICAL SIGNAL PROCESSING AND control 2023年第1期85卷

作者： Yang, Lei Gu, Yuge Bian, Guibin Liu, Yanhong Zhengzhou Univ Sch Elect & Informat Engn Zhengzhou 450001 Henan Peoples R China Robot Percept & Control Engn Lab Henan Prov Zhengzhou 450001 Henan Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Accurate localization of surgical instruments is of utmost importance for precise robot-assisted surgeries. With the development of artificial intelligence, deep convolutional neural networks (DCNNs) have been widely employed for automatic image segmentation, owing to their strong ability to generate contextual features, especially in the encoder-decoder framework. However, existing segmentation networks lack the feature capturing capability on micro objects and have shortcomings in processing local semantic features. These limitations can affect the precise segmentation of surgical instruments. In response to these issues, this paper proposes a multi-scale attention fusion network called MAF-Net, which comprises residual dense module, a multi-scale atrous convolution (MSAC) module, and an attention fusion module (AFM). To improve the processing ability of local contextual features, we propose replacing skip connections with residual dense module to acquire stronger contexts. Furthermore, a MSAC module is proposed for local feature enhancement, thereby enhancing attention on multi-scale features. In addition, an AFM module is introduced to integrate multi-scale information by cross-scale feature fusion. Experimental results, using two public datasets, Endovis2017 and kvasir-instrument, demonstrate that the proposed network has the ability to achieve precise surgical instrument segmentation and outperforms related advanced methods.

关键词： Semantic segmentation Deep learning Surgical instrument Multi-scale feature fusion Residual dense network

来源：评论

学校读者我要写书评

暂无评论

Data-Based Online Optimal control for Multi-player Nonlinear Non-zero-Sum Games Using Recursive Least Squares

Data-Based Online Optimal Control for Multi-player Nonlinear...

引用

2021 China Automation Congress, CAC 2021

作者： Yang, Gaofu Song, Ruizhuo Wei, Qinglai School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665426473

In this paper, optimal control of nonlinear systems for non-zero-sum games is solved with a data-based and recursive least square. The new adjustment law is similar to experience replay algorithm which refer history data and the covariance matrix is introduced for storing historical data, which can avoid the waste of space and time caused by storing a large amount of historical data and collecting data. In tuning process, we use a discount factor which shows how trust to the collected data to guide adjustment law to update the weight. Meanwhile, discount factor can avoid the covariance matrix tending to zero due to accumulation of data. After that, the convergence of the weight is analyzed. Finally, using a simulation to verify the effectiveness of the tuning law. © 2021 IEEE

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

A Bibliometric Analysis of IEEE T-ITS Literature Between 2010 and 2019

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2022年第10期23卷 17157-17166页

作者： Sun, Xingkai Ge, Shichao Wang, Xiao Lu, Hao Herrera-Viedma, Enrique Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China Qingdao Acad Intelligent Ind Qingdao 266109 Peoples R China Univ Granada Andalusian Res Inst Data Sci & Computat Intellige Granada 18011 Spain King Abdulaziz Univ Fac Engn Dept Elect & Comp Engn Jeddah 21589 Saudi Arabia

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems (T-ITS) has become a leading international journal in the field of ITS since its first issue published in 2000. To obtain a structural overview as well as the evolution of T-ITS in the last decade (2010-2019), we present a comprehensive bibliometric analysis from multiple perspectives based on the articles published during the same period in this paper. Our analyses of the T-ITS literature include: (a) statistical analysis;(b) topic analysis;and (c) network analysis. Statistical analysis was first conducted to identify the most highly cited papers, then the top productive and influential authors, institutions and countries/regions were given from paper counts and citations respectively. In order to identify important topics and patterns of evolution, author keywords were used to identify the most frequent topics and the theme river map can visually demonstrate their corresponding trends. Furthermore, keyword co-occurrence network was constructed to reveal the hotspots and the research landscape within this field. In addition, three networks are provided to visualize the relationships and reveal the collaboration patterns from different perspectives, including authors, institutions and countries/regions. The results provide an insight on the characteristics of the publications over the last decade, from which we can know the key contributors and groups who brought the significant growth of the journal. This paper can benefit researchers in terms of promoting understanding of the entire field with the development status and trends.

关键词： Bibliometrics Productivity Market research Internet Transportation Sun Collaboration Bibliometric analysis topic analysis network analysis intelligent transportation systems (ITS)

来源：评论

学校读者我要写书评

暂无评论

Parallel vision and learning for intelligent perception in smart driving 1

Parallel vision and learning for intelligent perception in s...

引用

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Zhang, Hui Li, Yidong Li, Xuan Wang, Fei-Yue Beijing Jiaotong University Beijing China Peng Cheng Laboratory Shenzhen China Institute of Automation Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex Systems Beijing China

ISBN: (纸本)9781665433372

Modern vision models are built upon large-scale diversified dataset, which is labor-intensive and cost-ineffective to collect and label. They are usually effective under simple constrained conditions, while the performance gets worse under actual traffic scenes. To address aforementioned problems, we propose a visual analysis framework based on parallel vision and learning for intelligent perception in smart driving. Specifically, our framework first generate and select data exploiting artificial image system. Then, computational experiments are conducted with predictive learning for model design, learning, and evaluation. Our framework is powered with virtual-actual interactive ability through parallel execution, integrating information from different scenes. The difficulty of the visual model in the actual scene can be applied to guide the model training in the artificial scene. We also carried out a case study to preliminarily demonstrate the effectiveness of the proposed framework. © 2021 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

From DAO to TAO: Finding The Essence of Decentralization

From DAO to TAO: Finding The Essence of Decentralization

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Juanjuan Li Xiaolong Liang Rui Qin Fei-Yue Wang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Faculty of Innovation Engineering Macau University of Science and Technology Macau China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Decentralized Autonomous Organizations (DAOs) have been gaining popularity in recent years due to their promise of realizing the decentralized Web 3.0. However, most DAOs rely heavily on token-centric value systems as well as allocate decision-making authority and yield-sharing rights according to the held tokens, which often lead to monopolization of power and rights. To address this issue, this paper contributes to propose a truly democratic organization model, named True Autonomous Organizations and Operations (TAOs), that does not count upon tokens and is guided by principles of contribution-based and on-demand allocation. We first discuss the design of TAOs, including their infrastructures, power structures, and value systems, and then provide a technical roadmap for implementing TAOs in the DeSci context. This research can provide a valuable guidance for the construction and application of TAOs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Social Vision for Intelligent Vehicles: From Computer Vision to Foundation Vision

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第11期8卷 4474-4476页

作者： Yu, Hui Wang, Yutong Tian, Yonglin Zhang, Hui Zheng, Wenbo Wang, Fei-Yue Univ Portsmouth Sch Creat Technol Portsmouth PO1 2DJ England Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Wuhan Univ Technol Sch Comp Sci & Artificial Intelligence Wuhan 430070 Peoples R China Wuhan Univ Technol Sanya Sci & Educ Innovat Pk Sanya 572000 Peoples R China Beijing Jiaotong Univ Beijing 100044 Peoples R China

The development of Artificial intelligent (AI), deep learning and computer vision technologies has enabled various new applications and features of intelligent vehicles. However, there are still application scenarios that have not been addressed, such as the new social and human-vehicle interaction within the intelligent vehicle cabin, where social vision could play an important role. To this end, this letter presents a summary of discussions as part of Distributed/Decentralized Hybrid Workshop on Sustainability for Transportation and Logistics (DHW-STL) dedicating to the development of sustainable interaction systems.

关键词： Social Vision Parallel Vision Knowledge Vision Foundation Vision intelligent vehicles social interaction sustainability

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：