检索结果-内蒙古大学图书馆

TMF-Net: A Transformer-Based Multiscale Fusion Network for Surgical Instrument Segmentation From Endoscopic Images

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2023年 72卷 1页

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

Automatic surgical instrument segmentation is a necessary step for the steady operation of surgical robots, and the segmentation accuracy directly affects the surgical effect. Nevertheless, accurate surgical instrument segmentation from endoscopic images remains a challenging task due to the complex environment and instrument motion during surgery. Based on the encoder-decoder structure, a transformer-based multiscale fusion network, named TMF-Net, is proposed to address the difficulties in the area of surgical instrument segmentation. To realize the effective feature representation based on the pretrained ResNet34 and transformer and to strengthen both advantages of different encoder units, a dual-encoder unit is proposed to simultaneously learn the semantic relationship between adjacent pixels and distant pixels and comprehensively capture the global context information. Meanwhile, to retain more contextual information, a trapezoid atrous spatial pyramid pooling (trapezoid ASPP) block is proposed for feature enhancement of local features with different receptive fields to enrich feature information. Furthermore, in addition to multiscale surgical instruments in endoscopic images, a multiscale attention fusion (MAF) block is proposed to fuse multiscale feature maps to make the segmentation network direct more attention to the efficient channels so that it can improve the segmentation accuracy. Two typical datasets are used for performance analysis and verification, including Kvasir-Instrument and Endovis2017. Experimental results indicate that the proposed TMF-Net could effectively improve segmentation accuracy on surgical instruments, and it could also yield a competitive segmentation result in comparison with advanced detection methods.

关键词： Deep learning multiscale attention fusion (MAF) semantic segmentation surgical instruments transformer

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Image Classification Method Based on Attention Mechanism and Semantic Information Fusion

引用

SENSORS 2023年第4期23卷 2311页

作者： Wang, Yaru Feng, Lilong Song, Xiaoke Xu, Dawei Zhai, Yongjie North China Elect Power Univ Dept Automat Baoding 071003 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

The zero-shot image classification (ZSIC) is designed to solve the classification problem when the sample is very small, or the category is missing. A common method is to use attribute or word vectors as a priori category features (auxiliary information) and complete the domain transfer from training of seen classes to recognition of unseen classes by building a mapping between image features and a priori category features. However, feature extraction of the whole image lacks discrimination, and the amount of information of single attribute features or word vector features of categories is insufficient, which makes the matching degree between image features and prior class features not high and affects the accuracy of the ZSIC model. To this end, a spatial attention mechanism is designed, and an image feature extraction module based on this attention mechanism is constructed to screen critical features with discrimination. A semantic information fusion method based on matrix decomposition is proposed, which first decomposes the attribute features and then fuses them with the extracted word vector features of a dataset to achieve information expansion. Through the above two improvement measures, the classification accuracy of the ZSIC model for unseen images is improved. The experimental results on public datasets verify the effect and superiority of the proposed methods.

关键词： image classification attention mechanism matrix decomposition attributes word vectors

来源：评论

学校读者我要写书评

暂无评论

Towards Intelligent and Trustworthy Crowdsourcing systems with Cyber-physical Social Intelligence via Retrieval-augmented Generation

Towards Intelligent and Trustworthy Crowdsourcing Systems wi...

引用

Cyber-Physical Social Intelligence (ICCSI), International Conference on

作者： Jing Yang Xingxia Wang Qinghua Ni Yuhang Liu Jing Wang 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 Macao China Macau University of Science and Technology Macao China State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350376739

ISBN: (纸本)9798350376746

In recent years, crowdsourcing systems that tackle complex tasks through the collective efforts of many individuals have garnered substantial attention. However, the existing crowd-sourcing systems face some challenges such as overreliance on human experience and effort, information overload, and risks of privacy breaches. To overcome these challenges, this paper proposes an intelligent and trustworthy crowdsourcing frame-work based on blockchain and retrieval-augmented generation. The framework centers around foundational models to integrate the three distinct and sequentially interdependent phases: task decomposition, task allocation or recommendation, and task execution, enabling the automatic provision of a personalized, comfortable, and efficient user experience. Blockchain and smart contracts are utilized to protect user privacy and interests without leaning on any third trusted authority. Additionally, the operational process of the framework is explained and validated by taking printed circuit board design and manufacturing as a case study and ChatGPT as its generator.

关键词： Crowdsourcing Retrieval augmented generation Smart contracts Privacy breach User experience Stability analysis Blockchains Social intelligence Resource management Reliability

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Autonomous Landing of a Hybrid Robot on a Powerline

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2023年 72卷 1页

作者： Li, Zhishuo Tian, Yunong Yang, Guodong Li, En Zhang, Yanfeng Chen, Minghao Liang, Zize Tan, Min 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

In recent years, various types of inspection robots have been developed to automate powerline inspection. The hybrid robot combines the advantages of climbing and flying robots and has a promising prospect in powerline inspection. But landing a hybrid robot on the target powerline among multiple ones is challenging. Flights require robust detection of powerlines and stable tracking of the target powerline. We propose a complete solution for the autonomous landing of a hybrid robot on a powerline. First, a special feature extraction operator and the corresponding density-based feature recognition algorithm are designed to detect multiscale powerlines. Second, a binocular vision-based depth estimation method for the landing point in the powerline is described. Third, two spatio-temporal dictionaries are established to track the target one in multiple powerlines. Meanwhile, landing strategies and control methods are presented to achieve a stable landing task. Finally, a hybrid robot is designed to validate the proposed method. The experiment results demonstrate the accuracy of the powerline detection and depth estimation algorithm, as well as the effectiveness of the robot in tracking and landing tasks.

关键词： Robots Feature extraction Robot kinematics Inspection Robot vision systems Cameras Task analysis Depth estimation hybrid robot powerline detection and tracking powerline inspection

来源：评论

学校读者我要写书评

暂无评论

Multitasking bi-level evolutionary algorithm for data-intensive scientific workflows on clouds

引用

EXPERT systems WITH APPLICATIONS 2024年第PartB期238卷

作者： Cai, Xingjuan Li, Mengxia Zhang, Yan Zhao, Tianhao Zhang, Wensheng Chen, Jinjun Taiyuan Univ Sci & Technol Shanxi Key Lab Big Data Anal & Parallel Comp Taiyuan 030024 Shanxi Peoples R China Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Swinburne Univ Technol Dept Comp Sci & Software Engn Melbourne Australia

With the deployment of workflow and other applications, cloud computing is accessible and offers assistance for optimizing workflow execution and enhancing performance. Existing research, however, tends to disregard the influence of dataset migration on workflow execution and focuses more on task execution time. This study suggests a new model for the problem of data-intensive workflow execution. Firstly, according to the structure of the workflow scheduling problem, it is divided into two sub-problems: data placement and task scheduling. The two sub-problems interact with each other and a bi-level optimum model is established. By seeking a better allocation strategy for the dataset placement and then seeking the best task-scheduling solution. Secondly, an improved multitasking bi-level evolutionary algorithm (IM-BLEA) is proposed. When dealing with the lower-level optimization problem (LLOP), offspring are selected by sorting individuals by their performance and overall performance in the population, and this environmental selection enhances the diversity and searchability of the population. Finally, compared with the other multitasking algorithm, IM-BLEA has good performance. Simulation results based on real scientific workflows show that the algorithm improves the values of transfer time and number of selected data centers by 56% and 10% compared to the comparison algorithm.

关键词： Evolutionary multitasking algorithms Bi-level optimization Data-intensive scientific workflow Data placement Task scheduling

来源：评论

学校读者我要写书评

暂无评论

Topology Prediction and Structural controllability Analysis of complex Networks Without Connection Information

引用

IEEE TRANSACTIONS ON systems MAN CYBERNETICS-systems 2022年第9期52卷 6015-6027页

作者： Yang, Dongsheng Sun, Yunhe Wei, Qinglai Zhang, Huaguang Li, Ting Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Beijing Inst Graph Commun Coll Mech & Elect Engn Beijing 102600 Peoples R China

In this article, we consider complex networks without connection information. The absence of global structure induces a great obstacle in the structural controllability analysis of these networks. Thus, a topology predicting method based on the connection probability matrix is proposed to provide a global structure for structural controllability analysis in this article. Furthermore, the modified principles of predicting global network topologies are established to acquire a more accurate global connection relationship. Eventually, the drive node set of these networks is determined by predicting global topologies. The accuracy of the proposed topology predicting method is verified by numerical simulations in the context of artificial networks and real networks. The results reveal that the global topology and structural controllability of complex networks with large scale and high edge density could be accurately predicted by utilizing the proposed method.

关键词： controllability Topology complex networks Sun Pattern matching Couplings Web sites complex networks structural controllability topology prediction

来源：评论

学校读者我要写书评

暂无评论

SegDQ: Segmentation assisted multi-object tracking with dynamic query-based transformers

引用

NEUROCOMPUTING 2022年第0期481卷 91-101页

作者： Liu, Yating Bai, Tianxiang Tian, Yonglin Wang, Yutong Wang, Jiangong Wang, Xiao Wang, Fei-Yue 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 Univ Sci & Technol China Dept Automat Hefei 230027 Peoples R China Qingdao Acad Intelligent Ind Qingdao 266000 Peoples R China

Multi-Object Tracking (MOT) has been one of the most important topics in computer vision. The tradi-tional tracking-by-detection framework of MOT is severely suffered from the poor detection results. In this paper, based on Transformer, we introduce the tracking-by-query MOT framework, and propose to apply semantic segmentation as an auxiliary task to optimize the training of MOT trackers, which addresses more on extracted foreground features. In addition, a feature-dependent dynamic object query (DOQ), instead of a fixed-learned object query (LOQ), is put forward to retrieve the new detections, improving the flexibility and constringency of the framework. We tested our SegDQ method on various scenarios including MOTChallenge 15, 16 and 17 datasets. The experimental results show that it obvi-ously improves the MOTA and IDF1 indexes of tracking results. (c) 2022 Published by Elsevier B.V.

关键词： Multi-object tracking Transformer Semantic task Dynamic query

来源：评论

学校读者我要写书评

暂无评论

Acting as a Decision Maker: Traffic-Condition-Aware Ensemble Learning for Traffic Flow Prediction

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2022年第4期23卷 3190-3200页

作者： Chen, Yuanyuan Chen, Hongyu Ye, Peijun Lv, Yisheng Wang, Fei-Yue Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Harbin Univ Sci & Technol Sch Automat Harbin 150080 Peoples R China Qingdao Acad Intelligent Ind Qingdao 266109 Peoples R China Macau Univ Sci & Technol Inst Engn Taipa Macao Peoples R China

Accurate traffic prediction under various conditions is an important but challenging task. Due to the complicated non-stationary temporal dynamics in traffic flow time series and spatial dependencies on roadway networks, there is no particular method that is clearly superior to all others. Here, we focus on investigating ensemble learning that benefits from multiple base models, and propose a traffic-condition-aware ensemble approach that acts as a decision maker by stacking multiple predictions based on dynamic traffic conditions. To sense traffic conditions, we apply the Convolutional Neural Network (CNN) model to capture the spatiotemporal patterns embedded in traffic flow. Then, the high-level features extracted by CNN are used to generate weights to ensemble multiple predictions of different models. Extensive experiments are performed with a real traffic dataset from the Caltrans Performance Measurement System. We compare the proposed approach with competitive models, including Gradient Boosting Regression Tree (GBRT) model, Weight Regression model, Support Vector Regression (SVR) model, Long Short-term Memory (LSTM) model, Historical Average (HA) model and CNN model. Experimental results demonstrate that our method can effectively improve the performances of traffic flow prediction.

关键词： Traffic flow prediction ensemble learning deep learning

来源：评论

学校读者我要写书评

暂无评论

ASCL: Adversarial supervised contrastive learning for defense against word substitution attacks

引用

NEUROCOMPUTING 2022年 510卷 59-68页

作者： Shi, Jiahui Li, Linjing Zeng, Daniel 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 101408 Peoples R China Tianjin Zhongke Intelligent Recognit Co Ltd Tianjin 300450 Peoples R China Chinese Acad Sci Inst Automat Beijing Peoples R China

Attacks with adversarial examples can tremendously worsen the performance of deep neural networks (DNNs). Hence, defending against such adversarial attacks is crucial for nearly all DNN-based applica-tions. Adversarial training is an effective and extensively adopted approach for increasing the robustness of DNNs in which benign examples and their adversarial counterparts are considered together in the training stage. However, this may result in a decrease in accuracy on benign examples because it does not account for the inter-class distance of benign examples. To overcome the aforementioned dilemma, we devise a novel defense approach named adversarial supervised contrastive learning (ASCL), which combines adversarial training with supervised contrastive learning to enhance the robustness of DNN-based models while maintaining their clean accuracy. We validate the effectiveness of the proposed ASCL approach in the scenario of defending against word substitution attacks by means of extensive experiments on benchmark tasks and datasets. The experimental results show that ASCL reduces the attack success rate to 20% while maintaining the accuracy for clean inputs within a 2% margin. (c) 2022 Elsevier B.V. All rights reserved.

关键词： Adversarial example Adversarial training Model robustness Contrastive learning Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Hydrodynamics of a Flexible Flipper for an Underwater Vehicle-Manipulator System

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2022年第2期27卷 868-879页

作者： Bai, Xuejian Wang, Yu Wang, Rui Wang, Shuo Tan, Min Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China CAS Ctr Excellence Brain Sci & Intelligence Techn Beijing Peoples R China

Motivated by the requirement for developing a lightweight and nimble underwater vehicle-manipulator system (UVMS), this article presents a novel design of the overall framework and the functional modules for a flippers-driven UVMS (F-UVMS), which is equipped with six biomimetic flipper propulsors to produce thrust. With taking into account the material properties and flexible deformation, the dynamic model of the flexible flipper is derived. The fluid-solid coupling analysis reveals the wake vorticity characteristics and the mechanism of the flexible flipper. Besides, by introducing the dimensionless swimming number S W , the force-parameter relationship of the flexible flipper is revealed. By comparing the hydrodynamic characteristics of the flexible flipper and rigid flipper, it can be concluded that the flexible flipper has higher propulsion efficiency. The motion patterns of the F-UVMS are designed by proposed coordinated control strategy. Moreover, through computational fluid dynamics method, the hydrodynamic effects of the biomimetic flipper propulsors during forward motion are analyzed. Finally, the force measurement experiments and the thrust efficiency experiments validate the practicability of the proposed biomimetic flipper propulsor. The motion feasibility of the F-UVMS is verified by the motion experiments.

关键词： Biomimetic robot flexible flipper hydrodynamic model underwater vehicle-manipulator system

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：