检索结果-内蒙古大学图书馆

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Liu, Yinhao Zhang, Baofeng Zhang, Zhili TianJin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems No. 391 Binshuixi Road Tianjin300384 China Intelligent Manufacturing Institute TianJin Sino-German University of Applied Sciences No. 2 Yashen Road Tianjin300350 China

ISBN: (纸本)9798350320831

The φ-OTDR technology is an optical fibre sensing method that enables real-time monitoring of fibre vibrations by using optical time domain reflection technology. However, during the process of transmitting signals through optical fibres, the issue of optical power attenuation arises, which ultimately results in a reduction of the long-distance signal recognition ability of the φ-OTDR system. This paper presents an innovative optical power attenuation compensation technique that utilizes the φ-OTDR system to address the challenge of signal attenuation in optical fibre. The proposed solution enhances the long-distance recognition ability of weak signals. To solve the attenuation issue, the polynomial fitting method is used. A comparison between the system's performance with and without a Raman amplifier is presented. To locate signals, mean square error and deviation from the average are utilized, while signal strength is determined by calculating the signal-to-noise ratio after fitting. This approach emphasizes precision in detecting relevant signals and optimizing system performance. The results show that the signal recognition ability of the φ-OTDR system improves significantly with the implementation of this compensation algorithm. © 2023 IEEE.

关键词： Optical fibers

来源：评论

学校读者我要写书评

暂无评论

Multi-Feature Fusion Transformer for Natural Language Inference 5

Multi-Feature Fusion Transformer for Natural Language Infere...

引用

5th International Conference on Robotics, Intelligent control and Artificial Intelligence, RICAI 2023

作者： Sun, Lei Li, Xiangyang Yan, Hengxin School of Electrical Engineering and Automation Tianjin University of Technology Tianj in Key Laboratory for Control Theory and Complicated Industry Systems Tianjin China School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China

ISBN: (纸本)9798350357950

Natural Language Inference (NLI) is a branch of Natural Language Processing (NLP) whose main task is to determine the relationship between two sentences. Such tasks essentially use pre-trained models to ensure accuracy, and many applications are found in human-computer dialog and question-answering systems. However, in some cases where small devices are deployed offline, lightweight model implementations are often required to save computational resources. To address this problem and ensure more efficient inference capabilities, this paper describes how to improve the preexisting Transformer and proposes a Multi-Feature Fusion Transformer Network for NLI processing. The model integrates sequence features and introduces a priori information to enhance local features. It also achieves a comprehensive fusion of sequence information, local features, and non-local features, thus compensating for many potential shortcomings of Transformer. At the same time, it maintains the lightweight feature of the model and facilitates the implementation of downstream tasks. We verified the above point by experiments, our model has better inference performance compared to previous models used for the same task. The accuracy in the SNLI dataset reached 89.0%, while the matched and mismatched versions of MultiNLI reached 79.3% and 78.7%. © 2023 IEEE.

关键词： Feature Fusion Natural language inference Natural language processing Transformer

来源：评论

学校读者我要写书评

暂无评论

Research on Hearing-Impaired EEG Emotion Recognition Based on Deep Residual Shrinkage Networks

Research on Hearing-Impaired EEG Emotion Recognition Based o...

引用

Chinese control Conference (CCC)

作者： Meiyi Cheng Qiang Gao Zhongli Bai Yirui Chen Yang Liu Yu Song School of Electrical Engineering and Automation Tianjin University of Technology Tianjin Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Tianjin

With the development of affective computing and computer science, electroencephalogram (EEG) based emotion recognition has attracted much more attention. In this paper, we collected EEG signals from fifteen healthy people and fifteen hearing-impaired people when they were watching five kinds of emotional pictures (fear, anger, sadness, happiness and neutral). The collected EEG signals are preprocessed to remove artifacts by independent component analysis (ICA). Then the differential power spectral density, entropy, and wavelet entropy features were extracted (PSD, DE, WE). The Deep Residual Shrinkage Networks (DRSNs) were composed of residual building units (RBU s) and an attention mechanism was used to capture the representative features, and then made a classification. The classification results prove that using DE as a feature for classification is better than other features, with an average accuracy being 76.35% and 80.47% for the hearing-impaired group and the normal group, respectively. Moreover, from the brain topography, we found that there are certain differences in brain function between hearing-impaired and healthy people.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed-Observer-Based on Longitudinal Flight control for Hypersonic Vehicle

Distributed-Observer-Based on Longitudinal Flight Control fo...

引用

Chinese control Conference (CCC)

作者： Yuehui Ji Yiming Zhao Jiaqi Chen Junjie Liu Qiang Gao Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China

An output feedback control is investigated to achieve stable tracking of velocity and altitude in hypersonic flight vehicle in the paper. A distributed observer is proposed to estimate the unmeasurable flight path angel and angle of attack through a strongly connected directed network topology. Then, a nonlinear control is addressed on the longitudinal dynamics of a rigid hypersonic flight vehicle (HFV) with partial measurable states and the estimated states. The system dynamic is divided into the altitude subsystem and the velocity subsystem. In the altitude subsystem, the backstepping design is proposed for constructing the controllers utilizing the estimated states. The nonlinear dynamic inversion controller is introduced to accomplish the velocity tracking. Finally, numerical simulations verify the effectiveness of the proposed control scheme in providing favorable tracking performance and exact state estimation ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GIB-RRT:a gamma interpolation bidirectional RRT algorithm

GIB-RRT:a gamma interpolation bidirectional RRT algorithm

引用

第35届中国控制与决策会议

作者： Jianyun Ni Hao Li Tie Wang Helei Du Jie Wu Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems School of Electronic Engineering and Automation Tianjin University of Technology Tianjin Climate Center

In a complex environment,when B-RRT and RRT algorithms are used for path planning,there will be problems such as long planned paths,large number of iterations,low sampling efficiency and long search *** solve these problems,this paper proposes a gamma interpolation bidirectional RRT algorithm——***,the algorithm uses a bidirectional search strategy to expand two random trees simultaneously to speed up the convergence *** the expansion process,an adaptive goal biasing strategy is introduced to improve the sampling efficiency,and the probability of expansion to the respective target point is continuously changed according to the number of collision detection *** the initial path is obtained,a greedy pruning algorithm is used to simplify the path points and reduce the path *** optimisation method of Gamma interpolation is then devised for the simplified path and combined with cubic uniform B-spline curve to generate shorter and smoothly executable *** proposed algorithm is compared with B-RRT,IB-RRT and B-RRT in different complex environments in simulation experiment,and the results show that the proposed algorithm has better search efficiency and is able to obtain optimal path in the least time and with the most stable efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FATUnetr:fully attention Transformer for 3D medical image segmentation

FATUnetr:fully attention Transformer for 3D medical image se...

引用

IEEE International Conference on Mechatronics and Automation

作者： QingFeng Li Jigang Tong Sen Yang Shengzhi Du Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot Laboratory Tianjin University of Technology Tianjin China Department of Electrical Engineering Tshwane University of Technology South Africa

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

Recent studies have explored the applicability of the Transformer model in 3D medical segmentation tasks. The core attention mechanism of transformer, has the property of capturing remote dependencies, which is highly robust when segmenting medical images. Inspired by the emerging visual groupings in Vision Transformers (ViTs), self-attention can be made more robust by improving the intermediate representation. We propose a novel framework called FATUnetr that aims to take advantage of the full attention module to improve accuracy. We also reduce the number of parameters by applying deeply separable convolution at the bottleneck layer. We have verified the effectiveness in the extracranial vault multiple atlas labelling (BTCV) dataset for multi-organ segmentation.

关键词： Image segmentation Visualization Three-dimensional displays Attention mechanisms Accuracy Convolution Transformer cores

来源：评论

学校读者我要写书评

暂无评论

Invariant and Dual-Invariant Subspaces of k-Valued Networks

引用

Journal of systems Science & Complexity 2025年第2期38卷 547-572页

作者： CHENG Daizhan QI Hongsheng ZHANG Xiao JI Zhengping Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Chinese Academy of Sciences Research Center of Semi-Tensor Product of Matrices:Theory and Applications Department of Applied Mathematics Hong Kong Polytechnic University School of Mathematical Sciences University of Chinese Academy of Sciences

For k-valued(control) networks, two types of(control) invariant subspaces are proposed,namely, the state-invariant and dual-invariant subspaces, which are subspaces of the state space and dual space, respectively. Algorithms are presented to check whether a dual subspace is dual-(control)invariant, and to construct state feedback controls. The bearing space of k-valued(control) networks is introduced. Using the structure of the bearing space, the universal invariant subspace is presented,which is independent of the dynamics of particular networks. Finally, the relation between the stateinvariant subspaces and the dual-invariant subspaces of a network is investigated. A duality property shows that if a dual subspace is invariant, then its perpendicular state subspace is also invariant, and vice versa.

关键词： Bearing spaces finite lattices finite rings invariant subspace k-valued (control) networks

来源：评论

学校读者我要写书评

暂无评论

Research on Detection System of Electronic Thermostat

Research on Detection System of Electronic Thermostat

引用

2021 China Automation Congress, CAC 2021

作者： Jie, Wang Zhu, Junchao Li, Zhiwei Tianjin Key Laboratory for Control Theory and Applications in Complicated System Tianjin University of Technology Tianjin China

ISBN: (纸本)9781665426473

As one of the core components of the engine cooling system, the electronic thermostat is in order to achieve the purpose of testing the performance of the electronic thermostat. This paper designs an electronic thermostat detection system. The system uses electrical proportional valves, solenoid valves, relays, acquisition controllers, industrial computers and other hardware devices. The software platform is built based on the Java development environment and MySQL database to realize the storage and display of test data, automatic testing and alarm processing. By detecting the motor current, external leakage differential pressure and flow characteristics, real-time data collection and analysis can be performed on the current value, the change of differential pressure and the flow conditions corresponding to the opening of the ball valve. After testing, this system can realize the inspection of the eligibility of the electronic thermostat, so as to verify whether the performance index of the electronic thermostat can reach the expected design. © 2021 IEEE

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

A High-Precision Edge Detection Algorithm Based on Improved Sobel Operator-Assisted HED 14

A High-Precision Edge Detection Algorithm Based on Improved ...

引用

14th IEEE International Conference on Cyber Technology in Automation, control, and Intelligent systems, CYBER 2024

作者： Yuan, Yeborui Chen, Wenyuan Tang, Jie Yang, Jia School of Electrical Engineering and Automation Tianjin University of Technology Tianjin300384 China Shenyang Institute of Automation Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang State Key Laboratory of Robotics 110016 China University of Chinese Academy of Sciences Beijing100049 China School of Electrical Engineering and Automation Tianjin University of Technology Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Tianjin300384 China

ISBN: (纸本)9798331506056

In response to the problem of poor detection performance of the traditional Sobel operator in edge detection, a high-precision edge detection algorithm based on Sobel operator-assisted Holistically-nested Edge Detection (HED) network was proposed, which is named ISAHED here. The algorithm is designed as follows. Firstly, an improved Sobel operator based on the traditional Sobel operator was proposed through adding gradient direction. Then, the image output by the improved Sobel operator is taken as the ground-truth image and as the end-to-end comparison object in a HED-like network. Finally, the ISAHED algorithm outputs edge images with better quality through iterative learning of the HED-like neural network. The experimental results prove that the proposed ISAHED algorithm has better edge detection performance by visually observing the final edge images and further evaluating the values of FOM. This work provides an important reference for the further development of the edge detection technology. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

PFSC:Pyramid R-CNN for Point-Voxels with Focal Sparse Convolutional Networks for 3D Object Detection

PFSC:Pyramid R-CNN for Point-Voxels with Focal Sparse Convol...

引用

IEEE International Conference on Mechatronics and Automation

作者： Zhao Su Xuehui Liang Jigang Tong Sen Yang Shengzhi Du Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot Laboratory Tianjin University of Technology Tianjin China Department of Electrical Engineering Tshwane University of Technology Pretoria South Africa

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

In the point cloud 3D object detection task, the point cloud data is unevenly distributed in 3D space. Therefore, whether it is regular sparse convolution or submanifold sparse convolution, there is a significant difference in the detection performance when dealing with objects at different positions using sparse convolutional networks. Therefore, this paper proposes an improvement using focal sparse convolution to break the limitations of traditional convolution methods and enhance the representation ability of sparse convolution. Focal sparse convolution is utilized to replace the currently better-performing two-stage object detection network based on the combination of points and voxels, enhancing the end-to-end training effectiveness and achieving better detection results. And an optional detachable auxiliary network is added, which, during the training stage, combines point features to guide the backbone network in learning the structural information of the 3D point cloud, enhancing the localization accuracy of the backbone network. Extensive experiments have been conducted on the KITTI dataset to validate the proposed method, yielding promising detection results and demonstrating the effectiveness of the approach.

关键词： Point cloud compression Training Location awareness Three-dimensional displays Accuracy Mechatronics Convolution

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：