检索结果-内蒙古大学图书馆

Data Driven control and Learning systems (DDCLS)

作者： Zhuxin Wang Juan Wang Chengyi Xia Tianjin Key Laboratory for Control Theory and Complicated Industry Systems School of Electrical and Electronic Engineering Tianjin University of Technology Tianjin China School of Artificial Intelligence Tiangong University Tianjin China

Knee meniscus tear is a common joint disorder that is usually diagnosed with the help of MRI imaging. However, the diagnosis of a meniscal tear places high technical demands on physicians, and the results of the diagnosis are also inconsistent. In this paper, a meniscal tear detection method based on YOLOv5 target detection network is developed to help physicians make more accurate diagnoses. To begin, a channel and space parallel attention module is designed and integrated into the feature fusion part of the network to improve the network's attention to the tear area. Then, ConvNeXt is used in the backbone network part to improve the C3 module to obtain the ConvC3 module, which strengthens the ability of the backbone network to extract the features of the meniscal tear lesion area. After labelling and creating the dataset, the improved YOLOv5 network is trained to obtain the target model. The experimental results show that compared with the original model, the improved YOLOv5 model has an increased mAP from 82.5% to 84.8%, a slight decrease in GFLOPs as well, and presents an overall considerable improvement. This model plays an important role in the diagnosis of meniscal tears.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Optical Power Attenuation Compensation Algorithm of φ-OTDR System

Research on Optical Power Attenuation Compensation Algorithm...

引用

IEEE International Conference on Mechatronics and Automation

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

The $\varphi$-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 $\varphi$-OTDR system. This paper presents an innovative optical power attenuation compensation technique that utilizes the $\varphi$-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 $\varphi$-OTDR system improves significantly with the implementation of this compensation algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Moving pattern-based modeling using a new type of interval ARX model

arXiv

引用

arXiv 2023年

作者： Changping, Sun Tianjin Key Laboratory for Control Theory & Application in Complicated Systems Tianjin University of Technology Tianjin300384 China School of Electrical Engineering and Automation Tianjin University of Technology Tianjin300384 China

In this paper, firstly, to overcome the shortcoming of traditional ARX model, a new operator between an interval number and a real matrix is defined, and then it is applied to the traditional ARX model to get a new type of structure interval ARX model that can deal with interval data, which is defined as interval ARX model (IARX). Secondly, the IARX model is applied to moving pattern-based modeling. For better characterizing pattern moving space, the "cardinality" of pattern moving space (CPMS) is defined. Finally, to verify the validity of the proposed modeling method, it is applied to a sintering process. The simulation results show the moving pattern-based modeling using the new type of interval ARX model is robust to variation in parameters of the model, and the performance of the modeling using the proposed IARX is superior to that of the previous work. © 2023, CC BY.

关键词： Sintering

来源：评论

学校读者我要写书评

暂无评论

TEMPORAL-SPATIAL REPRESENTATION LEARNING TRANSFORMER FOR EEG-BASED EMOTION RECOGNITION

arXiv

引用

arXiv 2022年

作者： Wang, Zhe Wang, Yongxiong Hu, Chuanfei Yin, Zhong Song, Yu School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology China Key Laboratory of Measurement and Control of CSE Ministry of Education Southeast University China Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Tianjin University of Technology China

Both the temporal dynamics and spatial correlations of Electroencephalogram (EEG), which contain discriminative emotion information, are essential for the emotion recognition. However, some redundant information within the EEG signals would degrade the performance. Specifically, the subjects reach prospective intense emotions for only a fraction of the stimulus duration. Besides, it is a challenge to extract discriminative features from the complex spatial correlations among a number of electrodes. To deal with the problems, we propose a transformer-based model to robustly capture temporal dynamics and spatial correlations of EEG. Especially, temporal feature extractors which share the weight among all the EEG channels are designed to adaptively extract dynamic context information from raw signals. Furthermore, multi-head self-attention mechanism within the transformers could adaptively localize the vital EEG fragments and emphasize the essential brain regions which contribute to the performance. To verify the effectiveness of the proposed method, we conduct the experiments on two public datasets, DEAP and MAHNOB-HCI. The results demonstrate that the proposed method achieves outstanding performance on arousal and valence classification. Copyright © 2022, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Research on Carbon Monoxide Content Prediction Based on Improved Particle Swarm Optimization SVM

Research on Carbon Monoxide Content Prediction Based on Impr...

引用

第33届中国控制与决策会议

作者： Jianyun Ni Mingyang Zhao Yong Wang Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems School of Electrical and Electronic Engineering Tianjin University of Technology

In the petroleum processing industry,the carbon monoxide(CO) content of the flue gas emitted by the heating furnace is predicted according to the various gases that will be generated in the on-site environment of the heating ***,a Particle Swarm Optimization Support Vector Machine(PSO-SVM) model is proposed for the prediction of carbon monoxide *** optimizing the parameters of SVM for particle swarm optimization,it is easy to fall into the problem of local optimization and premature *** improved particle swarm optimization(IPSO) algorithm is proposed:in the optimization process,adding a passive aggregation term to improve the speed formula of the PSO algorithm can make the particles reach the global optimal ***,the carbon monoxide content is predicted by the improved PSO optimization support vector *** experimental results show that the improved particle swarm algorithm is used to fully explore the potential of the SVM model,and compared with the experimental results of other prediction models,it is proved that the model has the advantages of high accuracy.

关键词： CO content PSO Passive aggregation term SVM

来源：评论

学校读者我要写书评

暂无评论

Approximation Secure control of Cyber-physical systems under False Data Injection Attacks

Approximation Secure Control of Cyber-physical Systems under...

引用

第32届中国过程控制会议(CPCC2021)

作者： Xuxi Yang Qiang Gao Yuehui Ji Enzeng Dong School of Electrical and Electronic Engineering and Tianjin Key Laboratory for Control Theory & Applications in Complicated SystemsTianjin University of Technology

For the strict-feedback cyber-physical systems(CPSs),an approximation secure control is formulated based on backstepping,sliding mode disturbance observer and fuzzy logic system,to resist the stealthy false data injection attacks through sensor *** system state cannot be measured exactly as the sensors are attacked by *** initial system dynamic subjected to false data injection attacks is modelled as uncertainty dynamics and unknown control *** first n-1 step in the recursive control,sliding mode disturbance observer are designed to estimate the lumped *** the last step,two fuzzy logic system are introduced to approximate the lumped uncertainty and unknown control *** closed-loop stability analysis is discussed and proved Lyapunov *** numerical simulation can validate the effectiveness of the proposed control scheme.

关键词： Secure control Cyber-physical systems False Data Injection Attacks Sliding Mode Disturbance Observer

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

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

引用

Robotics, Intelligent control and Artificial Intelligence (RICAI), International Conference on

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

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%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Discrete-Time Sliding Mode control Method for Multi-Cylinder Hydraulic Press 17

A Discrete-Time Sliding Mode Control Method for Multi-Cylind...

引用

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Jia, Chao Wei, Jiaqi Dong, Enzeng Gao, Xuewei He, Haocheng Tianjin University of Technology Tianjin Key Laboratory for Control Theory and Applications in Complicated System Tianjin300384 China

ISBN: (纸本)9781728164151

In this paper, a discrete-time sliding mode control method for multi-cylinder hydraulic presses is proposed, which can be applied exactly for computer real-time discrete control in practical engineering. Proposed method bases on discretetime multi-cylinder hydraulic press model and adopts the design method of the distributed controller. First, the expected virtual force is designed according to the overall output demand, and the discrete-time sliding mode controller is designed to obtain the virtual force. Then the virtual force is separated by control allocation method to obtain the desired output force of each cylinder, finally, the second discrete-time sliding mode controller is designed to control the actual output force of each cylinder. The simulation results show that the proposed method has a good effect on output and leveling control of multi-cylinder hydraulic press and solves its problems of non-linear control and redundancy in discrete-time model. © 2020 IEEE.

关键词： Sliding mode control

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

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

引用

IEEE International Conference on Cyber Technology in Automation, control, and Intelligent systems

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

ISBN: (数字)9798331506056

ISBN: (纸本)9798331506063

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.

关键词： Automation Image edge detection Image processing Neural networks control systems Iterative algorithms Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Application of Improved Canny Algorithm in Image of Surgical Instruments 17

Application of Improved Canny Algorithm in Image of Surgical...

引用

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Liu, Hongli Lu, Kuan Shao, Lei Li, Ji Tianjin University of Technology Binshui Xidao Tianjin Key Laboratory for Control Theory Applications in Complicated Systems Xiqing District Tianjin300384 China

ISBN: (纸本)9781728164151

In order to improve the inventory efficiency of surgical instruments, a vision system needs to be installed. The edge detection of the image of surgical instruments is an important step to inventory surgical instruments. However, due to the wide variety of surgical instruments and the different sizes, it is necessary to improve the existing edge detection algorithm to satisfy the actual needs. Canny algorithm has been successfully applied in many computer vision systems, but it needs to be set manually when selecting high-low thresholds, it has poor adaptability and relies on human experience, so it cannot be directly applied to edge detection of surgical instruments. In this paper, based on the study of the traditional Canny algorithm, an improved Canny operator edge detection algorithm is proposed which shows the ability to autonomously select the threshold. Experimental results show that the improved Canny algorithm can effectively retain the true edge information, make the edges more continuous, and effectively achieve the edge detection of surgical instruments compared with the traditional Canny algorithm and the multi-scale morphology algorithm. © 2020 IEEE.

关键词： Image enhancement

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：