检索结果-内蒙古大学图书馆

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

Review of Research on Motor Imagery in the Field of Rehabilitation 4

Review of Research on Motor Imagery in the Field of Rehabili...

引用

4th International Conference on Computer Science, Electronic Information engineering and Intelligent control Technology, CEI 2024

作者： Ji, Xin Guo, Tinghang Li, Xiaohan Yin, Qianhan Li, Runze Qin, Zhuanping Han, Yu Lu, Guangda Control Automation and Electrical Engineering College Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing & Intelligent Tianjin China

ISBN: (纸本)9798350378542

Motor imagery has the advantages of non-invasiveness, safety and economic efficiency in post-stroke motor function rehabilitation, and has a wide application prospect in the field of medical rehabilitation. In this paper, we sort out the current status of the application of motor imagery brain-computer interface technology, summarize the development of motor imagery decoding algorithms and their application in the field of motor rehabilitation, discuss and analyze the research progress of motor imagery brain-computer interface technology in medical rehabilitation, and summarize the development trend of its development, so as to provide new therapeutic methods and ideas for the future of medical rehabilitation. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Robust control of two-wheeled bicycle robot under wind disturbance 2

Robust control of two-wheeled bicycle robot under wind distu...

引用

2nd Asia Conference on Electronics engineering, ACEE 2024

作者： Yuan, Ruijian Zhang, Yongli Geng, Lihui Li, Xuehui Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing and Intelligent Control School of Automation and Electrical Engineering Tianjin China

ISBN: (纸本)9798350375251

The two-wheeled bicycle robot (TWBR) is a new intelligent transportation, which can be used for special tasks such as forest operation and disaster relief. Although the TWBR is not structurally complex, the dynamics are very complex to model. It is extremely difficult to build an accurate mathematical model. Wind disturbance is, in principle, always present on open roads and influence on the driving stability increases. Aiming at mathematical modeling error caused by mass center of the TWBR frame and external disturbance caused by wind force, this paper introduces a suitable control method. Firstly, the Kane method is adopted for modeling. Secondly, robust control can provide stability and performance guarantee for both uncertainty and disturbance. Finally, the results of simulation and physical experiment show the effectiveness of the robust H∞ control for TWBR. In this paper, MATLAB/Simulink is used to establish a combined mathematical model of wind force as an experimental external disturbance. The robust H∞ controller based on linear matrix inequality (LMI) and Linear quadratic regulator(LQR) are realized. It is verified that the robust H∞ controller has better effectiveness than the LQR controller when facing the uncertainty and external disturbance. © 2024 IEEE.

关键词： Bicycles

来源：评论

学校读者我要写书评

暂无评论

Optimized Complex Convolutional Neural Network for Steady-State Visual Evoked Potentials Signal classification 25

Optimized Complex Convolutional Neural Network for Steady-St...

引用

25th IEEE China Conference on System Simulation Technology and its Application, CCSSTA 2024

作者： Li, Qingbin Han, Chunxiao Liu, Yanli Liu, Junxiu Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing & Intelligent Control School of Automation and Electrical Engineering Tianjin China

ISBN: (纸本)9798350366600

The steady-state visual evoked potential (SSVEP) is one of the most commonly used paradigms in the BCI system, which produces a significant response to visual stimuli of a specific frequency. How to better improve the classification performance of SSVEP signals is currently the main task. In this paper, a modified C-CNN-SVM model of EEG signal is proposed, aiming to enhance the precision of SSVEP signal classification. Firstly, spectral features are obtained from the SSVEP signal using fast fourier transform (FFT) as input to the model. FFT obtains 128 data lengths of the SSVEP signal, including 64 real part data and 64 complex part data. Then, CNN is used to further extract features, and finally, support vector machine (SVM) is used for classification. The experimental results show that the modified C-CNN-SVM model achieves an average accuracy of 93.86%, which is better than the traditional CCA, FBCCA and TRCA algorithms. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Parameter Identification and control of Two-Wheel Balance Vehicle Model Based on Subspace Algorithm 2

Parameter Identification and Control of Two-Wheel Balance Ve...

引用

2nd Asia Conference on Electronics engineering, ACEE 2024

作者： Li, Xuehui Zhang, Yongli Geng, Lihui Yuan, Ruijian Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing and Intelligent Control School of Automation and Electrical Engineering Tianjin China

ISBN: (纸本)9798350375251

To address parameter uncertainty in the two-wheel balance vehicle (TWBV) system, a closed-loop subspace algorithm (CLSA) was employed to identify and correct uncertain structural parameters. This got in a more accurate system model. Based on the dynamics mechanism model of the TWBV, we designed a simple controller to achieve self-balancing control. We harvested the input and output sample data required for identification. The method used to filter out noise from the original signal and extract essential dynamic characteristics of the system is the input-output bias voltage function. The parameters of the dynamics model for the TWBV were subsequently identified and corrected using the CLSA. Finally, the linear quadratic regulator (LQR) controller is designed based on the model obtained from identification and compared with the original unidentified model. The results of the simulation and physical experiment show that the control system with the modified system after identification has better performance. This paper verifies the effectiveness of the proposed control strategy, which provides a reference scheme for solving model uncertainty in similar systems and improving control accuracy. © 2024 IEEE.

关键词： Vehicle wheels

来源：评论

学校读者我要写书评

暂无评论

Agile Maneuvering control for Non-contact Satellite Platform 7th

Agile Maneuvering Control for Non-contact Satellite Platfor...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Li, Zheng Ma, Shuai Chen, Bin Hu, Qinglei Zheng, Jianying Tianmushan Laboratory Hangzhou310023 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Beijing Institute of Control Engineering Beijing100090 China

ISBN: (纸本)9789819733279

Dual-super satellite is a new type of spacecraft structure that separates the satellite platform and payload, and blocks the transmission of micro-vibrations from the platform through mechanical isolation to provide an ultra-precise and ultra-stable payload environment. However, the cable used for energy supply and communication of the payload has an impact on the pointing performance of the payload. In order to solve the uncertainty of the payload dynamics model brought by the flexible cable and the low-frequency bounded interference problem, this paper proposes a sliding mode adaptive control method for the payload under the influence of cables. A feedforward compensation algorithm based on partial state observer is designed for bounded disturbance of satellite platform. The control method presented in this paper ensures the pointing performance of the payload during agile maneuvers, and demonstrates robustness against model uncertainty and low-frequency disturbances caused by cables through simulation studies. © The Author(s) Hangzhou 310023, under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Satellites

来源：评论

学校读者我要写书评

暂无评论

Doppler Measurement-Based Positioning and Tracking Methods with External Radiation Radar 2

Doppler Measurement-Based Positioning and Tracking Methods w...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Liu, Weifeng He, Linqing Tian, Zhengwang Shaanxi University of Science and Technology School of Electrical and Control Engineering Xi'an China Hangzhou Dianzi University School of Automation Hangzhou China

ISBN: (纸本)9798331515669

This paper introduces a new approach for addressing the complex problem of Multi-target tracking in external radiation radar systems equipped with Multi-static Doppler measurements. Drawing from research on sensor arrays and mobile sensors, the method utilizes the Generalized Labelled Multi-Bernoulli (GLMB) filter to navigate the intricacies of Multi-target tracking across sensor arrays. The study validates the effectiveness of the GLMB and the computationally efficient Gibbs-GLMB filters in a setup involving three transmitters and one receiver. Experimental results, assessed with the Optimal Sub-Pattern Assignment (OSPA) metric, suggest that the Gibbs-GLMB filter accelerates computation while potentially compromising on measurement precision, which could lead to reduced accuracy in specific cases. The investigation also examines the influence of sensor geometry on tracking results, indicating that there is an association between tracking performance and sensor arrangement. © 2024 IEEE.

关键词： Radar target recognition

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fault-Tolerant control for Stochastic High-Order Fully Actuated Systems with Local Faults

Adaptive Fault-Tolerant Control for Stochastic High-Order Fu...

引用

2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 2023

作者： Liu, Xueqing Chen, Maoyin Sheng, Li Zhou, Donghua Tsinghua University Department of Automation Beijing China College of Control Science and Engineering Qingdao China Shandong University of Science and Technology College of Electrical Engineering and Automation Qingdao China

ISBN: (纸本)9798350337754

This paper portrays a class of local faults, whose basic characteristic is that the fault occurs only when the system is in a certain state domain. In engineering practice, such faults are prevalent and could affect efficiency greatly. To accurately tolerate these local faults, a novel control strategy is proposed. The globally asymptotical stability in probability is guaranteed by using time-varying gains on pre-divided fields. Finally, a numerical example is presented to demonstrate the effectiveness of the proposed framework. © 2023 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Human Following Robot Based on Object Detection for Aerospace Application 1

Human Following Robot Based on Object Detection for Aerospac...

引用

1st International Conference of Adisutjipto on Aerospace electrical engineering and Informatics, ICAAEEI 2024

作者： Sumari, Arwin Datumava Wahvudi Aryandika, Ahnaf Bagus Purnami, Ndaru Atmi Dermawan, Denny Syamsiana, Ika Noer State Polytechnic of Malang Cognitive Artificial Intelligence Research Group Department of Electrical Engineering Malang Indonesia Adisutjipto Institute of Aerospace Technology Electrical Engineering Study Program Yogyakarta Indonesia Adisutjipto Institute of Aerospace Technology Aerospace Navigation Instrumentation Control Automation and Robotics System Research Group Electrical Engineering Study Program Yogyakarta Indonesia Adisutjipto Institute of Aerospace Technology Electrical Engineering Study Program Aerosp. Digit. Syst. Microprocessor Microcontroller and Programmable Logic Devices Research Group Yogyakarta Indonesia

ISBN: (纸本)9798331507930

In this research, the Human Following Robot (HFR) prototype has been designed and implemented using YOLO v3-Tiny and Tensor Flow Lite on Raspberry Pi hardware named Rewang. The HFR Rewang is designed to assist aircraft technicians by bringing maintenance tool kits to aircraft shelters. Rewang's movement is based on a camera as a vision sensor following the movement of human entities. Image input is processed by YOLO v3-Tiny through the determination of the bounding box, the calculation of Euclidean Distance, and the determination of the pixel value of the camera as the basis of Rewang's movement which is regulated by an L298N driver motor that controls two Direct Current (DC) motors for the left and right wheels. The test results show that Rewang can move at an average speed of 0.18 m/s at 2 m with a travel time of 11 seconds with a light intensity of more than 250 lux. The minimum and maximum distance of object detection is as far as 120 cm and 400 cm, with an object detection accuracy of 95.8%. Rewang allows the HFR to have a larger carrying capacity to bring more complete aircraft maintenance tools and is prospective for other aerospace and general applications. © 2024 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

An Improved Hunger Games Search Algorithm-based Multi-peak MPPT control for PV System under Partial Shading

引用

Recent Patents on Mechanical engineering 2023年第4期16卷 261-273页

作者： Yi, Lingzhi Ma, Hao Wang, Yahui Liu, Jiangyong Shi, Hao Cheng, Siyue College of Automation and Electronic Engineering Xiangtan University Hunan Xiangtan411105 China Hunan Engineering Research Center of Multi-energy Cooperative Control Technology Hunan Xiangtan411105 China College of Electrical and Information Engineering Hunan University Hunan Changsha410082 China

Background: In photovoltaic power generation systems, partial shading may cause the PV array to mismatch, thus leading to multi-peak output characteristics, which makes the conventional Maximum Power Point Tracking (MPPT) algorithm easily fall into local extremes and cause power loss. Objective: The study aimed to accurately and quickly track the maximum power point of PV arrays in partial shading through swarm intelligence algorithms. Methods: Based on the above, a MPPT control algorithm based on Chaos Adaptive Hunger Games Search with Dynamic Lévy Mutation Strategy (CAHGSL) is proposed in this paper. By introducing an improved logistics chaos map initialization population, a nonlinear adaptive convergence factor and a dynamic Lévy mutation strategy enhance their ability to jump out of local extremes during multi-peak MPPT and improve their tracking speed and efficiency. Results: Under the three working conditions, the tracking efficiency of the MPPT algorithm proposed in this paper has been achieved by more than 99.5% in an average time of 0.152s, which is higher tracking efficiency compared to the PO, PSO, and HGS algorithms. Conclusion: The results show that the MPPT algorithm proposed in this paper can balance the tracking speed and efficiency with less power oscillation during the tracking process, and can ensure stable output after convergence. The method proposed in this paper is helpful to improve the output power of PV arrays under partial shading. © 2023 Bentham Science Publishers.

关键词： Efficiency

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

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

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：