检索结果-内蒙古大学图书馆

8th International Conference on control Science and systems Engineering, ICCSSE 2022

作者： Tang, Jianhui Zhang, Pan Wu, Jundong Wang, Yawu School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9781665484138

Magnetically-controlled soft microrobots have great application prospects because of small size, flexible motion and wireless control. In this paper, a magnetically-controlled soft microrobot is designed and fabricated. In order to achieve its path-following control, two open-loop control strategies and a closed-loop one are developed. Especially, for the closed-loop control strategy, we present the image processing method and the pure pursuit algorithm, where the former is used to obtain the position and posture of the microrobot required for the latter. Finally, the developed open-loop and closed-loop control strategies are verified by carrying out the experiments. These methods are promising in numerous applications because of the ease of implementation. © 2022 IEEE.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Trajectory Prediction by Modeling the Interactions using Social LSTM Extensions

Pedestrian Trajectory Prediction by Modeling the Interaction...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Si, Zeze Zhao, Hongxia Tang, Haina Zhu, Fenghua Lv, Yisheng Lu, Hao Institute of Autamation Chinese Academy of Sciences State Key Laboratory for Management and Control of Complex Systems Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Qingdao Academy of Intelligent Industries Qingdao266000 China

ISBN: (纸本)9781665465335

In many driving situations, human mobility is an important topic in trajectory prediction. Considering the pedestrian trajectory as a sequence generative task, a prediction algorithm based on Social Long Short-Term Memory (Social LSTM) is implemented. In order to simulate the social interaction between pedestrians, Social Pooling (S-Pooling) is used to aggregate the hidden state of pedestrians, while the attention mechanism is utilized to aggregate information differently according to the importance of surrounding pedestrians. Furthermore, Convolutional Neural Networks (CNN) is introduced into Social LSTM model to consider both the interaction between people and the characteristic of scene scale in the prediction process. Experiments are carried out against baseline methods, and the results demonstrated that combining Social LSTM with attention mechanism or CNN can improve the performance of pedestrian trajectory prediction. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Double Domain Guided Real-Time Low-Light Image Enhancement for Ultra-High-Definition Transportation Surveillance

arXiv

引用

arXiv 2023年

作者： Qu, Jingxiang Liu, Ryan Wen Gao, Yuan Guo, Yu Zhu, Fenghua Wang, Fei-Yue The School of Navigation The State Key Laboratory of Maritime Technology and Safety Wuhan University of Technology Wuhan430063 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Real-time transportation surveillance is an essential part of the intelligent transportation system (ITS). However, images captured under low-light conditions often suffer the poor visibility with types of degradation, such as noise interference and vague edge features, etc. With the development of imaging devices, the quality of the visual surveillance data is continually increasing, like 2K and 4K, which has more strict requirements on the efficiency of image processing. To satisfy the requirements on both enhancement quality and computational speed, this paper proposes a double domain guided real-time low-light image enhancement network (DDNet) for ultra-high-definition (UHD) transportation surveillance. Specifically, we design an encoder-decoder structure as the main architecture of the learning network. In particular, the enhancement processing is divided into two subtasks (i.e., color enhancement and gradient enhancement) via the proposed coarse enhancement module (CEM) and LoG-based gradient enhancement module (GEM), which are embedded in the encoder-decoder structure. It enables the network to enhance the color and edge features simultaneously. Through the decomposition and reconstruction on both color and gradient domains, our DDNet can restore the detailed feature information concealed by the darkness with better visual quality and efficiency. The evaluation experiments on standard and transportation-related datasets demonstrate that our DDNet provides superior enhancement quality and efficiency compared with the state-of-the-art methods. Besides, the object detection and scene segmentation experiments indicate the practical benefits for higher-level image analysis under low-light environments in ITS. The source code is available at https://***/QuJX/DDNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Real-Time Driver Distraction Detection Using Lightweight Convolution Neural Network with Cheap Multi-scale Features Fusion Block 17th

Real-Time Driver Distraction Detection Using Lightweight Con...

引用

17th Chinese Intelligent systems Conference, CISC 2021

作者： Li, Yuanyuan Xu, Peng Zhu, Zhiqin Huang, Xinghua Qi, Guanqiu Chongqing University of Posts and Telecommunications Chongqing400065 China Key Laboratory of Complex System Safety and Control Ministry of Education Chongqing University Chongqing400044 China Computer Information Systems Department Buffalo State College BuffaloNY14222 United States

ISBN: (纸本)9789811663239

Degraded driving performance is closely related to distracted driving behavior. Therefore, in this paper we introduce a fast and accurate convolution neural network (CNN) architecture named CMFFNet, which is designed for the edge devices with limited computational resources and application scenario of detecting driver distraction. CMFFNet is built on a multi-branch architecture that uses CMFF blocks to guarantee efficiency. CMFF block is based on depth-wise separable convolution, which consists of a CMFF module, a multi-branch structure fuses filtered multi-scale spatial information to enhance feature representation capability, followed by a MAPGC bottleneck, utilizing two point-wise group convolutions and a channel shuffle operation to implement efficient channel projection. Compare with recently proposed lightweight CNNs, CMFFNet can achieve better performance on StateFarm’s Dataset, e.g. higher accuracy (absolute 5.5%) and lower latency (about 18 ms) compared with MobileNetV3-Large. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Anti-sway control of Crane Based on Equivalent-Input-Disturbance Method and Feedback Linearization

Anti-sway Control of Crane Based on Equivalent-Input-Disturb...

引用

第42届中国控制会议

作者： Shuhan He Gang Yu Yongbo Li Fengyu Zhang Wangyong He School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation Complex Systems Huaxin Cement Technology Management (Wuhan) Co. Ltd

The anti-sway issue with crane systems is discussed in this essay. Because cranes are undriveable and nonlinear,implementing anti-sway controllers becomes much more challenging. This work suggests a crane anti-sway controller that uses feedback linearization(FL) in conjunction with the Equivalent-Input-Disturbance(EID) technique to address the issues. to reduce the problem that the feedback linearization largely relies on the model's *** crane system is first treated as a linear system, after which the unmodeled disturbances, nonlinear components, and external disturbances of the system are treated as the total disturbances of the system, and the effects of these disturbances are then compensated for using disturbance estimation. Finally, simulation experiments confirm that the maximum steady-state fluctuations of the position and angle of the anti-sway controller based on the equivalent input disturbance method and the feedback linearization method are 14 and 6.85percent, respectively, of those estimated without *** demonstrates the potency of this approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Trajectory Tracking Algorithm Based on Interior Point Method for A Class of Mobile Manipulators

A Trajectory Tracking Algorithm Based on Interior Point Meth...

引用

Chinese Automation Congress (CAC)

作者： Xuechen Rao Yahui Gan Xiaoteng Wang School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education NanJing China

At present, due to the high redundancy and strong coupling characteristics of mobile manipulator systems, there are few and in-depth studies on coordinated motion planning. Aiming at the above problems, this paper proposes a coordinated control algorithm that can track the desired trajectory of the end-effector based on a class of 5-DOF mobile manipulators. The algorithm takes the power consumption and trajectory stability of the entire system as the optimization objectives, and sets the function of the selected optimization objective on the desired trajectory, and performs optimization based on the interior point method of convex optimization to converge to the optimal solution faster. Finally, the system is simulated to verify the correctness and effectiveness of the control algorithm.

关键词： Smoothing methods Trajectory tracking Simulation Robot kinematics Redundancy Mathematical models End effectors

来源：评论

学校读者我要写书评

暂无评论

Oilwell Downhole RFID Reader based on Discrete Components

Oilwell Downhole RFID Reader based on Discrete Components

引用

2021 International Conference on Signal Processing and Communication Technology, SPCT 2021

作者： Liu, Xiaokun Zhu, Jixuan School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (数字)9781510653344

ISBN: (纸本)9781510653337

RFID (Radio Frequency Identification) is expected to provide a new way for the efficient and low-cost control of oilwell downhole tools, and bring huge economic benefits. However, the RF (radio frequency) base station chips on the market could not withstand the high temperature of downhole. In this paper, discrete components are used to build RF front-end circuits to realize the drive and demodulation functions of RF base station chips. The circuit parameters are adjusted and optimized through circuit simulation. Then, the software and hardware design of the downhole reader are accomplished. Finally, experimental results show that the proposed downhole reader based on discrete components can successfully demodulate and read the tag data. © 2022 SPIE.

关键词： Circuit simulation

来源：评论

学校读者我要写书评

暂无评论

"Why not looking backward?" a robust two-step method to automatically terminate Bayesian optimization 23

"Why not looking backward?" a robust two-step method to auto...

引用

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Shuang Li Ke Li Wei Li Control and Simulation Center Harbin Institute of Technology China and National Key Laboratory of Modeling and Simulation for Complex Systems China Department of Computer Science University of Exeter Exeter UK

Bayesian optimization (BO) is a powerful method for tackling expensive blackbox optimization problems. As a sequential model-based optimization strategy, BO iteratively explores promising solutions until a predetermined budget, either iterations or time, is exhausted. The decision on when to terminate BO significantly influences both the quality of solutions and its computational efficiency. In this paper, we propose a simple, yet theoretically grounded, two-step method for automatically terminating BO. Our core concept is to proactively identify if the search is within a convex region by examining previously observed samples. BO is halted once the local regret within this convex region falls below a predetermined threshold. To enhance numerical stability, we propose an approximation method for calculating the termination indicator by solving a bilevel optimization problem. We conduct extensive empirical studies on diverse benchmark problems, including synthetic functions, reinforcement learning, and hyperparameter optimization. Experimental results demonstrate that our proposed method saves up to ≈ 80% computational budget yet is with an order of magnitude smaller performance degradation, comparing against the other peer methods. In addition, our proposed termination method is robust in terms of the setting of its termination criterion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition Based on Clustering Assistance

Speech Emotion Recognition Based on Clustering Assistance

引用

2022 Chinese Automation Congress, CAC 2022

作者： Peng, Zhi-Kun Liu, Zhen-Tao Han, Meng-Ting China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9781665465335

Speech emotion recognition (SER) is a key technology to achieve natural human-computer interaction. The development of SER is significantly influenced by the scale of the sample. In recent years, the study of SER has been intensified by introducing data augmentation methods. However, most of these methods directly augment the sample data scale, neglecting the rational analysis and utilization of the feature distribution of samples. In this paper, we propose a new framework for SER based on clustering assistance, which can utilize the feature distribution information of the sample data directly and effectively. It considers the sample proportion of each emotion category in the clusters obtained by clustering, converts it into a probability score, which is called the clustering emotion probability score, and fuses it with the emotion probability score from the simple classification model according to different fusion weighting factors. We evaluated the proposed method with the baseline model on the IEMOCAP dataset. Experimental results show that our method achieves better results than the baseline model in terms of both weighted and unweighted accuracy. © 2022 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

A Multi-Channel Adaptive Cancellation Algorithm for Active Suppression of Motion-Induced Noise in Magnetic Antennas

A Multi-Channel Adaptive Cancellation Algorithm for Active S...

引用

On-Line Conference (ONCON), Industrial Electronics Society Annual

作者： Mingyi Hu Junlei Song Yi Yan Ying Liu Xiaoxue Li Kaifeng Dong Fang Jin Wenqin Mo Yajuan Hui School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

ISBN: (数字)9798331540319

ISBN: (纸本)9798331540326

During super low frequency (SLF) magnetic induction communication, the sensitive antenna carried by autonomous underwater vehicles (AUVs) is highly susceptible to vibration, resulting in a large amount of noise in communication signals, which seriously affects communication performance. The type of motion-induced noise typically exhibits randomness and nonlinearity. Based on the strong correlation between the motion-induced noise and the antenna's vibration signal, we propose a multi-channel normalized least mean square (MCNLMS) algorithm. The algorithm utilizes the six degrees of freedom vibration acceleration information from both ends of the magnetic antenna as the reference signal input for the canceller, providing more comprehensive information related to motion-induced noise than the single-channel adaptive noise cancellation algorithm. Experimental results indicate that the MCNLMS algorithm demonstrates effective suppression of the motion-induced noise, achieving an average reduction of approximately 7 dB within the 160–170 Hz communication band. Additionally, it exhibits improved stability and faster convergence.

关键词： Vibrations Industrial electronics Correlation Adaptive arrays Magnetic noise Approximation algorithms Noise cancellation Antennas Magnetic susceptibility Convergence

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：