检索结果-内蒙古大学图书馆

第三十九届中国控制会议

作者： Hengyu Huang Min Wu Sike Ma Luefeng Chen Chengda Lu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

The study of bit-rock interaction model is essential to describe the rock breaking process. In practice, it is difficult to get downhole measurement, and the downhole rock-breaking data is difficult to obtain. Therefore, this paper uses finite element simulation to obtain the kinetic data of bit-rock interaction, based on the analysis and comparison of existing models, an effective analysis method is provided for bit-rock interaction. Firstly, by using the Drucker-Prager rock criterion, actual bit and rock parameters, we develop the finite element bit-rock interaction experiments, and we obtain the data of rotating speed, rate-ofpenetration, weight-on-bit. Then, based on multiple nonlinear regression method, we identify the existing Young model, Jorden and Shirley model, Richard model, Ritto model parameters. Through the analysis and comparison of identification effects and characteristics of each model, we obtain the relationship among parameters of the bit-rock interaction.

关键词： Bit-rock interaction Weight on bit Finite element method Parameter identification

来源：评论

学校读者我要写书评

暂无评论

Wind power prediction based on multiple support vector machines

Wind power prediction based on multiple support vector machi...

引用

第三十九届中国控制会议

作者： Min Ding Zhe Chen School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

Wind power forecasting is of great significance in grid dispatching. This paper proposes a statistical model based on feature classification least squares support vector machine, which can predict short-term wind power. First of all, this paper analyzes the data of an actual power plant. After analyzing the data, it is found that there is uncertainty in the existence of multiple powers at the same wind speed. Then, in order to resolve this uncertainty, the wind speed and wind speed trend samples are density clustered according to the DBSCAN method. The clustering results are divided into several categories, and the samples of different categories are modeled by least squares support vector machines. Finally, the effectiveness of the proposed prediction model is compared with that of unclassified samples through the prediction model. Simulation results show that the designed model has higher prediction power accuracy.

关键词： Wind power prediction feature classification least squares support vector machine

来源：评论

学校读者我要写书评

暂无评论

Spectral Reflectance Reconstruction from Camera Responses by Adaptively Constructing Weight Matrix Combining Colorimetric and Lightness Similarities

Spectral Reflectance Reconstruction from Camera Responses by...

引用

第三十九届中国控制会议

作者： Xin Wang Hui Jiang Jing-Jing Zhang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

An improved method for spectral reflectance reconstruction from digital camera raw RGB responses of pixels is proposed by adaptively weighting training samples considering colorimetric and lightness similarities. The proposed method was based on an adaptive local weighted linear regression model by using a Gaussian function in weighting matrix *** novelty of our method is designing the weighting matrix combining colorimetric and lightness similarities. The proposed method was tested using two different standard color charts, with a simulated digital camera based on the camera spectral sensitivity. Experimental results indicate that the proposed method exhibits considerable improvements in terms of the spectral reflectance and the colorimetric values in comparison with existing methods.

关键词： Spectral Reflectance Reconstruction Lightness Similarity Pseudo Inverse

来源：评论

学校读者我要写书评

暂无评论

Novel Synchronization Criteria of Chaotic Lur’e systems With Time-varying Delayed Feedback PD control

Novel Synchronization Criteria of Chaotic Lur’e Systems Wit...

引用

第三十九届中国控制会议

作者： Run-Zhe Tao Ying Zhang Lei-Chao Pang Xing-Chen Shangguan Dan-Yun Li School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

This paper is concerned with the problem of asymptotical synchronization of chaotic Lur’e systems controlled via PD controller with time-varying delay. Firstly, a new Lyapunov-Krasovskii functional（LKF） with more information of time-varying delay is constructed. Then, by applying the Wirtinger-based integral inequality and the extended reciprocally convex combination lemma（RCCL）, a new synchronization criterion for time-varying delay is obtained, and a less conservatism corollary for the constant delay is established by weakening some terms of LKF. Finally, a numerical example is given to show the better performance of the proposed criteria.

关键词： Synchronization Chaotic Lur’e systems Time-varying delay PD feedback control

来源：评论

学校读者我要写书评

暂无评论

Feature Matching Algorithm Based on SURF and Lowes Algorithm

Feature Matching Algorithm Based on SURF and Lowes Algorithm

引用

第三十九届中国控制会议

作者： Xiaoqi Wang Weihua Cao Chaolong Yao Hang Yin School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

Feature extraction and matching of images is a key step in 3D reconstruction, and its accuracy directly affects the accuracy of 3D reconstruction. In this paper, aiming at the mismatch caused by the high similarity between screws, proposes a feature matching algorithm based on median filtering, Lowes algorithm and scale-invariant feature transform(SURF), called M-L-SURF algorithm. First, the median filtering is performed on the screw image to remove noise, then the SURF algorithm is used for feature extraction and matching, and finally, the Lowe's algorithm is used to filter the matching results. The results of experiments show that the M-L-SURF algorithm can achieve a 97.4% correct rate of screw image matching. The matching results obtained in this paper can be better applied to the subsequent work of 3D reconstruction.

关键词： Median filtering SURF Feature matching Lowes algorithm

来源：评论

学校读者我要写书评

暂无评论

Distributed Resilient State Estimation for Time-Varying Fractional-Order Discrete complex Networks with Encoding-Decoding Scheme

Distributed Resilient State Estimation for Time-Varying Frac...

引用

Chinese control Conference (CCC)

作者： Yu Chen Jun Hu Jiaxing Li Aozhan Zhou Hui Yu Department of Applied Mathematics Harbin University of Science and Technology Harbin China Heilongjiang Provincial Key Laboratory of Optimization Control and Intelligent Analysis for Complex Systems Harbin University of Science and Technology Harbin China School of Automation Harbin University of Science and Technology Harbin China

In this paper, the distributed state estimation method with resilient attenuation feature is proposed for time-varying fractional-order complex networks under encoding-decoding mechanism. The encoding-decoding-induced dynamic errors for distinct nodes are characterized by the truncated Gaussian distributions. In order to compensate the effects induced by encoding-decoding scheme, the variances of encoding-decoding-induced dynamic errors are considered in process of designing the resilient distributed estimation algorithm. In particular, the upper bounds of updated estimation error covariances are derived firstly. Subsequently, the upper bounds are minimized by constructing the gain matrices at each sampling instant. Besides, a sufficient condition is provided to guarantee the boundedness of estimation error dynamics in the mean-square sense. Finally, the validity of distributed resilient state estimation scheme is demonstrated by a simulation example.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Composite Cost-Sensitive Neural Network for Imbalanced Classification

A Composite Cost-Sensitive Neural Network for Imbalanced Cla...

引用

第三十九届中国控制会议

作者： Lei Chen Yuan Zhu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

Imbalanced data with skewed class distributions and different misclassification costs is common in many real-world applications. Traditional classification approach does not work well for imbalanced data, because they assume equal costs for each class. To deal with this problem, cost-sensitive approaches assign different misclassification costs for different classes without disrupting the true original distributions of samples. However, due to lack of prior knowledge, the misclassification costs are usually unknown and hard to choose in practice. Whats more, even instances in the same class may have different misclassification costs. As an extension of class-dependent costs, this paper presents a composite cost-sensitive deep neural network(CCS-DNN) for imbalanced classification. A specifically-designed cost-sensitive matrix, which is composed of exampledependent costs and class-dependent costs, is embedded into the loss function to improve the classification performance. And the parameters of both the cost-sensitive matrix and the network are jointly optimized during training. The results of comparative experiments on some benchmark datasets indicate that the CCS-DNN performs better than other baseline methods.

关键词： Cost-sensitive Learning Composite Costs Imbalanced Classification Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Forget less,count better:a domain-incremental self-distillation learning benchmark for lifelong crowd counting

引用

Frontiers of Information Technology & Electronic Engineering 2023年第2期24卷 187-202页

作者： Jiaqi GAO Jingqi LI Hongming SHAN Yanyun QU James ZWANG Fei-Yue WANG Junping ZHANG Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-inspired Intelligence Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai 201210China School of Information Science and Technology Xiamen UniversityXiamen 361005China College of Information Sciences and Technology the Pennsylvania State UniversityUniversity ParkPA 16802USA State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Crowd counting has important applications in public safety and pandemic control.A robust and practical crowd counting system has to be capable of continuously learning with the newly incoming domain data in real-world scenarios instead of fitting one domain ***-the-shelf methods have some drawbacks when handling multiple domains:(1)the models will achieve limited performance(even drop dramatically)among old domains after training images from new domains due to the discrepancies in intrinsic data distributions from various domains,which is called catastrophic forgetting;(2)the well-trained model in a specific domain achieves imperfect performance among other unseen domains because of domain shift;(3)it leads to linearly increasing storage overhead,either mixing all the data for training or simply training dozens of separate models for different domains when new ones are *** overcome these issues,we investigate a new crowd counting task in incremental domain training setting called lifelong crowd *** goal is to alleviate catastrophic forgetting and improve the generalization ability using a single model updated by the incremental ***,we propose a self-distillation learning framework as a benchmark(forget less,count better,or FLCB)for lifelong crowd counting,which helps the model leverage previous meaningful knowledge in a sustainable manner for better crowd counting to mitigate the forgetting when new data arrive.A new quantitative metric,normalized Backward Transfer(nBwT),is developed to evaluate the forgetting degree of the model in the lifelong learning *** experimental results demonstrate the superiority of our proposed benchmark in achieving a low catastrophic forgetting degree and strong generalization ability.

关键词： Crowd counting Knowledge distillation Lifelong learning

来源：评论

学校读者我要写书评

暂无评论

An Improved Faster-RCNN Algorithm for Object Detection in Remote Sensing Images

An Improved Faster-RCNN Algorithm for Object Detection in Re...

引用

第三十九届中国控制会议

作者： Rui Liu Zhihua Yu Daili Mo Yunfei Cai School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

Compared with conventional object detection, remote sensing images are taken from the air. The angle of view is not fixed and the object direction, scale which compared with conventional object detection algorithm are quite different. These factors lead to the object detection in remote sensing images difficult. To solve the above problems, this paper proposes an improved remote sensing object detection method based on Faster-RCNN algorithm. Using online difficult example mining technology,feature pyramid structure, Soft-NMS technology, and RoI-Align technology to enhance the capabilities of Faster-RCNN in small object detection task in remote sensing images. The algorithm in this paper was evaluated on the RSOD-Dataset, compared with the original Faster-RCNN algorithm, the proposed algorithm improves the detection accuracy and training convergence speed,which shows that these improvements are of great significance to the object detection algorithm of remote sensing images.

关键词： Remote Sensing Images Faster-RCNN Small Object Detection

来源：评论

学校读者我要写书评

暂无评论

A Novel Eye State Detection Method via WBCNN

A Novel Eye State Detection Method via WBCNN

引用

第三十九届中国控制会议

作者： Zhen-Tao Liu Si-Han Li Cheng-Shan Jiang Dan-Yun Li Man Hao School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

In the field of face recognition and analysis, eye state detection is an essential step, which is the prerequisite and breakthrough of drowsiness estimation and auxiliary driving. This paper presents an eye state detection method based on Weight Binarization Convolution Neural Network（WBCNN）. The weight of the network is constrained by binarization, which can limit the weight to 1 or-1, reducing the power dissipation and internal storage considerably. The human eye state features which can be extracted by convolution neural network effectively, and binary network not only contributes to reducing the storage size of the model, but also accelerates the computation. Experiments on eye state detection were conducted on the Closed Eyes in the wild（CEW） and FER2013 Databases, from which the results show that our method achieved average test accuracy of 97.41%on CEW. We used the FER2013 facial expression database for pre-training, which can make up for the lack of CEW training samples. The computational speed of non-binary is slower than binary network. Moreover, less storage capacity is required by our method.

关键词： Eye state detection Convolution neural network Image processing Weight Binarization

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：