检索结果-内蒙古大学图书馆

2023 China Automation Congress, CAC 2023

作者： Zeng, Tian Xiao, Li Peng, Gang Wang, Aoze Wang, Zhuo Sun, Zhigang School of Artificial Intelligence and Automation Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan China

ISBN: (纸本)9798350303759

The key for bulldozers to realize automatic operation in mine scenes is whether they can accurately identify and accurately segment the retaining walls, however, because the point cloud dataset of the mine site is too few, resulting in the deep learning-based identification and segmentation algorithm cannot be applied in this scene. At the same time, because of the rugged road surface of the mine scene, the existence of a lot of dust, numerous disturbances, retaining wall features are not obvious and other problems, the algorithms proposed by previous scholars are not perfect enough to solve the problem. We propose a point cloud recognition and segmentation algorithm based on clustering and evaluation function of integrated features. Ours firstly compensates the skew of the point cloud map with RANSAC and down samples the data by gridding the point cloud. Then reduces the influence of dust and truck materials in the scene by normal vector and variance information. Finally, screens out the candidate target class by density clustering, and identifies and segments the retaining wall by integrated feature. Our proposed algorithm is validated in several different real mine scenarios and the results show that ours has high accuracy and strong robustness. © 2023 IEEE.

关键词： Retaining walls

来源：评论

学校读者我要写书评

暂无评论

Adaptive cubature Kalman filter with the estimation of correlation between multiplicative noise and additive measurement noise

引用

Chinese Journal of Aeronautics 2022年第5期35卷 40-52页

作者： Quanbo GE Zhongcheng MA Jinglan LI Qinmin YANG Zhenyu LU Hong LI School of Electronics and Information Engineering Tongji UniversityShanghai 201804China Institute of Systems Science and Control Engineering School of AutomationHangzhou Dianzi UniversityHangzhou 310018China State Key Laboratory of Industrial Control Technology and the College of Control Science and EngineeringZhejiang UniversityHangzhou 310027China Jiangsu Key Laboratory of Meteorological Observation and Information Processing Nanjing University of Information Science and TechnologyNanjing 210044China Chinese Flight Test Establishment Xi’an 710089China

Mobile robots are often subject to multiplicative noise in the target tracking tasks,where the multiplicative measurement noise is correlated with additive measurement *** this paper,first,a correlation multiplicative measurement noise model is *** is able to more accurately represent the measurement error caused by the distance sensor dependence ***,the estimated performance mismatch problem of Cubature Kalman Filter(CKF)under multiplicative noise is *** improved Gaussian filter algorithm is introduced to help obtain the CKF algorithm with correlated multiplicative *** practice,the model parameters are unknown or inaccurate,especially the correlation of noise is difficult to obtain,which can lead to a decrease in filtering accuracy or even *** address this,an adaptive CKF algorithm is further provided to achieve reliable state estimation for the unknown noise correlation coefficient and thus the application of the CKF algorithm is ***,the estimated performance is analyzed theoretically,and the simulation study is conducted to validate the effectiveness of the proposed algorithm.

关键词： Adaptive CKF Correlated noise Estimation accuracy Multiplicative noise Performance analysis Target tracking

来源：评论

学校读者我要写书评

暂无评论

Generalized Self-Adaption Network for Domain Adaptation 2

Generalized Self-Adaption Network for Domain Adaptation

引用

2nd International Conference on Artificial Intelligence and intelligent information processing, AIIIP 2023

作者： Bian, Yongheng Ke, Xiao College of Computer and Data Science Fuzhou University Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing Fuzhou350116 China Key Laboratory of Spatial Data Mining & Information Sharing Ministry of Education Fuzhou350003 China

ISBN: (纸本)9798350371451

The purpose of domain adaptation is to transfer knowledge learned in the labeled source domain to unlabeled but related target domains without requiring a large number of target domain labels. The latest method of domain adaptation mainly adjusts the distribution of the source and target domains to adapt to the target domain. Despite significant success, when there are significant distribution differences between the source and target domains, the adaptability in the target domain still decreases, which may be due to insufficient exploration of domain specific features leading to domain offset issues. To address this issue, we propose the GSA-NET framework in this article. We designed an adversarial dropout method to improve the generalization performance of the model in the target domain by pushing the decision boundary away from the feature dense region. At the same time, in order to effectively match the distribution of advanced features across domains, we deploy feature adaptation modules before the classification layer, which can significantly reduce domain differences. Our experiments on two cross domain benchmarks, Office Home and Office-31, have shown that the proposed method is significantly superior to existing methods. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Representation of Semantic Word Embeddings Based on SLDA and Word2vec Model

引用

Chinese Journal of Electronics 2023年第3期32卷 647-654页

作者： TANG Huanling ZHU Hui WEI Hongmin ZHENG Han MAO Xueli LU Mingyu GUO Jin School of Computer Science and Technology Shandong Technology and Business University Co-innovation Center of Shandong Colleges and Universities: Future Intelligent Computing Key Laboratory of Intelligent Information Processing in Universities of Shandong Shandong Technology and Business University School of Information and Electronic Engineering Shandong Technology and Business University Information Science and Technology College Dalian Maritime University School of Computer and Information Technology Liaoning Normal University

To solve the problem of semantic loss in text representation, this paper proposes a new embedding method of word representation in semantic space called wt2svec based on supervised latent Dirichlet allocation(SLDA) and Word2vec. It generates the global topic embedding word vector utilizing SLDA which can discover the global semantic information through the latent topics on the whole document set. It gets the local semantic embedding word vector based on the Word2vec. The new semantic word vector is obtained by combining the global semantic information with the local semantic information. Additionally, the document semantic vector named doc2svec is generated. The experimental results on different datasets show that wt2svec model can obviously promote the accuracy of the semantic similarity of words,and improve the performance of text categorization compared with Word2vec.

关键词： Semantics Text categorization Resource management Task analysis

来源：评论

学校读者我要写书评

暂无评论

Non-Line-of-Sight Multipath Classification Method for BDS Using Convolutional Sparse Autoencoder with LSTM

引用

Tsinghua Science and Technology 2025年第1期30卷 68-86页

作者： Yahang Qin Zhenni Li Shengli Xie Bo Li Ming Liu Victor Kuzin School of Automation Guangdong University of Technologyand also with Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete ManufacturingGuangzhou 510006China School of Automation Guangdong University of TechnologyGuangdong Key Laboratory of IoT Information TechnologyGuangzhou 510006China 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Key Laboratory of Intelligent Information Processing and System Integration of IoTMinistry of EducationGuangzhou 510006China Department of Electronic and Computer Engineering Hong Kong University of Science and TechnologHong Kong 999077China Academician of Russian Engineering Academy Moscow Moscow 125009Russia

Multipath signal recognition is crucial to the ability to provide high-precision absolute-position services by the BeiDou Navigation Satellite System(BDS).However,most existing approaches to this issue involve supervised machine learning(ML)methods,and it is difficult to move to unsupervised multipath signal recognition because of the limitations in signal *** by an autoencoder with powerful unsupervised feature extraction,we propose a new deep learning(DL)model for BDS signal recognition that places a long short-term memory(LSTM)module in series with a convolutional sparse autoencoder to create a new autoencoder ***,we propose to capture the temporal correlations in long-duration BeiDou satellite time-series signals by using the LSTM module to mine the temporal change patterns in the time ***,we develop a convolutional sparse autoencoder method that learns a compressed representation of the input data,which then enables downscaled and unsupervised feature extraction from long-duration BeiDou satellite series ***,we add an l_(1/2) regularizer to the objective function of our DL model to remove redundant neurons from the neural network while ensuring recognition *** tested our proposed approach on a real urban canyon dataset,and the results demonstrated that our algorithm could achieve better classification performance than two ML-based methods(e.g.,11%better than a support vector machine)and two existing DL-based methods(e.g.,7.26%better than convolutional neural networks).

关键词： convolutional sparse autoencoder BeiDou Navigation Satellite System(BDS) long short-term memory(LSTM) multipath classification

来源：评论

学校读者我要写书评

暂无评论

Trajectory Planning of Robot Terminal Pose by Interpolation Method 38

Trajectory Planning of Robot Terminal Pose by Interpolation ...

引用

38th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2023

作者： Chen, Biao Hu, Shan Bing, Zhigang 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)9798350303636

In order to improve the stability of the robot at work, this paper adds an insertion point between the end of the robot and the next target point, and changes the original linear trajectory to a new trajectory planned by interpolation method. The simulation experiment is carried out in MATLAB software. The interpolation method curve is compared with the linear curve. The optimization results show that the velocity and acceleration curves under the interpolation method become more gentle, which verifies the effectiveness of the method. © 2023 IEEE.

关键词： interpolation method linear posture robot

来源：评论

学校读者我要写书评

暂无评论

Forward and Inverse Solution Analysis of 3-URU Parallel Mechanism 5

Forward and Inverse Solution Analysis of 3-URU Parallel Mech...

引用

5th International Symposium on Robotics and intelligent Manufacturing Technology, ISRIMT 2023

作者： Wang, Yanchao Zhang, Hongxin Tian, Liguo Xie, Zikang Sun, Miao Tianjin University of Technology and Education Tianjin300222 China Tianjin Key Laboratory of Information Sensing & Intelligent Control Tianjin300222 China

ISBN: (纸本)9798350316087

This paper introduces 3-URU, a parallel mechanism developed independently. Based on spiral theory, the degree of freedom of the mechanism is analyzed, and it is confirmed that the mechanism can realize three-dimensional translation. An improved Denavit-Hartenberg (DH) method was used to describe the operation space of the branch chain of the mechanism, and the coordinate transformation matrix of the branch chain was established. The joint Angle and the length of the connecting rod of the parallel mechanism were converted into the position and attitude information of the end, and the forward and inverse solution formula was derived. Finally, the kinematics model of the parallel mechanism is built by simulation and the correctness of the forward and inverse solution formula is verified. © 2023 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

A Physiological Signal Emotion Recognition Method Based on Domain Adaptation and Incremental Learning 1

A Physiological Signal Emotion Recognition Method Based on D...

引用

1st International Conference on Cyber-Energy Systems and intelligent Energy, ICCSIE 2022

作者： Li, Junnan Wang, Xiaoping Huazhong University of Science and Technology The School of Artificial Intelligence and Automation The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China

ISBN: (纸本)9781665452151

Temporal concept shift (TCS) is an unavoidable problem in physiological signal-based emotion recognition tasks, i.e., the data distribution of physiological signals is constantly changing over time, which gradually degrades the model accuracy. To this end, we propose a method based on a combination of domain adaptation and incremental learning to reduce the impact of temporal concept drift. In this paper, domain adaptation is used to reduce the distribution differences and incremental learning is used to prevent the learned knowledge from being forgotten. Finally, we validate the effectiveness of our approach on two real datasets. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning with Hierarchical Graph Structure for Flexible Job Shop Scheduling

Reinforcement Learning with Hierarchical Graph Structure for...

引用

2023 International Annual Conference on Complex Systems and intelligent Science, CSIS-IAC 2023

作者： Zhang, Linli Li, Dewei Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Dept. of Automation Shanghai China

ISBN: (纸本)9798350309003

The flexible job shop scheduling problem (FJSP) is a NP-hard combinatorial optimization challenge, having extensive real-world industrial applications. For a given instance of FJSP, a scheduling solution need to be devised, which entails determining the appropriate machine for each operation and establishing the sequence in which operations are processed on a given machine, all while adhering to certain constraints. However, many of the methods are lacking in flexibility, unable to cope effectively with multi-relational operations and machine selection scenarios. This can make the representation of state and action challenging in practice, leading to a significant increase in decision complexity. This paper considers these issues by a hierarchical graph structure with a model that synergistically integrates two modules: the environment and the decision module. The environment module is characterized by a hierarchical graph neural network which defines the multi-relational FJSP instance where all machine and operation data are stored. The decision module incorporates the Actor-Critic networks, designed to train reasoning strategies and enhance decision performance, based on the states and rewards provided at each step by the environment module. The objective is to derive optimal scheduling strategies through interactions between the decision agent and the environment, targeting the minimum resources consumed or makespan. Numerical simulations validate the efficacy of the proposed approach, showing its potential to yield superior results and thereby enhance performance. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Automatic Schizophrenia Detection from Scalp EEG Using CNN with Wide Convolutional Kernel and ELM 5

Automatic Schizophrenia Detection from Scalp EEG Using CNN w...

引用

5th Asia Symposium on Image processing, ASIP 2023

作者： Wei, Chun Qin, Yingmei Liu, Jing Jiang, Lijie Che, Yanqiu Tianjin University of Technology and Education School of Automation and Electrical Engineering Tianjin Key Laboratory of Information Sensing & Intelligent Control Tianjin China

ISBN: (纸本)9798350323429

Detection of schizophrenia is of great significance in clinical practice. In conventional machine learning methods, manual feature extraction is required, which is a hard and time-consuming task. This paper proposes a hybrid model consisting of a convolutional neural network (CNN) with a wide convolution kernel and an extreme learning machine (ELM). By changing the size of the convolution kernel to form a suitable wide convolution kernel, and automatically extracting and optimizing the features of the scalp electroencephalogram (EEG), the performance of the model is effectively improved and accurate detection of schizophrenia is achieved. The input of this model is the original multi-channel EEG picture after short-time Fourier transform, and the output are two types of classification labels for schizophrenia and healthy people. In the end, the detection accuracy of schizophrenia reached 95.59%. This model has a powerful advantage in detecting schizophrenia. © 2023 IEEE.

关键词： Electroencephalography

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：