检索结果-内蒙古大学图书馆

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： Wei Liu Mingqiang Gao Shuaidong Duan Longsheng Wei School of Automation China University of Geosciences 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: (纸本)9781665446006

With the development of artificial intelligence, the anomaly detection plays more and more important role in security monitoring field. Because it is difficult to label abnormal data, most of the supervised methods consumed a lot of manpower and obtained low performance and generality. Inspired by this motivation, this paper proposes a semi-supervised method for anomaly detection in video frames based on GAN (Generative Adversarial Network), in which only normal data was used as the training sample. The quality gap between the predicted frame and the ground truth is used as the basis to determine whether it is abnormal. Moreover, the mathematical morphology approach was adopted to locate the anomaly area in the frames. Experiments show that our method can successfully detect abnormal frames in video and can also locate the area where abnormal behavior occurs in frames.

关键词： Training Conferences Morphology Generative adversarial networks Feature extraction Security Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Chaos and fracture of a stiff thin film on a finite-thickness bi-layer substrate under an axial periodic load

Chaos and fracture of a stiff thin film on a finite-thicknes...

引用

第八届国际振动工程会议

作者： Haohao Bi Bo Wang Bohan Zhang Chao Xu Zichen Deng Department of Applied Mathematics Northwestern Polytechnical University Department of Engineering Mechanics Northwestern Polytechnical University Ministry of Industry and Information Technology Key Laboratory of Dynamics and Control of Complex Systems Northwestern Polytechnical University

To improve the robustness of the film-substrate type's stretchable electronics, an intermediate layer is introduced. However, due to the introducing of the intermediate layer between the film layer and the soft substrate layer to form tri-layer structure, the dynamic behaviour of this structure would be influenced. In this paper, the chaos and fracture of the tri-layer structure under an axial periodic load are investigated. Firstly, taking the shear stress between the film and the intermediate layer, and the deformation of the intermediate layer and the substrate layer into account, a more accurate analytical model has been established. Based on the Lagrange equation, the governing equation of the tri-layer structure has been derived. Then, the symplectic Runge-Kutta method is used to solve the corresponding equation. Numerical examples are performed to discuss the influences of the Young's modulus and thickness of the intermediate layer on the chaos and fracture of the tri-layer structure. These obtained results would be helpful for the design of higher reliability of the film/substrate-type stretchable electronics.

关键词： Chaos and fracture of a stiff thin film on a finite-thickness bi-layer substrate under an axial periodic load

来源：评论

学校读者我要写书评

暂无评论

Radar Vital Signs Detection Method Based on Variational Mode Decomposition and Wavelet Transform

Radar Vital Signs Detection Method Based on Variational Mode...

引用

Chinese Automation Congress (CAC)

作者： Shaopeng Ma Wei Xue Kehui Chen Zexi Wang School of Automation China University of Geosciences 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: (纸本)9781665426480

To deal with noise interference in frequency modulated continuous wave (FMCW) radar vital signs and the interference of breathing harmonics on the heartbeat signal, a vital signs detection method based on variational mode decomposition (VMD) and wavelet transform is proposed. First, VMD is applied to decompose the vital signs into a series of intrinsic mode function (IMF) components. Then, the IMF components with spectral peaks in the frequency range of breathing and heartbeat are selected to reconstruct the breathing and heartbeat signals respectively. Finally, the wavelet transform threshold method is used to remove the noise in the breathing and heartbeat signals. The experimental results show the proposed method can overcome the influence of breathing harmonics, accurately extract the breathing and heartbeat signals, and effectively improve the signal-to-noise ratio and detection accuracy of heart rate.

关键词： Frequency modulation Continuous wavelet transforms Automation Heart beat Radar detection Radar Interference

来源：评论

学校读者我要写书评

暂无评论

Incomplete Multi-view Clustering for Single cell RNA Sequencing Data

Incomplete Multi-view Clustering for Single cell RNA Sequenc...

引用

Chinese Automation Congress (CAC)

作者： Tijian Zhu Yuan Zhu Chuan-Ke Zhang 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

ISBN: (纸本)9781665426480

With the rapid development of sequencing technology, researchers can obtain a large number of single cell RNA sequencing (scRNA-seq) data which is useful for analysis of cell fate decision and growth process at individual cell resolution. But due to the limitations of sequencing technology, the data acquired has dropouts which may affect the results of down-steam analysis. Therefore, many algorithms have been proposed to impute the data before clustering, here in, imputation and clustering are considered as two separate processing stage. In this paper, we adopt a clustering algorithm—Incomplete Multiple Kernel k-means Clustering with Mutual Kernel Completion (MKKM-IK-MKC) to analyze scRNA-seq data. It unifies imputation and clustering into a process. Comparing with some existing "two stage" (imputation +clustering) algorithms, the experimental results on five scRNA-seq datasets from various species demonstrate the effective performance of our new proposed method.

关键词： Dimensionality reduction Sequential analysis Automation RNA Clustering algorithms Optimization methods Iterative methods

来源：评论

学校读者我要写书评

暂无评论

S4TP: Social-Suitable and Safety-Sensitive Trajectory Planning for Autonomous Vehicles

arXiv

引用

arXiv 2024年

作者： Wang, Xiao Tang, Ke Dai, Xingyuan Xu, Jintao Du, Quancheng Ai, Rui Wang, Yuxiao Gu, Weihao Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education Anhui University Hefei230031 China Haomo Technology Co. Ltd. Beijing100192 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Qingdao Academy of Intelligent Industries Qingdao266114 China The School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

In public roads, autonomous vehicles (AVs) face the challenge of frequent interactions with human-driven vehicles (HDVs), which render uncertain driving behavior due to varying social characteristics among humans. To effectively assess the risks prevailing in the vicinity of AVs in social interactive traffic scenarios and achieve safe autonomous driving, this article proposes a social-suitable and safety-sensitive trajectory planning (S4TP) framework. Specifically, S4TP integrates the Social-Aware Trajectory Prediction (SATP) and Social-Aware Driving Risk Field (SADRF) modules. SATP utilizes Transformers to effectively encode the driving scene and incorporates an AV’s planned trajectory during the prediction decoding process. SADRF assesses the expected surrounding risk degrees during AVs-HDVs interactions, each with different social characteristics, visualized as two-dimensional heat maps centered on the AV. SADRF models the driving intentions of the surrounding HDVs and predicts trajectories based on the representation of vehicular interactions. S4TP employs an optimization-based approach for motion planning, utilizing the predicted HDVs’ trajectories as input. With the integration of SADRF, S4TP executes real-time online optimization of the planned trajectory of AV within low-risk regions, thus improving the safety and the interpretability of the planned trajectory. We have conducted comprehensive tests of the proposed method using the SMARTS simulator. Experimental results in complex social scenarios, such as unprotected left-turn intersections, merging, cruising, and overtaking, validate the superiority of our proposed S4TP in terms of safety and rationality. S4TP achieves a pass rate of 100% across all scenarios, surpassing the current state-of-the-art methods Fanta of 98.25% and Predictive-Decision of 94.75%. Copyright © 2024, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Survival prediction of LGG patients based on deep learning of MRI data and genomic data integration

Survival prediction of LGG patients based on deep learning o...

引用

Chinese Automation Congress (CAC)

作者： Lingzhi Sun Yong He School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China

ISBN: (纸本)9781665426480

Low-grade gliomas (LGG) is the most common primary intracranial tumor, with high incidence rate, high recurrence rate, high mortality rate and low cure rate. Therefore, it is necessary to predict the survival of LGG patients in diagnosis. Considering the complementarity of information, the new proposed algorithm in this study is designed to integrate Magnetic Resonance Image (MRI) data and gene expression data using deep learning method to predict the Disease Specific Survival (DSS) of LGG patients. Firstly, MRI data of 44 patients is screened from TCIA database, and then the corresponding gene expression data of 44 patients is searched from TCGA database. Then, 724 image feature data extracted from MRI data are filtered and extracted by deep learning method, and DSS tags are used to train the model; deep learning method is used to extract 20530 features of gene expression data, and DSS tags are also used for training. As a contrast, the deep learning method is used to integrate the two features to train the model. Experiments are evaluated on MRI data, gene expression data and the integration data of MRI and gene expression data, respectively. The results show that by using the integration of MRI data and gene expression data performs better than using single data in terms of the time-dependent receiver operating characteristic(ROC) and the area under the curve (AUC) of the ROC curve criteria.

关键词： Deep learning Training Databases Magnetic resonance imaging Feature extraction Data models Gene expression

来源：评论

学校读者我要写书评

暂无评论

Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planning

arXiv

引用

arXiv 2023年

作者： Chen, Long Teng, Siyu Li, Bai Na, Xiaoxiang Li, Yuchen Li, Zixuan Wang, Jinjun Cao, Dongpu Zheng, Nanning Wang, Fei-Yue The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Waytous Ltd United Kingdom BNU-HKBU United International College Zhuhai519087 China Hong Kong Baptist University Kowloon999077 Hong Kong The College of Mechanical and Vehicle Engineering Hunan University China The Department of Engineering University of Cambridge United Kingdom The College of Artificial Intelligence Xi’an Jiaotong University China The School of Mechanical Engineering Tsinghua University China

Growing interest in autonomous driving (AD) and intelligent vehicles (IVs) is fueled by their promise for enhanced safety, efficiency, and economic benefits. While previous surveys have captured progress in this field, a comprehensive and forward-looking summary is needed. Our work fills this gap through three distinct articles. The first part, a"Survey of Surveys" (SoS), outlines the history, surveys, ethics, and future directions of AD and IV technologies. The second part,"Milestones in Autonomous Driving and Intelligent Vehicles Part I: control, Computing System Design, Communication, HD Map, Testing, and Human Behaviors" delves into the development of control, computing system, communication, HD map, testing, and human behaviors in IVs. This part, the third part, reviews perception and planning in the context of IVs. Aiming to provide a comprehensive overview of the latest advancements in AD and IVs, this work caters to both newcomers and seasoned researchers. By integrating the SoS and Part I, we offer unique insights and strive to serve as a bridge between past achievements and future possibilities in this dynamic field. Copyright © 2023, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

How Simulation Helps Autonomous Driving: A Survey of Sim2real, Digital Twins, and Parallel Intelligence

arXiv

引用

arXiv 2023年

作者： Hu, Xuemin Li, Shen Huang, Tingyu Tang, Bo Huai, Rouxing Chen, Long The School of Artificial Intelligence Hubei University Hubei Wuhan430062 China The Department of Electrical and Computer Engineering Worcester Polytechnic Institute WorcesterMA01609 United States Beijing Huairou Academy of Parallel Sensing Beijing101499 China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100864 China The Waytous Inc. Beijing100083 China

Safety and cost are two important concerns for the development of autonomous driving technologies. From the academic research to commercial applications of autonomous driving vehicles, sufficient simulation and real world testing are required. In general, a large scale of testing in simulation environment is conducted and then the learned driving knowledge is transferred to the real world, so how to adapt driving knowledge learned in simulation to reality becomes a critical issue. However, the virtual simulation world differs from the real world in many aspects such as lighting, textures, vehicle dynamics, and agents' behaviors, etc., which makes it difficult to bridge the gap between the virtual and real worlds. This gap is commonly referred to as the reality gap (RG). In recent years, researchers have explored various approaches to address the reality gap issue, which can be broadly classified into three categories: transferring knowledge from simulation to reality (sim2real), learning in digital twins (DTs), and learning by parallel intelligence (PI) technologies. In this paper, we consider the solutions through the sim2real, DTs, and PI technologies, and review important applications and innovations in the field of autonomous driving. Meanwhile, we show the state-of-the-arts from the views of algorithms, models, and simulators, and elaborate the development process from sim2real to DTs and PI. The presentation also illustrates the far-reaching effects and challenges in the development of sim2real, DTs, and PI in autonomous driving. Copyright © 2023, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Motion Transfer based on Front and Back View for Rehabilitative Exercise

Motion Transfer based on Front and Back View for Rehabilitat...

引用

第40届中国控制会议

作者： Yuting Ge Jinhua She Chi Xu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Engineering Tokyo University of Technology

As a part of rehabilitation training,rehabilitation gymnastics plays an important role in restoring the patients’ bodily *** facilitate the evaluation of rehabilitation exercises,in this work we propose multi-view on a motion transfer framework which is based on GANs and parameterized human *** we can generate virtual exercise images sampled from the front and back view of one person with the appearance *** transfer methods based on 2D information can hardly deal with the ambiguity of human pose and lack of appearance ***,this work uses a 3D parametric human model to represent the human body and poses,sampling,and combining pixels from pictures token from both front and back view of a source character,to generate target images under given *** whole framework we used can be divided into three stages.1) In the first stage the 3D human mesh will be reconstructed.2) In the second stage,transformation maps of multi-view will be calculated,which can show the coordinates of required pixels for sampling and placing.3) In the third stage,a generated adversarial network is employed to optimize the coarse result from the second stage and make it more *** our experiments,the whole framework achieves good results,especially it is proved that sampling features from both the front and back view can preserve more details of appearance by comparison experiment.

关键词： Motion transfer Rehabilitation exercises Deep learning Generative Adversarial Network

来源：评论

学校读者我要写书评

暂无评论

A novel signal processing algorithm for measurement while drilling(MWD) system

A novel signal processing algorithm for measurement while dr...

引用

第40届中国控制会议

作者： ShiLong Cheng Yule Hu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Faculty of Engineering China University of Geosciences

measurement while drilling(MWD) is a widely used signal transmission technology in the drilling *** present,the domestic pulse identification method is relatively simple,using the basic threshold method to identify,only set the threshold which will leading a number of missing detection mud pulse in the complex working *** this paper,a novel data processing algorithm is proposed for measurement while drilling *** method designed in this paper identifies the start time of data frame by using correlation coefficient and synchronization head model,then,based on the principle that the amplitude of mud pulse signal is larger than that of noise pulse signal,the maximum pulse signal in the length of a group of mud pulse series is extracted as mud pulse *** simulation is executed using the data from the actual drilling process and the results show the effectiveness of the proposed method.

关键词： measurement while drilling Pulse recognition Correlation coefficient Sliding time window

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：