检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Huang, Jingwei Wang, Chuansheng Huang, Jiayan Fan, Haoyi Grau, Antoni Zhang, Fuquan The College of Computer and Big Data Fuzhou University Fuzhou China The Department of Automatic Control Polytechnic University of Catalonia Barcelona Spain The New Engineering Industry College Putian University Putian China School of Computer and Artificial Intelligence Zhengzhou University China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China College of Computer and Control Engineering Minjiang University Fuzhou China Key Laboratory of Sichuan Province Sichuan Conservatory of Music Chengdu China Fuzhou Technology Innovation Center of Intelligent Manufacturing information System Minjiang University Fuzhou China Fujian Polytechnic Normal University Fujian Province University Fuzhou China

Driver drowsiness electroencephalography (EEG) signal monitoring can timely alert drivers of their drowsiness status, thereby reducing the probability of traffic accidents. Graph convolutional networks (GCNs) have shown significant advancements in processing the non-stationary, time-varying, and non-Euclidean nature of EEG signals. However, the existing single-channel EEG adjacency graph construction process lacks interpretability, which hinders the ability of GCNs to effectively extract adjacency graph features, thus affecting the performance of drowsiness monitoring. To address this issue, we propose an edge-end lightweight dual graph convolutional network (LDGCN). Specifically, we are the first to incorporate neurophysiological knowledge to design a Baseline Drowsiness Status Adjacency Graph (BDSAG), which characterizes driver drowsiness status. Additionally, to express more features within limited EEG data, we introduce the Augmented Graph-level Module (AGM). This module captures global and local information at the graph level, ensuring that BDSAG features remain intact while enhancing effective feature expression capability. Furthermore, to deploy our method on the fourth-generation Raspberry Pi, we utilize Adaptive Pruning Optimization (APO) on both channels and neurons, reducing inference latency by almost half. Experiments on benchmark datasets demonstrate that LDGCN offers the best trade-off between monitoring performance and hardware resource utilization compared to existing state-of-the-art algorithms. All our source code can be found at https://***/BryantDom/Driver-Drowsiness-Monitoring. Copyright © 2024, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Distribution of Dislocation-Twin Interaction in Twip Steel Under Different Loading Modes

SSRN

引用

SSRN 2022年

作者： Guo, Xiangru Mao, Ningdong Sun, Chaoyang Wang, Chunhui Cui, Yinan Xiong, Zhiping Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin300384 China School of Mechanical Engineering University of Science and Technology Beijing Beijing100083 China Applied Mechanics Lab School of Aerospace Engineering Tsinghua University Beijing100084 China National Key Laboratory of Science and Technology on Materials under Shock and Impact Beijing Institute of Technology Beijing100081 China

The tension-compression asymmetry and orientation effect of dislocation-twin boundary (TB) interactions in twinned TWIP steels were investigated using the discrete dislocation dynamics simulations and Schmid's law. The different types of dislocations dominate the TB migration in the twinned TWIP steel during tension and compression with the same loading orientation, and the asymmetric dislocation reactions at TB were attributed to the different leading partials produced after the dissociation of dislocation under different loading modes (tension or compression). Moreover, the complex dislocation-TB interactions, such as dislocations traversing TB, cross slip, dissociation, pile up and so on, were determined by considering the orientation effect of dislocation activation and the asymmetry of dislocation dissociation. The research advances the understanding of asymmetric behavior of twin and its influence on the macro hardening in plastic deformation of TWIP steels. © 2022, The Authors. All rights reserved.

关键词： Dissociation

来源：评论

学校读者我要写书评

暂无评论

An Early Fault Detection Method of the Induced Draft Fan Based on Long-Short Term Memory Network and Double Warning Thresholds

An Early Fault Detection Method of the Induced Draft Fan Bas...

引用

Chinese control and Decision Conference, CCDC

作者： Wei Wei You Lv Yizhuo Liu Qing Li Shisen Xu Jun Li School of Control and Computer Engineering North China Electric Power University Beijing P. R. China Key Laboratory of Power Station Energy Transfer Conversion and System North China Electric Power University Beijing P. R. China Beijing Key Laboratory of New Technology and System on Measuring and Control for Industrial Process North China Electric Power University Beijing P. R. China Huaneng Technology Innovation Center Beijing P. R. China Xian Thermal Power Research Institute Company Limited Xian P. R. China

ISBN: (纸本)9781665478977

The induced draft (ID) fan is a significant piece of auxiliary equipment in thermal power plants. An early detection of possible faults in the ID fan may be used for effective predictive maintenance, thereby reducing the overall maintenance cost and improving the reliability and availability of thermal power plants. This paper proposed a genetic algorithm and long-short term memory network (GA-LSTM)-based condition monitoring approach using normal operation data of the ID fan. Furthermore, the LSTM network and the sliding window technique were introduced to construct double thresholds, which contains a dynamic threshold and a static threshold. The GA-LSTM-double thresholds method was applied to a coal-fired power plant to achieve early fault detection and diagnosis. The results demonstrates that the proposed method is capable of detecting minor anomalies in advance.

关键词： Fans Fault detection Neurons Predictive models Indexes Reliability State estimation

来源：评论

学校读者我要写书评

暂无评论

Towards an inclusive computational model of visual cortex

Towards an inclusive computational model of visual cortex

引用

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： M. Gheiratmand H. Soltanian-Zadeh H. Khaloozadeh Electrical Engineering Department K.N. Toosi University of Technology Tehran Iran Radiology Department Henry Ford Health System Image Analysis and Communications Laboratory Detroit MI USA School of Cognitive Sciences Institute for Studies Theoretical Physics and Mathematics (IPM) Tehran Iran Control and Intelligent Processing Center of Excellence Electrical and Computer Engineering Department University of Tehran Tehran Iran

Understanding the primatespsila visual system has been one of the challenging problems of different groups of scientists for years. Though many studies, from physiology and neuroscience to computer vision, are done on different aspects of visual processing in the cortex, a comprehensive computational model of visual cortex is still missing. We have implemented a computational model of object recognition in ventral visual pathway in our previous work. This hierarchical model covers visual areas V1/V2, V4/PIT, and AIT sending inputs to the Prefrontal Cortex (PFC) for categorization. To extend our model, in this work, we have added a simple model of motion detection in neurons of areas V1 and MT of the dorsal stream to our previous model. This has enabled the model to perform another principal function of the visual cortex, i.e., motion perception.

关键词： Brain modeling Computational modeling Neurons Biological system modeling Object recognition Motion analysis Solid modeling Visual system Computer vision Motion detection

来源：评论

学校读者我要写书评

暂无评论

A Ray-tracing and Deep Learning Fusion Super-resolution Modeling Method for Wireless Mobile Channel

A Ray-tracing and Deep Learning Fusion Super-resolution Mode...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Zhao Zhang Danping He Xiping Wang Ke Guan Zhangdui Zhong Jianwu Dou State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China Beijing Engineering Research Center of High-Speed Railway Broadband Mobile Communications Beijing China Frontiers Science Center for Smart High-Speed Railway System Beijing China Key Laboratory of Railway Industry of Broadband Mobile Information Communications Beijing China State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen China ZTE Corporation Shenzhen China

Mobile channel modeling has always been the core part for design, deployment and optimization of communication system, especially in 5G and beyond era. Deterministic channel modeling could precisely achieve mobile channel description, however with defects of equipment and time consuming. In this paper, we proposed a novel super resolution (SR) model for cluster characteristics prediction. The model is based on deep neural networks with residual connection. A series of simulations at 3.5 GHz are conducted by a three-dimensional ray tracing (RT) simulator in diverse scenarios. Cluster characteristics are extracted and corresponding data sets are constructed to train the model. Experiments demonstrate that the proposed SR approach could achieve better power and cluster location prediction performance than traditional interpolation method and the root mean square error (RMSE) drops by 51% and 78% relatively. Channel impulse response (CIR) is reconstructed based on cluster characteristics, which could match well with the multi-path component (MPC). The proposed method can be used to efficiently and accurately generate big data of mobile channel, which significantly reduces the computation time of RT-only.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mechanochromic Properties of Acridine Heterocyclic Derivatives with a Donor-Acceptor Configuration

SSRN

引用

SSRN 2023年

作者： Shi, Wei Rong, Bin Li, Shuzhe Lin, Yang Liao, Yingjie Cao, Chenhui Pan, Saihu Wei, Bin Key Laboratory of Advanced Display and System Applications Ministry of Education Shanghai University Shanghai200072 China School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China School of Microelectronics and Control Engineering Changzhou University Changzhou213164 China Anhui Sholon New Material Technology Co. Ltd. Anhui Chuzhou239500 China Shanxi Datong University China

The mechanochromic properties of two acridine heterocyclic derivatives with a donor-acceptor configuration, 10-phenyl-10-(4-(7,7,13,13-tetramethyl-7,13-dihydro-5H-indeno[1,2-b]acridin-5-yl)phenyl)anthracene-9(10H)-one (DpAn-InAc) and 10-(4-(5,5-dimethylbenzofuro[3,2-c]acridin-13(5H)-yl)phenyl)-10-phenylanthracen-9(10H)-one (DpAn-BzAc), were investigated. The average red shift of the emission peak was 18 nm for DpAn-InAc, with the long grinding time bringing the greatest shift, while both the highest and the lowest pretreat temperature brought a greater impact on the luminescent peak. The grinded DpAn-BzAc preheated at 100 °C showed the maximum wavelength shift, which was ascribed to the lower glass transition temperature of DpAn-BzAc. Meanwhile, the discolored sample could be recovered by ethanol fumigation, proving that the discoloration was reversible. XRD analyses revealed that under the anisotropic force, the microcrystalline structure of DpAn-InAc and DpAn-BzAc were destroyed, resulting in the shift of the fluorescence peak. The fluorescence shift of DpAn-BzAc was more obvious than that of DpAn-InAc, while its recovery was inferior compared to DpAn-InAc, which was due to its looser molecular structure. Finally, DpAn-InAc and DpAn-BzAc were applied in delivering rewritable encrypted information and both of the two molecules have shown capabilities in transmitting coded information. This work sheds light on using the molecule with donor-acceptor molecular structure in the stimuli-responsive field, and shows their potential application in transmitting encrypted information. © 2023, The Authors. All rights reserved.

关键词： Fluorescence

来源：评论

学校读者我要写书评

暂无评论

Aadaptive genetic algorithm based on real coded and its application

引用

Beijing Gongye Daxue Xuebao / Journal of Beijing University of Technology 2007年第2期33卷 144-149页

作者： Gao, Xue-Jin Wang, Pu Sun, Chong-Zheng Yi, Jian-Qiang Zhang, Ya-Ting Zhang, Hui-Qing College of Electronic Information and Control Engineering Beijing University of Technology Beijing 100022 China Key Laboratory of Complex System and Intelligence Science Chinese Acad. of Sci. Beijing 100033 China

To solve the problem of the premature convergence and the slow convergence of Genetic Algorithms, an adaptive Genetic Algorithms based on real coded (RAGA) was proposed to improve the coding modes, genetic operators, etc. Optimization simulation results based on typical complex functions show that the optimal convergence rate and global hitting probability of the proposed algorithm are much better than those of simple Genetic algorithms.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

An algorithm on releasing range of traffic guidance information based on simulated annealing

An algorithm on releasing range of traffic guidance informat...

引用

作者： Chen, De-Wang Pei, Li-Jun Liu, Jing State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing 100044 China School of Electronic and Information Engineering Beijing Jiaotong University Beijing 100044 China Beijing STONE Intelligent Transportation System Integration Co. Ltd. Beijing 100081 China

ISBN: (纸本)9787894631046

In this paper, releasing range model of traffic guidance information is formulated based on combinatorial optimization by the correlation analysis of road traffic flow in time and space. As it is hard to get the optimal solution in a limited time through analysis, a greedy algorithm and a simulated annealing (SA) based algorithm are presented to solve the model. Some traffic flow data detected by remote microwave sensors in some road links in Beijing urban expressway are employed to compare the two algorithms. The results show that SA based algorithm has achieved better result even its running time is little longer than the greedy algorithm. Therefore the proposed SA based algorithms can be used to improve the pertinency, validity and automation of releasing traffic guidance information.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Synthesis and Photocatalytic Capability of Cr- TiO2 film

Synthesis and Photocatalytic Capability of Cr- TiO2 film

引用

2007年纳米光电子学国际学术会议

作者： Xiaojuan Lu Duowang Fan Duojin Fan Hongzhong Liu School of Automation and Electric Engineering Lanzhou Jiaotong University Lanzhou 730070 People's MOE key lab of Opto-electronic Technology and Intelligence Controll Lanzhou Jiaotong University La Lanzhou Dachen Automatic Control System Co. Ltd Lanzhou 730070 and People's Republic of China State Key Laboratory for Manufacturing Systems Engineering Xi'an Jiaotong university Xi'an 710049

A TiO2 catalyst doped by Cr was prepared by the sol-gel method and characterized by UV-2550 and FS. The results reveal that the Cr6+-doped TiO2 film has the higher photocatalytic activity than pure TiO2 *** Semiconductor photocatalysts, mainly TiO2, have attracted much attention in last decade because of their potential application in the removal of many organic and inorganic pollutants in air or water. Many studies have been carried out on the application and modification of TiO2, and various photocatalytic reactors have been investigated according to respective application demands for the purification of air and water. In the water and wastewater treatment field, slurry reactor is the most common device because of its high specific surface area and good dispersion. However, the use of TiO2 slurry reactor is still limited mainly due to difficult separation of TiO2 particles from treated water. To overcome the problem, Titania beads, TiO2 based thin film, fiberglass loaded with titania, and encapsulated titania within a zeolite framework have been prepared and used in fixed bed. However, the activity of TiO2 photocatalyst is reduced to a considerable extent by these immobilization techniques because the effective surface area of photocatalysts is decreased considerably. The aim of this study is to obtain a magnetically separable photocatalyst, which is stable and easy to be prepared. In the work, Cr as magnetic cores was prepared by liquid catalytic phase transfer method at low temperature, and magnetically separable TiO2- Cr photocatalysts were synthesized. Their physicochemical properties and photocatalytic activity for degradation of methyl orange in water were investigated.

关键词： Chromium Water pollution Inductors Semiconductor films Wastewater treatment Slurries Magnetic separation Air pollution Purification Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Method for Path Loss Prediction in Mobile Communication systems

Deep Learning Method for Path Loss Prediction in Mobile Comm...

引用

International Symposium on Antennas, Propagation and EM Theory (ISAPE)

作者： Zhuocheng Xu Huiyun Cao Yue Yin Xiaohan Zhang Lina Wu Danping He Yuanbo Wang School of Electronic and Information Engineering Beijing Jiaotong University Beijing China State Key Laboratory of Rail Traffic Control and Safety Beijing China Beijing Engineering Research Center of High-speed Railway Broadband Mobile Communications Beijing China Frontiers Science Center for Smart High-speed Railway System Beijing China CHN energy shuohuang railway development company Ltd Hebei China

ISBN: (纸本)9781665418133

The study of wireless channel propagation characteristics is important to channel availability analysis and wireless network optimization. The existing deterministic channel models are greatly restricted by the high complexity. This paper proposes a deep learning (DL) method for path loss (PL) prediction in mobile communication systems, which uses satellite images and neural network (NN) to achieve efficient and reliable prediction. A Deep Neural Network (DNN) framework is established based on a Convolutional Neural Network (CNN) and a Back Propagation Neural Network (BPNN), where CNN extracts environmental features of propagation paths from satellite images and BPNN predicts PL according to the distance features and environmental features. The results show that DNN proposed in this paper can reduce the time cost with satisfying accuracy compared to the traditional Ray-tracing method with the lack of a detailed model of the scene and material parameters. The DL method for making a quick prediction of the PL in this paper can be used to optimize the mobile communication systems.

关键词： Deep learning Satellites Wireless networks Ray tracing Predictive models Feature extraction Mobile communication

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：