检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Wang, Shaoyang Lv, Tiejun Ni, Wei Beaulieu, Norman C. Guo, Y. Jay Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China Sydney2122 Australia Beijing Key Laboratory for Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China Global Big Data Technologies Centre University of Technology Sydney UltimoNSW2007 Australia

This paper presents a novel and effective deep reinforcement learning (DRL)-based approach to addressing joint resource management (JRM) in a practical multi-carrier non-orthogonal multiple access (MC-NOMA) system, where hardware sensitivity and imperfect successive interference cancellation (SIC) are considered. We first formulate the JRM problem to maximize the weighted-sum system throughput. Then, the JRM problem is decoupled into two iterative subtasks: subcarrier assignment (SA, including user grouping) and power allocation (PA). Each subtask is a sequential decision process. Invoking a deep deterministic policy gradient algorithm, our proposed DRL-based JRM (DRL-JRM) approach jointly performs the two subtasks, where the optimization objective and constraints of the subtasks are addressed by a new joint reward and internal reward mechanism. A multi-agent structure and a convolutional neural network are adopted to reduce the complexity of the PA subtask. We also tailor the neural network structure for the stability and convergence of DRL-JRM. Corroborated by extensive experiments, the proposed DRL-JRM scheme is superior to existing alternatives in terms of system throughput and resistance to interference, especially in the presence of many users and strong inter-cell interference. DRL-JRM can flexibly meet individual service requirements of users. © 2021, CC BY.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

The impact of information on system operations 6

The impact of information on system operations

引用

6th Annual International Conference on Network and Information Systems for Computers, ICNISC 2020

作者： Guan, Tianchao Zhou, Shumin Li, Tongfei Xu, Duo Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Beijing Jiaotong University Beijing100044 China China Railway Fifth Survey And Design Institute Group CO. LTD. Beijing102600 China Beijing Key Laboratory of Traffic Engineering Beijing University of Technology Beijing100124 China Postgraduate School People's Public Security University of China Beijing100038 China

The operating system is a complex system that includes supply and demand. Changes in external information have an impact on the operation of the system, especially on both supply and demand. This paper analyzes the supply and demand and establishes the nonlinear programming problem of system operation under the social optimal goal. With the increase of external information intervention, there will be more suitable travel fares for the demand side. However, the supply side's related operating indicators (for example, frequency, bus fleet, and vehicle capacity, etc.) have shown a trend of first increasing and then decreasing due to existing resource constraints. It can be seen that under the same information interference, there are differences in the law of change between the supply and demand sides. Besides, an example is used to verify the effectiveness of the model. Through the model and calculation examples, we can know that the supplier and the demander can meet their own needs under the social optimal goal. This provides certain theoretical support for future research information on system operation. © 2020 Journal of Physics: Conference Series.

关键词： Economics

来源：评论

学校读者我要写书评

暂无评论

Optimal Feature Combination Using SVM Algorithms for Brain-computer Interface

Optimal Feature Combination Using SVM Algorithms for Brain-c...

引用

IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)

作者： Jun Long Shulei Yu Network Resource Management and Trust Evaluation Key Laboratory of Hunan School of Computer Engineering Central South University National Engineering Laboratory for Medical Big Data Application Central South University Changsha China

ISBN: (数字)9781728170053

ISBN: (纸本)9781728170060

This paper aims to establish a four-class classification brain-computer interface model with the optimal combination of features. By exploring the influence of feature vector combinations in different time windows on brain-computer interface (BCI) classification, the optimal 2-feature combination could be get. Four types of movement paradigms were studied based on the concentration of oxygenated hemoglobin (HbO) in the brain motor region. A total of 10 volunteers completed a set of movement patterns which included hand griping and arm lifting of two upper limbs. After extracting signal mean(SM) and signal slope(SS) eigenvectors, the “one-versus-one” SVM algorithm was used for classification. The highest average classification accuracy rate reached 80.48%, and most of the participants got the highest classification accuracy in the combination time window of SM feature (0~5s) and SS feature (5~7s). In the case of the same time window of SM feature, the classification accuracy increased gradually with the selection of 3~5s, 4~6s, 5~7s respectively in the time window of SS feature.

关键词： Task analysis Training Mathematical model Support vector machines Brain-computer interfaces Fitting Brain modeling

来源：评论

学校读者我要写书评

暂无评论

String Stability of Automated Vehicles Based on Experimental Analysis of Feedback Delay and Parasitic Lag

SSRN

引用

SSRN 2022年

作者： Ma, Ke Wang, Hao Zuo, Zewen Hou, Yuxuan Jiang, Rui Jiangsu Key Laboratory of Urban ITS Southeast University Nanjing China Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies Southeast University Nanjing China School of Transportation Southeast University Nanjing China Department of Civil and Environmental Engineering University of South Florida 4202 E Fowler Avenue ENC 3300 TampaFL33620 United States 2 Si pai lou Nanjing210096 China Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Ministry of Transport Beijing Jiaotong University Beijing100044 China

Recent literature has shown that the potential of automated vehicles (AVs) application can improve roadway capacity and traffic flow stability. However, Adaptive Cruise Control (ACC) system, as a longitudinal AV technology widely used, still has several unknown features and lacks evidence from field experiments. To verify the string stability of the AV platoon, we designed and conducted a series of novel experiments via two vehicles with an ACC system to simulate AV platoon behavior. We collected various data sent by Controller Area Network (CAN)-bus and sensors by constructing the linear control model of upper layers and setting it into AV control. Two approaches to data processing allow us to accurately estimate the range of sensor time delay and parasitic dynamics lag. The analyses results of experimental data indicate the parameters range of time delay and further optimize the lower dynamic response model. Then we propose a new ACC lower model based on a first order inertia system with a pure time delay. Based on the experiment results, we parameterize the controller by a linearized AV dynamics model with Laplace transform of the velocity and gap errors from the time domain to the frequency domain, and it can determine the AV string stability criterion. Additionally, we figure out how it impacts the four Stable Types in the control parameters area by investigating the impact of parasitic parameters. The results show that our new model has more strict stability conditions. Although the current sensor delay can satisfy the string stability criterion at a large time headway, dynamics parasitic lag and its pure delay cannot fulfill the criterion under any conditions. More importantly, different from many studies that only use commercial ACC vehicles and cannot independently design control models and parameters, this empirical study based on the ROS platform, conducted a field experiment that inputs the self-designed car-following model into the control system of the

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Revisited parasitic bipolar effect in FDSOI MOSFETs: mechanism, gain extraction and circuit applications

Revisited parasitic bipolar effect in FDSOI MOSFETs: mechani...

引用

International Conference on Ultimate Integration of Silicon, ULIS

作者： GQ. Wang FY. Liu B. Li JJ. Luo Y. Huang XH. Su YC. Wang ZS. Han CN. Wu JM. Zhang S. Cristoloveanu College of Big Data and Information Engineering Guizhou University Guiyang China Key Laboratory of Silicon Device and Technology Chinese Academy of Sciences Beijing China College of Big Data and Information Engineering Guizhou University Guiyang China IMEP-LAHC INP-Grenoble/Minatec Grenoble France

ISBN: (数字)9781728187655

ISBN: (纸本)9781728187662

The parasitic bipolar effect in fully-depleted (FD) silicon-on-insulator (SOI) transistors is revisited including impact ionization and band-to-band tunneling. The current gain β of the parasitic bipolar transistor (PBT) was measured at different temperatures and drain voltages. Back-gate biasing was demonstrated to efficiently suppress the bipolar amplification. TCAD simulations showed that the parasitic bipolar effect enhanced the leakage power in circuits. A strategy to counter its effect is proposed based on the power analysis of 6T SRAM cell with back-gate modulation.

关键词： Temperature measurement Voltage measurement Power demand Silicon-on-insulator Tunneling Internet of Things Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

Automatic Pointer Meter Reading Based on Machine Vision 4

Automatic Pointer Meter Reading Based on Machine Vision

引用

4th IEEE International Conference on Image, Vision and Computing, ICIVC 2019

作者： Hung, Mao-Hsiung Hsieh, Chaur-Heh Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou China Yango University College of Information Engineering Fuzhou China

ISBN: (纸本)9781728123257

Pointer meters in power systems are wildly used. Although smart meters gradually replace pointer meters to conveniently acquire measurement, digitalization of some special meters have not been available. The paper presents a new method based on machine vision to detect pointer meter reading automatically. Two phases of training and testing are proposed in this method. In the training phase, a template of meter feature points on a training image is extracted. In the testing phase, the template matching performs on a testing image to find feature points. Then, an elliptic arc fitting based on the feature points to generate a 1-D signal. Finally, the 1-D signal is used to locate the pointer and the reading result is obtained. Differing with existing methods, the proposed method performs effectively and efficiently automatic meter reading without using Hough transformation. © 2019 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

GST-GCN: A Geographic-Semantic-Temporal Graph Convolutional Network for Context-aware Traffic Flow Prediction on Graph Sequences

GST-GCN: A Geographic-Semantic-Temporal Graph Convolutional ...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Jing Chen Shijie Liao Jiaxin Hou Kesu Wang Junhao Wen Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education China School of Big Data & Software Engineering Chongqing University Chongqing China

ISBN: (数字)9781728185262

ISBN: (纸本)9781728185279

Traffic flow prediction is an important foundation for intelligent transportation systems. The traffic data are generated from a traffic network and evolved dynamically. So spatio-temporal relation exploration plays a support role on traffic data analysis. Most researches focus on spatio-temporal information fusion through a convolution operation. To the best of our knowledge, this is the first work to suggest that it is necessary to distinguish the two aspects of spatial correlations and propose the two types of spatial graphs, named as geographic graph and semantic graph. Then two novel stereo convolutions with irregular acceptive fields are proposed. The geographic-semantic-temporal contexts are dynamically jointly captured through performing the proposed convolutions on graph sequences. We propose a geographic-semantic-temporal graph convolutional network (GST-GCN) model that combines our graph convolutions and GRU units hierarchically in a unified end-to-end network. The experiment results on the Caltrans Performance Measurement System (PeMS) dataset show that our proposed model significantly outperforms other popular spatio-temporal deep learning models and suggest the effectiveness to explore geographic-semantic-temporal dependencies on deep learning models for traffic flow prediction.

关键词： Deep learning Measurement Three-dimensional displays Convolution Semantics Predictive models Meteorology

来源：评论

学校读者我要写书评

暂无评论

NIR-II fluorescence image enhancement via multi-step modulation

引用

Expert Systems with Applications 2025年 293卷

作者： Xiaoming Yu Jie Tian Zhenhua Hu CAS Key Laboratory of Molecular Imaging Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing 100049 China Key Laboratory of Big Data-Based Precision Medicine of Ministry of Industry and Information Technology School of Engineering Medicine Beihang University Beijing 100191 China Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education School of Life Science and Technology Xidian University Xi’an 710071 China National Key Laboratory of Kidney Diseases Beijing 100853 China

The second near-infrared (NIR-II) fluorescence imaging is an emerging biomedical imaging modality. The characteristics of real-time high-resolution imaging during surgery create huge potential for its future development. Further, NIR-II can be divided into NIR-IIa window and NIR-IIb window. The light energy of the NIR-IIb window significantly suppresses light divergence, resulting in clearer images. Limited by the lack of molecular probes for NIR-IIb, clinical translation is very difficult. We propose a new multi-output image translation model to achieve the enhancement from NIR-IIa to NIR-IIb. Its key module lies in the designed Multi-Step Modulation, which can improve the artifact problem caused by AdaIN’s direct fusion of feature maps and reference style code, and preserve the content structure of the input images. It includes a three-step modulation. The first step is to fuse the feature maps output from the encoding layers to enhance the structural information of the input images. The second step is divided into two parts to inject style code through AdaIN, and then generate two modulation parameters for the final fusion stage. The third step aggregates the structure preservation and style fusion of the first two stages, and uses the generated modulation parameters to modify the feature maps at the current stage. Images generated by multi-output models are prone to artifacts and are inconsistent with the original input images. We design a new processing method (averaging multiple output results of a single input image) to improve the image enhancement effect, and based on this method, we construct a paired NIR-II fluorescence image enhancement dataset. Extensive experiments demonstrate that our model and designed processing method can generate high-quality NIR-II fluorescence images. The constructed dataset can be obtained in https://***/axyuhh/MSM .

关键词：

来源：评论

学校读者我要写书评

暂无评论

StarGAT: Star-Shaped Hierarchical Graph Attentional Network for Heterogeneous Network Representation Learning

StarGAT: Star-Shaped Hierarchical Graph Attentional Network ...

引用

IEEE International Conference on data Mining (ICDM)

作者： Wen-Zhi Li Ling Huang Chang-Dong Wang Yu-Xin Ye School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Computational Science Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China College of Mathematics and Informatics South China Agricultural University Guangzhou China Guangdong Provincial Key Laboratory of Public Finance and Taxation with Big Data Application Guangzhou China College of Computer Science and Technology Jilin University Changchun China

ISBN: (纸本)9781665423991

Many real-world graphs can be viewed as Heterogeneous Networks or Heterogeneous Information Networks (HINs) for that they comprise a diversity of node types and relation types. Due to the efficient representation ability of Graph Neural Network and the idea of random walk, many recent studies apply graph representation learning to HINs and achieve satisfactory results. However, these works either treat different node types in a metapath equally, which is inconsistent with the original graph semantic information for that different node types should have different statuses, or only consider the first-order (node-level) and second-order (metapath-level, a.k.a. link-level) information aggregation while ignoring the higher-order relations. To tackle these two problems, we propose a novel Star-Shaped Hierarchical Graph Attentional Network (StarGAT) model to boost representation learning in HINs. Specifically, we assume nodes in HINs can be categorized into a star-shaped structure including one center node type and a bunch of auxiliary node types in a specific task; and we encode node-level, link-level and motif-level attentions in a hierarchical manner to capture richer semantic information. Extensive experiments on three datasets illustrate the model effectiveness.

关键词： Representation learning Conferences Semantics Heterogeneous networks Graph neural networks data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Influencing Factors of College Students' Intention of Online Health Information Behavior Based on Social Cognitive Theory 2

Research on Influencing Factors of College Students' Intenti...

引用

2019 2nd International Conference on Advanced Algorithms and Control engineering, ICAACE 2019

作者： Kong, Jia Deng, Sanhong Zhang, Yue School of Information Management Nanjing University Nanjing210023 China Jiangsu Key Laboratory of Data Engineering and Knowledge Service Nanjing University Nanjing210023 China

Based on the Social Cognition Theory, we constructed the influencing factors model of college students' intention of online health information behavior from three levels of individual, society and information systems, which was analyzed by using the PLS-SEM. Research shows that self-efficacy, information service quality, social support, information literacy and information quality significantly influence college students' intention of online health information behavior. However, the influence of perceived risk and information system quality is not significant. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： Information systems

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：