检索结果-内蒙古大学图书馆

Multifractal temporally weighted detrended partial cross-correlation analysis to quantify intrinsic power-law cross-correlation of two non-stationary time series affected by common external factors

arXiv

引用

arXiv 2020年

作者： Li, Bao-Gen Ling, Dian-Yi Yu, Zu-Guo Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Xiangtan Hunan411105 China School of Electrical Engineering and Computer Science Queensland University of Technology GPO Box 2434 BrisbaneQ4001 Australia

When common factors strongly influence two cross-correlated time series recorded in complex natural and social systems, the results will be biased if we use multifractal detrended cross-correlation analysis (MF-DXA) without considering these common factors. Based on multifractal temporally weighted detrended cross-correlation analysis (MF-TWXDFA) proposed by our group and multifractal partial cross-correlation analysis (MF-DPXA) proposed by Qian et al., we propose a new method-multifractal temporally weighted detrended partial cross-correlation analysis (MF-TWDPCCA) to quantify intrinsic power-law cross-correlation of two non-stationary time series affected by common external factors in this paper. We use MF-TWDPCCA to characterize the intrinsic cross-correlations between the two simultaneously recorded time series by removing the effects of other potential time series. To test the performance of MF-TWDPCCA, we apply it, MF-TWXDFA and MF-DPXA on simulated series. Numerical tests on artificially simulated series demonstrate that MF-TWDPCCA can accurately detect the intrinsic cross-correlations for two simultaneously recorded series. To further show the utility of MF-TWDPCCA, we apply it on time series from stock markets and find that there exists significantly multifractal power-law cross-correlation between stock returns. A new partial cross-correlation coefficient is defined to quantify the level of intrinsic cross-correlation between two time series. Copyright © 2020, The Authors. All rights reserved.

关键词： Fractals

来源：评论

学校读者我要写书评

暂无评论

Design and Optimization of Camera HAL Layer Based on Android 4th

Design and Optimization of Camera HAL Layer Based on Android

引用

4th International Conference on Smart Computing and Communications, SmartCom 2019

作者： Gan, Yu Hu, Wei Wang, Yonghao College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industria System Wuhan China Digital Media Lab Birmingham City University Birmingham United Kingdom

ISBN: (纸本)9783030341381

Nowadays, in the field of mobile and communication, with the rapid popularization and application of Internet and network, and the continuous expansion to the family field, the trend of integration of consumer electronics, computer and communication (3C) is becoming increasingly obvious, and embedded system naturally becomes a research hotspot. The embedded operating system Android has been widely used in mobile devices, such as smart phones, smart watches and so on. Our design is based on the Android platform to optimize and improve Camera HAL. This design is applied to the development of the Android system, the design of the Camera subsystem, the description of the Camera subsystem from the structure, function and data flow, and then proceed to structural optimization. This design uses TI AM335x as the hardware platform, based on Android system, designed and implemented the Android Camera hardware abstraction layer and Camera subsystem. At the end of the development, after the actual experimental test, the development of the system achieved the expected function and worked well. © 2019, Springer Nature Switzerland AG.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

A Campus Carpooling System Based on GPS Trajectories 12th

A Campus Carpooling System Based on GPS Trajectories

引用

12th International Conference on Security, Privacy, and Anonymity in Computation, Communication, and Storage, SpaCCS 2019

作者： Wang, Xuesong Liu, Yizhi Jiang, Zhengtao Peng, You Yin, Tianhao Liao, Zhuhua Zhao, Jingqiang School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China Key Laboratory of Knowledge Processing and Networked Manufacturing in Hunan Province Xiangtan411201 China Network Information Center Hunan University of Science and Technology Xiangtan411201 China

ISBN: (纸本)9783030248994

College students are special because they relatively have tighter in economy but have greater consistency in leisure time. They prefer to go out together with schoolfellows due to higher trusts and closeness. Moreover, the electronic map is difficult to be updated. Campus-roads recently are updated rapidly. And many alleys in campuses are not shown in the electronic map. Therefore, we devise and implement a campus carpooling system based on GPS trajectories. It includes three parts. Firstly, the campus road network is extracted based on GPS trajectories. Next, the shortest sharing path in the campus is computed in terms of the campus road network. Then, passengers are matched automatically by the carpooling matching algorithm (CMA) in our system. Experiments show that our system is able to provide a safer and more comfortable carpooling experience for college students. © 2019, Springer Nature Switzerland AG.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral classification based on lightweight 3-D-CNN with transfer learning

arXiv

引用

arXiv 2020年

作者： Zhang, Haokui Li, Ying Jiang, Yenan Wang, Peng Shen, Qiang Shen, Chunhua Shaanxi Provincial Key Laboratory of Speech and Image Information Processing School of Computer Science Northwestern Polytechnical University Xi’an710129 China School of Computer Science University of Adelaide AdelaideSA5005 Australia Faculty of Business and Physical Sciences Aberystwyth University AberystwythSY23 3DB United Kingdom

Recently, hyperspectral image (HSI) classification approaches based on deep learning (DL) models have been proposed and shown promising performance. However, because of very limited available training samples and massive model parameters, DL methods may suffer from overfitting. In this paper, we propose an end-to-end 3-D lightweight convolutional neural network (CNN) (abbreviated as 3-D-LWNet) for limited samples-based HSI classification. Compared with conventional 3-D-CNN models, the proposed 3-D-LWNet has a deeper network structure, less parameters, and lower computation cost, resulting in better classification performance. To further alleviate the small sample problem, we also propose two transfer learning strategies: 1) cross-sensor strategy, in which we pretrain a 3-D model in the source HSI data sets containing a greater number of labeled samples and then transfer it to the target HSI data sets and 2) cross-modal strategy, in which we pretrain a 3-D model in the 2-D RGB image data sets containing a large number of samples and then transfer it to the target HSI data sets. In contrast to previous approaches, we do not impose restrictions over the source data sets, in which they do not have to be collected by the same sensors as the target data sets. Experiments on three public HSI data sets captured by different sensors demonstrate that our model achieves competitive performance for HSI classification compared to several state-of-the-art methods. © 2020, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

The Application of PAD Teaching Method in computer Network Course

引用

IOP Conference Series: Earth and Environmental Science 2021年第1期693卷

作者： Lining Liu Yongsheng Zhang Penglong Zhang Wenqian Sun School of Information Science and Engineering Shandong Normal University Jinan 250358 China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology

As a new teaching mode and method, PAD has been developed in recent years. This teaching mode has been applied in the teaching of universities, ordinary primary and secondary schools and vocational colleges. It has achieved good teaching results. In order to improve teaching effect, improve the students' autonomy and enthusiasm and cultivate the independent innovative talents needed by the society, more and more computer teachers have also begun to apply PAD to the computer classroom. 'computer Network' is a basic and compulsory course for learning computers. 'transmission media' in this course is selected as the specific content, and PAD is used for teaching design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Seizure Diagnosis Using Discriminative Fractal Features from Feature Selection 15th

EEG-Based Seizure Diagnosis Using Discriminative Fractal Fea...

引用

15th International Conference on Intelligent Computing, ICIC 2019

作者： Yang, Su Li, Gang Lu, Jing Sun, Yi Huang, Zhengyu Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai201203 China Department of Neurology East Hospital Tongji University School of Medicine Shanghai200120 China School of Computer Science Xi’an University of Technology Xi’an China

ISBN: (纸本)9783030267629

EEG classification has received much attention in computer-aided diagnosis for seizure. However, the present feature extraction strategies lead to uninterpretable features to which human vision is not sensitive, and due to the lack of explicit knowledge consistent with human intuition in such features, their usage in clinic diagnosis is limited. Inspired by human perception of seizure patterns, from a morphological point of view, we propose to make use of blanket-covering dimensions for seizure diagnosis, which act as a morphological lens of waveform complexity to enable visually straightforward features consistent with human perception. Moreover, we apply feature selection to mine the relevant features for seizure diagnosis from a pool of blanket-covering dimensions computed by combining different scales. The fractal dimensions computed as such combined with multifractals lead to 97.72% precision in classifying healthy people, seizure-inactive patients, and seizure-active patients on a public benchmark. © 2019, Springer Nature Switzerland AG.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Geo-spatial ontology matching through compact evolutionary algorithm 2nd

Geo-spatial ontology matching through compact evolutionary a...

引用

2nd International Conference on Smart Vehicular technology, Transportation, Communication and Applications, VTCA 2018

作者： Xue, Xingsi Liu, Jianhua College of Information Science and Engineering Fujian University of Technology FuzhouFujian350118 China Intelligent Information Processing Research Center Fujian University of Technology FuzhouFujian350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology FuzhouFujian350118 China Fujian Key Lab for Automotive Electronics and Electric Drive Fujian University of Technology FuzhouFujian350118 China

ISBN: (纸本)9783030045845

Geo-spatial ontologies can provide a formal description of concepts, relationships, activities, features and rules in GIS domain. However, simply use them only allows to partially solve semantic conflicts, and does not completely solve heterogeneity issues that are caused by themselves. Geo-spatial ontology matching technique can find the correspondences between semantic identical entities, and solve the heterogeneous problem between two geo-spatial ontologies. Be inspired by the successful application of Evolutionary Algorithm (EA) in instance matching domain, in this paper, it is utilized to match the heterogeneous geo-spatial ontologies. To reduce the runtime and memory consumption required by EA, a compact version of it is presented, which does not work on the whole population but a probability representation on it. In addition, a geo-spatial similarity measure is presented to determine the identical geo-spatial entities, and an optimal model is constructed for geo-spatial ontology matching problem. The experimental results show that cEA-based geo-spatial ontology matching technique can efficiently determine the alignment. © Springer Nature Switzerland AG 2019.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to Intrusion detection based on improved density peak clustering for imbalanced data on sensor-cloud systems Journal of Systems Architecture volume 118 (2021) 102212

引用

Journal of Systems Architecture 2021年 119卷

作者： Ming Yan Yewang Chen Xiaoliang Hu Dongdong Cheng Yi Chen Jixiang Du The College of Computer Science and Technology Huaqiao University Xiamen China Beijing Key Laboratory of Big Data Technology for Food Safety Beijing Technology and Business University Beijing China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Xiamen China College of Big Data and Intelligent Engineering Yangtze Normal University Chongqing China

来源：评论

学校读者我要写书评

暂无评论

Improved Quality Aware Network Using Quality and Max Pooling Based Late Feature Fusion for Video-Based Person Re-Identification

Improved Quality Aware Network Using Quality and Max Pooling...

引用

International Conference on computer Science and Network technology (ICCSNT)

作者： Yude Shi Xiao Ke Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Mathematics and Computer Science Fuzhou University Fuzhou China

ISBN: (纸本)9781728133003

Video-based person re-identification is an important research area in computer vision. Quality Aware Network (QAN) is a model that is robust to noise in the videos. It calculates the weighted average of all the frames' image features, with each frame's quality score as the weight, and generates a video feature. However, the QAN has poor ability to distinguish pedestrians with highly similar clothing. To address this problem, we analyze the advantages and shortcomings of Quality Pooling and Max Pooling in theory, and propose the Frame Quality and Max Pooling based Late Feature Fusion Method (QMFF). It aims at enhancing the QAN's ability to distinguish pedestrians with similar clothing. First, use Quality Pooling to get the initial ranking list. Then, for each Query, judge whether the top-N candidates in the ranking list are highly similar in clothing to one another. If the Query meets the similarity criterion, Max Pooling with Frame Quality Filter is used. Local salient features selected by Max Pooling help distinguish pedestrians more accurately. Experimental results on the iLIDS-VID dataset show that the proposed method is superior to the QAN and many recently proposed methods.

关键词： Videos Clothing Feature extraction Face recognition computer science Databases Training

来源：评论

学校读者我要写书评

暂无评论

Music Rhythm Customized Mobile Application Based on information Extraction 4th

Music Rhythm Customized Mobile Application Based on Informat...

引用

4th International Conference on Smart Computing and Communications, SmartCom 2019

作者： Li, Yining Hu, Wei Wang, Yonghao College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industria System Wuhan China Digital Media Lab Birmingham City University Birmingham United Kingdom

ISBN: (纸本)9783030341381

information extraction technology to be able to measure, store, collect all kinds of information, especially the direct access to important information, which is based on mobile applications and more convenient for the information gathering process, user and information feedback, greatly reduce the cost of information technology, makes the implementation of large-scale information extraction technology possible. As for this paper, first of all, mainly introduces the basic theory of music rhythm customization mobile application;Secondly, the development and implementation of this application are introduced;Finally, it summarizes and anticipates the future development trend of music rhythm customization technology. After implementation, users only need to import music or video that they want to modify, select the corresponding style or double speed, and then get relevant audio results through system software processing. And make music rhythm customization easy to operate, which remove a lot of irrelevant operations, so that users do not need to know the relevant professional knowledge can be processed. © 2019, Springer Nature Switzerland AG.

关键词： Music

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：