检索结果-内蒙古大学图书馆

International Conference on Computational Intelligence and Security

作者： Xiaobo Song Xinyi Zhang Xiaoli Wang Yuan Li The 20th Research Institute of China Electronics Technology Group Corporation Xi'an Shaanxi China School of Computer Science and Technology Xidian University Xi'an Shaanxi China Basic Course Teaching Department Xi'an Vocational and Technical College Xi'an Shaanxi China

Since climate changes and air pollution have a direct impact on the number of emergency respiratory patients visited, in this paper, we study predicting methods of daily patient visits in respiratory department based on deep learning. We validate our methods via experiments on the actual data of the First Affiliated Hospital of Xi'an Medical University. To improve the accuracy of prediction, we propose four data preprocessing methods, including meteorological lag and time sensitive method, sliding window method, seasonal classification method, as well as correlation analysis method. Experimental results show that the prediction accuracy of the deep learning model is improved from 76.28% to 86.37% after adopting our four preprocessing methods. The maximum error between predicted and actual visits is less than 20.

关键词： Climate change Data processing Patient monitoring Deep learning Medical services Respiratory system Predictive models

来源：评论

学校读者我要写书评

暂无评论

An Automatic Music Generation Method Based on Rscln_Transformer Network

SSRN

引用

SSRN 2022年

作者： Zhang, Yumei Lv, Xiaojiao Li, Qi Wu, Xiaojun Su, Yuping Yang, Honghong School of Computer Science Shaanxi Normal University Xi’an China Key Laboratory of Intelligent Computing and Service Technology for Folk Song Ministry of Culture and Tourism Xi’an China Key Laboratory of Modern Teaching Technology Ministry of Education Shaanxi Normal University Xi’an China

With the development of artificial intelligence and deep learning, a large number of music generation methods have been proposed. Recently, Transformer has been widely used in music generation. However, the structural complexity of music puts forward higher requirements for music generation. In this paper, we propose a new automatic music generation network which consists of a Recursive Skip Connection with Layer Normalization (RSCLN) model, a Transformer-XL model and a multi-head attention mechanism. Our method not only alleviate the gradient disappearance problem in the model training, but also increase the ability of the model to capture the correlation of music information before and after, so as to generate music works closer to the original music style. Effectiveness of the RSCLN_Transformer-XL music automatic generation method is verified through music similarity evaluation experiments using music structure similarity and listening test. The experimental results show that the RSCLN_Transformer-XL music automatic generation model can generate better music than the Transformer-XL model. © 2022, The Authors. All rights reserved.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Investigation of the Impact of Height and Bandwidth on Path Loss Exponent of 5G FR1 Wireless Networks at 800, 3500, and 5900 MHz 2

Investigation of the Impact of Height and Bandwidth on Path ...

引用

2nd International Conference on Multidisciplinary Engineering and Applied science, ICMEAS 2023

作者： Imam-Fulani, Yusuf Olayinka Faruk, Nasir Usman, Aliyu D. Abdulkarim, Abubakar Tekanyi, Abdoulie M.S Yaro, Abdulmalik S. Alozie, Emmanuel Garba, Salisu Adewole, Kayode S. Oloyede, Abdulkarim A. Sowande, Olugbenga A. Abdullahi Baba, Bashir Musa, Abdulwaheed Imoize, Agbotiname Lucky Adediran, Yinusa A. Olagunju, Hawau I. Taura, Lawan S. University of Ilorin Department of Telecommunication Science Ilorin Nigeria Ahmadu Bello University Department of Electronics and Telecommunication Engineering Zaria Nigeria Sule Lamido University Department of Information Technology Kafin Hausa Nigeria Sule Lamido University Directorate of Information and Communication Technology Kafin Hausa Nigeria Ahmadu Bello University Department of Electrical Engineering Zaria Nigeria Kampala International University Department of Electrical and Telecommunication Engineering Kampala Uganda University of Hradec Králové Faculty of Informatics and Management Department of Informatics and Qualitative Methods Hradec Králové Czech Republic Sule Lamido University Department of Software Engineering Kafin Hausa Nigeria University of Ilorin Department of Computer Science Ilorin Nigeria Kwara State University Department of Electrical and Computer Engineering Malete Nigeria University of Johannesburg Institute for Intelligent Systems Johannesburg South Africa University of Lagos Department of Electrical and Electronics Engineering Lagos Nigeria Ruhr University Institute of Digital Communication Department of Electrical Engineering and Information Technology Bochum Germany University of Ilorin Department of Electrical and Electronics Engineering Ilorin Nigeria Sule Lamido University Department of Physics Kafin Hausa Nigeria

ISBN: (纸本)9798350358834

5G communication systems provide an end-to-end wireless connection to billions of users and devices across the globe. The quality of signals received during radio communication is notably influenced by the behavior of the radio propagation channel. A major parameter used in characterizing this channel is the Path Loss Exponent (PLE). Several works that have estimated and analyzed the PLE mostly considered the effect of distance and carrier frequency. However, the effect of base station antenna height and channel bandwidth on the PLE for 5G networks have not been adequately considered. To address this, the impact of antenna height of base station and channel bandwidth on the PLE within the 5G Frequency Range 1 (FR1) frequencies was investigated in this study, specifically at 800, 3500, and 5900 MHz. The licensed EDX Signal Pro software® with Cirrus high resolution global terrain and clutter data base was utilized to model, simulate and analyze the PLE for Kano City, Nigeria. Results showed that for the tested frequencies, an increase in either base station height or channel bandwidth leads to a significant reduction in the PLE. This study can be utilized by network planning engineers and the wireless research community to further improve network implementation and optimization toward understanding the behavior of signal propagation in 5G networks and beyond. © 2023 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Kepler problem and chiral effective dynamics

arXiv

引用

arXiv 2022年

作者： Bolonek-Lasoń, Katarzyna Gonera, Joanna Kosiński, Piotr Department of Statistical Methods Faculty of Economics and Sociology University of Lodz 41/43 Rewolucji 1905 St. Lodz90-214 Poland Department of Computer Science Faculty of Physics and Applied Informatics University of Lodz 149/153 Pomorska St. Lodz90-236 Poland

It is shown that by an appropriate canonical transformation Kepler dynamics can be put in the form which allows to exhibit the structure of the symmetry transformations related to the superintegrability. They appear to fit nicely into general scheme of nonlinear realizations. In new coordinates the Kepler dynamics results from dimensional reduction of that describing low energy mesons with spontaneously broken chiral symmetry. Copyright © 2022, The Authors. All rights reserved.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Research on Generating Xi'an Drum Music Based on Generative Adversarial Network

Research on Generating Xi'an Drum Music Based on Generative ...

引用

Sensors, Electronics and computer Engineering (ICSECE), IEEE International Conference on

作者： Tianmian Liang Peng Li Yumei Cao Xiaojun Wu Huifang Zhao Chenye Qi Ministry of Culture and Tourism Key Laboratory of Intelligent Computing and Service Technology for Folk Song Xi’an China School of Computer Science Shaanxi Normal University Xi'an China Key Laboratory of Modern Teaching Technology Ministry of Education Xi’an China Engineering Laboratory of Teaching Information Technology of Shaanxi Province Xi’an China Xi'an Key Laboratory of Cultural Tourism Resources Development and Utilization Xi’an China School of Music Shaanxi Normal University Xi'an China

Currently most AI music generator platforms mainly focus on creating modern music, without focusing on the creation of folk music. And most music generation neural network models use recursive neural networks and their variants, resulting in excessively repetitive music information, greatly reducing the fun of music. When using only generative adversarial networks (GANs) to generate music, it is easy to experience unstable training, vanishing gradients, and mode collapse. Failure to consider time dependence can reduce the authenticity of generated music. In order to solve the problem that most of the conventional deep learning GAN music generation network models do not consider music theory rules in music generation and Xi'an drum music faces the scarcity of tracks and difficulties in composition, we proposed a GAN network music generative model based on music theory rules and characteristics of Chinese Folk Songs. When generating music, the generator CNN and the regulator CNN train together, and generate music melodies under the constraints of the voice column CNN module. The generated results are sent to the discriminator CNN, which submits feedback to the generator CNN for competition, to compensate for the shortcomings of previous technology and ultimately generate better melodies, thereby improving the authenticity, sweetness, and rhythm of the generated music.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Designing Problem-based Learning at a Department Level in Resources and Environment: An Interdisciplinary Study 22

Designing Problem-based Learning at a Department Level in Re...

引用

Proceedings of the 14th International Conference on Education Technology and computers

作者： Fenghua Li Chong Han Chunfang Zhou Mei Wang Dianyao Gong Che Yang Tao Du PBL Teaching Innovation Research Center of Northeastern University Department of Resources and Environment School of metallurgy Northeastern University China Department of Resources and Environment School of metallurgy Northeastern University China Department of Mathematics and Computer Science University of Southern Denmark Denmark The State Ley Laboratory of Rolling and Automation Northeastern University China School of metallurgy Northeastern University China

ISBN: (纸本)9781450397766

Interdisciplinary research, which aims to solve practical issues in the realm of industrial applications, has emerged as a key trend in the current transformation of knowledge production mode, creating a new type of educational strategy to match. Problem-based Learning (PBL) is a teaching paradigm that emphasizes the practical orientation and application qualities of a college education. Northeastern University's Resources and Environment department arose from the need to address complicated environmental challenges. It has inherent interdisciplinary characteristics and bears the social duty of sustainable development. The discipline seeks to link "Practical Cognition" with "Disciplinary Logic," as well as realign the "target-content-method" of education to meet current demands. The teaching-learning practice tries to correspond to the professional training goals and the student's capability output through the reform and practice of a divisional level with the PBL method, integration of multidisciplinary and industrial resources, carrying out teaching-learning activities based on interdisciplinary theory and PBL principles, improving students' transformative skills, and rebuilding sustainable social responsibilities.

关键词： Transformative skills teaching alignment Problem-based learning Interdisciplinary

来源：评论

学校读者我要写书评

暂无评论

Tensor-based Multimodal Learning for Prediction of Pulmonary Arterial Wedge Pressure from Cardiac MRI

arXiv

引用

arXiv 2023年

作者： Tripathi, Prasun C. Suvon, Mohammod N.I. Schobs, Lawrence Zhou, Shuo Alabed, Samer Swift, Andrew J. Lu, Haiping Department of Computer Science University of Sheffield Sheffield United Kingdom Centre for Machine Intelligence University of Sheffield Sheffield United Kingdom Department of Infection Immunity and Cardiovascular Disease University of Sheffield Sheffield United Kingdom Department of Clinical Radiology Sheffield Teaching Hospitals Sheffield United Kingdom INSIGNEO Institute for in Silico Medicine University of Sheffield Sheffield United Kingdom

Heart failure is a severe and life-threatening condition that can lead to elevated pressure in the left ventricle. Pulmonary Arterial Wedge Pressure (PAWP) is an important surrogate marker indicating high pressure in the left ventricle. PAWP is determined by Right Heart Catheterization (RHC) but it is an invasive procedure. A noninvasive method is useful in quickly identifying high-risk patients from a large population. In this work, we develop a tensor learning-based pipeline for identifying PAWP from multimodal cardiac Magnetic Resonance Imaging (MRI). This pipeline extracts spatial and temporal features from high-dimensional scans. For quality control, we incorporate an uncertainty-based binning strategy to identify poor-quality training samples. We leverage complementary information by integrating features from multimodal data: cardiac MRI with short-axis and four-chamber views, and cardiac measurements. The experimental analysis on a large cohort of 1346 subjects who underwent the RHC procedure for PAWP estimation indicates that the proposed pipeline has a diagnostic value and can produce promising performance with significant improvement over the baseline in clinical practice (i.e., ∆AUC = 0.10, ∆Accuracy = 0.06, and ∆MCC = 0.39). The decision curve analysis further confirms the clinical utility of our method. The source code can be found at: https://***/prasunc/PAWP. © 2023, CC BY.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Big Data Security and Privacy Protection in Colleges and Universities

Big Data Security and Privacy Protection in Colleges and Uni...

引用

International Conference on Intelligent Systems Applications in Multi-modal Information Analytics, 2019

作者： Guo, Jinlan Computer Teaching Department Shanghai University of Political Science and Law Shanghai China

ISBN: (纸本)9783030157388

An increasing number of universities choose to deploy big data and cloud computing to integrate information from various departments, and adopt data mining technology to improve teaching management levels and decision-making abilities. Based on the acquisition, storage, application and publishing of data, this paper proposes the whole technology framework of big data security system from three levels of network, equipment and application, and puts forward to strategies which can protect individual privacy in each link. © 2019, Springer Nature Switzerland AG.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

A privacy preserving algorithm for mining rare association rules by homomorphic encryption 6

A privacy preserving algorithm for mining rare association r...

引用

6th International Conference on Systems and Informatics, ICSAI 2019

作者： Ouyang, Weimin Huang, Qinhua Shanghai University of Political Science and Law Department of Computer Teaching Shanghai China

ISBN: (纸本)9781728152561

Privacy-preserving data mining have greate significance in the era of big data. The Privacy-preserving condition on rare association rules mining is about the sensitive information regarding participants. Each side have a private dataset, aims to collaboratively find rare association rules on data set like a logically unified frame, but actually composed of distributed private data set. We proposed a new efficient algorithm to discover privacy-preserving rare association rule mining technique. The main principle idea is that with the secure two-party computation theory we employ homomorphic encryption to hide the private information. © 2019 IEEE.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Deep Integration of Innovation and Entrepreneurship(InE)Education in Chinese University Classrooms

引用

计算机教育 2021年第12期 25-33页

作者： Yuli Zhao Yin Zhang Bin Zhang Kening Gao Hai Yu Zhiliang Zhu Software College Northeastern UniversityShenyang110000China Software College and the PBL Teaching Innovation and Research Center Northeastern UniversityShenyang110000China College of Computer Science and Engineering Northeastern UniversityShenyang110000China

Recently,InE has been regarded as a popular education strategy in Chinese ***,problems have been exposed in the adoption of InE,for example,in InE courses and *** purpose of this paper is to provide a possible solution to the problems,which is to organize effective InE courses by integrating InE with Inter-Course-level Problem-Based Learning(ICPBL).A detailed case is demonstrated by an ICPBL elective course design with deep integration of InE in the teaching,learning,and *** paper contributes to a new curriculum design for promoting InE education in practically for Chinese universities.

关键词： Engineering Education Innovation and Entrepreneurship Intercourse Inter-Course-level Problem-Based Learning(ICPBL)

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：