检索结果-内蒙古大学图书馆

IAF Space Education and Outreach Symposium 2021 at the 72nd International Astronautical Congress, IAC 2021

作者： Bering, Edgar A. Khan, Shuhab Moges, Mequanint Hampton, Donald Mölders, Nicole Thorsen, Denise Dunbar, Bonnie J. Lefer, Barry L. Gamblin, Rachel B. Greer, Michael Greer, Presley Gunawan, Bryan Hernandez, Elizabeth Lehnen, Jamie Nguyencuu, Andy Piña, Megan Porat, Itay Prince, John R. Pessoa, Ana Gabriela Simmons, James Tovar, Chloe Ulinski, Alexandra Departments of Physics and Electrical Engineering University of Houston 3507 Cullen Blvd. #617 HoustonTX77204-5005 United States Department of Earth and Atmospheric Sciences University of Houston 3507 Cullen Blvd. #312 HoustonTX77204-5007 United States Department of Engineering Technology 4730 Calhoun Road #304 HoustonTX77204-4020 United States Geophysical Institute University of Alaska Fairbanks 2156 Koyukuk Drive FairbanksAK99775 United States Department of Aerospace Engineering Texas A&M University 701 H.R. Bright Bldg. #609B College StationTX77843-3141 United States Tropospheric Composition Program Earth Sciences Division NASA Headquarters 300 E St SW WashingtonDC20024 United States NASA Johnson Space Center Cimarron Software Services Inc. 2101 NASA Parkway HoustonTX77058 United States Alumni University of Houston 3507 Cullen Blvd. HoustonTX77204 United States UT Southwestern Medical Center 5323 Harry Hines Blvd DallasTX75390 United States Department of Computer Science University of Houston 3551 Cullen Blvd. #501 HoustonTX77204-3010 United States University of Pennsylvania School of Design 210 S. 34th St. PhiladelphiaPA19104 United States

ISBN: (纸本)9781713843177

The Undergraduate Student Instrumentation Project (USIP) was a NASA program created to engage undergraduate students in rigorous scientific research for the purposes of innovation and developing the next generation of professionals in space research. It is now run by the University of Houston using local resources. This student-led project, based on the 5E instructional model, is executed by the students from initial ideation of research objectives to the design, testing, and deployment of scientific payloads. The 5E Instructional model places the student at the center of knowledge building, while instructors facilitate interaction with content and guide the inquiry process. Since 2013, this project has been not only an effective vehicle for delivering STEM education but is also effective in increasing classroom engagement and interest in space. Space research is inherently interdisciplinary and crosscuts Geoscience, engineering, and Technology. The project is designed to integrate engineering, technology, physics, material science, and earth and atmospheric sciences as an important opportunity for the students to gain access to cross-disciplinary experiential research. In addition to classroom engagement, the students build their own payloads and ground instruments. This project increases students’ command of essential skills such as teamwork, collaboration, problem solving, technology, communication, innovation, and leadership. For the faculty, the project was an extended exercise in professional development, learning how to implement project level inquiry-based education on this scale. For the students, this formative experience continues to encourage the development of a much broader range of technical skills than is typically offered within an undergraduate degree. Furthermore, the extensive time and energy that students commit to this project promotes a strong sense of personal and professional responsibility and emphasizes the necessity of coherent teamwork.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Variational Autoencoder based Latent Factor Decoding of Multichannel EEG for Emotion Recognition

Variational Autoencoder based Latent Factor Decoding of Mult...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xiang Li Zhigang Zhao Dawei Song Yazhou Zhang Chunyang Niu Junwei Zhang Jidong Huo Jing Li Key Laboratory of Medical Artificial Intelligence Shandong Computer Science Center National Supercomputer Center in Jinan Qilu University of Technology Shandong Academy of Sciences China School of Computer Science and Technology Beijing Institute of Technology China Software Engineering College Zhengzhou University of Light Industry China School of Computer Science and Technology Tianjin University China Jiuquan Satellite Launch Center China

Robust cross-subject emotion recognition based on multichannel EEG has always been a hard work. In this work, we hypothesize there exists default brain variables across subjects in emotional processes. Hence, the states of the latent variables that related to emotional processing must contribute to building robust recognition models. We propose to utilize variational autoencoder (VAE) to determine the latent factors from the multichannel EEG. Through sequence modeling method, we examine the emotion recognition performance based on the learnt latent factors. The performance of the proposed methodology is verified on two public datasets (DEAP and SEED), and compared with traditional matrix factorization based (ICA) and autoencoder based (AE) approaches. Experimental results demonstrate that neural network is suitable for unsupervised EEG modeling and our proposed emotion recognition framework achieves the state-of-the-art performance. As far as we know, it is the first work that introduces VAE into multichannel EEG decoding for emotion recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-View Unsupervised Feature Selection with Dynamic Sample Space Structure

Multi-View Unsupervised Feature Selection with Dynamic Sampl...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Leyuan Zhang Meiling Liu Rifeng Wang Tingting Du Jiaye Li Guangxi Key Lab of Multi-source Information Mining & Securit Guangxi Normal University Guilin China College of Software and Information Security Guangxi University for Natinalities Nanning China School of Computer Science and Communication Engineering Guangxi University of Science and Technology Liuzhou China

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

With the rapid growth of complex high-dimensional sparse data and the limitation of a single perspective, there is an increasing demand for new methods of feature selection from multiple perspectives. The feature selection method based on minimum regression is usually learning projection matrix, which is lack of theoretical explanation to evaluate the importance of features. Moreover, these methods cannot find the global and sparse solutions of the projection matrix. In this paper, we propose a new multi-view unsupervised feature selection method, which can learn the global and sparse solutions of the projection matrix. The new method extends the least squares regression model by adjusting the regression coefficients in least squares regression by using a set of scale factors for feature ranking. It shows that the new model can learn global and sparse solutions. In addition, the introduction of the scale factor provides a theoretical explanation for why we can use the projection matrix to sort features. In order to optimize the new model, a simple and effective algorithm for proof convergence is proposed. By classifying and clustering the data after feature selection, we can see the superiority of our algorithm.

关键词： Feature extraction Sparse matrices Computational modeling Heuristic algorithms Training Correlation Euclidean distance

来源：评论

学校读者我要写书评

暂无评论

A Cat Swarm Optimization-Based QoS Routing in ICN

A Cat Swarm Optimization-Based QoS Routing in ICN

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Dandan Cheng Xingwei Wang Shuang Zhang Min Huang College of Computer Science and Engineering Shenyang China College of Software Shenyang China College of Information Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9781538680988;9781538680971

Information-Centric Networking (ICN), as a promising networking paradigm, is facing some challenges with its routing, such as content retrieval, efficiency, etc. In this paper, a Cat Swarm Optimization (CSO)based Quality of Service (QoS)Routing mechanism (CSOQR)is proposed to solve the routing problems in ICN. Firstly, a network model is built to imitate biological behaviors including link model and intelligent node model. Secondly, a user's Quality of Experience (QoE)is mapped to the corresponding QoS level, thus the user's QoS satisfaction is calculated. Then, the forwarding probability of an interface is calculated according to user's QoS satisfaction, and two forwarding interfaces are selected respectively based on Tracing Mode Face Choosing (TMFC)and Seeking Mode Face Choosing (SMFC). In this way, multiple content sources can be found through multiple paths to improve routing success rate, and we devise a migration strategy to balance node load. Finally, the proposed mechanism is simulated on both CERNET and CERNET2. Simulation results show that the proposed CSOQR has good performance in terms of routing success rate, routing hop count and node load.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Community-based Malware Immunization Strategy

Community-based Malware Immunization Strategy

引用

International Conference on Systems and Informatics (ICSAI)

作者： Wei Yang Li Zhang Teng Chen Yu Yao Software College Northeastern University Shenyang China Huawei Technologies Co. Ltd Beijing China School of Computer Science and Engineering Northeastern University Shenyang China Engineering Research Center of Security Technology of Complex Network System Ministry of Education Shenyang China

ISBN: (数字)9781728152561

ISBN: (纸本)9781728152578

In recent years, security threats have occurred frequently, especially the large-scale spread of malware has brought huge losses to individuals and the country as a whole. This paper considers the nodes of the network have the feature of forming a community. A community-based malware immunization strategy is proposed according to the characteristics that information spread quickly within the community and spread slowly between communities. A concrete community detection method is proposed based on the K-shell and the label propagation algorithm, as well as key node selection algorithm is proposed in order to control the outbreak of malicious code with the fastest speed and at the lowest cost. The experiments demonstrate that the proposed approach can achieve maximum immunity with minimal cost comparing to classical immunization strategies.

关键词： Informatics

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid collaborative filtering approach to recommendation using reviews:the product attributes perspective 30

A novel hybrid collaborative filtering approach to recommend...

引用

30th International Conference on software engineering and Knowledge engineering, SEKE 2018

作者： Cao, Min Zhou, Sijing Gao, Honghao Li, Youhuizi School of Computer Engineering and Science Shanghai University Shanghai200444 China Computing Center Shanghai University Shanghai200444 China Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai201112 China College of Computer Hangzhou Dianzi University Hangzhou310018 China

ISBN: (纸本)1891706446

The product recommendation research has been focusing on modelling users' reviews to construct the relation of users and products. Thus, the recommended performance can be improved by obtaining virtual ratings from corresponding reviews. However, these perspectives on reviews do not take into account the product field characteristic, which may impact the recommendation performance. To this point, this paper proposes a hybrid collaborative filtering approach to compute the correlation value considering product attributes. First, Product Attribute Weight and Product Attribute Score are introduced to formalize the product attributes for user and product respectively in a quantitative way. After that, the recommended ranking formula for the new model is presented. Finally, we carry out experimental analysis to show our method can effectively improve the performance of recommendation under a sparseness dataset. © 2018 Universitat zu Koln. All rights reserved.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Enhancing countries' fitness with recommender systems on the international trade network

arXiv

引用

arXiv 2019年

作者： Liao, Hao Wu, Xing-Tong Vidmer, Alexandre Huang, Xiao-Min Liu, Ming-Kai Zhou, Mingyang Zhang, Yi-Cheng National Engineering Laboratory for Big Data System Computing Technology Guangdong Province Key Laboratory of Popular High Performance Computers College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Physics University of Fribourg Fribourg1700 Switzerland

Prediction is one of the major challenges in complex systems. The prediction methods have shown to be effective predictors of the evolution of networks. These methods can help policy makers to solve practical problems successfully and make better strategy for the future. In this work, we focus on exporting countries' data of the international trading network. A recommendation system is then used to identify the products corresponding to the production capacity of each individual country, but are somehow overlook by the country. Then, we simulate the evolution of the country's fitness if it would have followed the recommendations. The result of this work is the combination combine these two methods to provide insights to countries on how to enhance the diversification of their exported products in a scientific way and improve national competitiveness significantly, especially for developing countries. Copyright © 2019, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient hybrid precoding design for integrated multicast-unicast millimeter wave communications with SWIPT

arXiv

引用

arXiv 2020年

作者： Hao, Wanming Sun, Gangcan Zhou, Fuhui Mi, De Shi, Jia Xiao, Pei Leung, Victor C.M. School of Information Engineering Zhengzhou University Zhengzhou450001 China 5G Innovation Center Institute of Communication Systems University of Surrey GuildfordGU2 7XH United Kingdom 5G Innovation Center Institute of Communication Systems University of Surrey GuildfordGU2 7XH United Kingdom College of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics Nanjing210000 China State Key Laboratory of Integrated Services Networks Xi'dian University Xian710071 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Electrical and Computer Engineering University of British Columbia VancouverBCV6T1Z4 Canada

In this paper, we investigate the energy-efficient hybrid precoding design for integrated multicast-unicast millimeter wave (mmWave) system, where the simultaneous wireless information and power transform is considered at receivers. We adopt two sparse radio frequency chain antenna structures at the base station (BS), i.e., fully-connected and subarray structures, and design the codebook-based analog precoding according to the different structures. Then, we formulate a joint digital multicast, unicast precoding and power splitting ratio optimization problem to maximize the energy efficiency of the system, while the maximum transmit power at the BS and minimum harvested energy at receivers are considered. Due to its difficulty to directly solve the formulated problem, we equivalently transform the fractional objective function into a subtractive form one and propose a two-loop iterative algorithm to solve it. For the outer loop, the classic Bi-section iterative algorithm is applied. For the inner loop, we transform the formulated problem into a convex one by successive convex approximation techniques and propose an iterative algorithm to solve it. Meanwhile, to reduce the complexity of the inner loop, we develop a zero forcing (ZF) technique-based low complexity iterative algorithm. Specifically, the ZF technique is applied to cancel the inter-unicast interference and the first order Taylor approximation is used for the convexification of the non-convex constraints in the original problem. Finally, simulation results are provided to compare the performance of the proposed algorithms under different schemes. Copyright © 2020, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

PNet: An Efficient Network for Pneumonia Detection 12

PNet: An Efficient Network for Pneumonia Detection

引用

12th International Congress on Image and Signal Processing, BioMedical engineering and Informatics, CISP-BMEI 2019

作者： Li, Zhongliang Yu, Juan Li, Xuechen Li, Yingqi Dai, Weicai Shen, Linlin Mou, Lisha Pu, Zuhui Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Institute of Translational Medicine Shenzhen University Health Science Center Shenzhen University School of Medicine Shenzhen China Imaging Department Shenzhen University Health Science Center Shenzhen University School of Medicine Shenzhen China Shenzhen Second People's Hospital First Affiliated Hospital Shenzhen University Shenzhen China Imaging Department Shenzhen Bao'an District Songgang People's Hospital Shenzhen China Imaging Department Fifth People's Hospital of Longgang District Shenzhen China

ISBN: (纸本)9781728148526

Pneumonia is a common lung disease and affects millions of people worldwide each year. The chest X-ray is one of the most commonly accessible radiological examinations for screening and diagnosing lung diseases. Usually, chest X-ray images (CXRs) are taken at physical examination and evaluated by radiologists. The unbalance between tremendous numbers of CXRs and limited number of radiologists need to be solved by computer Assisted Diagnosis (CAD). As deep neural networks have shown promising results in CAD, we implemented a deep learning-based framework, PNet, for pneumonia detection. 10784 chest X-ray images collected at the Shenzhen No.2 People's Hospital were employed for training and evaluation. The experimental results showed that the proposed PNet (1,695,777 parameters) achieved higher accuracy and F1 score than classical networks like AlexNet (42,725,889 parameters) and VGG16 (27,560,769 parameters). © 2019 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Data poisoning attacks on neighborhood-based recommender systems

arXiv

引用

arXiv 2019年

作者： Chen, Liang Xu, Yangjun Xie, Fenfang Huang, Min Zheng, Zibin school of data and computer science Sun Yat-Sen University Guangzhou China school of data and computer science Sun Yat-Sen University Guangzhou China National Engineering Research Center of Digital Life Sun Yat-sen University Guangzhou China College of software South China University of Technology Guangzhou China

Nowadays, collaborative filtering recommender systems have been widely deployed in many commercial companies to make profit. Neighbourhood-based collaborative filtering is common and effective. To date, despite its effectiveness, there has been little effort to explore their robustness and the impact of data poisoning attacks on their performance. Can the neighbourhood-based recommender systems be easily fooled? To this end, we shed light on the robustness of neighbourhood-based recommender systems and propose a novel data poisoning attack framework encoding the purpose of attack and constraint against them. We firstly illustrate how to calculate the optimal data poisoning attack, namely UNAttack. We inject a few well-designed fake users into the recommender systems such that target items will be recommended to as many normal users as possible. Extensive experiments are conducted on three real-world datasets to validate the effectiveness and the transferability of our proposed method. Besides, some interesting phenomenons can be found. For example, 1) neighbourhood-based recommender systems with Euclidean Distance-based similarity have strong robustness. 2) the fake users can be transferred to attack the state-of-the-art collaborative filtering recommender systems such as Neural Collaborative Filtering and Bayesian Personalized Ranking Matrix Factorization. Copyright © 2019, The Authors. All rights reserved.

关键词： Recommender 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：