检索结果-内蒙古大学图书馆

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： ling Lin Qian Yu Wen Ji Yang Gao State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Electronics and Information Engineering College Yili Normal University Yining Xinjiang China School of Data and Computer Science Shandong Womens University China

Along with the prosperity of the Mobile Internet, a large amount of stream data has emerged. Stream data cannot be completely stored in memory because of its massive volume and continuous arrival. Moreover, it should be accessed only once and handled in time due to the high cost of multiple accesses. Therefore, the intrinsic nature of stream data calls facilitates the development of a summary in the main memory to enable fast incremental learning and to allow working in limited time and memory. Sampling techniques are one of the commonly used methods for constructing data stream summaries. Given that the traditional random sampling algorithm deviates from the real data distribution and does not consider the true distribution of the stream data attributes, we propose a novel sampling algorithm based on feature-selected and -preserved algorithm. We first use matrix approximation to select important features in stream data. Then, the feature-preserved sampling algorithm is used to generate high-quality representative samples over a sliding window. The sampling quality of our algorithm could guarantee a high degree of consistency between the distribution of attribute values in the population (the entire data) and that in the sample. Experiments on real datasets show that the proposed algorithm can select a representative sample with high efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An ANTLR-based flattening framework for AltaRica 3.0 model

引用

International Journal of Performability engineering 2019年第9期15卷 2462-2475页

作者： Hu, Jun Chen, Shuo Chen, Defeng Kang, Jiexiang Wang, Hui College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China Department of Software China National Aeronautic Radio Electronics Research Institute Shanghai200233 China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing210007 China School of Mechanical Engineering Hefei University of Technology Hefei230601 China

AltaRica is a modeling language that is capable of hierarchical modelling and fault behavior description for industrial safety-critical system design. AltaRica 3.0 is the latest version, and its semantics are based on a formal GTS (Guarded Transition Systems) model. One of the key steps in the process of safety analysis toward AltaRica 3.0 models is that how to flatten a hierarchical AltaRica 3.0 model into a semantically equivalent GTS semantic model. This paper proposes an AltaRica 3.0 model flattening algorithm framework based on ANTLR (Another Tool for Language Recognition). Firstly, considering the different structural features of Block and Class, the AltaRica 3.0 model is sliced carefully in order to obtain the corresponding AST (Abstract Syntax Tree). Secondly, a set of recursive transformation algorithms are designed to extract and transform the AltaRica model elements, which are stored in the AST nodes based on the traversal technique of the AST. Then, a semantically equivalent flattened GTS model can be obtained. Lastly, several case studies show that the algorithms designed in this paper can effectively implement the flattening process of AltaRica 3.0 models. © 2019 Totem Publisher, Inc. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Lingke: A Fine-grained Multi-turn Chatbot for Customer Service 27

Lingke: A Fine-grained Multi-turn Chatbot for Customer Servi...

引用

27th International Conference on Computational Linguistics, COLING 2018

作者： Zhu, Pengfei Zhang, Zhuosheng Li, Jiangtong Huang, Yafang Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China College of Zhiyuan Shanghai Jiao Tong University China School of Computer Science and Software Engineering East China Normal University China

ISBN: (纸本)9781948087537

Traditional chatbots usually need a mass of human dialogue data, especially when using supervised machine learning method. Though they can easily deal with single-turn question answering, for multi-turn the performance is usually unsatisfactory. In this paper, we present Lingke, an information retrieval augmented chatbot which is able to answer questions based on given product introduction document and deal with multi-turn conversations. We will introduce a fine-grained pipeline processing to distill responses based on unstructured documents, and attentive sequential context-response matching for multi-turn conversations. © COLING *** right reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Solving Service Selection Problem Based on a Novel Multi-Objective Artificial Bees Colony Algorithm

引用

Journal of Shanghai Jiaotong university(science) 2017年第4期22卷 474-480页

作者：黄利萍张斌苑勋张长胜高岩 Software College Northeastern University School of Computer Science and Engineering Northeastern University Institute of Information Science & Engineering Shenyang Ligong University

Service computing is a new paradigm and has been widely used in many fields. The multi-objective service selection is a basic problem in service computing and it is non-deterministic polynomial (NP)-hard. This paper proposes a novel multi-objective artificial bees colony (n-MOABC) algorithm to solve service selection problem. A composite service instance is a food source in the algorithm. The fitness of a food source is related to the quality of service (QoS) attributes of a composite service instance. The search strategy of the bees are based on dominance. If a food source has not been updated in successive maximum trial (Max Trial) times, it will be abandoned. In experiment phase, a parallel approach is used based on map-reduce framework for n-MOABC algorithm. The performance of the algorithm has been tested on a variety of data sets. The computational results demonstrate the effectiveness of our approach in comparison to a novel bi-ant colony optimization (NBACO) algorithm and co-evolution algorithm. © 2017, Shanghai Jiaotong University and Springer-Verlag GmbH Germany.

关键词： novel multi-objective artificial bees colony(n-MOABC) multi-objective service selection search strategy

来源：评论

学校读者我要写书评

暂无评论

Erratum to “Entropy-based fuzzy support vector machine for imbalanced datasets” [Knowl.-Based Syst. 115 (2017) 87–99]

引用

Knowledge-Based Systems 2020年 192卷

作者： Salim Rezvani Xizhao Wang Big Data Institute College of Computer Science and Software Engineering Guangdong Key Lab. of Intelligent Information Processing Shenzhen University Shenzhen 518060 Guangdong China

In this note, we show that the calculation of statistics X F 2 and F F in sections 4.5 and 4.6 of the paper (Fan et al., 2017) is not correct. Also, based on the calculation of Critical Difference (CD) of Bonferroni–Dunn test, we show that the conclusion on ”significantly outperforming the compared algorithms”, drawn by the authors using the P -value test, is not convincing.

关键词： Information entropy fuzzy support vector machine Bonferroni–Dunn test Friedman test

来源：评论

学校读者我要写书评

暂无评论

Student Space Missions – Facilitating Pathways to Success for Next Generation Professionals in Space

Student Space Missions – Facilitating Pathways to Success f...

引用

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

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：