检索结果-内蒙古大学图书馆

2017 International Conference on Mathematics, Modelling and Simulation Technologies and Applications（MMSTA 2017)

作者： Wan-li SONG Wei-wei CHEN Ming-zhu ZHANG Key Laboratory of Trusted Cloud Computing and Big Data Analysis School of Information EngineeringNanjing Xiao Zhuang University

It is a tough task for teachers to answer all questions from students effectively and *** this paper,we design and implements an intelligent question answering system using Natural Language Processing,template classification,support vector *** system also calculates the similarity between the question and answer pairs by cosine similarity algorithm,and returns the most similar *** the user is not satisfied with the answer,the system will write the question into the public section to fall back on other *** answer will be evaluated and added to the QA base if it is passed with the corresponding *** that the questions and answers in the QA base continue to *** use the QA base of a network forum as the basic library to carry out the *** implementation and experimental results indicate that the proposed approach is achievable.

关键词： Intelligent system Question classification Question similarity Cosine similarity

来源：评论

学校读者我要写书评

暂无评论

Exploring deep gradient information for biometric image feature representation

引用

Neurocomputing 2016年 213卷 162-171页

作者： Jianjun Qian Jian Yang Ying Tai Hao Zheng School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Trusted Cloud Computing and Big Data Analysis Nanjing Xiaozhuang University China

This paper presents a novel but simple biometric image feature representation method, called exploring deep gradient information (DGI). DGI first captures the local structure of an image by computing the histogram of gradient orientation of each macro-pixel (local patch around the reference pixel). Thus, one image can be decomposed into L sub-images (sub-orientation images) according to the gradient information of each macro-pixel since there are L bins in the local histogram. To enrich the gradient information, we also consider the gradient orientation and magnitude of original image as sub-images. For each sub-image, histogram of oriented gradient (HOG) is used to further explore the gradient orientation information. All HOG features are concatenated into one augmented super-vector. Finally, fisher linear discriminate analysis (FLDA) is applied to obtain the low-dimensional and discriminative feature vector. We evaluated the proposed method on the real-world face image datasets NUST-RWFR, Pubfig and LFW, the PolyU Finger-Knuckle-Print database and the PolyU Palmprint database. Experimental results clearly demonstrate the effectiveness of the proposed DGI compared with state-of-the-art algorithms, e.g., SIFT, HOG, LBP, POEM, LARK and IDLS.

关键词： Image representation Deep gradients Feature extraction Biometrics

来源：评论

学校读者我要写书评

暂无评论

Online Test Paper Composition Based on Genetic Algorithm

Online Test Paper Composition Based on Genetic Algorithm

引用

2018 3rd International Conference on Modelling, Simulation and Applied Mathematics(MSAM 2018)

作者： Wanli Song School of Information Engineering Nanjing Xiaozhuang University Key Laboratory of Trusted Cloud Computing and Big Data Analysis Nanjing XiaoZhuang University

The application of online examination is used more and more widely. Test paper composition is the core function in this application. Online examination system requires that the test paper should be quick and flexible, and the composition of questions should be reasonable and random. Test paper should not only meet the specific needs of users, ensure fairness, impartiality, but also be accurate and efficient. The intelligent test paper composition algorithm based on genetic algorithm is studied in this paper. Then this method is used to organize the structure of the test paper automatically, composites the examination content. Proposals are put forward to examines the degree of students' mastery of knowledge based on this method. This algorithm can automatically composite test papers according to the conditions of difficulty degree, knowledge coverage, and the proportion of questions. It can automatically composite test papers for online assessment. The practice of online testing system based on this algorithm shows that the algorithm is scientific and effective. On the premise of guaranteeing the quality of the test paper, it greatly improves the efficiency and pertinence of online testing. It is beneficial to improve students' learning efficiency and intellectualization of education.

关键词： test paper composition education intellectualization genetic algorithm E-learning

来源：评论

学校读者我要写书评

暂无评论

News Recommendation System Based on Collaborative Filtering and SVM

News Recommendation System Based on Collaborative Filtering ...

引用

2018 3rd International Conference on Automation, Mechanical and Electrical Engineering (AMEE 2018)

作者： Wan-li SONG School of Information Engineering Nanjing Xiaozhuang University Key Laboratory of Trusted Cloud Computing and Big Data Analysis Nanjing Xiao Zhuang University

News system requires news classification and personalized recommendation to improve user's efficiency and interest, and to enhance user's experiences. This paper constructed a news automatic classification and recommendation system through natural language processing, text classification, collaborative filtering algorithm. The published news contents were word-segmented and model-trained automatically first to determine which category the news belonging to. Users can also manually modify the classification so that later classification can be updated and improved. After that, the similarity between users was calculated by collaborative filtering and the users having higher similarity with the recommended users were selected. The news seen by the certain users were recommended to the users that were divided into the same group. This paper takes the news corpus of Fudan University's text classification research center as experimental data. Text classification accuracy is tested by this corpus. The experimental results show that the system can serve the news users well. It achieves effective classification and recommendation of news personally.

关键词： Recommendation algorithm Automatic classification Similarity Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Schema-driven performance evaluation for highly concurrent scenarios 23rd

Schema-driven performance evaluation for highly concurrent s...

引用

23rd International Conference on database Systems for Advanced Applications, DASFAA 2018

作者： Zhang, Jingwei Feng, Li Yang, Qing Lin, Yuming Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic Technology Guilin541004 China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin541004 China Guangxi Key Laboratory of Automatic Measurement Technology and Instrument Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9783319914541

Online applications needs to support highly concurrent access and to response to users as soon as possible. Two primary factors make the above requirements to be a technical challenge, one is the large user base, the other is the sharp rise in traffic caused by some specific activities, such as ticketing on *** during Spring Festival season, shopping on *** during its dual 11 promotions, etc. For the latter, a core focus is how to expand the performance of those existing hardware and software and then to ensure the quality of services when a sharp rise on access happened. Since database schemas have a direct link with data access granularity, etc., this paper considers database schemas as an important factor for performance optimization on highly concurrent access and also covers other elements affecting access performance, such as cache, concurrency, etc., to analyze the performance factors for databases. Extensive experiments are designed to conduct both performance testing and analyzing under different schemas. The experimental results show that a reasonable configuration can contribute a good database performance, which provides factual basis for optimizing highly concurrent applications. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： database systems

来源：评论

学校读者我要写书评

暂无评论

Time-based trajectory data partitioning for efficient range query 23rd

Time-based trajectory data partitioning for efficient range ...

引用

23rd International Conference on database Systems for Advanced Applications, DASFAA 2018

作者： Yue, Zhongwei Zhang, Jingwei Zhang, Huibing Yang, Qing Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin541004 China Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic Technology Guilin541004 China Guangxi Key Laboratory of Automatic Measurement Technology and Instrument Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9783319914541

The popularity of mobile terminals has given rise to an extremely large number of trajectories of moving objects. As a result, it is critical to provide effective and efficient query operations on large-scale trajectory data for further retrieval and analysis. Considering data partition has a great influence on processing large-scale data, we present a time-based partitioning technique on trajectory data. This partitioning technique can be applied on the distributed framework to improve the performance of range queries on massive trajectory data. Furthermore, the proposed method adopts time-based hash strategy to ensure both the partition balancing and less partitioning time. Especially, existing trajectory data are not required to be repartitioned when new data arrive. Extensive experiments on three real data sets demonstrated that the performance of the proposed technique outperformed other partitioning techniques. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network based Relation Extraction: An overview

arXiv

引用

arXiv 2021年

作者： Wang, Hailin Qin, Ke Zakari, Rufai Yusuf Lu, Guoming Yin, Jin Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

Knowledge is a formal way of understanding the world, providing a human-level cognition and intelligence for the next-generation artificial intelligence (AI). One of the representations of knowledge is semantic relations between entities. An effective way to automatically acquire this important knowledge, called Relation Extraction (RE), a sub-task of information extraction, plays a vital role in Natural Language Processing (NLP). Its purpose is to identify semantic relations between entities from natural language text. To date, there are several studies for RE in previous works, which have documented these techniques based on Deep Neural Networks (DNNs) become a prevailing technique in this research. Especially, the supervised and distant supervision methods based on DNNs are the most popular and reliable solutions for RE. This article 1) introduces some general concepts, and further 2) gives a comprehensive overview of DNNs in RE from two points of view: supervised RE, which attempts to improve the standard RE systems, and distant supervision RE, which adopts DNNs to design sentence encoder and de-noise method. We further 3) cover some novel methods and recent trends as well as discuss possible future research directions for this task. © 2021, CC0.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

ResLPA: Label Propagation with Residual Learning 2021

ResLPA: Label Propagation with Residual Learning

引用

7th International Conference on computing and Artificial Intelligence, ICCAI 2021

作者： Luo, Yi Huang, Rui Chen, Aiguo Zeng, Xi School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Lianyungang Jierui Electronics Co. Ltd. Lianyungang China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu China China Electronics Technology Cyber Security Co. Ltd. Chengdu China

ISBN: (纸本)9781450389501

Label Propagation Algorithm (LPA) predicts what label a node in a graph has by its accumulated label information after iteratively propagating label information among adjacent nodes. Subsequent studies of LPA try to assign weights on connections to adjust the propagation between different node pairs. However, such approaches still rely on the assumption that adjacent nodes should have similar labels. To predict when the label distribution may differ from this assumption, we propose Residual Label Propagation (ResLPA). It approximates residuals between labels with node features, then adds the approximated residuals to the label information as corrections before propagating. In experiments on five real-world graphs, ResLPA matches or exceeds state-of-the-art LPA-based methods, GCN-based methods and their integrations. © 2021 ACM.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Tourism Micro-blog Comments

Sentiment Analysis of Tourism Micro-blog Comments

引用

2016 International Conference on Artificial Intelligence: Techniques and Applications(AITA 2016)

作者： Wan-li SONG Jun-hua WANG Key Laboratory of Trusted Cloud Computing and Big Data Analysis School of Information EngineeringNanjing XiaoZhuang University Nanjing Vocational Institute of Transport Technology College of Computer and Information Hohai University

Recent years,an amount of tourism micro-blog comments on the Internet have become an important source of information for potential customers and to improve the service quality. These micro-blog comments do help to research tourism resources or services before making decisions. Thus,sentiment analysis of tourism micro-blog comments has become a hot issue in the field of natural language processing and text mining. We designed a system called SASTMC by using web crawler,Chinese words segmentation,emotion words dictionary and an improved TF-IDF algorithm. It enhances expression ability of sentiment information of text words. Experiments on Sina micro-blog comments datasets demonstrate that our method can do the task well.

关键词： Micro-blog comment Web crawler Words segmentation Sentiment analysis TF-IDF

来源：评论

学校读者我要写书评

暂无评论

Recommending more suitable music based on users’ real context 14th

Recommending more suitable music based on users’ real conte...

引用

14th EAI International Conference on Collaborative computing: Networking, Applications and Worksharing, CollaborateCom 2018

作者： Yang, Qing Zhan, Le Han, Li Zhang, Jingwei Bi, Zhongqin School of Electronic Engineering and Automation Guilin University of Electronic Technology Guilin541004 China Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic Technology Guilin541004 China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin541004 China College of Computer Science and Technology Shanghai University of Electronic Power Shanghai200090 China

ISBN: (纸本)9783030129804

Music recommendation is an popular function for personalized services and smart applications since it focuses on discovering users’ leisure preference. The traditional music recommendation strategy captured users’ music preference by analyzing their historical behaviors to conduct personalized recommendation. However, users’ current states, such as in busy working or in a leisure travel, etc., have an important influence on their music enjoyment. Usually, those existing methods only focus on pushing their favorite music to users, which may be not the most suitable for current scenarios. Users’ current states should be taken into account to make more perfect music recommendation. Considering the above problem, this paper proposes a music recommendation method by considering both users’ current states and their historical behaviors. First, a feature selection process based on ReliefF method is applied to discover the optimal features for the following recommendation. Second, we construct different feature groups according to the feature weights and introduce Naive Bayes model and Adaboost algorithm to train these feature groups, which will output a base classifier for each feature group. Finally, a majority voting strategy decides the optimal music type and each user will be recommended more suitable music based on their current context. The experiments on the real datasets show the effectiveness of the proposed method. © 2019, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Adaptive boosting

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：