检索结果-内蒙古大学图书馆

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)

作者： Nikumani Choudhury Rakesh Matam Mithun Mukherjee Department of Computer Science & Engineering Indian Institute of Information Technology Guwahati India Guangdong Provincial Key Laboratory of Petrochemical Equipment Fault Diagnosis Guangdong University of Petrochemical Technology Maoming China

IEEE 802.15.4 devices operating in beacon-enabled mode synchronize their beacon transmissions to restrict collisions and increase network lifetime. Other avenues of conserving energy in these resource constrained networks is via adaptive duty-cycling. This can be achieved by accounting for the idle listening of a coordinator and its associated devices. But, duty-cycling in a synchronized network often results in loss of synchronization and necessitates re-synchronization. In this paper, we first showcase the scope for additional energy savings in a synchronized network that can be accounted for using a adaptive duty-cycling scheme. Thereafter, we present the necessary condition that needs to be met to perform duty-cycling. We analytically determine the associated cost of synchronization in presence of an active duty-cycling mechanism and compare it with the energy conserved by performing the later. The simulation results concur with our findings and emphasize on the need for operation of synchronization and duty-cycling schemes in sync with each other to boost the overall energy savings of the network.

关键词： Synchronization IEEE 802.15 Standard Schedules Network topology Receivers Energy consumption

来源：评论

学校读者我要写书评

暂无评论

Application of Case Teaching Method in Artificial Intelligence Teaching

Application of Case Teaching Method in Artificial Intelligen...

引用

作者： Li Huang Wei Hu Chong Tan College of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology

Aiming at the current situation of poor quality of artificial intelligence teaching and weak students' interest in learning, a case teaching method is proposed. This paper analyzes the teaching status of artificial intelligence firstly, and then systematically describes the case teaching method. Finally, the necessity of introducing case teaching method into artificial intelligence teaching is studied. Practice shows that the case teaching method can effectively enhance students' self-learning ability, improve students' comprehensive innovation ability, and promote the development of artificial intelligence teaching.

关键词： Case teaching method Artificial intelligence Teaching case Course

来源：评论

学校读者我要写书评

暂无评论

The Order and Failure Estimation of Redundancy System Based on Cobweb Model 4th

The Order and Failure Estimation of Redundancy System Based ...

引用

4th Euro-China Conference on Intelligent Data Analysis and Applications, ECC 2017

作者： Xie, Chao-Fan Xu, Lin Xu, Lu-Xiong Zhang, Fuquan Network Center Fuqing Branch of Fujian Normal University Fuqing FuzhouFujian China Economic Institute Fujian Normal University Fuqing FuzhouFujian China Electronic Information and Engineering Institute Fuqing Branch of Fujian Normal University Fuqing FuzhouFujian China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China School of Software Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9783319685267

In order to improve the reliability and life of components, product providers often take the form of redundant backup. The lower the failure rate of the product itself and the more the number of redundant backups, the more reliable and stable system is, but the number of redundant backups will greatly increase the cost of the product. Moreover, the product can not be detected through dismantling products to achieve, This provides the provider with the possibility of speculation, so the provider will provide a lower degree of redundancy of products or secondary products with high-level redundancy is a huge problem faced by buyers. The study will use the method of truncation estimation to make a asymptotic estimation, provide statistic reference formula and feasible calculation method for the purchaser, which can greatly reduce the cost of the demand and the reliability of the system operation. © 2018, Springer International Publishing AG.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Lighting the way to a smart world: Lattice-based cryptography for internet of things

arXiv

引用

arXiv 2018年

作者： Xu, Rui Cheng, Chi Qin, Yue Jiang, Tao Hubei Key Laboratory of Intelligent Geo-Information Processing School of Computer Science China University of Geosciences Wuhan China School of Electronics Information and Communications Huazhong University of Science and Technology Wuhan China

The Ukraine power grid cyberattacks remind us that the smart Internet of Things (IoT) can help us control our light-bulbs, but if under attacks it might also take us into darkness. Nowadays, many literatures have tried to address the concerns on IoT security, but few of them take into consideration the sever threats to IoT coming from the advances of quantum computing. As a promising candidate for the future post-quantum cryptography standard, lattice-based cryptography enjoys the advantages of strong security guarantees and high efficiency, which make it extremely suitable for IoT applications. In this paper, we summarize the advantages of lattice-based cryptography and the state of art of their implementations for IoT devices. Copyright © 2018, The Authors. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An end-to-end neural network approach to story segmentation 9

An end-to-end neural network approach to story segmentation

引用

9th Asia-Pacific Signal and information processing Association Annual Summit and Conference, APSIPA ASC 2017

作者： Yu, Jia Xie, Lei Xiao, Xiong Chng, Eng Siong Shaanxi Provincial Key Laboratory of Speech and Image Information Processing School of Computer Science Northwestern Polytechnical University Xi'an China School of Computer Engineering Nanyang Technological University Singapore

ISBN: (纸本)9781538615423

This paper proposes an end-to-end story segmentation approach based on long short-term memory (LSTM) - recurrent neural network (RNN). Traditional story segmentation approaches are a two-stage pipeline consisting of feature extraction and segmentation, each of which has its individual objective function. In other words, the objective function used to extract features is different from the true performance measure of story segmentation, which may degrade the segmentation results. In this paper, we combine the two components and optimize them jointly, using an LSTM-RNN. Specifically, one LSTM layer is used to extract sentence vectors, and another LSTM layer is used to predict story boundaries by taking as input of the sentence vectors. Importantly, the whole network is optimized directly to predict story boundaries. We also investigate bi-directional LSTM (BLSTM) that can utilize past and future information in the process of extracting sentence vectors and story boundary prediction. Experimental results on the TDT2 corpus show that the proposed approach achieves state-of-the-art performance in story segmentation. © 2017 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Sleep Disorder Classification Method based on Logistic Regression with Apnea-ECG Dataset 2019

Sleep Disorder Classification Method based on Logistic Regre...

引用

2019 International Conference on Artificial Intelligence and Advanced Manufacturing, AIAM 2019

作者： Cai, Liangming Chen, Chunqiang Wang, Xiaoling Yang, Xiong Lin, Shurui Huang, Jiefeng Jiang, Jinping Datta, Rituparna Du, Min Jiang, Haiyan Zhu, Minchen Huang, Jingshan College of Physics and Information Engineering Fuzhou University Fuzhou China Zhicheng College University of South Alabama United States HaiXi Institutes Chinese Academy of Science Fuzhou China Zhicheng College Fuzhou University Fuzhou China Department of Respiratory Medicine First Affiliated Hospital of Fujian Medical University Fuzhou China College of Electrical Engineering and Automation Fuzhou University Fuzhou China School of Computing University of South Alabama Mobile United States Provincial Key Laboratory of Eco-industrial Green Technology Wuyi College Wuyishan China College of Mathematics and Computer Science Fuzhou University Fuzhou China Fuzhou University Fuzhou China University of South Alabama United States

ISBN: (纸本)9781450372022

Adequate sleep is significant for human to actively pursue daily activity. On the other hand, insomnia is directly proportional to aging and health deterioration. Sleep disorder classification is important for medical scientists as well as machine learning researchers. In the paper, we have developed a sleep disorder classification method for Electrocardiogram (ECG) data. The data set have two labels;sleep disorder or not, which can be categorized as binary output. As a result, logistic regression is used as classification technique. For initial experimentation, an existing data set is used. The data set consists of every 10 second data up to 6000 seconds for 35 patients. We have used 70% data for training, and 30% data for testing purpose. Our results from logistic regression show that the logistic regression method is efficient to detect sleep disorders. The prediction result is found to be 59%. The future research in this direction would be to take data from hospitals and use our developed algorithm for sleep disorder classification and prediction. © 2019 Association for Computing Machinery.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Reform of computer Teaching for Practical Application

Reform of Computer Teaching for Practical Application

引用

作者： Li Huang Kai Zhang Wei Hu Mingchao Yu College of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology

In view of the rapid development of contemporary computer technology, the problems that can be solved by computer technology are more and more complicated. Therefore, it is required that contemporary college students need to master certain computer operation skills and basic application skills of computer software combined with their professional knowledge before they officially enter the society. In this context, aiming at the computer-based teaching mode of non-computer majors in colleges and universities, the author analyzes the current situation of computer basic teaching in colleges and universities through his many years of teaching experience, and discusses the shortcomings in the development of computer courses in colleges and universities. Based on the degree of social requirements for contemporary college students to master computer technology, how to make university computer teaching cater to the continuous development and progress of computer science and technology, combined with the future computer skills of undergraduate students, the author puts forward some computer teaching reform opinions.

关键词： computer foundation Teaching mode Application ability

来源：评论

学校读者我要写书评

暂无评论

CitationAS: A summary generation tool based on clustering of retrieved citation content 2

CitationAS: A summary generation tool based on clustering of...

引用

2nd Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics, CLBib 2017

作者： Wang, Jie Ma, Shutian Zhang, Chengzhi Department of Information Management Nanjing University of Science and Technology Nanjing210094 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control -Acty Fuzhou 350108 China

Usually, if researchers want to understand research status of any field, they need to browse a great number of related academic literatures. Luckily, in order to work more efficiently, automatic documents summarization can be applied for taking a glance at specific scientific topics. In this paper, we focus on summary generation of citation content. An automatic tool named CitationAS is built, whose three core components are clustering algorithms, label generation and important sentences extraction methods. In experiments, we use bisecting K-means, Lingo and STC to cluster retrieved citation content. Then Word2Vec, WordNet and combination of them are applied to generate cluster label. Next, we employ two methods, TF-IDF and MMR, to extract important sentences, which are used to generate summaries. Finally, we adopt gold standard to evaluate summaries obtained from CitationAS. According to evaluations, we find the best label generation method for each clustering algorithm. We also discover that combination of Word2Vec and WordNet doesn't have good performance compared with using them separately on three clustering algorithms. Combination of Ling algorithm, Word2Vec label generation method and TF-IDF sentences extraction approach will acquire the highest summary quality.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Cross-domain attribute representation based on convolutional neural network*

arXiv

引用

arXiv 2018年

作者： Zhang, Guohui Liang, Gaoyuan Su, Fang Qu, Fanxin Wang, Jing-Yan Huawei Technologies Co. Ltd. Shanghai China Jiangsu University of Technology Jiangsu213001 China Shaanxi University of Science & Technology Xi’an China Northwestern Polytechnical University Xi’an China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China

In the problem of domain transfer learning, we learn a model for the prediction in a target domain from the data of both some source domains and the target domain, where the target domain is in lack of labels while the source domain has sufficient labels. Besides the instances of the data, recently the attributes of data shared across domains are also explored and proven to be very helpful to leverage the information of different domains. In this paper, we propose a novel learning framework for domain-transfer learning based on both instances and attributes. We proposed to embed the attributes of different domains by a shared convolutional neural network (CNN), learn a domain-independent CNN model to represent the information shared by different domains by matching across domains, and a domain-specific CNN model to represent the information of each domain. The concatenation of the three CNN model outputs is used to predict the class label. An iterative algorithm based on gradient descent method is developed to learn the parameters of the model. The experiments over benchmark datasets show the advantage of the proposed model. Copyright © 2018, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

On the Convex Model of Speckle Reduction

On the Convex Model of Speckle Reduction

引用

International conference on Imaging, Vision and Learning Based on Optimization and PDEs, IVLOPDE 2016

作者： Fang, Faming Fang, Yingying Zeng, Tieyong Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China Department of Computer Science & Technology East China Normal University Shanghai China Department of Mathematics Hong Kong Baptist University Kowloon Tong Hong Kong Department of Mathematics The Chinese University of Hong Kong Ma Liu Shui Hong Kong

ISBN: (纸本)9783642543005

Speckle reduction is an important issue in image processing realm. In this paper, we propose a novel model for restoring degraded images with multiplicative noise which follows a Nakagami distribution. A general penalty term based on the statistical property of the speckle noise is used to guarantee the convexity of the denoising model. Moreover, to deal with the minimizing problem, a generalized Bermudez-Moreno algorithm is adopted and its convergence is analysed. The experimental results on some images subject to multiplicative noise as well as comparisons to other state-of-the-art methods are also presented. The results can verify that the new model is reasonable. © Springer International Publishing AG 2018.

关键词： Speckle

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：