检索结果-内蒙古大学图书馆

Correction to: Type 2 Diabetes with Artificial Intelligence Machine Learning: Methods and Evaluation

Archives of Computational Methods in engineering 2021年第7期28卷 5039-5039页

作者： Ismail, Leila Materwala, Huned Tayefi, Maryam Ngo, Phuong Karduck, Achim P. Intelligent Distributed Computing and Systems Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University Al Ain Abu Dhabi United Arab Emirates National Water and Energy Center United Arab Emirates University Al Ain Abu Dhabi United Arab Emirates Norwegian Centre for E-Health Research Tromsø Norway Faculty of Informatics Furtwangen University Furtwangen Germany

来源：评论

学校读者我要写书评

暂无评论

Dual-Site Activation Coupling with a Schottky Junction Boosts the Electrochemiluminescence of Carbon Nitride

引用

Angewandte Chemie 2023年第33期135卷

作者： Zhichao Wu Prof. Jing Wen Ying Qin Ling Ling Lei Jiao Prof. Ruizhong Zhang Zhen Luo Mengzhen Xi Prof. Liuyong Hu Prof. Wenling Gu Prof. Chengzhou Zhu National Key Laboratory of Green Pesticide International Joint Research Center for Intelligent Biosensing Technology and Health College of Chemistry Central China Normal University Wuhan 430079 P. R. China Contribution: Data curation (lead) Investigation (lead) Writing - original draft (lead) Hubei Key Laboratory of Plasma Chemistry and Advanced Materials Hubei Engineering Technology Research Center of Optoelectronic and New Energy Materials Wuhan Institute of Technology Wuhan 430205 P. R. China Contribution: Software (equal) Contribution: Data curation (supporting) Tianjin Key Laboratory of Molecular Photoelectronic Sciences Department of Chemistry Tianjin University Tianjin 300072 P. R. China Contribution: Formal analysis (supporting) Contribution: Conceptualization (supporting) Supervision (supporting) Writing - review & editing (supporting) Contribution: Funding acquisition (supporting) Methodology (supporting) Supervision (supporting) Writing - review & editing (supporting) Contribution: Funding acquisition (lead) Project administration (lead) Supervision (lead) Writing - review & editing (lead)

来源：评论

学校读者我要写书评

暂无评论

Reflections on teaching electrical & computer engineering courses at the bachelor level 9

Reflections on teaching electrical & computer engineering co...

引用

9th International Conference on Computer Supported Education, CSEDU 2017

作者： Osen, Ottar L. Bye, Robin T. Software and Intelligent Control Engineering Laboratory Department of ICT and Natural Sciences Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology NTNU Postboks 1517 ÅlesundNO-6025 Norway

ISBN: (纸本)9789897582400

This paper reflects on a number of observations the authors have made over many years of teaching courses in electrical and computer engineering bachelor programmes. We suggest various methods and tips for improving lectures, attendance, group work, and compulsory coursework, and discuss aspects of facilitating active learning, focussing on simple in-classroom activities and larger problem-based activities such as assignments, projects, and laboratory work. Moreover, we identify solving real-world problems by means of practical application of relevant theory as key to achieving intended learning outcomes. Our observations and reflections are then put into a theoretical context, including students' approaches of learning, constructive alignment, active learning, and problem-based versus problem-solving learning. Finally, we present and discuss some recent results from a student evaluation survey and draw some conclusions. © 2017 by SCITEPRESS - Science and technology Publications, Lda. All rights reserved.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Predicting Churn: How Multilayer Perceptron Method Can Help with Customer Retention in Telecom Industry

引用

IOP Conference Series: Materials Science and engineering 2020年第1期864卷

作者： NNA Sjarif NF Azmi HM Sarkan SM Sam MZ Osman Advanced Informatics Department Razak Faculty of Technology and Informatics Universiti Teknologi Malaysia Jalan Sultan Yahya Petra 54100 Kuala Lumpur Malaysia Soft Computing Research & Intelligent System Group (SPINT) Faculty of Systems Computer & Software Engineering Universiti Malaysia Pahang Lebuhraya Tun Razak 26300 Gambang Pahang Malaysia

Customer churn prediction has been used widely in various kind of domain especially subscription-basis industries. With the rapid growth of telecommunication industry over the last decade, this industry not only focuses on providing numerous products, but also satisfying the customers as it is one of the key solutions to remain competitive. This research proposed MultiLayer Perceptron Method for churn prediction. The evaluation is compared with three classifiers which includes are Support Vector Machine, Naïve Bayes and Decision Tree in term of several aspects. In preprocessing phase, we employed Principal Component Analysis and normalization to find the correlation among all the variables. For the postprocessing, InfoGainAttribute is used to identify the highest factor attribute that leads to customer retention. It is found that MultiLayer Perceptron outperforms other classifiers and international plan plays important role to retain customer from leaving organization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Based on Spatio-Temporal and Sparse Features of Network Traffic in VANETs

Anomaly Detection Based on Spatio-Temporal and Sparse Featur...

引用

2019 IEEE Global Communications Conference (GLOBECOM)

作者： Laisen Nie Huizhi Wang Shimin Gong Zhaolong Ning Mohammad S. Obaidat Kuei-Fang Hsiao School of Electronics and Information Northwestern Polytechnical University Xi'an P.R.China Qingdao Research Institute of Northwestern Polytechnical University Qingdao P.R.China School of Intelligent Systems Engineering Sun Yat-sen University China State Key Laboratory for Novel Software Technology Nanjing University China ECE Department Nazarbayev University Astana Kazakhstan College of Computing and Informatics University of Sharjah UAE The King Abdullah II School of Information Technology The University of Jordan Amman Jordan University of Science and Technology Beijing China Department of Information Management Ming Chuan University Taiwan

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

Vehicular Ad-Hoc Networks (VANETs) have received a great attention recently due to their potential and various applications. However, the initial phase of the VANET has many research challenges that need to be addressed, such as the issues of security and privacy protection caused by the openness of wireless communication networks among the city-wide applied regions. Specially, anomaly detection for a VANET has become a challenging problem, due to the changes in the scenario of VANETs comparing with traditional wireless networks. Motivated by this issue, we focus on the problem of anomaly detection in VANETs, and propose an effective anomaly detection approach based on the convolutional neural network in this paper. The proposed approach takes into account the spatio-temporal and sparse features of VANET traffic, and it uses a convolutional neural network architecture and a loss function based on Mahalanobis distance for anomaly detection. Furthermore, a comprehensive assessment is provided to validate the proposed approach, which illustrates the effectiveness of this approach.

关键词： Anomaly detection Feature extraction Vehicular ad hoc networks Kernel Estimation Security Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Predicting commercial activeness over urban big data

引用

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2017年第3期1卷 1-20页

作者： Yang, Su Wang, Minjie Wang, Wenshan Sun, Yi Gao, Jun Zhang, Weishan Zhang, Jiulong Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University 825 Zhangheng Rd Shanghai201203 China Department of Software Engineering China University of Petroleum Qingdao266580 China School of Computer Science Xian University of Technology Xian710048 China

This study aims at revealing how commercial hotness of urban commercial districts (UCDs) is shaped by social contexts of surrounding areas so as to render predictive business planning. We define social contexts for a given region as the number of visitors, the region functions, the population and buying power of local residents, the average price of services, and the rating scores of customers, which are computed from heterogeneous data including taxi GPS trajectories, point of interests, geographical data, and user-generated comments. Then, we apply sparse representation to discover the impactor factor of each variable of the social contexts in terms of predicting commercial activeness of UCDs under a linear predictive model. The experiments show that a linear correlation between social contexts and commercial activeness exists for Beijing and Shanghai based on an average prediction accuracy of 77.69% but the impact factors of social contexts vary from city to city, where the key factors are rich life services, diversity of restaurants, good shopping experience, large number of local residents with relatively high purchasing power, and convenient transportation. This study reveals the underlying mechanism of urban business ecosystems, and promise social context-aware business planning over heterogeneous urban big data. © 2017 Association for Computing Machinery.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Multiobjective optimization differential evolution enhanced with principle component analysis for constrained optimization

arXiv

引用

arXiv 2018年

作者： Huang, Wei Xu, Tao He, Jun Li, Kangshun Tianjin Key Laboratory of Intelligent and Novel Software Technology School of Computer Science and Engineering Tianjin University of Technology China Department of Computer Science Aberystwyth University AberystwythSY23 3DB United Kingdom School of Science and Technology Nottingham Trent University NottinghamNG11 8NS United Kingdom College of Mathematics and Informatics South China Agricultural University Guangzhou510642 China

Multiobjective optimization evolutionary algorithms have been successfully applied to solving constrained optimization problems. This paper proposes a new multiobjective optimization differential evolution algorithm for constrained optimization. Through a study of fitness landscapes using principle component analysis, we discover a statistic method of identifying the valley direction in a valley landscape. Based on this discovery, a new search operator called PCA-projection is constructed which projects an individual to a position along the valley direction. Then multiobjective optimization differential evolution using this projection operator is designed for constrained optimization. A comparative experiment has been implemented between the proposed algorithm and a state-of-the-art multiobjective differential evolution algorithm on a standard set of 24 benchmarks. Experimental results show that the new algorithm makes a significant improvement in terms of solution accuracy. The proposed algorithm is also competitive with ten evolutionary algorithms participated in an IEEE CEC 2006 competition and is ranked third in terms of the final rank. Copyright © 2018, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Deep learning models for EEG-based rapid serial visual presentation event classification

引用

Journal of Information Hiding and Multimedia Signal Processing 2018年第1期9卷 177-187页

作者： Zhang, Fu-Quan Mao, Zi-Jing Huang, Yu-Fei Xu, Lin Ding, Gang Yi Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China School of Software Beijing Institute of Technology Room A9-301 Juyuan Jinshan Jiyuan Fuzhou350008 China Department of Electronic Engineering University of Texas at San Antonio One UTSA Circle San Antonio Arrow Oaks 126 San AntonioTX78249 United States Innovative Information Industry Research Institute Fujian Normal University Fuqing Brunch of Fujian Normal University Campus County 1 Longjiang Road FuqingFuzhou350300 China School of Software Beijing Institute of Technology Room 611 Software Building 5 South Zhongguancun Street Haidian Beijing100081 China

We consider deep learning (DL) for event classification using electroencephalogram (EEG) measurements of brain activities. We proposed HDNN or hierarchical deep neural network, and CNN4EEG, a new convolution neural network (CNN). Both DL models are designed to improve the representation of spatial and local temporal correlations inherent in EEG data. These models were tested for image target prediction in a time-locked rapid serial visual presentation (RSVP) experiment. The performances were compared with the state-of-the-art RSVP classification algorithms including HDCA and XDAWN and with other popular machine learning algorithms. The results show that global spatial local temporal CNN (CNN4EEG) achieved a 13% improvement over the best competing non-DL algorithm and a 9% improvement over canonical CNN for image processing, and a 6% over deep neural network (DNN). Our results suggest that the unique design of temporal and spatial filters in CNN4EEG can improve the representation of EEG data, hence the prediction performance. © 2018, Ubiquitous International. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Physical origins of ruled surfaces on the reduced density matrices geometry

引用

Science China(Physics,Mechanics & Astronomy) 2017年第2期60卷 1-8页

作者： Ji-Yao Chen Zhengfeng Ji Zheng-Xin Liu Xiaofei Qi Nengkun Yu Bei Zeng Duanlu Zhou State Key Laboratory of Low Dimensional Quantum Physics Department of Physics Tsinghua University Beijing 100084 China Perimeter Institute for Theoretical Physics Waterloo N2L 2Y5 Canada Centre for Quantum Computation ＆ Intelligent Systems School of Software Faculty of Engineering and Information Technology University of Technology Sydney Sydney 2007 Australia State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing 100190 China Department of Physics Renmin University of China Beijing 100872 China Department of Mathematics Shanxi University Taiyuan 030000 China Institute for Quantum Computing University of Waterloo Waterloo N2L 3G1 Canada Department of Mathematics ＆ Statistics University of Guelph Guelph N1G 2W1 Canada Institute of Physics Chinese Academy of Sciences Beijing 100190 China

The reduced density matrices （RDMs） of many-body quantum states form a convex set. The boundary of low dimensional projections of this convex set may exhibit nontrivial geometry such as ruled surfaces. In this paper, we study the physical origins of these ruled surfaces for bosonic systems. The emergence of ruled surfaces was recently proposed as signatures of symmetry- breaking phase. We show that, apart from being signatures of symmetry-brealdng, ruled surfaces can also be the consequence of gapless quantum systems by demonstrating an explicit example in terms of a two-mode Ising model. Our analysis was largely simplified by the quantum de Finetti＇s theorem--in the limit of large system size, these RDMs are the convex set of all the symmetric separable states. To distinguish ruled surfaces originated from gapless systems from those caused by symmetry- breaking, we propose to use the finite size scaling method for the corresponding geometry. This method is then applied to the two-mode XY model, successfully identifying a ruled surface as the consequence of gapless systems.

关键词： ruled surfaces reduced density matrices bosonic system geometry

来源：评论

学校读者我要写书评

暂无评论

Design of an intelligent Bridge Structure Health Monitoring System

引用

IOP Conference Series: Earth and Environmental Science 2019年第2期300卷

作者： Xuan Ji Hesong Hu Zhuo Yang Xiaodan Huang Lingsheng Tan Chief Engineer Office Guangzhou Institute of Building Science CO. LTD. 510440 China Chief Engineer Office Guangzhou Institute of Building Science CO. LTD. 510440 China Department of intelligent software and equipment Guangzhou Institute of Building Science CO. LTD. 510440 China School of Software South China University of Technology 510006 China School of Civil Engineering Guangzhou University 510006 China

This paper designs an intelligent bridge structure health monitoring system (BSHMS) based on ZigBee wireless sensor network. Based on 3G wireless transmission technology and ZigBee technology, it serves as a wireless monitoring platform with amulti-level network architecture composed of data acquisition node, centre node(gateway) and remote server. In this paper, system hardware circuit and software system redesigned, CC2530is applied in the Contiki operating system. Then, various modules of the entire system are tested and debugged online. The test shows that the system can run stably and capture various data accurately before transmitting it to the rear server, thus meeting the design requirements.

关键词：

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：