检索结果-内蒙古大学图书馆

2020 International Multi-Conference on Industrial engineering and Modern Technologies, FarEastCon 2020

作者： Tormozov, V.S. Zolkin, A.L. Vasilenko, K.A. Pacific National University Senior Lecturer of the Software Engineering for Computers and Computer-based Systems Sub-faculty Tikhookeanskaya St. 136 Khabarovsk680054 Russia Ph.D. in Engineering Science Povolzhskiy State University of Telecommunications and Informatics Senior Lecturer of Computer and Information Sciences Department of the Povolzhskiy State University of Telecommunications and Informatics Samara443010 Russia Highest Category Lecturer Service and Design College of the Vladivostok State University of Economics and Service Service and Design College of the Vladivostok State University of Economics and Service Vladivostok690092 Russia

ISBN: (纸本)9781728169514

The article proposes a method that allows to solve the complex combinatorial problem of structural optimization of an artificial neural network with a large dimension of the space of optimization parameters using the stochastic mutation function with a constant coefficient of variation. A study on assessment of applicability of this approach to solve the problem is given. This method is proposed to be used for the forecasting of time series values. © 2020 IEEE.

关键词： Structural optimization

来源：评论

学校读者我要写书评

暂无评论

Uplink Throughput Maximization for Low Latency in Wireless Powered Communication Networks

Uplink Throughput Maximization for Low Latency in Wireless P...

引用

International Conference on Communication Technology (ICCT)

作者： M.S. Syam Yue Ling Che Sheng Luo Kaishun Wu College of Information Engineering Shenzhen University College of Computer Science and Software Engineering Shenzhen University

With the coming of 5G era, wireless transmissions of high data rates in the uplink (UL) are intensely demanded, for supporting low-latency wireless transmissions in various applications. In this paper, a joint downlink (DL) and UL optimization to maximize the sum of UL throughput of devices for a given sum of DL throughput in a wireless powered communication network (WPCN) with two devices is considered. The time frame is divided into two phases: a DL phase followed by a UL phase. In the DL, a hybrid access point (H-AP) first conducts wireless energy transfer (WET) to both devices, and then conducts wireless information transfer (WIT) to each device respectively. In the UL, each device conducts WIT to the H-AP in its allocated time. Each device exploits the total harvested energy from the H-AP in the DL to support its DL information reception and decoding as well as WIT in the UL. We optimize the time allocation for WET and WIT in the DL, WIT for each device in the UL, as well as transmit power of H-AP and devices, so as to maximize total UL throughput of the network for a given DL throughput, subject to energy causality constraints for each device, H-AP's and each device's transmit power constraint and time allocation constraint. However, this problem is non-convex and thus is difficult to be solved. To address this difficulty, we transform this problem into a convex optimization problem, and solve it efficiently. Simulation results are also conducted to show the performance of the proposed system.

关键词： Throughput Resource management Wireless communication Uplink Convex functions Transforms Time factors

来源：评论

学校读者我要写书评

暂无评论

A Framework of Blockchain-Based Security for WBANs

A Framework of Blockchain-Based Security for WBANs

引用

Smart BlockChain (SmartBlock), International Conference on

作者： Han Deng Xiangwei Meng Jun Guo Erhui Xi Hui Zhao Big Data Development and Research Center Guangzhou College of Technology and Business Guangzhou China School of Computer science and Engineering Hunan University of Science and Technology Xiangtan China School of Software Engineering Quanzhou University of Information Engineering Quanzhou China Guangzhou College of Technology and Business Guangzhou China Educational Information Technology Laboratory Henan University Kaifeng China

Purposed to collect and store human physiological data, WBANs as a telemedicine system play a significant role in sensor networks. The complex network environment presents a formidable challenge to the stability of the system and the security of the database. The traditional centralized architecture is to store the registration data of the sensor node and the patient's physiological data in the hub node. When the hub node is subjected to Denial of Service attacks (DoS) and Distributed Denial of Service attacks (DDoS), there will be a single point of failure, so that the sensor node cannot establish a communication connection with the hub node. In this paper, a cloud server layer architecture based on blockchain technology is proposed for WBNAs to ensure system stability and patient data security. Meanwhile, Ciphertext-Policy Attribute-Based Encryption (CP-ABE) scheme is used to ensure patient physiological data safety.

关键词： Wireless communication Cloud computing Architecture Distributed databases Blockchain Medical services Permission

来源：评论

学校读者我要写书评

暂无评论

Implementation of Multiplicative Seasonal ARIMA Modeling and Flood Prediction Based on Long-Term Time Series Data in Indonesia 1

引用

5th International Conference on Artificial Intelligence and Security, ICAIS 2019

作者： Supatmi, Sri Huo, Rongtao Sumitra, Irfan Dwiguna School of Computer and Software Nanjing University of Information Science and Technology NanjingJiangsu China Computer Engineering Department Universitas Komputer Indonesia BandungWest Java Indonesia Postgraduate of Information System Department Universitas Komputer Indonesia BandungWest Java Indonesia

ISBN: (数字)9783030242657

ISBN: (纸本)9783030242640

Time series modeling and prediction has fundamental importance in the various practical field. Thus, a lot of productive research works is working in this field for several years. Many essential methods have been proposed in publications to improve the accuracy and efficiency of time series modeling and prediction. This research aims to present the proposed prediction model namely Multiplicative seasonal ARIMA model (MSARIMA) based on non-stationary time series data to predicting the flood event. In this paper, we have described the performance of the ARMA model, the ARIMA model, and MSARIMA model to predict the flood event in the Region over Indonesia in 42 years (1976–2017). We have used the two performance measures respectively (MAPE, and RMSPE) to evaluate prediction accuracy as well as to compare different models fitted to a time series data. The result has shown the proposed predicting model has the best performance accuracy than the others model in this research. © 2019, Springer Nature Switzerland AG.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Hybrid-attention guided network with multiple resolution features for person re-identification

arXiv

引用

arXiv 2020年

作者： Zhang, Guoqing Yang, Junchuan Zheng, Yuhui Wang, Ye Wu, Yi Chen, Shengyong School of Computer and Software Nanjing University of Information Science Technology Nanjing210044 China School of Marketing Logistics Management Nanjing University of Finance and Economics Nanjing China Wormpex AI Research School of Computer Science Engineering Tianjin University of Technology

Extracting effective and discriminative features is very important for addressing the challenges of person re-identification (re-ID). Prevailing deep convolutional neural networks usually use high-level features for identifying pedestrian. However, some essential spatial information resided in low-level features will be lost when learning the high-level features. Most existing person re-ID methods mainly rely on hand-craft bounding boxes, where person images are precisely aligned. It is unrealistic in practical applications due to the inaccuracy of automatic detection algorithms. To address these problems, we propose a hybrid-attention guided network with multiple resolution features for person re-ID. We first construct a multi-resolution fusion strategy to ensure that multi-resolution features can be spatially aligned during feature fusion and at the same time ensure the discriminability of features after fusion. Then, we introduce the attention mechanism and multi-granularity operation to reduce the impact of irregular bounding boxes by gently expanding the size of feature maps. In addition, a new multi-pool feature extractor is designed to obtain different types of information by using two different pools and the feature representation capability can be further improved. Extensive experiments display the superiority of our approach. Our code is available at https://***/libraflower/MutipleFeature-for-PRID. Copyright © 2020, The Authors. 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

Erratum to “Progressive conditional GAN-based augmentation for 3D object recognition” [Neurocomputing 460 (2021) 20–30]

引用

Neurocomputing 2022年 473卷 158-158页

作者： A.A.M. Muzahid Wan Wanggen Ferdous Sohel Mohammed Bennamoun Li Hou Hidayat Ullah School of Electronic and Electrical Engineering Shanghai University of Engineering Science Shanghai 201620 China School of Communication and Information Engineering Shanghai University Shanghai 200444 China Institute of Smart City Shanghai University Shanghai 200444 China Information Technology Centre for Crop and Food Innovation Murdoch University Murdoch WA 6150 Australia Department of Computer Science and Software Engineering The University of Western Australia Perth WA 6009 Australia School of Information Engineering Huangshan University Huangshan 245041 China

来源：评论

学校读者我要写书评

暂无评论

Multi-operator network sharing for massive IoT

arXiv

引用

arXiv 2020年

作者： Xiao, Yong Krunz, Marwan Shu, Tao School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan430074 China Department of Electrical and Computer Engineering the University of Arizona TucsonAZ85721 United States School of Electrical and Data Engineering University of Technology Sydney UltimoNSW2007 Australia Department of Computer Science and Software Engineering Auburn University AuburnAL36849 United States

A recent study predicts that by 2020, up to 50 billion Internet-of-Things (IoT) devices will be connected to the Internet, straining the capacity of the wireless infrastructure, which has already been overloaded with data-hungry mobile applications. How to accommodate the demand for both massivescale IoT devices and high-speed cellular services in the physically limited spectrum without significantly increasing the operational and infrastructure costs is one of the main challenges for operators. In this article, we introduce a new multi-operator network sharing framework that supports the coexistence of IoT and high-speed cellular services. Our framework is based on the radio access network (RAN) sharing architecture recently introduced by 3GPP as a promising solution for operators to improve their resource utilization and reduce system roll-out cost. We evaluate the performance of our proposed framework using real base station location data in the city of Dublin collected from two major operators in Ireland. Numerical results show that our proposed framework can almost double the total number of supported IoT devices and simultaneously coexist with other cellular services. Copyright © 2020, 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

A commit change-based weighted complex network approach to identify potential fault prone classes 13

A commit change-based weighted complex network approach to i...

引用

13th International Conference on software Technologies, ICSOFT 2018

作者： Chong, Chun Yong Lee, Sai Peck School of Information Technology Monash University Malaysia Jalan Lagoon Selatan Bandar Sunway Selangor47500 Malaysia Department of Software Engineering Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia

ISBN: (纸本)9789897583209

Over the past few years, attention has been focused on utilizing complex network analysis to gain a high-level abstraction view of software systems. While many studies have been proposed to use interactions between software components at the variable, method, class, package, or combination of multiple levels, limited studies investigated how software change history and evolution pattern can be used as a basis to model software-based weighted complex network. This paper attempts to fill in the gap by proposing an approach to model a commit change-based weighted complex network based on historical software change and evolution data captured from GitHub repositories with the aim to identify potential fault prone classes. Experiments were carried out using three open-source software to validate the proposed approach. Using the well-known change burst metric as a benchmark, the proposed method achieved average precision of 0.77 and recall of 0.8 on all the three test subjects. Copyright © 2018 by SCITEPRESS - science and Technology Publications, Lda. All rights reserved

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Variational information Diffusion for Probabilistic Cascades Prediction

Variational Information Diffusion for Probabilistic Cascades...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Fan Zhou Xovee Xu Kunpeng Zhang Goce Trajcevski Ting Zhong School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Robert H. Smith School of Business University of Maryland College Park USA Department of Electrical and Computer Engineering Iowa State University USA

ISBN: (数字)9781728164120

ISBN: (纸本)9781728164137

Understanding in-network information diffusion is a fundamental problem in many application domains and one of the primary challenges is to predict the size of the information cascade. Most of the existing models rely either on hypothesized point process (e.g., Poisson and Hawkes process), or simply predict the information propagation via deep neural networks. However, they fail to simultaneously capture the underlying structure of a cascade graph and the propagation of uncertainty in the diffusion, which may result in unsatisfactory prediction performance. To address these, in this work we propose a novel probabilistic cascade prediction framework: Variational Cascade (VaCas) graph learning networks. VaCas allows a non-linear information diffusion inference and models the information diffusion process by learning the latent representation of both the structural and temporal information. It is a pattern-agnostic model leveraging variational inference to learn the node-level and cascade-level latent factors in an unsupervised manner. In addition, VaCas is capable of capturing both the cascade representation uncertainty and node infection uncertainty, while enabling hierarchical pattern learning of information diffusion. Extensive experiments conducted on real-world datasets demonstrate that VaCas significantly improves the prediction accuracy, compared to state-of-the-art approaches, while also enabling interpretability.

关键词： Uncertainty Predictive models Neural networks Probabilistic logic Machine learning Computational modeling Diffusion processes

来源：评论

学校读者我要写书评

暂无评论

Image Processing-Based Flood Detection 10th

Image Processing-Based Flood Detection

引用

10th National Technical Seminar on Underwater System Technology, NUSYS 2018

作者： Ariawan, Angga Pebrianti, Dwi Ronny Akbar, Yudha Maulana Margatama, Lestari Bayuaji, Luhur Magister of Computer Science Universitas Budi Luhur Jakarta12260 Indonesia Faculty of Engineering Universitas Budi Luhur Jakarta12260 Indonesia Faculty of Information Technology Universitas Budi Luhur Jakarta12260 Indonesia Faculty of Computer Science and Software Engineering Universiti Malaysia Pahang Pekan Malaysia Faculty of Electrical and Electronics Engineering Universiti Malaysia Pahang Pekan Malaysia

ISBN: (纸本)9789811337079

This paper discusses about the design of an online flood detection and early warning system which integrated to using Raspberry-PI and optical sensor. Raspberry-PI is a single board of computer which in this case we design as an image processor to process image obtained from the webcam and update the result to the twitter. This research can help some of the citizens who live near the river to get the updated information regarding water conditions and the possibility of flooding so that they can take action to secure their properties and families as soon as possible. We use OpenCV as an image processing application. The steps are as follows: (1) Region of Interest to create a portion of an image to filter or perform some other operation. (2) Brightness and contrast adjustment in order to get brighter and better image before the next process. (3) Grayscale and threshold to create segmentation object with Otsu-thresholding. (4) Edge detection algorithm to find edge points on a roughly horizontal water line and riverbank height. By using the above method, the system can read and monitor the water level of a river or other water bodies. If the water level exceeds the specific threshold, the system will generate notification as early warning for the possibility of flooding by uploading the text and image to the twitter regarding that condition. The citizens will get the information if they follow that account (early warning system) on Twitter. The result of this simulation using prototype that we have made is that the system can read the water conditions with an increase in accuracy reaching 99.6%. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Water levels

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：