检索结果-内蒙古大学图书馆

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Uzair Nadeem Mohammed Bennamoun Ferdous Sohel Roberto Togneri Dept. of Computer Science and Software Engineering The University of Western Australia College of Science Health Engineering & Education Murdoch University Australia

Coral reefs are vital for marine ecosystem and fishing industry. Automatic classification of corals is essential for the preservation and study of coral reefs. However, significant intra-class variations and inter-class similarity among coral genera, as well as the challenges of underwater illumination present a great hindrance for the automatic classification. We propose an end-to-end trainable Deep Fusion Net for the classification of corals from two types of images. The network takes two simultaneous inputs of reflectance and fluorescence images. It is composed of three branches: Reflectance, Fluorescence and Integration. The branches are first trained individually and then fused together. Finally, the Deep Fusion Net is trained end-to-end for the classification of different coral genera and other non-coral classes. Experiments on the challenging Eliat Fluorescence Coral dataset show that the Deep Fusion net achieves superior classification accuracy compared to other methods.

关键词： Fluorescence Training Annotations Histograms Australia Industries Lighting

来源：评论

学校读者我要写书评

暂无评论

Towards a reliable approach on scaling in data acquisition

arXiv

引用

arXiv 2019年

作者： Paraschiv, Nicolae Fattahi, Jaouhar Pricop, Emil Zamfir, Florin Control Engineering Computers & Electronics Dept. Petroleum-Gas University of Ploiesti Ploiesti Romania Computer Science & Software Engineering Dept. Laval University Quebec City Canada

Data acquisition is an important process in the functioning of any control system. Usually, the acquired signal is analogic, representing a continuous physical measure, and it should be processed in a digital system based on an analog to digital converter (ADC) and a microcontroller. The ADC provides the converted value in ADC units, but the system and its operator need the value expressed in physical units. In this paper we propose a novel design solution for the scaling module, which is a key component of a digital measurement system. The scaling module refers to fitting the sensor result of a variable number of bits depending on the ADC resolution into physical units. A general method for scaling is proposed and a SageMath script is presented for obtaining easily the scaling function. In the last part of the paper, the proposed method is validated in a case study, by calculus, and it is implemented on a low-cost development system in order to create a wireless sensor node. Copyright © 2019, The Authors. All rights reserved.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Vanadium Redox & Lithium Ion Based Multi-Battery Hybrid Energy Storage System for Microgrid

Vanadium Redox & Lithium Ion Based Multi-Battery Hybrid Ener...

引用

IEEE PES Asia-Pacific Power and Energy engineering Conference (APPEEC)

作者： Oluwatobiloba Adeleke Abhisek Ukil Xibeng Zhang School of Electronics and Computer Science University of Southampton United Kingdom Dept. of Electrical Computer and Software Engineering University of Auckland New Zealand

Energy Storage System plays a vital role in assisting Microgrids to control fluctuating load demand with intermittent power supply. As well as enabling power quality to monitored and controlled, this paper introduces a power storage device, Vanadium oxide flow battery which would facilitate the expansion and allow flexibility with the Microgrid network.

关键词： Batteries State of charge Microgrids Vanadium Voltage control Lithium

来源：评论

学校读者我要写书评

暂无评论

Spectral Efficiency Maximization for Multiuser MISO-NOMA Downlink Systems with SWIPT

Spectral Efficiency Maximization for Multiuser MISO-NOMA Dow...

引用

IEEE Global Communications Conference

作者： Toan-Van Nguyen Van-Dinh Nguyen Tri-Nhu Do Daniel Benevides da Costa Beongku An Dept. of Electronics and Computer Engineering Graduate School Hongik University Republic of Korea Dept. of ICMC Convergence Technology Soongsil University Seoul Republic of Korea Dept. of Computer Science University of Texas at Dallas TX USA Dept. of Computer Engineering Federal University of Cear Sobral CE Brazil Dept. of Software and Communications Engineering Hongik University Republic of Korea

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

In this paper, we study the problem of jointly optimizing user pairing and beamforming design in multiuser multiple-input single-output (MU-MISO) non-orthogonal multiple access (NOMA) downlink systems with simultaneous wireless information and power transfer (SWIPT). Aiming at maximizing the achievable sum throughput subject to energy harvesting (EH) constraints, we propose a hybrid user pairing beamforming scheme (HBS), where two users with distinct channel conditions are optimally selected to perform user pairing. Moreover, we adopt a non-linear EH model for energy users to reveal their practical circuit characteristics. The sum throughput problem is formulated as a class of mixed-integer nonconvex optimization programming which is computationally prohibitive. To solve this challenging problem, we propose a low-complexity iterative algorithm, yet efficient, based on sequential convex approximation method to arrive at least the local optima. Numerical results are provided to demonstrate the performance improvement of the proposed HBS scheme over the multiuser beamforming one without user pairing, revealing to be an effective scheme for MU-MISO-NOMA downlink systems.

关键词： Array signal processing NOMA Interference Signal to noise ratio Downlink Throughput Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

Improving Physical Layer Security of NOMA Networks by Using Opportunistic Scheduling 10

Improving Physical Layer Security of NOMA Networks by Using ...

引用

10th International Conference on Ubiquitous and Future Networks, ICUFN 2018

作者： Shim, Kyusung Do, Tri Nhu An, Beongku Dept. of Electronics and Computer Engineering Graduate School Hongik University Korea Republic of Dept. of Software and Communications Engineering Hongik University Korea Republic of

ISBN: (纸本)9781538646465

In this paper, we study how to improve physical layer security capability of multiple near users and multiple far users non-orthogonal multiple access (NOMA) networks. To this end, we propose an opportunistic user scheduling scheme, named the best-secure-near-user best-secure-far-user (BSNBSF) scheme. The BSNBSF aims to select the best near-far user pair, whose data transmission is the most robust against the interception of an eavesdropper. In order to facilitate the performance analysis of the proposed user scheduling scheme in terms of secrecy outage probability (SOP), we derive an exact closed-form expression and a tight approximate closed-form expression for the SOP of the selected near and far users, respectively. Numerical results show that the BSNBSF scheme significantly improves the secrecy outage performance NOMA networks compared to that of the random near user and random far user selection scheme. Additionally, discussions on the complicate convex characteristic of the total SOP with respect to the power allocation coefficients and the impact the number of near and/or far users are provided. © 2018 IEEE.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

KerTSDroid: Detecting Android Malware at Scale through Kernel Task Structures

KerTSDroid: Detecting Android Malware at Scale through Kerne...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Xinning Wang Chong Li School of Engineering Ocean University of China Qingdao China Dept. of Computer Science and Software Engineering Auburn University Auburn AL USA

ISBN: (纸本)9781728125848

The explosive growth of data makes static and dynamic analysis in an individual machine difficult to detect Android malware. Hence many popular open-source frameworks for large-scale data processing have been used to deal with iterative machine learning tasks due to the efficient parallel computation and the in-memory abstraction. In this paper we first propose KerTSDroid, a novel Android malware detection framework, to predict the malicious applications in parallel through kernel task structures in Android kernel layer. Then a data provider is orchestrated and implemented to construct the real-world dataset of 112 kernel features from 12,750 Android applications. A parallel predictor is also provided to identify Android malicious applications. Our experiments demonstrate that a Decision Tree method of KerTSDroid can achieve the best precision rate (96%-99%) with a lower overhead on average, the other three methods (Naive Bayes, Logistic Regression, and Support Vector Machine) lead to lower precision rate while discriminating abnormal behaviors with the in-memory parallel-data.

关键词： Android system Kernel features Apache spark Malware detection Machine learning Methyltestosterone Androids Spyware Artificial Intelligence Machine Learning Scale formation Seeds abnormal behavior

来源：评论

学校读者我要写书评

暂无评论

CutLang v2: Advances in a runtime-interpreted analysis description language for HEP data

arXiv

引用

arXiv 2021年

作者： Unel, Gokhan Sekmen, S. Toon, A.M. Gokturk, B. Orgen, B. Paul, A. Ravel, N. Setpal, J. University of California at Irvine Department of Physics and Astronomy Irvine United States Kyungpook National University Department of Physics Daegu Korea Republic of Saint Joseph University of Beirut Dept. of Computer Software Engineering Beirut Lebanon Bogazici University Department of Physics Istanbul Turkey The Abdus Salam International Centre for Theoretical Physics Trieste Italy University of Ankatso Department of Physics Antananarivo Madagascar R.N. Podar School Mumbai India

We will present the latest developments in CutLang, the runtime interpreter of a recently-developed analysis description language (ADL) for collider data analysis. ADL is a domain-specific, declarative language that describes the contents of an analysis in a standard and unambiguous way, independent of any computing framework. In ADL, analyses are written in human-readable plain text files, separating object, variable and event selection definitions in blocks, with a syntax that includes mathematical and logical operations, comparison and optimisation operators, reducers, four-vector algebra and commonly used functions. Adopting ADLs would bring numerous benefits to the LHC experimental and phenomenological communities, ranging from analysis preservation beyond the lifetimes of experiments or analysis software to facilitating the abstraction, design, visualization, validation, combination, reproduction, interpretation and overall communication of the analysis contents. Since their initial release, ADL and CutLang have been used for implementing and running numerous LHC analyses. In this process, the original syntax from CutLang v1 has been modified for better ADL compatibility, and the interpreter has been adapted to work with that syntax, resulting in the current release v2. Furthermore, CutLang has been enhanced to handle object combinatorics, to include tables and weights, to save events at any analysis stage, to benefit from multi-core/multi-CPU hardware among other improvements. In this contribution, these and other enhancements are discussed in details. In addition, real life examples from LHC analyses are presented together with a user manual. Copyright © 2021, The Authors. All rights reserved.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Multihop Cognitive WPCNs with Imperfect CSI

Performance Analysis of Multihop Cognitive WPCNs with Imperf...

引用

IEEE Global Communications Conference

作者： Toan-Van Nguyen Tri-Nhu Do Vo Nguyen Quoc Bao Daniel Benevides da Costa Beongku An Dept. of Electronics and Computer Engineering in Graduate School Hongik University Republic of Korea Dept. of Computer Science University of Texas Dallas TX USA Faculty of Telecommunications Posts and Telecommunications Institute of Technology Vietnam Dept. of Computer Engineering Federal University of Cear Sobral CE Brazil Dept. of Software and Communications Engineering Hongik University Republic of Korea

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

This paper studies the performance of multi-hop cognitive wireless powered communication networks (WPCNs), where secondary nodes can harvest energy from multiple dedicated power beacons and access spectrum of primary receivers (PRs) to support data transmission. Specifically, we consider a practical scenario of cognitive WPCNs, where the channel state information (CSI) of interference links is assumed to be imperfect. To improve the network performance, we propose dual-hop scheduling scheme (DHS) for multi-hop network, where two best relays in two consecutive clusters are selected for data transmission. We then analyze the performance of the proposed scheme in terms of outage probability and outage floor. Numerical results show that DHS scheme outperforms random scheduling scheme, arising as an efficient scheme for multi-hop transmission. Furthermore, the effects of the number of hops, number of power beacons, and time switching ratio on multi-hop cognitive WPCNs are evaluated and discussed.

关键词： Relays Spread spectrum communication Interference Power system reliability Probability Data communication Switches

来源：评论

学校读者我要写书评

暂无评论

Smart Parking System Based on Convolutional Neural Network Models

Smart Parking System Based on Convolutional Neural Network M...

引用

International Conference on Information Science and Control engineering (ICISCE)

作者： Wenjin Zhang Jason Yan Cui Yu Dept. of Computer Science & Software Engineering Monmouth University NJ USA High Technology High School NJ USA

ISBN: (数字)9781728157122

ISBN: (纸本)9781728157139

Most people have probably experienced the hassle of parking space scarceness. To alleviate this problem, the relatively traditional solution is making use of sensors, which has its drawbacks in terms of installation and maintenance cost especially if precise location is in consideration. In order to find a more affordable and functional solution, in this project, cameras are chosen for data input, and deep learning neural networks models are developed. Convolutional neural networks have achieved very good performance in the area of computer vision in recent years. We explore in this direction and propose VGG Extended Model and Mini Parking CNN Model. Testing is done to evaluate the time cost and recognition accuracy. Feasibility is prototyped, named as SmartParking. The Mini Parking CNN Model demonstrates excellent performance and this system built with it can help users to find empty parking space accurately and effectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Network2Vec: Learning node representation based on space mapping in networks

arXiv

引用

arXiv 2019年

作者： Huang, Zhenhua Wang, Zhenyu Zhang, Rui Zhao, Yangyang Xie, Xiaohui Mehrotra, Sharad School of Software Engineering South China University of Technology Dept. of Computer Science University of California Irvine United States

Complex networks represented as node adjacency matrices constrains the application of machine learning and parallel algorithms. To address this limitation, network embedding (i.e., graph representation) has been intensively studied to learn a fixed-length vector for each node in an embedding space, where the node properties in the original graph are preserved. Existing methods mainly focus on learning embedding vectors to preserve nodes proximity, i.e., nodes next to each other in the graph space should also be closed in the embedding space, but do not enforce algebraic statistical properties to be shared between the embedding space and graph space. In this work, we propose a lightweight model, entitled Network2Vec, to learn network embedding on the base of semantic distance mapping between the graph space and embedding space. The model builds a bridge between the two spaces leveraging the property of group homomorphism. Experiments on different learning tasks, including node classification, link prediction, and community visualization, demonstrate the effectiveness and efficiency of the new embedding method, which improves the state-of-the-art model by 19% in node classification and 7% in link prediction tasks at most. In addition, our method is significantly faster, consuming only a fraction of the time used by some famous methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

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：