检索结果-内蒙古大学图书馆

29th International Conference on Computational and Experimental engineering and sciences, ICCES 2023

作者： Hao, Ning Li, Yunwei Ma, Yusen Zhang, Xinan Beijing Institute of Spacecraft Environment Engineering Haidian District Space City Beijing100048 China College of Computer Science and Technology Harbin Engineering University Harbin150001 China Modeling and Emulation in E-Government National Engineering Laboratory Harbin Engineering University Harbin150001 China School of Physics Mathematics and Computing University of Western Australia PerthWA6009 Australia

ISBN: (纸本)9783031449468

Ship remote sensing target recognition is a critical task in various maritime applications, including surveillance, navigation assistance, and disaster management. However, traditional methods face challenges in detecting and recognizing ships in complex maritime environments, which include various types of ships, sea conditions, and environmental factors. In recent years, deep learning-based object detection algorithms have shown promising results in detecting and recognizing ships in remote sensing images. In this paper, we propose a ship remote sensing target recognition method based on the YOLOV5 algorithm. Our approach uses a deep convolutional neural network to extract high-level features from remote sensing images and detect and classify ships. The proposed method uses anchor-based object detection to identify ship locations and a multi-scale feature fusion strategy to capture different ship sizes and orientations. We also introduce a new ship dataset, which includes various ship types and sea conditions, to evaluate the performance of our proposed method. Experimental results show that our method outperforms other common ship detection algorithms in terms of detection accuracy. Our method can significantly contribute to improving ship detection and recognition in real-world maritime applications, especially in complex scenarios. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

Simulating Long-Range Atmospheric Turbulence in the Laboratory with an Artificial Turbulence Simulator

SSRN

引用

SSRN 2024年

作者： Tan, Wei Bai, Yanfeng Huang, Xianwei Zhu, Xiaohui Zou, Xuanpengfan Zhou, Qi Jiang, Teng Liu, Mingwei Nan, Suqin Fu, Xiquan College of Computer Science and Electronic Engineering Hunan University Changsha410082 China School of Physics and Electronics Science Hunan University of Science and Technology Xiangtan411201 China School of Computer Science Hunan University of Technology and Business Changsha410205 China

Atmospheric turbulence is the predominant propagation medium in random environments, significantly impacting beam propagation, particularly over long distances. In this study, we establish an equivalent experimental setup in the laboratory to simulate long-range atmospheric turbulence. The experiment employs a water tank, wave maker, and transparent perforated plate to generate turbulence with predetermined scales. We investigate the behavior of a laser beam propagating through a random environment induced by water flow from various directions. The scintillation index and rms displacement of the beam's hot spot at the receiver are utilized to characterize the influence of water turbulence on light intensity fluctuations and beam wander, respectively. By inverting the intensity of water turbulence based on scintillation index and beam wander measurements, we observe an error magnitude less than one order of magnitude between them. Compared to atmospheric turbulence, our laboratory-generated water turbulence is four orders of magnitude stronger. This work establishes an equivalent connection between atmospheric and water turbulence, enabling realistic simulation of long-range laser propagation under actual atmospheric conditions. © 2024, The Authors. All rights reserved.

关键词： Atmospheric turbulence

来源：评论

学校读者我要写书评

暂无评论

Image Based Feature Separation Using RBM Tech with ADBN Tech for Accurate Fruit Classification 5

Image Based Feature Separation Using RBM Tech with ADBN Tech...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Revathi, V. Kavin, Balasubramanian Prabhu Thirumalraj, Arunadevi Gangadevi, E. Balusamy, Balamurugan Gite, Shilpa New Horizon College of Engineering Department of Applied Sciences - Physics Ring Road Bellandur Post Bengaluru India School of Computing Srm Institute of Science and Technology Department of Data Science and Business Systems Chengalpattu Tamil Nadu Kattankulathur603 203 India K.Ramakrishnan College of Technology Department of Computer Science Engineering Tamil Nadu Trichy India Loyola College Department of Computer Science Chennai600034 India Delhi India Symbiosis Institute of Technology Pune Aiml Department Pune412115 India

ISBN: (纸本)9798350383522

One of the fastest-growing subfields of computer vision and picture categorization is fruit identification. The fruit industry could start using a standardised categorization system so that shoppers can easily distinguish between different types and quality levels of fruit. From a health perspective, fruit quality is essential. The task of classifying fruits is crucial in many commercial contexts. A supermarket cashier may use a fruit categorization system to better recognise the varieties of fruit and their associated costs. It might also be used to determine whether or not a given kind of fruit is suitable for a person's diet. The rising use of intelligent imaging equipment may be directly attributed to the proliferation and development of AI software. Deep learning methods, such as CNN, are now being used by researchers for picture categorization. CNN's superior performance may be achieved without using any manually-crafted characteristics, in contrast to the older methods. For automated categorization, it employs a plethora of filters that strip relevant visual information. Classifying fruits accurately is a challenge in the horticulture sector and calls for the knowledge of an expert. For accurately and quantitatively analysing fruits, the currently mentioned categorization techniques fall short. Therefore, it is beneficial to review the latest suggestions for categorizing fruits. To solve this problem, we need a computerised system that can automatically sort fruits into their respective categories. Deep learning models, such as the Restricted Boltzmann Machine (RBM) and the Adam based Deep Belief Network (DBN), are used in this assignment to categorise fruits according to the attributes that have been determined to be optimum and generated. The proposed approach has been shown to have effective accuracy and quantitative analysis outcomes, and this is just the beginning of this realisation. In addition, the suggested scheme's relatively strong computational mo

关键词： Deep Belief Network Fruits Classification Fruits Grading Handcrafted features Restricted Boltzmann Machine

来源：评论

学校读者我要写书评

暂无评论

A Study on the Mechanical Properties of Rare Earth-based Aluminium Composite

引用

Journal of The Institution of Engineers (India): Series D 2023年第1期104卷 15-25页

作者： Balamurugan, K. Deepthi, T. Subramanian, Ananda Kumar Banerjee, Amit Agarwal, Daksh Biswas, Arindam Sinha, Arijit Department of Mechanical Engineering Vignan’s Foundation for Science Technology & Research Andhra Pradesh Guntur522213 India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India Physics Department Bidhan Chandra College West Bengal Asansol713 303 India Department of Materials Science and Engineering University of Pennsylvania PhiladelphiaPA19104 United States Lam Research Corporation FremontCA94538 United States Department of Mining Engineering Kazi Nazrul University West Bengal Asansol713340 India Department of Metallurgical Engineering Kazi Nazrul University West Bengal Asansol713340 India

The present investigation signifies the effect of incorporation of lanthanum phosphate nanopowder at different weight ratios in aluminium matrix. The lanthanum phosphate reinforcements in the 50–80 nm size range are synthesized through a cost-effective sol–gel process, without any subsequent secondary process. The composite is fabricated by the ultrasonic-assisted stir casting process, a low cost and a less defective manufacturing process. Various mechanical properties, viz. ultimate tensile strength, flexural strength, compressive strength and hardness, are examined. From the study, it is concluded that MMC with 15 wt% the lanthanum phosphate leads to the best tensile, compression and flexural properties as well as hardness. Blending the reinforcement in the matrix is a challenging task, besides the selection of suitable stirring conditions which greatly reduces the agglomerations. The higher bonding force between the reinforcement and the matrix makes the reinforcement a suitable material in the aluminium matrix composite, and it is confirmed through density functional theory studies. The superior properties of the Al/LaPO4 composite make it a suitable replacement material for aerospace and defence applications. © 2022, The Institution of Engineers (India).

关键词： Tensile testing

来源：评论

学校读者我要写书评

暂无评论

Composite metamorphic relations for integration testing 22

Composite metamorphic relations for integration testing

引用

8th International Conference on computer Technology Applications, ICCTA 2022

作者： Iakusheva, Sofia Khritankov, Anton Phystech School of Applied Mathematics and Informatics Moscow Institute of Physics and Technology Russia Faculty of Computer Science Dept. of Software Engineering Hse University Russia

ISBN: (纸本)9781450396226

Metamorphic testing is a testing method for problems without test oracles. Integration testing allows for detecting errors in complex systems that may not be found during the testing of their components. In this paper, we propose a novel approach that applies metamorphic testing in integration testing. The main idea is to develop a composite metamorphic relation for the system represented as an acyclic graph. This relation is a logical function of metamorphic relations for the parts of the system (vertices of the graph). It takes into account the features of the parts. Also, it can simplify the search for failure by identifying the subsystem with error. In this paper's theoretical part, we describe an algorithm of relation design. Then, we apply our method to a bioinformatics system for comparative genetic analysis of tissues using production tools. This experiment proves our method can be applied to real-life pipelines and find errors in them. © 2022 ACM.

关键词： Integration testing

来源：评论

学校读者我要写书评

暂无评论

Filling Deterministic Approximate Gap in Denoising Diffusion Probabilistic Models with Energy 38

Filling Deterministic Approximate Gap in Denoising Diffusion...

引用

38th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2023

作者： Kan, Ge Wang, Tian Liu, Deyuan Wang, Jian Fu, Yao Snoussi, Hichem Beihang University School of Automation Science and Electrical Engineering Beijing100191 China Beihang University Zhongguancun Laboratory Institute of Artificial Intelligence Sklsde Beijing100191 China Wuhan University School of Computer Science Wuhan430072 China Chinese Academy of Sciences Changchun Institute of Optics Fine Mechanics and Physics Changchun130033 China University of Technology of Troyes Laboratory of Computer Science and Digital Society Troyes France

ISBN: (纸本)9798350303636

Diffusion probabilistic models (DPMs) have shown the best generative quality and admit impressive likelihood meanwhile. However, its variants take very long generative processes during sampling, because of the small noise scale assumption, say, sets the variance of the forward diffusion kernel to be very small. Under which, the generative denoising processes are of tractable Gaussian form. To shorten the generative process, we explore the non-Gaussian reverse kernel under the large noise scale assumption and analysis the deterministic approximate gap of Gaussian denoising process. To fill the gap, we enhance the standard DPM with conditional energy and introduce variantional sampler to construct tractable generative process. The new probabilistic model, termed denoising diffusion energy-based model (DDEBM), are trained with two stage adversarial optimization. Experiments show our models demonstrate competitive generative performance with only four steps. © 2023 IEEE.

关键词： Diffusion probabilistic model Energy-based model Generative model Image generation

来源：评论

学校读者我要写书评

暂无评论

Optical spatiotemporal vortices

引用

eLight 2023年第1期3卷 156-168页

作者： Chenhao Wan Andy Chong Qiwen Zhan School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai 200093China School of Optical and Electronic Information and Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074HubeiChina Department of Physics Pusan National UniversityGeumjeong-GuBusan 46241South Korea Zhangjiang Laboratory 100 Haike RoadShanghai 201204China Shanghai Key Lab of Modern Optical System University of Shanghai for Science and TechnologyShanghai 200093China

Spatiotemporal vortices of light,featuring transverse orbital angular momentum(OAM)and energy circulation in the spatiotemporal domain,have received increasing attention *** experimental realization of the controllable generation of spatiotemporal vortices triggers a series of research in this *** review article covers the latest developments of spatiotemporal vortices of light ranging from theoretical physics,experimental generation schemes,and characterization methods,to applications and future *** new degree of freedom in photonic OAM endowed by spatiotemporal vortices paves the way to the discovery of novel physical mechanisms and photonic applications in light science.

关键词： Spatiotemporal optical vortex Orbital angular momentum Spin-orbit interaction Linear momentum density Toroidal vortex Topological charge

来源：评论

学校读者我要写书评

暂无评论

Study of the influence of parameters to explore the Properties of Graphene Nanoribbon Field Effect Transistors

Study of the influence of parameters to explore the Properti...

引用

2022 IEEE International Conference of Electron Devices Society Kolkata Chapter, EDKCON 2022

作者： Behera, Sriyanka Pattanaik, Satya Ranjan Dash, Gananath Sambalpur University Electron Devices Group School of Physics Sambalpur768019 India Gandhi Institute for Technology Department of Computer Science and Engineering Bhubaneswar752054 India

ISBN: (纸本)9781665472050

Graphene based devices are impelling the innovations for the final implementation of flexible electronic devices within new perspectives of the future technological developments. Specially, GNRFET has placed in a superior position due to the existence of finite bandgap and the ability to tune the same by a simple way (of varying the width). Therefore, we have explored the properties of GNRFET by using some analytic approach with a view to assess its efficacy as a Field Effect Transistor (FET). Reduction of a 2-dimensional (2D) Poisson equation to a one-dimensional (1D) form in an effective manner is the main of focus of this method. The approach was used to study the influence of geometrical and electrical parameters on I-V characteristics of the GNRFET. The results of this work pave the way for the possibilities for device engineers to characterize GNRFETs based on the requirements of a specific device application. The resulting convergence of the inflection point is an interesting feature of our *** existence of a critical voltage, beyond which the current rises in its value with temperature, is an pre-eminent feature of our GNRFET model. © 2022 IEEE.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Context Learning Strategy for Interference-Aware Beam Allocation in mmWave Vehicular Communications

arXiv

引用

arXiv 2024年

作者： Kose, Abdulkadir Lee, Haeyoung Foh, Chuan Heng Shojafar, Mohammad Department of Computer Engineering Abdullah Gul University Kayseri Turkey School of Physics Engineering and Computer Science University of Hertfordshire Hatfield United Kingdom University of Surrey Guildford United Kingdom

Millimeter wave (mmWave) has been recognized as one of key technologies for 5G and beyond networks due to its potential to enhance channel bandwidth and network capacity. The use of mmWave for various applications including vehicular communications has been extensively discussed. However, applying mmWave to vehicular communications faces challenges of high mobility nodes and narrow coverage along the mmWave beams. Due to high mobility in dense networks, overlapping beams can cause strong interference which leads to performance degradation. As a remedy, beam switching capability in mmWave can be utilized. Then, frequent beam switching and cell change become inevitable to manage interference, which increase computational and signalling complexity. In order to deal with the complexity in interference control, we develop a new strategy called Multi-Agent Context Learning (MACOL), which utilizes Contextual Bandit to manage interference while allocating mmWave beams to serve vehicles in the network. Our approach demonstrates that by leveraging knowledge of neighbouring beam status, the machine learning agent can identify and avoid potential interfering transmissions to other ongoing transmissions. Furthermore, we show that even under heavy traffic loads, our proposed MACOL strategy is able to maintain low interference levels at around 10%. © 2024, CC0.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Reservoir Computing with Nanowire Exchange-Coupled Spin Torque Oscillator Arrays 1

引用

20th International Conference on Unconventional Computation and Natural Computation, UCNC 2023

作者： Dale, Matt Evans, Richard F. L. Sebald, Angelika Stepney, Susan Department of Computer Science University of York York United Kingdom School of Physics Engineering and Technology University of York York United Kingdom York Cross-disciplinary Centre for Systems Analysis University of York York United Kingdom

ISBN: (数字)9783031340345

ISBN: (纸本)9783031340338

Spin torque oscillators (STOs) feature transient non-linear behaviour that can be exploited for computation. When combined in arrays, they can be networked to produce more complex collective behaviours than single devices alone. We simulate a physical reservoir computer comprising an array of STOs, using a macro spin approximation. We demonstrate that STOs can be networked together in arrays using nanowires, and that by altering the properties of these nanowires we can optimise the magnetic exchange coupling between the oscillators for computational purposes. We train a simulated array of coupled oscillators to compute various time-independent and time-dependent benchmark tasks. We explore the effects of array size, heterogeneous coupling, and connection topologies. We demonstrate the computational potential of programming the exchange coupling in arrays of oscillators through nanowires. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Nanowires

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：