检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Chen, Yunwang Kang, Yaozhong Zhao, Ziqi Hong, Yue Meng, Lingxiao Meng, Max Q.-H. Southern University of Science and Technology Shenzhen Key Laboratory of Robotics Perception and Intelligence Shenzhen518055 China SUSTech Department of Electrical and Electronic Engineering Shenzhen China School of System Design and Intelligent Manufacturing SUSTech Shenzhen China

ISBN: (纸本)9781665481090

This paper presents a collaborative fall detection and response system integrating Wi-Fi sensing with robotic assistance. The proposed system leverages channel state information (CSI) disruptions caused by movements to detect falls in non-line-of-sight (NLOS) scenarios, offering non-intrusive monitoring. Besides, a companion robot is utilized to provide assistance capabilities to navigate and respond to incidents autonomously, improving efficiency in providing assistance in various environments. The experimental results demonstrate the effectiveness of the proposed system in detecting falls and responding effectively. © 2024 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Multi-physics Coupling Analyses of Nuclear Thermal Propulsion Reactor 23rd

Multi-physics Coupling Analyses of Nuclear Thermal Propulsio...

引用

23rd Pacific Basin Nuclear Conference, PBNC 2022

作者： Han, Wenbin Guan, Zechuan Huang, Shanfang Deng, Jian Department of Engineering Physics Tsinghua University Beijing China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu China China Institute of Atomic Energy Beijing China

ISBN: (纸本)9789819910229

Nuclear thermal propulsion (NTP) reactors have high-temperature solid-state characteristics and significant thermal expansion, which therefore require multi-physics coupling analyses. In this paper, the framework of Neutronics, Thermal-Hydraulics and Mechanics coupling (N/T-H/M) of nuclear thermal propulsion reactor is developed, and the typical reactor XE-2 is analyzed with this method. The results show that the N/T-H/M coupling will bring -1049 pcm negative reactivity, of which the thermal expansion effect accounts for 22%, indicating that the nuclear thermal propulsion reactor has a certain capacity for self-regulation. However, thermal expansion will lead to 0.88 mm peak deformation and 233 MPa peak stress, which will severely threaten the mechanical tolerance of the materials. Therefore, there is a trade-off between the advantages and disadvantages of the high-temperature solid-state core while designing NTP reactors. © 2023, The Author(s).

关键词： Thermal expansion

来源：评论

学校读者我要写书评

暂无评论

UWM-Net: A Mixture Density Network Approach with Minimal Dataset Requirements for Underwater Image Enhancement

UWM-Net: A Mixture Density Network Approach with Minimal Dat...

引用

Artificial Intelligence (CAI), IEEE Conference on

作者： Jun Huang Zongze Li Ruihao Zheng Zhenkun Wang School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

The learning-based underwater image enhancement, which is suitable for batch processing, is a pivotal research direction in underwater image processing. Extensive paired image data are required in existing learning-based methods, which necessitate considerable preprocessing and hinder the application of these methods. To address these limitations, we propose a semi-supervised approach called UWM-Net: firstly, we use a compact dataset of underwater image pairs to train the Mixture Density Network (MDN) with an underwater scene setting; subsequently, U-Net can learn underwater image enhancement more efficiently. The MDN can transform standard images into underwater scenes, reducing the reliance on paired data and making much smaller training datasets. In experimental studies, UWM-Net using only 18 pairs of underwater image data achieves highly competitive results in terms of 3 metrics compared with advanced models.

关键词： Measurement Training Learning systems Image quality Image color analysis Refining Training data

来源：评论

学校读者我要写书评

暂无评论

EXPERIMENT AND SIMULATION OF Q-? RESONANCE USING FOUR-LAYER BENDING-SHEAR TYPE SPECIMEN 9

EXPERIMENT AND SIMULATION OF Q-? RESONANCE USING FOUR-LAYER ...

引用

9th ECCOMAS Thematic Conference on Computational Methods in Structural Dynamics and Earthquake engineering, COMPDYN 2023

作者： Kai, Ryohei Kohiyama, Masayuki School of Science for Open and Environmental Systems Graduate School of Science and Technology Keio University 3-14-1 Hiyoshi Kohoku-ku Yokohama223-8522 Japan Department of System Design Engineering Faculty of Science and Technology Keio University 3-14-1 Hiyoshi Kohoku-ku Yokohama223-8522 Japan

Torsional vibration of buildings subjected to earthquake motion has been studied for many years, but the torsional vibration of high-rise buildings has not yet been clarified. Many previous studies have focused on eccentricity, the mismatch between the center of gravity and the rigid center, as the cause of torsional vibration. However, in buildings with no eccentricity, torsional vibrations could be observed. The authors' research group focused on the "Q-? effect," a phenomenon in which torsional torque is generated due to geometric nonlinearity and "Q-? resonance," a phenomenon in which resonance occurs when the period of torsional torque generation coincides with the natural period of the torsional mode. In order to analyze the characteristics of Q-? resonance, a small-scale specimen was designed and fabricated from an 81-story high-rise building with biaxially symmetrical plans, which was reduced to four stories. As a result, the torsional response of the experimental and simulation results generally agreed, confirming that the torsional response increases when the Q-? resonance condition is satisfied. In addition, a comparison of the torsional response with a specimen with a smaller tower ratio and less bending deformation was conducted, and it was confirmed that the peak of the torsional response was steeper in the present study case. © 2023 COMPDYN Proceedings. All rights reserved

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

INTRODUCING FEATURE MATCHING AND SMOOTHING LOSS: A NOVEL GAN FOR IMPROVED SAMPLE GENERATION 13

INTRODUCING FEATURE MATCHING AND SMOOTHING LOSS: A NOVEL GAN...

引用

13th International Conference on Quality, Reliability, Risk, Maintenance, and Safety engineering, QR2MSE 2023

作者： Yang, Junfeng Liu, Fengchang Mi, Jinhua Yin, Shengjie Bai, Libing School of Automation Engineering University of Electronic Science and Technology of China Chengdu China Center for System Reliability and Safety University of Electronic Science and Technology of China Chengdu China Department of SRM Design Shanghai Space Propulsion Technology Research Institute Shanghai China

ISBN: (纸本)9781839539848

Fault diagnosis of planetary gearboxes constitutes a vital element of rotating machinery. In recent years, fault diagnosis techniques for planetary gearboxes predicated on deep learning have undergone extensive research. However, in scenarios with limited samples, these deep learning methodologies can grapple with data scarcity issues, negatively impacting the model's generalization capacity and diagnostic performance. To mitigate this, Generative Adversarial Networks (GANs) have been integrated into planetary gearbox fault diagnosis to fabricate synthetic data, thereby augmenting the training dataset. Nevertheless, GANs face challenges in effectively learning local feature information from samples, leading to substantial disparities in local features between the generated data and the original data. Furthermore, the sampling of fault vibration signals from planetary gearboxes often exhibits a high frequency, with relatively smooth signal transitions, while the vibration signal samples generated by GANs often fluctuate excessively, demonstrating significant differences from the original vibration signals. To address this issue, this study introduces an enhanced GAN network that incorporates a feature attention matching mechanism in the computation of the loss function. This mechanism aims to amplify the feature similarity between the generated samples and local samples. Concurrently, a smoothness loss is introduced into the loss function to ensure the changes in the generated signal samples are more gradual. Experimental results indicate that this proposed method can generate superior quality samples, and the generated samples can achieve high accuracy on the WD-CNN diagnostic network. © The Institution of engineering & technology 2023.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Decomposition-Based Memetic Algorithm for Multi-Objective Fleet Size and Mix Vehicle Routing Problem

Decomposition-Based Memetic Algorithm for Multi-Objective Fl...

引用

Congress on Evolutionary Computation

作者： Yunpeng Ba Ruihao Zheng Zhenkun Wang School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

The heterogeneous fleet vehicle routing problem (HFVRP) is of great significance in logistics and transportation. This paper considers a crucial and challenging HFVRP variant, namely multi-objective fleet size and mix vehicle routing problem with unlimited fleet, fixed cost, and dependent cost (MO-FSMVRPFD). A decomposition-based memetic algorithm called MOEA/D-ALS is proposed to cope with MO-FSMVRPFD. MOEA/D-ALS uses the multi-objective evolutionary algorithm based on decomposition (MOEA/D) as the backbone. Beyond that, it adopts a replacement strategy based on maximal fitness improvement (MFI). In addition, the local search is conducted on difficult subproblems for further refinement. The experimental studies on 18 instances show that MOEA/D-ALS exhibits a significant performance superiority over two other representative algorithms. The effectiveness of both the MFI strategy and the adaptive local search procedure is also validated.

关键词： Memetics Measurement Costs Vehicle routing Transportation Evolutionary computation Logistics

来源：评论

学校读者我要写书评

暂无评论

Towards Lightweight Underwater Depth Estimation

Towards Lightweight Underwater Depth Estimation

引用

Artificial Intelligence (CAI), IEEE Conference on

作者： Keyu Zhou Jin Chen Shuangchun Gui Zhenkun Wang School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

Underwater depth estimation is crucial in the applications of marine robotics. It can provide environment information for target tracking, robot navigation, and 3D reconstruction of underwater terrain. Existing works transform underwater images into in-air conditions to adapt methods that are designed for natural images. However, this may result in expensive computational resources. To overcome this limitation, we propose a lightweight knowledge distillation framework for underwater depth estimation. We utilize a powerful model designed for underwater images as the teacher model and a lightweight CNN model as the student model. We distill global features to enable the student to acquire both local and global information, thereby improving estimation performance. Our framework includes a global transformation module for efficient global feature distillation and a global-local fusion module to combine local and global information for final estimation. Experimental results on the FLSea dataset demonstrate that our student model is lighter than the teacher model while outperforming lightweight in-air models. Our network is 60% lighter than the teacher model and achieves a 3.1% improvement in the δ 1 metric compared to the lightweight in-air model.

关键词： Measurement Adaptation models Three-dimensional displays Target tracking Navigation Computational modeling Estimation

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Controller for a Unity-Power Factor Boost Converter in Three-Phase Induction Motor Drives Applications 8

Fuzzy Controller for a Unity-Power Factor Boost Converter in...

引用

8th International engineering Conference on Renewable Energy and Sustainability, ieCRES 2023

作者： Awad, Hilmy Magagula, Gculisiwe Nassar, Yasser El-Khozondar, Hala J. Bayoumi, Ehab H.E. Helwan University Faculty of Technology and Education Department of Electrical Technology Cairo Egypt University of Eswatini Faculty of Science and Engineering Department of Electrical and Electronics Engineering Kwaluseni Swaziland Wadi Alshatti University Faculty of Eng. Mechanical & Renewable Energy Engineering Department Libya The Islamic University of Gaza Electrical Eng. and Smart System Gaza Palestine Faculty of Engineering Department of Mechanical Engineering El Sherouk Cairo11837 Egypt

ISBN: (纸本)9798350300758

The unity power factor is attained when both the displacement and distortion factors are unity by having a sinusoidal current waveform that is in phase with the line voltage. This paper proposes using Fuzzy Logic Controllers (FLC) to achieve a unity power factor in three-phase induction motor drive applications. Cascade controller loops are used to monitor and control the converter current and the voltage. The proposed control technique is evaluated under different operational conditions, where the dc converter voltage and load are varied. The simulation results show that the unity power factor operation of the boost converter for the induction motor has a fast response and good dynamic performance. © 2023 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Deep Optimal VGG16 Based COVID-19 Diagnosis Model

引用

Computers, Materials & Continua 2022年第1期70卷 43-58页

作者： M.Buvana K.Muthumayil S.Senthil kumar Jamel Nebhen Sultan S.Alshamrani Ihsan Ali Department of Computer Science and Engineering PSNA College of Engineering and TechnologyDindigul624622India Department of Information Technology PSNA College of Engineering and TechnologyDindigul624622India Department of Electrical and Electronics Engineering New Prince Shri Bhavani College of Engineering and TechnologyChennai600073India Prince Sattam Bin Abdulaziz University College of Computer Engineering and SciencesAlkharj11942Saudi Arabia Department of Information Technology College of Computer and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer System and Technology Faculty of Computer Science and Information TechnologyUniversity of MalayaKuala Lumpur50603Malaysia

Coronavirus(COVID-19)outbreak was first identified in Wuhan,China in December *** was tagged as a pandemic soon by the WHO being a serious public medical *** spite of the fact that the virus can be diagnosed by qRT-PCR,COVID-19 patients who are affected with pneumonia and other severe complications can only be diagnosed with the help of Chest X-Ray(CXR)and Computed Tomography(CT)*** this paper,the researchers propose to detect the presence of COVID-19 through images using Best deep learning model with various *** features like Speeded-Up Robust Features(SURF),Features from Accelerated Segment Test(FAST)and Scale-Invariant Feature Transform(SIFT)are used in the test images to detect the presence of *** optimal features are extracted from the images utilizing DeVGGCovNet(Deep optimal VGG16)model through optimal learning *** task is accomplished by exceptional mating conduct of Black Widow *** this strategy,cannibalism is *** this phase,fitness outcomes are rejected and are not satisfied by the proposed *** results acquired from real case analysis demonstrate the viability of DeVGGCovNet technique in settling true issues using obscure and testing ***16 model identifies the imagewhich has a place with which it is dependent on the distinctions in *** impact of the distinctions on labels during training stage is studied and predicted for test *** proposed model was compared with existing state-of-the-art models and the results from the proposed model for disarray grid estimates like Sen,Spec,Accuracy and F1 score were promising.

关键词： COVID 19 multi-feature extraction vgg16 optimal learning rate

来源：评论

学校读者我要写书评

暂无评论

Application of artificial intelligence techniques in modeling attenuation behavior of ionization radiation: a review

引用

Radiation Detection technology and Methods 2023年第1期7卷 56-83页

作者： Joseph Konadu Boahen Samir A.Elsagheer Mohamed Ahmed S.G.Khalil Mohsen A.Hassan Materials Science and Engineering Department School of Innovative Design EngineeringEgypt-Japan University of Science and Technology(E-JUST)P.O.Box 179New Borg El-Arab CityEgypt Computer Science and Information Technology Programs Egypt-Japan University of Science and Technology(E-JUST)AlexandriaEgypt Faculty of Engineering Aswan UniversityAswanEgypt Institute of Basic and Applied Science Egypt-Japan University of Science and Technology(E-JUST)179 New Borg El-Arab CityAlexandriaEgypt Environmental and Smart Technology Group Faculty of ScienceFayoum UniversityFayoum63514Egypt

Introduction Shielding of ionizing radiations,which are gamma rays,neutrons,and X-rays,can be achieved by attenuating its intensity using different *** is therefore crucial in ensuring the safety of lives and essential equipment in areas such as nuclear power plants,radiotherapy facilities,space exploration,and *** Intelligent technologies have become desirable in modeling shielding materials’attenuation behavior due to their unique *** The overview aims to present the recent application of AI technologies in modeling the radiation attenuation behavior of *** A total of 41 relevant articles were obtained using Scopus and web of science *** search was restricted to articles and conference papers published within the last two *** From the overview,it was realized that AI techniques can predict the attenuation properties of shielding materials and optimize the shield *** methods can be grouped into predictive models which are:fuzzy logic,Support Vector Regression,Neural Networks,and optimization models which include Genetic algorithms,Ant Colony,and Particle Swarm *** networks are the most robust and widely used *** predictive models are used in predicting parameters such as attenuation coefficient,buildup factor,shield thickness,and radiation dose rates,whiles the optimization techniques are employed in single and multi-objective attenuator *** In the overview,the accuracies and complexities of the various AI techniques have been discussed giving insight into their *** AI techniques are easy to model compared to conventional methods and can save computational time when coupled with conventional statistical and deterministic models or employed as a standalone technique.

关键词： Ionization radiation Attenuation behavior Artificial intelligence Modeling

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：