检索结果-内蒙古大学图书馆

AIAA SciTech Forum and Exposition, 2023

作者： Sarojini, Darshan Ruh, Marius L. Sperry, Mark Yan, Jiayao Fletcher, Andrew Joshy, Anugrah Jo Scotzniovsky, Luca Ivanov, Alexander Orndorff, Nicholas Gandarillas, Victor Asher, Isaac Chambers, Jeff Gill, Hyunjune Lee, Seongkyu Cheng, Zeyu Rodriguez, Gabriel Zhao, Shuofeng Mi, Chunting Nascenzi, Thomas Cuatt, Timothy Winter, Tyler Guibert, Alexandre Cronk, Ashley Kim, Alicia Meng, Shirley Hwang, John T. Department of Mechanical and Aerospace Engineering University of California San Diego 9500 Gilman Dr La Jolla CA92093 United States Flight Physics Aurora Flight Sciences A Boeing Company 9950 Wakeman Drive ManassasVA20110 United States Engineering Department Aurora Flight Sciences A Boeing Company 9950 Wakeman Drive ManassasVA20110 United States Department of Mechanical and Aerospace Engineering University of California Davis 1 Shields Avenue DavisCA95616 United States Department of Electrical and Computer Engineering San Diego State University 5500 Campanile Dr San Diego92182 United States Research and Development M4 Engineering Inc 4020 Long Beach Blvd # 2 Long BeachCA90807 United States Structural Engineering Department University of California San Diego 9500 Gilman Dr La Jolla CA92093 United States Materials Science and Engineering Program University of California San Diego 9500 Gilman Dr La Jolla CA92093 United States Department of NanoEngineering University of California San Diego 9500 Gilman Dr La Jolla CA92093 United States

ISBN: (数字)9781624106996

ISBN: (纸本)9781624106996

This paper presents a framework under development for enabling large-scale multi-fidelity modeling and optimization of electric vertical takeoff and landing concepts (eVTOL). The key features of the framework are a geometry-centric approach to multidisciplinary design optimization (MDO), a modular functional-form representation of the disciplines involved in aircraft design, and fully automated derivative computations thereby allowing efficient gradient-based optimization. The framework is first presented in a general manner agnostic to the vehicle concept or the physics-based analyses used. The key disciplines involved in the design of eVTOL aircraft and the couplings between the disciplines are described. The framework is then applied to the design of the NASA lift-plus-cruise concept. Low-fidelity solvers of aerodynamics, propulsion, structural estimation, acoustics, powertrain, and battery are coupled together. The optimization considers 108 design variables and 16 constraints. It is shown that MDO considering geometric variables results in a design with lower gross mass than when the geometric variables are not considered. The optimization turnaround time of 30 minutes on a standard workstation demonstrates the capabilities of fully-coupled large-scale MDO using gradient-based optimization. The framework is under development and an open-source version will be released in the near future. © 2023, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Block Attention Module Based Lightweight Convolutional Neural Network Model for Rotating Machinery Fault Diagnosis

SSRN

引用

SSRN 2023年

作者： Lu, Na Li, Ruiqiang Zhang, Guangtao Cao, Chaofan Chen, Xudong Guo, Jinjun Malik, Om Parkash Yellow River Laboratory Zhengzhou University Zhengzhou45000 China School of Water and Civil Engineering Zhengzhou University Zhengzhou45000 China Rundian Energy Science and Technology Co. Ltd. Zhengzhou450052 China Department of Electrical and Computer Engineering University of Calgary CalgaryABT2N 1N4 Canada

Most deep learning methods have too many parameters for rotating machinery fault diagnosis. As a result, high computer performance is required, which may be difficult to achieve in some circumstances. To address this problem, a Convolutional Block Attention Module based lightweight Convolutional Neural Network (CBAM-LightCNN) model is proposed. To obtain optimal fault diagnosis results, the hyperparameters of this model are optimized by using Neural Network Intelligence (NNI). Besides, a new multi-sensor data fusion (DF) method is designed to fuse the raw multi-sensor data before feeding it into the CBAM-LightCNN. Compared with other traditional CNN models, this method not only reduces the number of parameters but also avoids dependence on user experience for feature extraction and hyperparameter settings. Through the experimental validation of two datasets consisting of the Case Western Reserve University (CWRU) dataset and hydropower unit operation dataset, the proposed method illustrates better diagnostic performance with 100% recognition accuracy in comparison with Artificial Neural Network (ANN), and traditional CNN methods. © 2023, The Authors. All rights reserved.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Audio Captioning Using Soft and Hard Prompts

arXiv

引用

arXiv 2024年

作者： Zhang, Yiming Xu, Xuenan Du, Ruoyi Liu, Haohe Dong, Yuan Tan, Zheng-Hua Wang, Wenwu Ma, Zhanyu The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Department of Electronic Systems Aalborg University Aalborg9220 Denmark The Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test sets from the same dataset. Such methods have two limitations. First, these methods are often data-hungry and require time-consuming and expensive human annotations to obtain audio-text pairs. Second, these models often suffer from performance degradation in cross-domain scenarios, i.e., when the input audio comes from a different domain than the training set, which, however, has received little attention. We propose an effective audio captioning method based on the contrastive language-audio pre-training (CLAP) model to address these issues. Our proposed method requires only textual data for training, enabling the model to generate text from the textual feature in the cross-modal semantic space. In the inference stage, the model generates the descriptive text for the given audio from the audio feature by leveraging the audio-text alignment from CLAP. We devise two strategies to mitigate the discrepancy between text and audio embeddings: a mixed-augmentation-based soft prompt and a retrieval-based acoustic-aware hard prompt. These approaches are designed to enhance the generalization performance of our proposed model, facilitating the model to generate captions more robustly and accurately. Extensive experiments on AudioCaps and Clotho benchmarks show the effectiveness of our proposed method, which outperforms other zero-shot audio captioning approaches for in-domain scenarios and outperforms the compared methods for cross-domain scenarios, underscoring the generalization ability of our method. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A CNN-based framework for land use land cover classification of heterogeneous terrain using satellite images

引用

Neural Computing and Applications 2025年 1-28页

作者： Tarafdar, Anurina Middya, Asif Iqbal Banerjee, Sounak Khatua, Sunirmal Roy, Sarbani Department of Computer Science and Engineering Heritage Institute of Technology Chowbaga Road Anandapur East Kolkata Township West Bengal Kolkata700107 India Department of Computer Science and Engineering Jadavpur University 188 Raja S.C. Mallick Rd West Bengal Kolkata700032 India Department of Computer Science and Engineering University of Calcutta JD-2 JD Block Sector III West Bengal Bidhannagar Kolkata700106 India

One of the important topics in remote sensing is land use land cover classification. This paper presents a framework that aims to correctly classify land use land cover into seven different landscape characteristics such as agricultural area, agricultural green area, greenery, land, mountain region, settlement, and water body using a convolutional neural network (CNN) model. Thousands of satellite images of different regions in India are obtained from the Google Maps platform using the Maps Static API. These images are pre-processed using image augmentation techniques, and the proposed CNN model is thoroughly trained with this dataset. Several existing deep CNN models such as VGG-16, ResNet-50, and InceptionV3 are also considered. Instead of training these CNN models from scratch, transfer learning is used and these pre-trained networks are fine-tuned by replacing the final layers with additional layers. All the models are trained rigorously using the satellite image dataset and their performances are compared. Results show that the proposed CNN model classifies the test dataset with 89.03% accuracy. Although ResNet-50 provides the most promising results with a classification accuracy of 90.94% on the test dataset, the proposed CNN model has much fewer parameters than ResNet-50, and therefore its training and prediction times are shorter. The model training time and the per-image prediction time of the proposed model are 77.06% and 30.55% less than those of ResNet-50, respectively. Some case studies are also conducted to show the application of the proposed model in classifying the land use land cover of different locations. Additionally, the efficacy of the model is validated by using it for land use land cover classification on the RGB version of the benchmark EuroSAT dataset. The results show that the proposed model can effectively perform land use land cover classification on the EuroSAT dataset with 94.02% accuracy. © The Author(s), under exclusive licence to S

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Calorimetric Studies and Thermodynamic Modeling of Ag–Mg–Ti Liquid Alloys

引用

Materials 2024年第8期17卷 1786页

作者： Gozdur, Weronika Gąsior, Wladyslaw Zrobek, Maciej Budziak, Andrzej Dębski, Roman Gierlotka, Wojciech Pęska, Magda Polański, Marek Dębski, Adam Institute of Metallurgy and Materials Science Polish Academy of Sciences 25 Reymonta Street Kraków30-059 Poland Faculty of Energy and Fuels AGH University of Krakow Al. Mickiewicza 30 Kraków30-059 Poland Institute of Computer Science AGH University of Krakow Al. Mickiewicza 30 Kraków30-059 Poland Department of Materials Science and Engineering National Dong Hwa University Hualien970024 Taiwan Department of Functional Materials and Hydrogen Technology Military University of Technology 2 Kaliskiego St. Warsaw00-908 Poland

Due to the absence of thermodynamic data concerning the Ag–Mg–Ti system in the existing literature, this study aims to fill this gap by offering the outcomes of calorimetric investigations conducted on ternary liquid solutions of these alloys. The measurements were performed using the drop calorimetry method at temperatures of 1294 K and 1297 K for the liquid solutions with the following constant mole fraction ratio: xAg/xMg = 9/1, 7/3, 1/1, 3/7 [(Ag0.9Mg0.1)1−xTix, (Ag0.7Mg0.3)1−xTix, (Ag0.5Mg0.5)1−xTix, (Ag0.3Mg0.7)1−xTix)], and xAg/xTi = 19/1 [(Ag0.95Ti0.05)1−xMgx]. The results show that the mixing enthalpy change is characterized by negative deviations from the ideal solutions and the observed minimal value equals −13.444 kJ/mol for the Ag0.95Ti0.05 alloy and xMg = 0.4182. Next, based on the thermodynamic properties of binary systems described by the Redlich–Kister model and the determined experimental data from the calorimetric measurements, the ternary optimized parameters for the Ag–Mg–Ti liquid phase were calculated by the Muggianu model. Homemade software (TerGexHm 1.0) was used to optimize the calorimetric data using the least squares method. Next, the partial and molar thermodynamic functions were calculated and are presented in the tables and figures. Moreover, this work presents, for comparative purposes, the values of the enthalpy of mixing of liquid Ag–Mg–Ti alloys, which were calculated using Toop’s model. It was found that the best agreement between the modeled and experimental data was observed for the cross-sections xAg/xTi = 19/1 [(Ag0.95Ti0.05)1−xMgx] and xAg/xMg = 9/1 [(Ag0.9Mg0.1)1−xTix]. The results of the experiments presented in this paper are the first step in the investigation and future evaluation of the thermodynamics of phases and the calculation of the phase diagram of the silver–magnesium–titanium system. © 2024 by the authors.

关键词： Calorimetry

来源：评论

学校读者我要写书评

暂无评论

Compact Silicon Nitride Interferometer

Compact Silicon Nitride Interferometer

引用

Frontiers in Optics + Laser science 2021, FiO+LS 2021 - Part of Frontiers in Optics, FiO 2021

作者： Armin, Fahimeh Nabki, Frederic Ménard, Michaël Department of Computer Science Université du Québec à Montréal MontréalQCH2X 3Y7 Canada Department of Electrical Engineering Ecole de Technologie Supérieure MontréalQCH3C 1K3 Canada

We demonstrate a silicon nitride interferometer with waveguides having different effective indexes instead of lengths to avoid waveguide bends, reduce losses and footprint. Frontiers in Optics / Laser science © O... 详细信息

ISBN: (纸本)9781557528209

关键词： Silicon nitride

来源：评论

学校读者我要写书评

暂无评论

How more data can hurt: Instability and regularization in next-generation reservoir computing

arXiv

引用

arXiv 2024年

作者： Zhang, Yuanzhao dos Santos, Edmilson Roque Cornelius, Sean P. Santa Fe Institute 1399 Hyde Park Road Santa FeNM87501 United States Department of Electrical and Computer Engineering Clarkson University PotsdamNY13699 United States Clarkson Center for Complex Systems Science Clarkson University PotsdamNY13699 United States Department of Physics Toronto Metropolitan University TorontoONM5B 2K3 Canada

It has been found recently that more data can, counter-intuitively, hurt the performance of deep neural networks. Here, we show that a more extreme version of the phenomenon occurs in data-driven models of dynamical systems. To elucidate the underlying mechanism, we focus on next-generation reservoir computing (NGRC)—a popular framework for learning dynamics from data. We find that, despite learning a better representation of the flow map with more training data, NGRC can adopt an ill-conditioned "integrator" and lose stability. We link this data-induced instability to the auxiliary dimensions created by the delayed states in NGRC. Based on these findings, we propose simple strategies to mitigate the instability, either by increasing regularization strength in tandem with data size, or by carefully introducing noise during training. Our results highlight the importance of proper regularization in data-driven modeling of dynamical systems. Copyright © 2024, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Mathematical Modeling of 18F-Fluoromisonidazole (18F-FMISO) Radiopharmaceutical Transport in Vascularized Solid Tumors

arXiv

引用

arXiv 2024年

作者： Abazari, Mohammad Amin Soltani, M. Eydi, Faezeh Rahmim, Arman Kashkooli, Farshad Moradi Department of Mechanical Engineering K. N. Toosi University of Technology Tehran Iran Department of Electrical and Computer Engineering Faculty of Engineering School of Optometry and Vision Science Faculty of Science University of Waterloo WaterlooN2L 3G Canada Department of Integrative Oncology BC Cancer Research Institute VancouverBCV5Z 1L3 Canada University of Waterloo WaterlooONN2L 3G Canada Cancer Biology Research Center Cancer Institute of Iran Tehran University of Medical Sciences Tehran Iran Departments of Radiology and Physics University of British Columbia VancouverBC Canada

18F-Fluoromisonidazole (18F-FMISO) is a highly promising positron emission tomography radiopharmaceutical for identifying hypoxic regions in solid tumors. This research employs spatiotemporal multi-scale mathematical modeling to explore how different levels of angiogenesis influence the transport of radiopharmaceuticals within tumors. In this study, two tumor geometries with heterogeneous and uniform distributions of capillary networks were employed to incorporate varying degrees of microvascular density. The synthetic image of the heterogeneous and vascularized tumor was generated by simulating the angiogenesis process. The proposed multi-scale spatiotemporal model accounts for intricate physiological and biochemical factors within the tumor microenvironment, such as the transvascular transport of the radiopharmaceutical agent, its movement into the interstitial space by diffusion and convection mechanisms, and ultimately its uptake by tumor cells. Results showed that both quantitative and semi-quantitative metrics of 18F-FMISO uptake differ spatially and temporally at different stages during tumor growth. The presence of a high microvascular density in uniformly vascularized tumor increases cellular uptake, as it allows for more efficient release and rapid distribution of radiopharmaceutical molecules. This results in enhanced uptake compared to the heterogeneous vascularized tumor. In both heterogeneous and uniform distribution of microvessels in tumors, the diffusion transport mechanism has a more pronounced than convection. The findings of this study shed light on the transport phenomena behind 18F-FMISO radiopharmaceutical distribution and its delivery in the tumor microenvironment, aiding oncologists in their routine decision-making processes. © 2024, CC BY.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Self-dual singularity through lasing and antilasing in thin elastic plates

引用

Physical Review B 2021年第13期103卷 134101-134101页

作者： M. Farhat P.-Y. Chen S. Guenneau Y. Wu Computer Electrical and Mathematical Science and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia Department of Electrical and Computer Engineering University of Illinois at Chicago Chicago Illinois 60607 USA UMI 2004 Abraham de Moivre-CNRS Imperial College London London SW7 2AZ United Kingdom

We show here that a coherent perfect absorber and laser (CPAL) enabled by parity-time (PT)-symmetry breaking may be exploited to build monochromatic amplifying devices for flexural waves. The fourth-order partial differential equation governing the propagation of flexural waves in thin-elastic piezoelectric plates leads to 4×4 transfer matrices, and captures the interplay between propagating and evanescent waves that is translated into PT-symmetry properties specific to elastic plate systems. We thus demonstrate the possibility of using CPAL for such systems and we argue the possibility of using this concept to detect extremely small-scale vibration perturbation with important outcomes in surface science (imaging of nanometer vibration) and geophysics (improving seismic sensors like velocimeters). The device can also generate finite signals using very low exciting intensities and/or alternatively can be used as a perfect absorber for flexural energy, by tailoring the left and right incident wave amplitude and phase, with evident energy harvesting applications.

关键词： Bending Elastic modulus Mechanical & acoustical properties PT-symmetry

来源：评论

学校读者我要写书评

暂无评论

Triple IRS-Aided Communications: Row-Column Sparsity Enhanced Bayesian Tensor Learning for Channel Estimation

引用

IEEE Transactions on Communications 2025年

作者： Hu, Limei Shao, Xiaodan Qiu, Tingzhi Chen, Feng Cheng, Lei Wu, Qingqing Southwest University College of Artificial Intelligence College of Electronic and Information Engineering Brain-Inspired Computing and Intelligent Control of Chongqing Key Laboratory National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing400715 China University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada Zhejiang University College of Information Science and Electronic Engineering Hangzhou310058 China Shanghai Jiao Tong University Department of Electronic Engineering Shanghai China

Channel acquisition presents a major challenge in deploying intelligent reflecting surfaces (IRS) aided communication systems, due to massive reflective elements that create a complex multi-path channel and increase channel dimensions. For an IRS-aided communication system, complete channel includes three parts: From the users to IRS, from the IRS to BS, and from the BS back to the IRS. Thus, a generalized multi-IRS cascaded communication system with three cascaded IRSs is considered. Unfortunately, existing channel estimation methods focus on single or double IRS cascades, which is not applicable to the case of triple cascaded IRS channel estimation directly. In this paper, we study the uplink channel estimation for triple cascaded IRSs aided single-user single-input single-output (SISO) systems. Specifically, the triple IRS cascaded channel is typically sparse. It permits us to characterize the channel estimation as a problem of sparse matrix recovery. Then, the sparse learning is explored to achieve robust channel estimation with limited training overhead. Particularly, the sparse channel matrices of the cascaded triple IRS channels have a common row-column block sparsity structure. However, a unique challenge lies in characterizing and enhancing such a common row-column sparsity. To tackle this issue, we apply a random matrix prior to promote the common row-column-wise sparsity of the channel matrix, and then an efficient Bayesian tensor inference algorithm is proposed to estimate the IRS channel. Finally, simulation results confirm that the proposed scheme outperforms traditional counterparts in terms of accuracy. © 1972-2012 IEEE.

关键词： Channel estimation

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：