检索结果-内蒙古大学图书馆

2024 OES China Ocean Acoustics, COA 2024

作者： Lu, Xiaotian Gong, Zhixiong School of Ocean and Civil Engineering Shanghai Jiao Tong University State Key Laboratory of Ocean Engineering Shanghai China School of Ocean and Civil Engineering Key Laboratory of Marine Intelligent Equipment and System Shanghai Jiao Tong University State Key Laboratory of Ocean Engineering Shanghai China

ISBN: (纸本)9798350340297

It is challenging to predict the patterns of radiated acoustic field from a complex moving source while this topic is important in the field of ocean acoustics. A possible method is to decompose the complex field into the addition of fundamental sources such as monopolar and dipolar ones. In this study, we derive the analytical solution of radiated acoustic fields generated by a moving monopolar or dipolar source, and the combination of them based on the Lorentz transformation. The analytical expressions of the radiated sound pressure by a moving monopolar or dipolar source are given with no limit on the moving direction and excitation frequency. Numerical simulations are conducted to reveal the Doppler effect of the moving sources and the potential application of the combination of monopolar and dipolar sources to simulate complex fields. This work may help design acoustic models to predict the radiated sound field by complex sources in the field of ocean engineering. © 2024 IEEE.

关键词： Ocean engineering

来源：评论

学校读者我要写书评

暂无评论

DHCT-DT: Dual-branch Hybrid CNN-Transformer Combined with Dual-Teacher Semi-Supervised Network for Kidney Ultrasound Image Segmentation

DHCT-DT: Dual-branch Hybrid CNN-Transformer Combined with Du...

引用

2024 IEEE International Conference on systems, Man, and Cybernetics, SMC 2024

作者： Luo, Yang Liu, Jun Ding, Mengqian School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China

ISBN: (纸本)9781665410205

Accurate segmentation of kidney ultrasound (KUS) images is of great significance for the diagnosis of kidney diseases. However, KUS images have challenges such as low contrast, large size variations, and acoustic shadow interference. In addition, obtaining labeled data is a major challenge in the field of medical image segmentation. This paper proposes a dual-branch hybrid CNN Transformer combined with a dual teacher semi-supervised segmentation network (DHCT-DT) based on the MT model. The reliability of guidance can be improved between two teachers by constructing consistency regularization constraints. The U-Net architecture is employed between the main teacher and student model. The auxiliary teacher model adopts a dual-branch hybrid CNN Transformer architecture. The multi-scale channel fusion attention mechanism (MSCF) is introduced to capture the feature correlation information of KUS images at different scales and channels. Two different training methods can combine their advantages to fully extract local and global information from images. To demonstrate the applicability of the proposed method, experiments were conducted on two datasets: a KUS dataset and a breast ultrasound (BUS) dataset. Both datasets demonstrated the most competitive segmentation performance. For example, in a semi-supervised experiment using only 10% labeled data in the BUS dataset, the Dice coefficient, Jaccard coefficient, HD, and ASSD reached 82.28%, 76,36%, 13.36mm, and 3.71mm. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Shear failure behaviors and degradation mechanical model of rockmass under true triaxial multi-level loading and unloading shear tests

引用

International Journal of Mining Science and technology 2024年第10期34卷 1385-1408页

作者： Zhi Zheng Ronghua Li Pengzhi Pan Jinghua Qid Guoshao Su Hong Zheng State Key Laboratory of Featured Metal Materials and Life-cycle Safety for Composite Structures Key Laboratory of Disaster Prevention and Structural Safety of Ministry of EducationCollege of Civil Engineering and ArchitectureGuangxi UniversityNanning 530004China State Key Laboratory of Geomechanics and Geotechnical Engineering Institute of Rock and Soil MechanicsChinese Academy of SciencesWuhan 430071China China Energy Engineering Group Guangxi Electric Power Design Institute Co.Ltd. Nanning 530007China State Key Laboratory of Intelligent Construction and Healthy Operation and Maintenance of Deep Underground Engineering China University of Mining and TechnologyXuzhou 221116China

The redistribution of three-dimensional(3D)geostress during underground tunnel excavation can easily induce to shear failure along rockmass structural plane,potentially resulting in engineering ***,the current understanding of rockmass shear behavior is mainly based on shear tests under2D stress without lateral stress,the shear fracture under 3D stress is unclear,and the relevant 3D shear fracture theory research is ***,this study conducted true triaxial cyclic loading and unloading shear tests on intact and bedded limestone under different normal stress σ_(n) and lateral stressσ_(p)to investigate the shear strength,deformation,and failure *** results indicate that under differentσ_(n)and σ_(p),the stress–strain hysteresis loop area gradually increases from nearly zero in the pre-peak stage,becomes most significant in the post-peak stage,and then becomes very small in the residual stage as the number of shear test cycles *** shear peak strength and failure surface roughness almost linearly increase with the increase inσ_(n),while they first increase and then gradually decrease asσ_(p)increases,with the maximum increases of 12.9%for strength and 15.1%for *** shear residual strength almost linearly increases withσ_(n),but shows no significant change withσ_(p).Based on the acoustic emission characteristic parameters during the test process,the shear fracture process and microscopic failure mechanism were *** the shear stressτincreases,the acoustic emission activity,main frequency,and amplitude gradually increase,showing a significant rise during the cycle near the peak strength,while remaining almost unchanged in the residual *** true triaxial shear fracture process presents tensile-shear mixture failure characteristics dominated by microscopic tensile *** on the test results,a 3D shear strength criterion considering the lateral stress effect was proposed,and the determination met

关键词： True triaxial shear test Lateral stress effect Acoustic emission monitoring Shear parameters evolution Shear degradation mechanical model

来源：评论

学校读者我要写书评

暂无评论

VAGeo: View-specific Attention for Cross-View Object Geo-Localization

VAGeo: View-specific Attention for Cross-View Object Geo-Loc...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Li, Zhongyang Yuan, Xin Liu, Wei Xu, Xin School of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China

ISBN: (纸本)9798350368741

Cross-view object geo-localization (CVOGL) aims to locate an object of interest in a captured ground- or drone-view image within the satellite image. However, existing works treat ground-view and drone-view query images equivalently, overlooking their inherent viewpoint discrepancies and the spatial correlation between the query image and the satellite-view reference image. To this end, this paper proposes a novel View-specific Attention Geo-localization method (VAGeo) for accurate CVOGL. Specifically, VAGeo contains two key modules: view-specific positional encoding (VSPE) module and channel-spatial hybrid attention (CSHA) module. In object-level, according to the characteristics of different viewpoints of ground and drone query images, viewpoint-specific positional codings are designed to more accurately identify the click-point object of the query image in the VSPE module. In feature-level, a hybrid attention in the CSHA module is introduced by combining channel attention and spatial attention mechanisms simultaneously for learning discriminative features. Extensive experimental results demonstrate that the proposed VAGeo gains a significant performance improvement, i.e., improving acc@0.25/acc@0.5 on the CVOGL dataset from 45.43%/42.24% to 48.21%/45.22% for ground-view, and from 61.97%/57.66% to 66.19%/61.87% for drone-view. © 2025 IEEE.

关键词： Cross-view Object-level Localization Hybrid Attention Mechanism View-specific Positional Encoding

来源：评论

学校读者我要写书评

暂无评论

The Dual Path Multi-Feature Fusion Model combining CNN and Transformer for Age Estimation of Caenorhabditis elegans

The Dual Path Multi-Feature Fusion Model combining CNN and T...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Ding, Mengqian Liu, Jun Luo, Yang Wuhan University of Science and Technology School of Computer Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China

ISBN: (纸本)9798350386226

The relatively simple genome, short life cycle, and easy observation of Caenorhabditis elegans (C. elegans) make it an excellent model organism for aging research. Age-stage prediction of C. elegans can help to assess the effectiveness of anti-aging interventions, better explore the role of individual differences in the aging process, and thus promote the development of medicine. However, there are still some problems in accurately predicting the age stages of C. elegans. On the one hand, there may be individual differences among C. elegans due to natural variation and environmental factors. On the other hand, nematode data sets are scarce and image information is complex. In this paper, we perform the age prediction task by studying the body contour morphology, biomarkers, and internal organ changes of C. elegans. Specifically, to address the effects of individual differences and datasets, this paper combines the body contour features, protein aggregation features, and pharyngeal terminal bulb features of C. elegans. In addition, considering the complex information of C. elegans images, this paper proposes a hybrid CNN and Transformer feature extraction method (DFCT), which can fully extract the global and local features of the image. A Dual Path Adaptive Feature Fusion Module (DAFM) is used to fuse the features. A series of experiments are conducted to verify the effectiveness of the proposed method. The experimental results show that the method proposed in this paper outperforms other methods in terms of accuracy and precision, especially in dividing 25 age stages into 3 categories, with an accuracy of 85.93%. © 2024 IEEE.

关键词： age estimation biological image analysis Caenorhabditis elegans CNN and Transformer image classification

来源：评论

学校读者我要写书评

暂无评论

Analysis of pressure response at an observation well against pressure build-up by early stage of CO_(2)geological storage project

引用

Journal of Rock Mechanics and Geotechnical Engineering 2024年第2期16卷 470-482页

作者： Qiang Sun Kyuro Sasaki Qinxi Dong Zhenni Ye Hui Wang Huan Sun School of Civil Engineering and Architecture Hainan UniversityHaikou570228China Faculty of Engineering Kyushu University744 MotookaNishi-kuFukuoka819-0385Japan Key Laboratory of Equipment Safety and Intelligent Technology for Guangzhou Rail Transit System Guangzhou510430China

To ensure a safe and stable CO_(2)storage,pressure responses at an observation well are expected to be an important and useful field monitoring item to estimate the CO_(2)storage behaviors and the aquifer parameters during and after injecting CO_(2),because it can detect whether the injected CO_(2)leaks to the ground surface or the bottom of the *** this study,pressure responses were simulated to present design factors such as well location and pressure transmitter of the observation *** simulations on the pressure response and the time-delay from pressure build-up after CO_(2)injection were conducted by considering aquifer parameters and distance from the CO_(2)injection well to an observation *** measurement resolution of a pressure transmitter installed in the observation well was presented based on numerical simulation results of the pressure response against pressure build-up at the injection well and CO_(2)plume front ***,the pressure response at an observation well was estimated by comparing the numerical simulation results with the curve of CO_(2)saturation and relative *** was also suggested that the analytical solution can be used for the analysis of the pressure response tendency using pressure build-up and dimensionless parameters of hydraulic ***,a criterion was established for selecting a pressure transducer installed at an observation well to monitor the pressure responses with sufficient accuracy and resolution,considering the distance from the injection well and the pressure build-up at the injection well,for future carbon capture and storage(CCS)projects.

关键词： CO_(2)storage Saline aquifer Observation well Pressure response CO_(2)saturation

来源：评论

学校读者我要写书评

暂无评论

Data quantity governance for machine learning in materials science

引用

National Science Review 2023年第7期10卷 234-250页

作者： Yue Liu Zhengwei Yang Xinxin Zou Shuchang Ma Dahui Liu Maxim Avdeev Siqi Shi School of Computer Engineering and Science Shanghai University Shanghai Engineering Research Center of Intelligent Computing System Australian Nuclear Science and Technology Organisation School of Chemistry The University of Sydney State Key Laboratory of Advanced Special Steel School of Materials Science and Engineering Shanghai University Materials Genome Institute Shanghai University

Data-driven machine learning(ML) is widely employed in the analysis of materials structure-activity relationships,performance optimization and materials design due to its superior ability to reveal latent data patterns and make accurate ***,because of the laborious process of materials data acquisition,ML models encounter the issue of the mismatch between a high dimension of feature space and a small sample size(for traditional ML models) or the mismatch between model parameters and sample size(for deep-learning models),usually resulting in terrible ***,we review the efforts for tackling this issue via feature reduction,sample augmentation and specific ML approaches,and show that the balance between the number of samples and features or model parameters should attract great attention during data quantity *** this,we propose a synergistic data quantity governance flow with the incorporation of materials domain *** summarizing the approaches to incorporating materials domain knowledge into the process of ML,we provide examples of incorporating domain knowledge into governance schemes to demonstrate the advantages of the approach and *** work paves the way for obtaining the required high-quality data to accelerate materials design and discovery based on ML.

关键词： machine learning data governance data quantity materials science

来源：评论

学校读者我要写书评

暂无评论

Non-Line-of-Sight Multipath Classification Method for BDS Using Convolutional Sparse Autoencoder with LSTM

引用

Tsinghua Science and technology 2025年第1期30卷 68-86页

作者： Yahang Qin Zhenni Li Shengli Xie Bo Li Ming Liu Victor Kuzin School of Automation Guangdong University of Technologyand also with Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete ManufacturingGuangzhou 510006China School of Automation Guangdong University of TechnologyGuangdong Key Laboratory of IoT Information TechnologyGuangzhou 510006China 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Key Laboratory of Intelligent Information Processing and System Integration of IoTMinistry of EducationGuangzhou 510006China Department of Electronic and Computer Engineering Hong Kong University of Science and TechnologHong Kong 999077China Academician of Russian Engineering Academy Moscow Moscow 125009Russia

Multipath signal recognition is crucial to the ability to provide high-precision absolute-position services by the BeiDou Navigation Satellite system(BDS).However,most existing approaches to this issue involve supervised machine learning(ML)methods,and it is difficult to move to unsupervised multipath signal recognition because of the limitations in signal *** by an autoencoder with powerful unsupervised feature extraction,we propose a new deep learning(DL)model for BDS signal recognition that places a long short-term memory(LSTM)module in series with a convolutional sparse autoencoder to create a new autoencoder ***,we propose to capture the temporal correlations in long-duration BeiDou satellite time-series signals by using the LSTM module to mine the temporal change patterns in the time ***,we develop a convolutional sparse autoencoder method that learns a compressed representation of the input data,which then enables downscaled and unsupervised feature extraction from long-duration BeiDou satellite series ***,we add an l_(1/2) regularizer to the objective function of our DL model to remove redundant neurons from the neural network while ensuring recognition *** tested our proposed approach on a real urban canyon dataset,and the results demonstrated that our algorithm could achieve better classification performance than two ML-based methods(e.g.,11%better than a support vector machine)and two existing DL-based methods(e.g.,7.26%better than convolutional neural networks).

关键词： convolutional sparse autoencoder BeiDou Navigation Satellite system(BDS) long short-term memory(LSTM) multipath classification

来源：评论

学校读者我要写书评

暂无评论

A Lightweight and key Escrow-Free Access Control Scheme on Encrypted Data in Edge Computing 12

A Lightweight and Key Escrow-Free Access Control Scheme on E...

引用

12th International Conference on Advanced Cloud and Big Data, CBD 2024

作者： He, Heng Chen, Yuejia Lu, Jianfeng Zheng, Jiacheng School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China

ISBN: (纸本)9798331511074

Attribute-based encryption provides fine-grained access control, ensuring data security in edge computing. However, existing access control schemes face issues such as high computational complexity due to bilinear pairing and key escrow with a single authority, which limit their effectiveness for lightweight terminal devices. To address these challenges, we propose a lightweight and key escrow-free access control scheme on encrypted data. This scheme replaces bilinear pairing with fast elliptic curve scalar multiplication, transferring most computational tasks to edge servers while preserving privacy, thus alleviating the computational burden on terminal devices. Additionally, we design a blockchain-based distributed key management method that allows multiple edge servers to distribute private keys collaboratively, resolving the key-escrow issue. Security analysis and performance evaluation demonstrate that our scheme effectively ensures data confidentiality, resists collusion attacks, and achieves high computational efficiency on the user side with low storage overheads, making it highly suitable for lightweight devices in edge computing. © 2024 IEEE.

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Deep Reinforcement Learning for Photovoltaics and Battery Storage Aggregators Coordinated Operation in Active Distribution Network with Incomplete Information 49

Multi-Agent Deep Reinforcement Learning for Photovoltaics an...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Xia, Qinqin Wang, Yu Hu, Bo Shao, Changzheng Xie, Kaigui Li, Chunyan State Key Laboratory of Power Transmission Equipment and System Security and New Technology Chongqing China

ISBN: (纸本)9798350331820

To address the cost-effective voltage regulation in active distribution network (ADN), this paper proposes a multiagent deep reinforcement learning (MADRL) based photovoltaic (PV) and battery storage (BS) aggregators coordinated operation framework. The proposed framework treats PV and BS under each bus as an aggregator and enables model-free separated operation between multiple PV-BS aggregators and ADN by training the control agent of each PV-BS aggregator using MADRL. The coordinated operation only requires incomplete information from the internal information of each PV-BS aggregator and overall ADN information, thereby reducing communication overhead. A test system evaluates the performance of three model-free MADRL algorithms on the proposed PV-BS aggregators coordinated operation in ADN. It also validates the effectiveness of the MADRL for cost-effective voltage regulation in ADN with multiple PV-BS aggregators. © 2023 IEEE.

关键词： Reinforcement 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：