检索结果-内蒙古大学图书馆

15th International Conference on Digital Image Processing, ICDIP 2023

作者： Zhou, Xiaoteng Yu, Changli Yuan, Shihao Yuan, Xin Yu, Hangchi Luo, Citong School of Ocean Engineering Harbin Institute of Technology China School of Computer Science and Technology Harbin Institute of Technology China

ISBN: (纸本)9798400708237

Underwater automatic target recognition (UATR) has been a challenging research topic in ocean engineering. Although deep learning brings opportunities for target recognition on land and in the air, underwater target recognition techniques based on deep learning have lagged due to sensor performance and the size of trainable data. This letter proposed a framework for learning the visual representation of underwater acoustic imageries, which takes a transformer-based style transfer model as the main body. It could replace the low-level texture features of optical images with the visual features of underwater acoustic imageries while preserving their raw high-level semantic content. The proposed framework could fully use the rich optical image dataset to generate a pseudo-acoustic image dataset and use it as the initial sample to train the underwater acoustic target recognition model. The experiments select the dual-frequency identification sonar (DIDSON) and adaptive resolution imaging sonar (ARIS) as the underwater acoustic data source and also take fish, the most common marine creature, as the research subject. Experimental results show that the proposed method could generate high-quality and high-fidelity pseudo-acoustic samples, achieve the purpose of acoustic data augmentation and provide support for the underwater acoustic-optical images domain transfer research. © 2023 ACM.

关键词： Underwater acoustics

来源：评论

学校读者我要写书评

暂无评论

Characterization and degradation of β-Sn particles in thermal aged Pb-rich solder joint for low-temperature co-fired ceramic(LTCC)applications

引用

Rare Metals 2024年第10期43卷 5346-5361页

作者： Jin-Hong Liu Zhe Zhu Qiang-Qiang Nie Jun-Fu Liu Peng He Shu-Ye Zhang State Key Laboratory of Advanced Welding and Joining Harbin Institute of TechnologyHarbin 150001China Anhui Key Laboratory of Microsystem East China Research Institute of MicroelectronicsHefei 230088China School of Materials Science and Engineering Hefei University of TechnologyHefei 230009China

High-lead solder joints are still playing an indispensable role in military and space ***,in-depth characterization of high-lead solder joints and the underlying degradation mechanisms remain *** research first performed aging tests on Sn10Pb90 solder joints,the shear strength at room and elevated temperatures gradually reduced,and the resistance ***,a two-layered Ni-Sn intermetallic compound(IMC)structure was identified using transmission electron microscopy(TEM),which could be attributed to the change of Sn content in the ***,the internal annealing twin of a Sn particle was discovered,which could be attributed to creeping induced by thermal expansion coefficient(CTE)difference between Sn and *** analysis of partial and whole annealing twins was conducted through high-resolution TEM(HRTEM).Finally,four degradation mechanisms were *** of the IMC layer would result in increased brittleness and *** particle coarsening,apart from diminishing the ductility and toughness of the solder joint,it would also accelerate the creeping rate by weakening the phase boundary *** voids and cracks induced by phase boundary sliding,wedgeshaped cracking and pore-shaped cracking were discovered and their formation was *** importantly,the consumption of Sn resulted in a depletion of wettable layer,leading to the formation of Pb streams and isolated IMC islands,also known as the spalling and delamination of *** diffusion followed a spiral path,which was mutually influenced by orientation misfit and concentration gradient.A technique to prevent cracking was *** research is expected to provide significant technical references for high-lead solder joints.

关键词： High-lead solder joints Aging TEM characterization Degradation mechanisms Properties

来源：评论

学校读者我要写书评

暂无评论

Flu-Net: two-stream deep heterogeneous network to detect flu like symptoms from videos using grey wolf optimization algorithm

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第6期14卷 7733-7745页

作者： Gupta, Himanshu Imran, Javed Sharma, Chandani Department of Computer Science and Engineering Quantum University Roorkee India Computer Science and Engineering Department Thapar Institute of Engineering and Technology Patiala India

The outbreak of COVID-19 (also known as Coronavirus) has put the entire world at risk. The disease first appears in Wuhan, China, and later spread to other countries, taking a form of a pandemic. In this paper, we try to build an artificial intelligence (AI) powered framework called Flu-Net to identify flu-like symptoms (which is also an important symptom of Covid-19) in people, and limit the spread of infection. Our approach is based on the application of human action recognition in surveillance systems, where videos captured by closed-circuit television (CCTV) cameras are processed through state-of-the-art deep learning techniques to recognize different activities like coughing, sneezing, etc. The proposed framework has three major steps. First, to suppress irrelevant background details in an input video, a frame difference operation is performed to extract foreground motion information. Second, a two-stream heterogeneous network based on 2D and 3D Convolutional Neural Networks (ConvNets) is trained using the RGB frame differences. And third, the features extracted from both the streams are combined using Grey Wolf Optimization (GWO) based feature selection technique. The experiments conducted on BII Sneeze-Cough (BIISC) video dataset show that our framework can 70% accuracy, outperforming the baseline results by more than 8%. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Development of the high-strength ductile ferritic alloys via regulating the intragranular and grain boundary precipitation of G-phase

引用

Journal of Materials science & technology 2023年第5期136卷 180-199页

作者： Mujin Yang Chao Huang Jiajia Han Haichen Wu Yilu Zhao Tao Yang Shenbao Jin Chenglei Wang Zhou Li Ruiying Shu Cuiping Wang Huanming Lu Gang Sha Xingjun Liu School of Materials Science and Engineering Harbin Institute of TechnologyShenzhen 518055China Department of Mechanical and Energy Engineering Southern University of Science and TechnologyShenzhen 518055China College of Materials and Fujian Provincial Key Laboratory of Materials Genome Xiamen UniversityXiamen 361005China Test Center Ningbo Institute of Materials Technology and EngineeringChinese Academy of SciencesNingbo 315201China Department of Materials Science and Engineering City University of Hong KongHong KongChina Department of Materials Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China State Key Laboratory of Advanced Welding and Joining Harbin Institute of TechnologyShenzhen 150001China Institute of Materials Genome and Big Data Harbin Institute of TechnologyShenzhen 518055China

A typical G-phase strengthened ferritic model alloy(1Ti:Fe-20Cr-3Ni-1Ti-3Si,wt.%)has been carefully studied using both advanced experimental(EBSD,TEM and APT)and theoretical(DFT)*** the classic“solid solution and aging”process,the superfine(Fe,Ni)_(2)TiSi-L2_(1)particles densely precipitate within the ferritic grain and subsequently transform into the(Ni,Fe)_(16)Ti_(6)Si_(7)-G *** the meanwhile,the elemental segregation at grain boundaries and the resulting precipitation of a large amount of the(Ni,Fe)_(16)Ti_(6)Si_(7)-G phase are also *** nanoscale microstructural evolutions result in a remarkable increase in hardness(100-300 HV)and severe *** the“cold rolling and aging”process is used,the brittle fracture is effectively suppressed without loss of nano-precipitation strengthening *** yield strength of 1700 MPa with 4%elongation at break is *** key improvement in mechanical properties is mainly attributed to the pre-cold rolling process which effectively avoids the dense precipitation of the G-phase at the grain *** findings could shed light on the further exploration of the precipitation site via optimal processing strategies.

关键词： G-phase Precipitation strengthening Grain boundary segregation Nano-precipitates

来源：评论

学校读者我要写书评

暂无评论

SAR Images Change Detection Based on Attention Mechanism-Convolutional Wavelet Neural Network

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12133-12149页

作者： Jiahui, J.E. Wang, Lu Zhao, Chunhui Mathiopoulos, P. Takis Ohtsuki, Tomoaki Adachi, Fumiyuki Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Ministry of Industry and Information Technology Key Laboratory of Advanced Marine Communication and Information Technology Harbin150001 China National and Kapodistrian University of Athens Department of Informatics and Telecommunications 15772 Greece Keio University Department of Information and Computer Science Kanagawa 2238522 Japan Tohoku University International Research Institute of Disaster Science Sendai9808576 Japan

As synthetic aperture radar (SAR) image change detection can continuously acquire target information under all weather conditions, it has been used in the past for various applications. However, it is very challenging to use SAR images for small area change detection due to the presence of noise and the imbalance between classes. To deal with these problems this article proposes a SAR images change detection scheme which is based upon an Attention Mechanism and Convolutional Wavelet Neural Network. First, employing Multiscale Superpixel Reconstructed Difference Image effectively enhances the edge information of the images. Second, a two-stage Weighted Center Constrained Fuzzy C-Means clustering algorithm is proposed. To constrain incorrect migration in the subsequent clustering phase, the algorithm uses a two-stage clustering algorithm. During the first stage weights in the clustering process to improve the accuracy of the resulting clustering centers are introduced while during the second stage, these refined cluster centers can be constrained. Third, a Convolutional Squeeze-and-Excitation Attention Mechanism Wavelet Neural Network (CSWNN) is proposed which more accurately distinguishes uncertain pixels and thus reduces redundant features. The final Denoising Diffusion Probabilistic Model is introduced into the CSWNN to expand pseudolabeled samples. Comparing this algorithm with seven sets of contrast experiments on six real SAR datasets shows that the accuracy of detecting changes in small regions is 2% –9% better than the classical algorithm. © 2008-2012 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Text region detection algorithm for medical instruments screen based on improved DBNet 2

Text region detection algorithm for medical instruments scre...

引用

2nd International Conference on Pattern Recognition, Machine Vision and Intelligent Algorithms, PRMVIA 2024

作者： Liu, Jiaming Chen, Wei Heilongjiang University of Science and Technology School of Computer and Information Engineering Nantong China Heilongjiang University of Science and Technology School of Computer and Information Engineering Harbin China

ISBN: (纸本)9798350389746

Recognition of text in images has become increasingly important with the rapid development of cameras, and the main technology involved is Optical Character Recognition (OCR). In order to enhance the recognition accuracy of traditional text region detection algorithms for medical instrument screen data, which contains irregular and small objects, this paper introduces an improved scheme incorporating Adaptive Spatial Feature Fusion (ASFF) and Gaussian Error Linear Unit (GELU) activation function, and proposes the DBNeti model. The introduction of ASFF aims to address the limitations of fixed feature fusion in traditional text recognition algorithms and to enhance the performance of target detectors at different scales. The GELU is introduced as the activation function of the DBNet algorithm, utilizing its nonlinear characteristics, gradient preservation, and computational efficiency to enhance the expressiveness and generalization ability of the model. Experiments demonstrate that the improved model, DBNeti, has achieved optimal performance across all evaluation indices, including an Accuracy of 0.8189, a Recall of 0.3633, a Precision of 0.6858, and an F-measure of 0.4750. Compared to DBNet, DBNeti improves the Accuracy, Recall, Precision, and F-measure indices by 3.3%, 6.1%, 3.1%, and 4.2%, respectively. This study demonstrates the superiority of the DBNeti algorithm in the text recognition task. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Data-Model Interactive Remaining Useful Life Prediction Approach of Lithium-Ion Batteries Based on PF-BiGRU-TSAM

引用

IEEE Transactions on Industrial Informatics 2024年第2期20卷 1144-1154页

作者： Zhang, Jiusi Huang, Congsheng Chow, Mo-Yuen Li, Xiang Tian, Jilun Luo, Hao Yin, Shen Harbin Institute of Technology Department of Control Science and Engineering Harbin150001 China National Taipei University of Technology Department of Electrical Engineering Taipei10608 Taiwan Shanghai Jiao Tong University University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai200240 China Norwegian University of Science and Technology Department of Mechanical and Industrial Engineering Faculty of Engineering Trondheim7034 Norway

Accurate remaining useful life (RUL) prediction of lithium-ion batteries is critical for energy supply systems. In conventional data-driven RUL prediction approaches, the battery's degradation mechanism is difficult into incorporate in the RUL prediction. Furthermore, there are notable limitations in reflecting the significance of different time instances, and the uncertainty in the degradation process. Consequently, a novel data-model interactive RUL prediction approach based on particle filter-temporal attention mechanism-bidirectional gated recurrent unit (PF-BiGRU-TSAM) is proposed. Specifically, BiGRU-TSAM is trained offline through historical data, which assigns corresponding significance to battery capacities at different time instances. Moreover, regarding the interactive data-model for the online prediction phase based on PF-BiGRU-TSAM, the advantages of data-driven and model-based approaches are integrated, which accomplishes the purpose of modifying each other. The proposed PF-BiGRU-TSAM approach is validated with a real-world battery dataset. Experimental results demonstrate the proposed approach is better than some published approaches. Taking the 50th operational cycle of the four batteries B0005, B0006, B0007, and B0018 in the dataset as an instance, the absolute errors of the proposed PF-BiGRU-TSAM are 0, 1, 3, 3, respectively, which represents the proposed approach has an excellent performance. © 2005-2012 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A tree-growing graphic model for asymmetrical phantom networks in polymeric gels undergoing dynamic mechanochemical coupling

引用

science China(Technological sciences) 2024年第2期67卷 558-567页

作者： SHI WeiLin ZHOU Jian LU HaiBao ELMARAKBI Ahmed FU Yong-Qing National Key Laboratory of Science and Technology on Advanced Composites in Special Environments Harbin Institute of TechnologyHarbin 150080China College of Mechanical and Vehicle Engineering Hunan UniversityChangsha 410082China Faculty of Engineering and Environment University of NorthumbriaNewcastle upon Tyne NEI 8STUK

Network structures of various polymers have significant effects on their mechanical properties;therefore,numerous studies have investigated the constitutive relationship between symmetrical network structures and their rubber elasticity in ***,few studies have focused on asymmetrical network structures in polymers that undergo bond exchange reactions,selfassembly,or mechanochemical coupling—all of which are induced by transition probabilities of chemical bonding *** this study,an extended constraint junction and phantom network model is formulated using the tree-growing theory to establish a constitutive relationship between asymmetrical network structures and their rubber elasticity in polymers.A free-energy equation is further developed to explore working principles of configurational transitions on the dynamic rubber elasticity of symmetrical and asymmetrical network *** constitutive relationship between dynamic rubber elasticity and symmetrical and asymmetrical network structures has also been proposed for the gels undergoing mechanochemical and hydromechanical ***,the effectiveness of this newly proposed tree-growing model has been verified by comparing with the classical affine network model,finite element analysis,and the experimental results of gels reported in literature.

关键词： gel polymer network rubber elasticity asymmetric

来源：评论

学校读者我要写书评

暂无评论

Autogenous healing mechanism of cement-based materials

引用

Frontiers of Structural and Civil engineering 2023年第6期17卷 948-963页

作者： Desheng LI Hao ZHENG Kang GU Lei LANG Shang SHI Bing CHEN Department of Civil Engineering School of ScienceNanjing University of Science and TechnologyNanjing210094China School of Transportation Science and Engineering Harbin Institute of TechnologyHarbin150090China State Key Laboratory of Ocean Engineering Shanghai Jiao Tong UniversityShanghai200240China State Key Laboratory of Geomechanics and Geotechnical Engineering Institute of Rock and Soil MechanicsWuhan430071China

Autogenous self-healing is the innate and fundamental repair capability of cement-based materials for healing *** researchers have investigated factors that influence autogenous ***,systematic research on the autogenous healing mechanism of cement-based materials is *** healing process mainly involves a chemical process,including further hydration of unhydrated cement and carbonation of calcium oxide and calcium ***,the autogenous healing process is influenced by the material constituents of the cement composite and the ambient *** this study,different factors influencing the healing process of cement-based materials were *** electron microscopy and optical microscopy were used to examine the autogenous healing mechanism,and the maximum healing capacity was ***,detailed theoretical analysis and quantitative detection of autogenous healing were *** study provides a valuable reference for developing an improved healing technique for cement-based composites.

关键词： autogenous healing cement-based materials healing mechanism aggregation effect

来源：评论

学校读者我要写书评

暂无评论

C─H···πinteraction induced H-aggregates for wide range water content detection in organic solvents

Aggregate

引用

Aggregate 2024年第4期5卷 269-278页

作者： Jiajun Xu Meifen Huang Haijun Pang Zhehui Weng Guangzhi Hu Siman Zhang Qiuling Yang Qiong Wu Department of Chemical Science and Technology Kunming UniversityKunmingChina College of Physics Science and Technology Kunming UniversityKunmingChina The School of Material Science and Chemical Engineering Harbin University of Science and TechnologyHarbinChina Institute for Ecological Research and Pollution Control of Plateau Lakes Yunnan UniversityKunmingChina

J-aggregation and H-aggregation are identified as two classical models of function-ally oriented non-covalent interactions,and significant attention has been drawn by ***,due to the scarcity of single-crystal examples of H-aggregation,a comprehensive understanding of the relationship between its stacking mode and optical behaviour has been *** recent studies,two polyaromatic Schiff base compounds,Cl-Salmphen and H-Salmphen,were successfully synthe-sized,and both were found to exhibit *** thefindings,H-Salmphen was shown to display typical C─H···πinteractions,characteristic of Aggregation-Induced Emission(AIE)active molecules,whereas its halogenated counterpart was identified as behaving similar to Aggregation-Caused Quenching(ACQ)active *** types of results suggest that identical intermolecular interactions can produce differing optical *** was shed,at least in part,on the for-mation mechanisms of H-type aggregates and their luminescence properties from these ***,the high optical signal-to-noise ratio inherent to H-aggregates was utilized for the exploration of water content *** an outcome,a high-performancefluorescentfilter paper was developed,enabling easy real-time detection using a smartphone.

关键词： aggregation-caused quenching aggregation-induced emission enhanced C─H···πinteractions fluores-cence sensor H-aggregation

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：