检索结果-内蒙古大学图书馆

Image reconstruction from photoacoustic projections

Photonics Insights 2024年第3期3卷 145-209页

作者： Chao Tian Kang Shen Wende Dong Fei Gao Kun Wang Jiao Li Songde Liu Ting Feng Chengbo Liu Changhui Li Meng Yang Sheng Wang Jie Tian Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefeiChina School of Engineering Science University of Science and Technology of ChinaHefeiChina Department of Anesthesiology the First Affiliated Hospital of USTCDivision of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefeiChina Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing HefeiChina College of Automation Engineering Nanjing University of Aeronautics and AstronauticsNanjingChina School of Information Science and Technology ShanghaiTech UniversityShanghaiChina Shanghai Clinical Research and Trial Center ShanghaiChina CAS Key Laboratory of Molecular Imaging Institute of AutomationChinese Academy of SciencesBeijingChina School of Precision Instruments and Optoelectronics Engineering Tianjin UniversityTianjinChina Academy for Engineering and Technology Fudan UniversityShanghaiChina Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhenChina Department of Biomedical Engineering College of Future TechnologyPeking UniversityBeijingChina National Biomedical Imaging Center Peking UniversityBeijingChina Departments of Ultrasound State Key Laboratory of Complex Severe and Rare DiseasesPeking Union Medical College HospitalChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijingChina School of Engineering Medicine Beihang UniversityBeijingChina Key Laboratory of Big Data-Based Precision Medicine Beihang UniversityMinistry of Industry and Information TechnologyBeijingChina

Photoacoustic computed tomography(PACT)is a rapidly developing biomedical imaging modality and has attracted substantial attention in recent *** reconstruction from photoacoustic projections plays a critical role in image formation in *** we review six major classes of image reconstruction approaches developed in the past three decades,including delay and sum,filtered back projection,series expansion,time reversal,iterative reconstruction,and deep-learning-based *** principal ideas and implementations of the algorithms are summarized,and their reconstruction performances under different imaging scenarios are *** challenges,future directions,and perspectives for the development of image reconstruction algorithms in PACT are also *** review provides a self-contained reference guide for beginners and specialists in the photoacoustic community,to facilitate the development and application of novel photoacoustic image reconstruction algorithms.

关键词： optical imaging photoacoustic tomography image reconstruction deep learning

来源：评论

学校读者我要写书评

暂无评论

Dynamical friction and the evolution of black holes in cosmological simulations: A new implementation in OpenGadget3

arXiv

引用

arXiv 2024年

作者： Damiano, Alice Valentini, Milena Borgani, Stefano Tornatore, Luca Murante, Giuseppe Ragagnin, Antonio Ragone-Figueroa, Cinthia Dolag, Klaus Dipartimento di Fisica dell’Università di Trieste Sez. di Astronomia via Tiepolo 11 TriesteI-34131 Italy INAF – Osservatorio Astronomico di Trieste via Tiepolo 11 TriesteI-34131 Italy IFPU Institute for Fundamental Physics of the Universe Via Beirut 2 Trieste34014 Italy INFN Instituto Nazionale di Fisica Nucleare Via Valerio 2 TriesteI-34127 Italy ICSC - Italian Research Center on High Performance Computing Big Data and Quantum Computing via Magnanelli 2 Casalecchio di Reno40033 Italy INAF-Osservatorio di Astrofisica e Scienza dello Spazio di Bologna Via Piero Gobetti 93/3 BolognaI-40129 Italy Dipartimento di Fisica e Astronomia "Augusto Righi" Alma Mater Studiorum Università di Bologna via Gobetti 93/2 BolognaI-40129 Italy Universidad Nacional de Córdoba Laprida 854 CórdobaX5000BGR Argentina Universitäts-Sternwarte München Scheinerstr. 1 MünchenD-81679 Germany Max-Plank-Institut für Astrophysik Karl-Schwarzschild Strasse 1 GarchingD-85740 Germany

Aims. We introduce a novel sub-resolution prescription to correct for the unresolved dynamical friction (DF) onto black holes (BHs) in cosmological simulations, to describe BH dynamics accurately, and to overcome spurious motions induced by numerical effects. Methods. We implemented a sub-resolution prescription for the unresolved DF onto BHs in the OpenGadget3 code. We carried out cosmological simulations of a volume of (16 comoving Mpc)3 and zoomed-in simulations of a galaxy group and of a galaxy cluster. We assessed the advantages of our new technique in comparison to commonly adopted methods for hampering spurious BH displacements, namely repositioning onto a local minimum of the gravitational potential and ad hoc boosting of the BH particle dynamical mass. We inspected variations in BH demography in terms of offset from the centres of the host sub-halos, the wandering population of BHs, BH–BH merger rates, and the occupation fraction of sub-halos. We also analysed the impact of the different prescriptions on individual BH interaction events in detail. Results. The newly introduced DF correction enhances the centring of BHs on host halos, the effects of which are at least comparable with those of alternative techniques. Also, the correction becomes gradually more effective as the redshift decreases. Simulations with this correction predict half as many merger events with respect to the repositioning prescription, with the advantage of being less prone to leaving substructures without any central BH. Simulations featuring our DF prescription produce a smaller (by up to ∼ 50% with respect to repositioning) population of wandering BHs and final BH masses that are in good agreement with observations. Regarding individual BH–BH interactions, our DF model captures the gradual inspiraling of orbits before the merger occurs. By contrast, the repositioning scheme, in its most classical renditions, describes extremely fast mergers, while the dynamical mass misrepresents t

关键词： Cosmology

来源：评论

学校读者我要写书评

暂无评论

Explicit cross-lingual pre-training for unsupervised machine translation

arXiv

引用

arXiv 2019年

作者： Ren, Shuo Wu, Yu Liu, Shujie Zhou, Ming Ma, Shuai SKLSDE Lab Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing China Microsoft Research Asia Beijing China

Pre-training has proven to be effective in unsupervised machine translation due to its ability to model deep context information in cross-lingual scenarios. However, the cross-lingual information obtained from shared BPE spaces is inexplicit and limited. In this paper, we propose a novel cross-lingual pre-training method for unsupervised machine translation by incorporating explicit cross-lingual training signals. Specifically, we first calculate cross-lingual n-gram embeddings and infer an n-gram translation table from them. With those n-gram translation pairs, we propose a new pre-training model called Cross-lingual Masked Language Model (CMLM), which randomly chooses source n-grams in the input text stream and predicts their translation candidates at each time step. Experiments show that our method can incorporate beneficial cross-lingual information into pre-trained models. Taking pre-trained CMLM models as the encoder and decoder, we significantly improve the performance of unsupervised machine translation. Our code is available at https://***/Imagist-Shuo/CMLM. Copyright © 2019, The Authors. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Adaptive Handover Decision Inspired By Biological Mechanism in Vehicle Ad-hoc Networks

引用

Computers, Materials & Continua 2019年第9期61卷 1117-1128页

作者： Xuting Duan Jingyi Wei Daxin Tian Jianshan Zhou Haiying Xia Xin Li Kunxian Zheng Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing100191China Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems&SafetyControl Beijing100191China School of Transportation Science and Engineering Beihang UniversityBeijing100191China Department of Engineering and Design University of SussexBrightonBN19RHUK Research Institute of Highway Ministry Transport Beijing100088China Department of Computer Science and Technology Tsinghua UniversityHaidian DistrictBeijing100088China

In vehicle ad-hoc networks(VANETs),the proliferation of wireless communication will give rise to the heterogeneous access environment where network selection becomes *** by the self-adaptive paradigm of cellular attractors,this paper regards an individual communication as a cell,so that we can apply the revised attractor selection model to induce each connected *** at improving the Quality of Service(QoS),we presented the bio-inspired handover decision-making *** addition,we employ the Technique for Order Preference by Similarity to an Ideal Solution(TOPSIS)for any vehicle to choose an access *** paper proposes a novel framework where the bio-inspired mechanism is combined with *** a dynamic and random mobility environment,our method achieves the coordination of performance of heterogeneous networks by guaranteeing the efficient utilization and fair distribution of network resources in a global *** experimental results confirm that the proposed method performs better when compared with conventional schemes.

关键词： Revised attraction selection model TOPSIS VANETs QoS

来源：评论

学校读者我要写书评

暂无评论

Syntax-enhanced Pre-trained model

arXiv

引用

arXiv 2020年

作者： Xu, Zenan Guo, Daya Tang, Duyu Su, Qinliang Shou, Linjun Gong, Ming Zhong, Wanjun Quan, Xiaojun Jiang, Daxin Duan, Nan School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Microsoft Research Asia Beijing China Microsoft Search Technology Center Asia Beijing China Guangdong Key Laboratory Big Data Analysis and Processing Guangzhou China Key Lab. of Machine Intelligence and Advanced Computing Ministry of Education China

We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. Such a problem would lead to the necessity of having human-annotated syntactic information, which limits the application of existing methods to broader scenarios. To address this, we present a model that utilizes the syntax of text in both pre-training and fine-tuning stages. Our model is based on Transformer with a syntax-aware attention layer that considers the dependency tree of the text. We further introduce a new pre-training task of predicting the syntactic distance among tokens in the dependency tree. We evaluate the model on three downstream tasks, including relation classification, entity typing, and question answering. Results show that our model achieves state-of-the-art performance on six public benchmark datasets. We have two major findings. First, we demonstrate that infusing automatically produced syntax of text improves pre-trained models. Second, global syntactic distances among tokens bring larger performance gains compared to local head relations between contiguous tokens. Copyright © 2020, The Authors. All rights reserved.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Outlier detection algorithm based on density and distance

引用

Journal of Physics: Conference Series 2021年第1期1941卷

作者： Ying Qu Fei Guo School of Economics and Management Hebei University of Science and Technology Shijiazhuang Hebei 050018 China Data Science and Intelligent Computing Research Center Hebei University of Science and Technology Shijiazhuang Hebei 050018 China

In order to solve the problem that the existing outlier detection algorithm is difficult to detect the one-dimensional integer data set with uneven frequency distribution and uniform distance distribution and low accuracy, the advantages of density outlier detection and distance outlier detection can be combined. An outlier detection algorithm DAD (Density and Distance) based on density and distance was proposed. In order to improve the possibility of outlier sample distance, the algorithm can define the weight distance; introduce the global density outlier factor combined with the weight distance as the relative distance, and use the cutting edge strategy to quickly cut the outliers based on the minimum spanning tree. Then, an artificial data set was used to test the algorithm. Experimental results showed that the algorithm had a good outlier detection accuracy in dealing with data sets with uneven frequency distribution and uniform distance distribution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of Command and Dispatch System for Automatic Reading of Meter Images in Substations by UAV Inspection Photos

Computing Open

引用

computing Open 2024年第2期computing-open卷

作者： Guanghong Deng Liangpei Lin Baihao Lin Wenlong Jing Xiaodan Zhao Yong Li Rui Yang Shidun Xie Pengfeng Wei GuangDong Engineering Technology Research Center of UAV Remote Sensing Network Guangzhou iMapCloud Intelligent Technology Co. Ltd. Guangzhou 510095 P. R. China Guangdong Province Engineering Laboratory for Geographic Spatiotemporal Big Data Key Laboratory of Guangdong for Utilization of Remote Sensing and Geographical Information System Guangdong Open Laboratory of Geospatial Information Technology and Application Guangzhou Institute of Geography Guangdong Academy of Sciences Guangzhou 510070 P. R. China Foshan iMapCloud Intelligent Technology Co. Ltd. Foshan 528251 P. R. China

The application of the combination of unmanned aerial vehicles (UAVs) and artificial intelligence is a hot topic in the intelligent inspection of substations, and meter reading is a very challenging task. This paper proposes a method based on the combination of YOLOv6n object detection and Deeplabv3 + image segmentation and performs post-processing on the segmented images to obtain meter readings. First, YOLOv6n is used to detect the meter area of the aerial image and classify the meters. Second, the detected meter images are fed into the image segmentation model. The backbone network of the Deeplabv3 + algorithm is improved by using the MobileNetv3 network, which not only effectively extracts pointers and scales, but also makes the model more lightweight. Third, License Plate Recognition Network (LPRNet) is used to recognize digital meter images. In order to solve the problem of inaccurate pointer meter readings, to begin with, the segmented image is corroded; in addition, the circular dial area is flattened into a rectangular area by concentric circle sampling method. Finally, the meter reading is calculated by the position of the pointer, the scale and the total range of the meter. The post-processing part uses numba to optimize the inference speed. The experimental results show that in two datasets, The mean average precision of 50 (mAP50) accuracy of the YOLOv6n model using this method reached 99.71% and 98.60%, respectively, and the inference speed of a single image was 17.1 ms and 13.2 ms, respectively. The mean intersection over union (mIoU) of the image segmentation model reached 82.00%, 74.73%, 73.50%, 82.26% and 73.20%, respectively, and the single segmentation speed reached 33.7 ms. The LPRNet model has a recognition accuracy of 99.17% and a single image inference speed of 14.7 ms. At the same time, several mainstream object detection and semantic segmentation algorithms are compared. The experimental results show that the method in this paper greatly im

关键词： Object detection image segmentation YOLOv6n Deeplabv3 + meter reading

来源：评论

学校读者我要写书评

暂无评论

LUneXt: Simple and Efficient U-shaped Network Design for Medical Image Segmentation with Nonlinear Activation

Computing Open

引用

computing Open 2024年第2期computing-open卷

作者： Guanghong Deng Bing Yu Wenlong Jing Yong Li Xiaodan Zhao GuangDong Engineering Technology Research Center of UAV Remote Sensing Network Guangzhou iMapCloud Intelligent Technology Co. Ltd. Guangzhou 510095 P. R. China Guangdong Province Engineering Laboratory for Geographic Spatiotemporal Big Data Key Laboratory of Guangdong for Utilization of Remote Sensing and Geographical Information System Guangdong Open Laboratory of Geospatial Information Technology and Application Guangzhou Institute of Geography Guangdong Academy of Sciences Guangzhou 510070 P. R. China Foshan iMapCloud Intelligent Technology Co. Ltd. Foshan 528251 P. R. China

Medical image segmentation has always been a challenging task. This paper proposes a new LUneXt medical image segmentation model based on the characteristics analysis of medical image data sets and testing of different nonlinear activation units. Both normalized activations for the original negative input image activation have good optimization capabilities for the tokenization module parameters proposed in the original UneXt model. Using different activation coefficients for different foreground and background areas has achieved better results. The experimental results of this paper on the Breast Ultrasound Images (BUSI) data set reached an intersection over union (IoU) value of 62.64%, a Dice value of 76.12%, and a single inference speed of 807.57 ms. The experimental IoU value of the International Skin Imaging Collaboration (ISIC 2018) data set reached 82.95%, and the Dice value reached 90.50%. The single inference speed reached 842.58 ms. The LUneXt model is more robust than other models. While improving model performance, it does not introduce higher computational complexity and does not have a major impact on the processing speed of a single image.

关键词： Image segmentation medical images neural networks activation function

来源：评论

学校读者我要写书评

暂无评论

引用

2nd International Conference on Smart Vehicular Technology, Transportation, Communication and Applications, VTCA 2018

作者： Cai, Qiqin Liao, Lyuchao Zou, Fumin Song, Subin Liu, Jierui Zhang, Meirun Fujian Key Lab for Automotive Electronics and Electric Drive Fujian University of Technology FuzhouFujian350118 China Fujian Provincial Big Data Research Institute of Intelligent Transportation Fujian University of Technology FuzhouFujian350118 China Fujian Transport Information and Telecommunication Center Fujian Communication Department FuzhouFujian350001 China

ISBN: (纸本)9783030045845

With the rapid accumulation of GPS trajectory data, the vast amount of spatiotemporal trajectory data hides extremely rich and valuable information with potential travel behavior patterns. The similarity of the driver’s travel trajectory is key to mining patterns, but how to reasonably and efficiently evaluate the similarity remains a challenge. To address this problem, we propose a driving trajectory similarity measurement using grid-based dynamic time warping (GDTW) to evaluate similarity of driving trajectory. Building trajectory grid vector model (TGVM), the method solves the problems of position shift and large computation for the similarity measuring of big trajectory data. Extensive experiments were conducted with a real trajectory dataset to evaluate feasibility and efficiency of the proposed approaches. The results show that GDTW performs a more robust and efficient processing of trajectory similarity than does traditional approaches, reducing by about 5 times of time-consuming. © Springer Nature Switzerland AG 2019.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Context aware 3d unet for brain tumor segmentation

arXiv

引用

arXiv 2020年

作者： Ahmad, Parvez Qamar, Saqib Shen, Linlin Saeed, Adnan National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China School of Hydropower and Information Technology Huazhong University of Science and Technology Wuhan430074 China

Deep convolutional neural network (CNN) achieves remarkable performance for medical image analysis. UNet is the primary source in the performance of 3D CNN architectures for medical imaging tasks, including brain tumor segmentation. The skip connection in the UNet architecture concatenates features from both encoder and decoder paths to extract multi-contexual information from image data. The multi-scaled features play an essential role in brain tumor segmentation. However, the limited use of features can degrade the performance of the UNet approach for segmentation. In this paper, we propose a modified UNet architecture for brain tumor segmentation. In the proposed architecture, we used densely connected blocks in both encoder and decoder paths to extract multi-contexual information from the concept of feature reusability. The proposed residual inception blocks (RIB) are used to extract local and global information by merging features of different kernel sizes. We validate the proposed architecture on the multimodal brain tumor segmentation challenges (BRATS) 2020 testing dataset. The dice (DSC) scores of the whole tumor (WT), tumor core (TC), and enhancement tumor (ET) are 89.12%, 84.74%, and 79.12%, respectively. Our proposed work is in the top ten methods based on the dice scores of the testing dataset. © 2020, CC-BY.

关键词： Tumors

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：