检索结果-内蒙古大学图书馆

Sharpening semantic gradient in a planarized sentence representation

学校读者我要写书评

暂无评论

Neural networks : the official journal of the International Neural Network Society 2025年 190卷 107687页

作者： Caiwei Yang Yanping Chen Shuai Yu Bo Dong Jiwei Qin Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Guizhou University Guiyang 550025 Guizhou PR China State Key Laboratory of Public Big Data Guizhou university Guiyang 550025 Guizhou PR China. Electronic address: gs.cwyang21@***. State Key Laboratory of Public Big Data Guizhou university Guiyang 550025 Guizhou PR China. Electronic address: ypench@***. State Key Laboratory of Public Big Data Guizhou university Guiyang 550025 Guizhou PR China. Electronic address: gs.syu21@***. Department of Computer Science and Technology Xi'an Jiaotong University Xi'an 710049 Shanxi PR China. Electronic address: dong.bo@***. College of Information Science and Engineering Xinjiang University Urumqi 830046 Xinjiang PR China. Electronic address: jwqin_xju@***.

Mapping a sentence into a two-dimensional representation has the advantage of unfolding nested semantic structures in a sentence and encoding the interaction between tokens. In the planarized sentence representation, neighboring elements denote overlapped linguistic units in a sentence. An important phenomenon is that the semantic information of a true linguistic unit may penetrate neighboring elements, which blurs the semantic edge of a linguistic unit and disturbs the planarized sentence representation. Therefore, sharpening the semantic gradient helps aggravate semantic information from neighborhoods and depressing noises in neighboring elements. This paper reveals the mechanism of sharpening semantic gradient in the planarized sentence representation. Our method is evaluated on six evaluation datasets. The results show impressive improvement on three information extraction tasks. The success indicates that representing and processing sentences in a two-dimensional representation has a great potential to decode the sentential semantic structure and support sentence-level information extraction. Our code to implement the model is available at: https://***/caiwyang/Semantic_Gradient.

关键词： Information extraction Planarized sentence representation Semantic gradient

Fractional Modeling and Dynamic Analysis of Two Kinds of Viscoelastic Thin Plates with Gaussian White Noise

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Deng, Jinna Liu, Qiumei Yang, Aimin Chen, Yiming College of Science North China University of Science and Technology Tangshan063210 China Hebei Key Laboratory of Data Science and Application North China University of Science and Technology Tangshan063210 China The Key Laboratory of Engineering Computing in Tangshan City North China University of Science and Technology Tangshan063210 China Tangshan Intelligent Industry and Image Processing Technology Innovation Center North China University of Science and Technology Tangshan063210 China Hebei Engineering Research Center for the Intelligentization of Iron Ore Optimization and Ironmaking Raw Materials Preparation Processes North China University of Science and Technology Tangshan063210 China School of Science Yanshan University Qinhuangdao066004 China LE STUDIUM Loire Valley Institute for Advanced Studies Orléans & Tours Orléans45000 France

According to fractional order model, the governing equation of viscoelastic plate is established. Using the properties of the shifted Bernstein polynomials, the fractional order equation of viscoelastic plate is resolved, the conversion of fractional differential equations to algebraic equations, and operator matrices represented by Kronecker products are solved in the domain. The convergence study validates the algorithm's efficacy and precision in solving differential equations. The displacement of viscoelastic metal thin plate under different external loads (uniform distribution and linear distribution), the effect of white Gaussian noise on the thin metal plate displacement, the effect of different boundary conditions on thin metal plate displacement under harmonic load are studied, the displacements of metal and polymer plates under different loads are contrasted and stress and strain relationship of two kinds of plates are discussed. Based on the outcomes, it can be concluded that the shift Bernstein polynomial approach is useful for numerically simulating viscoelastic plates. © 2023, The Authors. All rights reserved.

关键词： Gaussian noise (electronic)

Magnon trap by chiral spin pumping

学校读者我要写书评

暂无评论

Physical Review B 2020年第5期102卷 054429-054429页

作者： Tao Yu Hanchen Wang Michael A. Sentef Haiming Yu Gerrit E. W. Bauer Max Planck Institute for the Structure and Dynamics of Matter Luruper Chaussee 149 22761 Hamburg Germany Fert Beijing Institute School of Microelectronics Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing 100191 China WPI-AIMR Institute for Materials Research and CSRN Tohoku University Sendai 980-8577 Japan

Chiral spin pumping is the generation of a unidirectional spin current in half of ferromagnetic films or conductors by dynamic dipolar stray fields from close-by nanomagnets. We formulate a general theory of long-range chiral interactions between magnets mediated by unidirectional traveling waves, e.g., spin waves in a magnetic film or microwaves in a waveguide. The traveling waves emitted by an excited magnet can be perfectly trapped by a second, initially passive magnet by a dynamical interference effect. When both magnets are excited by a uniform microwave, the chiral interaction between them creates a large imbalance in their magnon numbers.

关键词： Chirality Magnetization dynamics Magnons Spin blockade Magnetic mirrors & traps Transistors

CT Scan Synthesis for Promoting Computer-Aided Diagnosis Capacity of COVID-19 16th

学校读者我要写书评

暂无评论

CT Scan Synthesis for Promoting Computer-Aided Diagnosis Cap...

16th International Conference on intelligent computing, ICIC 2020

作者： Li, Heng Hu, Yan Li, Sanqian Lin, Wenjun Liu, Peng Higashita, Risa Liu, Jiang School of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Big Data Research Center University of Electronic Science and Technology of China Chengdu611731 China Tomey Corporation Nagoya451-0051 Japan Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen518055 China Ningbo Institute of Industrial Technology Chinese Academy of Sciences Ningbo China

ISBN: (纸本)9783030608019

Nowadays, with the rapid spread of Corona Virus Disease 2019 (COVID-19), this epidemic has become a threatening risk for global public health. Medical workers and researchers all over the world are struggling against the novel coronavirus in the front line. Because the computed tomography (CT) images from infected patients exposure characteristic abnormalities, automatic CT analyzers based on AI-based algorithms are extensively employed as effective weapons to aid clinicians. However, unbalanced data and lack of annotations obstruct AI-based algorithms applying in aided diagnosis because of their low performance. Therefore, in order to solve the above problems, a general-purpose solution is proposed to synthesize COVID-19 CT scans from non-COVID-19 data for providing high-quality negative-positive paired CT scans. Particularly, we introduce an elastic registration algorithm of CT images to manufacture paired training data. Then, a conditional Generative Adversarial Networks (GANs) based image-to-image translation model is implemented to synthesize COVID-19 CT scans from non-COVID-19 data. The effectiveness of our proposed algorithm used in COVID-19 aided diagnosis is verified in the experiments, and the identification and detection capacities of the classification models have been enhanced with the generated CT scans. Specifically, the precise lesion location is achieved by the generated data with a weakly supervised algorithm of class activation mapping (CAM). The model and code of this paper are publicly available at https://***/lihengbit/Synthesis-of-COVID-19-CT-Scan. © 2020, Springer Nature Switzerland AG.

关键词： Computer aided diagnosis

Dual ResGCN for balanced scene graph generation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Jingyi Zhang, Yong Wu, Baoyuan Fan, Yanbo Shen, Fumin Shen, Heng Tao Center for Future Media University of Electronic Science and Technology of China Chengdu610054 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu610054 China School of Data Science Chinese University of Hong Kong Shenzhen Shenzhen518172 Hong Kong Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data Shenzhen518172 China Tencent AI Lab Shenzhen519000 China

Visual scene graph generation is a challenging task. Previous works have achieved great progress, but most of them do not explicitly consider the class imbalance issue in scene graph generation. Models learned without considering the class imbalance tend to predict the majority classes, which leads to a good performance on trivial frequent predicates, but poor performance on informative infrequent predicates. However, predicates of minority classes often carry more semantic and precise information (e.g., ‘on’ v.s ‘parked on’). To alleviate the influence of the class imbalance, we propose a novel model, dubbed dual ResGCN, which consists of an object residual graph convolutional network and a relation residual graph convolutional network. The two networks are complementary to each other. The former captures object-level context information, i.e., the connections among objects. We propose a novel ResGCN that enhances object features in a cross attention manner. Besides, we stack multiple contextual coefficients to alleviate the imbalance issue and enrich the prediction diversity. The latter is carefully designed to explicitly capture relation-level context information i.e., the connections among relations. We propose to incorporate the prior about the co-occurrence of relation pairs into the graph to further help alleviate the class imbalance issue. Extensive evaluations of three tasks are performed on the large-scale database VG to demonstrate the superiority of the proposed method. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

An improved method of algal-bloom discrimination in Taihu Lake using Sentinel-1A data 6

学校读者我要写书评

暂无评论

An improved method of algal-bloom discrimination in Taihu La...

6th Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2019

作者： Wu, Lin Sun, Mengwei Min, Lin Zhao, Jianhui Li, Ning Guo, Zhengwei College of Computer and Information Engineering Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Henan Engineering Research Center of Intelligent Technology and Application Kaifeng475004 China

ISBN: (纸本)9781728129129

The algal bloom is a prominent manifestation of water pollution. Synthetic aperture radar (SAR) shows an advantage in water monitoring due to its characteristic of all-time and all-weather. The water regions where algae gather present dark in SAR image. However, dark regions may also be caused by other factors, such as low wind. This paper proposes an improved algal bloom discrimination method based on Artificial Neural Network (ANN) to recognize the dark regions of algal bloom. Taihu Lake is chosen as the research area in this study because of its serious bloom in recent years. By means of quasi-synchronous optical images, the dark region database of SAR images labeled algal bloom and non-algal bloom are obtained. Then the segmentation algorithm and region growing algorithm are used to acquire the feature from dark regions, and divided into training feature set and testing feature set. Finally, the training and testing feature set are used for ANN-based discrimination model construction and verification. According the experimental results, the overall accuracy reaches 80%, which indicates that ANN model has a good applicability in algal bloom recognition of SAR image. © 2019 IEEE.

关键词： Neural networks

HI-Net: Hyperdense inception 3D UNet for brain tumor segmentation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Qamar, Saqib Ahmad, Parvez Shen, Linlin Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China 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

The brain tumor segmentation task aims to classify tissue into the whole tumor (WT), tumor core (TC) and enhancing tumor (ET) classes using multimodel MRI images. Quantitative analysis of brain tumors is critical for clinical decision making. While manual segmentation is tedious, time-consuming, and subjective, this task is at the same time very challenging to automatic segmentation methods. Thanks to the powerful learning ability, convolutional neural networks (CNNs), mainly fully convolutional networks, have shown promising brain tumor segmentation. This paper further boosts the performance of brain tumor segmentation by proposing hyperdense inception 3D UNet (HI-Net), which captures multi-scale information by stacking factorization of 3D weighted convolutional layers in the residual inception block. We use hyper dense connections among factorized convolutional layers to extract more contexual information, with the help of features reusability. We use a dice loss function to cope with class imbalances. We validate the proposed architecture on the multi-modal brain tumor segmentation challenges (BRATS) 2020 testing dataset. Preliminary results on the BRATS 2020 testing set show that achieved by our proposed approach, the dice (DSC) scores of ET, WT, and TC are 0.79457, 0.87494, and 0.83712, respectively. © 2020, CC BY.

关键词： Convolution

Boundary-Aware context neural network for medical image segmentation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Ruxin Chen, Shuyuan Ji, Chaojie Fan, Jianping Li, Ye Joint Engineering Research Center for Health Big Data Intelligent Analysis Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China School of Software Engineering University of Science and Technology of China Shenzhen Institutes of Advanced Technology Shenzhen China

Medical image segmentation can provide a reliable basis for further clinical analysis and disease diagnosis. The performance of medical image segmentation has been significantly advanced with the convolutional neural networks (CNNs). However, most existing CNNs-based methods often produce unsatisfactory segmentation mask without accurate object boundaries. This is caused by the limited context information and inadequate discriminative feature maps after consecutive pooling and convolution operations. In that the medical image is characterized by the high intra-class variation, inter-class indistinction and noise, extracting powerful context and aggregating discriminative features for fine-grained segmentation are still challenging today. In this paper, we formulate a boundary-Aware context neural network (BA-Net) for 2D medical image segmentation to capture richer context and preserve fine spatial information. BA-Net adopts encoder-decoder architecture. In each stage of encoder network, pyramid edge extraction module is proposed for obtaining edge information with multiple granularities firstly. Then we design a mini multi-Task learning module for jointly learning to segment object masks and detect lesion boundaries. In particular, a new interactive attention is proposed to bridge two tasks for achieving information complementarity between different tasks, which effectively leverages the boundary information for offering a strong cue to better segmentation prediction. At last, a cross feature fusion module aims to selectively aggregate multi-level features from the whole encoder network. By cascaded three modules, richer context and fine-grain features of each stage are encoded. Extensive experiments on five datasets show that the proposed BA-Net outperforms state-of-The-Art approaches. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

Radio-continuum spectra of ram pressure stripped galaxies in the Coma Cluster

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Roberts, I.D. van Weeren, R.J. Lal, D.V. Sun, M. Chen, H. Ignesti, A. Brüggen, M. Lyskova, N. Venturi, T. Yagi, M. Leiden Observatory Leiden University PO Box 9513 Leiden2300 RA Netherlands National Centre for Radio Astrophysics Tata Institute of Fundamental Research Post Box 3 Ganeshkhind P.O. Pune411007 India Department of Physics & Astronomy University of Alabama in Huntsville 301 Sparkman Drive HuntsvilleAL35899 United States Research Center for Intelligent Computing Platforms Zhejiang Laboratory Hangzhou311100 China INAF–Padova Astronomical Observatory Vicolo dell’Osservatorio 5 PadovaI-35122 Italy Hamburger Sternwarte Universität Hamburg Gojenbergsweg 112 Hamburg21029 Germany Profsoyuznaya 84/32 Moscow117997 Russia Astro Space Center P. N. Lebedev Physical Institute of RAS Profsojuznaya 84/32 Moscow117997 Russia INAF–Istituto di Radioastronomia via Gobetti 101 BolognaI-40129 Italy Astronomy Data Center National Astronomical Observatory of Japan Mitaka Tokyo181-8588 Japan

Context. The population of galaxies in the local Universe is bi-modal in terms of specific star formation rate. This fact has led to a broad distinction between star-forming galaxies (typically cold-gas rich and late type) and quenched galaxies (typically cold-gas poor and early type). The ratio between quenched and star-forming galaxies is much larger in clusters than the field, and pinpointing which are the physical processes driving this excess quenching in clusters is an open question. Aims. We used the nearby Coma Cluster as a laboratory in order to probe the impact of ram pressure on star formation as well as to constrain the characteristic timescales and velocities for the stripping of the non-thermal ISM. Methods. We used high-resolution (6.5′′ ≈ 3 kpc), multi-frequency (144 MHz − 1.5 GHz) radio continuum imaging of the Coma Cluster to resolve the low-frequency radio spectrum across the discs and tails of 25 ram pressure stripped galaxies. With resolved spectral index maps across these galaxy discs, we constrained the impact of ram pressure perturbations on galaxy star formation. We measured multi-frequency flux-density profiles along each of the ram pressure stripped tails in our sample. We then fit the resulting radio continuum spectra with a simple synchrotron aging model. Results. We showed that ram pressure stripped tails in Coma have steep (−2 α −1) spectral indices. The discs of galaxies undergoing ram pressure stripping have integrated spectral indices within the expected range for shock acceleration from supernovae (−0.8 α −0.5), though there is a tail towards flatter values. In a resolved sense, there are gradients in spectral index across the discs of ram pressure stripped galaxies in Coma. These gradients are aligned with the direction of the observed radio tails, with the flattest spectral indices being found on the ‘leading half’. From best-fit break frequencies we estimated the projected plasma velocities along the tail to be on the order of h

关键词： Galaxies