检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Liu, Zhenghao Yi, Xiaoyuan Sun, Maosong Yang, Liner Chua, Tat-Seng Department of Computer Science and Technology Tsinghua University Beijing China Institute for Artificial Intelligence Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology State Key Lab on Intelligent Technology and Systems Tsinghua University Beijing China Beijing Academy of Artificial Intelligence Beijing Language and Culture University Beijing China School of Computing National University of Singapore Singapore

Grammatical Error Correction (GEC) aims to correct writing errors and help language learners improve their writing skills. However, existing GEC models tend to produce spurious corrections or fail to detect lots of errors. The quality estimation model is necessary to ensure learners get accurate GEC results and avoid misleading from poorly corrected sentences. Well-trained GEC models can generate several high-quality hypotheses through decoding, such as beam search, which provide valuable GEC evidence and can be used to evaluate GEC quality. However, existing models neglect the possible GEC evidence from different hypotheses. This paper presents the Neural Verification Network (VERNet) for GEC quality estimation with multiple hypotheses. VERNet establishes interactions among hypotheses with a reasoning graph and conducts two kinds of attention mechanisms to propagate GEC evidence to verify the quality of generated hypotheses. Our experiments on four GEC datasets show that VERNet achieves state-of-the-art grammatical error detection performance, achieves the best quality estimation results, and significantly improves GEC performance by reranking hypotheses. All data and source codes are available at https://***/thunlp/VERNet. Copyright © 2021, The Authors. All rights reserved.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Matching Biomedical Ontologies with Long Short-Term Memory Networks

Matching Biomedical Ontologies with Long Short-Term Memory N...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Chao Jiang Xingsi Xue Intelligent Information Processing Research Center Fujian University of Technology Fuzhou Fujian China School of Computer Science and Mathematics Fujian University of Technology Fuzhou Fujian China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou Fujian China Guangxi Key Laboratory of Automatic Detecting Technology and Instruments Guilin University of Electronic Technology Guilin Guangxi China Fujian Key Lab for Automotive Electronics and Electric Drive Fujian University of Technology Fuzhou Fujian China

ISBN: (数字)9781728162157

ISBN: (纸本)9781728162164

Semantic Web (SW) has attracted the increasing attention of researchers, which facilitates people to link and handle various data. Ontology is the kernel technique of SW, and biomedical ontology is a state-of-art biomedical knowledge modeling technique, which formally defines the biomedical concepts and their relationships. However, the same biomedical concepts in different biomedical ontologies could be defined in various contexts or with different terms, which yields the biomedical ontology heterogeneity problem. It is crucial to find mapping among heterogeneity concepts of different biomedical ontologies for bridging the semantic gaps, which is the so-called biomedical ontology matching. Biomedical ontology matching problem is an open challenge due to the rich semantic meaning and the flexible representation on a biomedical concept. To address this challenging problem, in this work, it is regarded as a binary classification problem, and a Long Short-Term Memory Networks (LSTM)-based ontology matching technique is proposed to solve it. Our proposal improves the quality of the alignment by introducing the char-embedding technique, which takes into account the semantic and context information of concepts. The comparing results with OAEI's participants show the effectiveness of our proposal.

关键词： Ontologies Semantics Logic gates Training Human anatomy Proposals Biomedical measurement

来源：评论

学校读者我要写书评

暂无评论

HU-Net: Hessian-incorporated U-Net for CBCT projection-domain metal segmentation with guidance from SAM

HU-Net: Hessian-incorporated U-Net for CBCT projection-domai...

引用

IEEE Conference on Cybernetics and intelligent Systems

作者： Chen Jiang Tianling Lyu Gege Ma Yan Xi Yang Chen Wentao Zhu Zhejiang Lab Hangzhou China Hangzhou Institute for Advanced Study of UCAS Hangzhou China Shanghai First-Imaging Tech. Shanghai China Laboratory of Image Science and Technology Southeast University Nanjing China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing China

ISBN: (数字)9798350364194

ISBN: (纸本)9798350364200

Metal artifact is a prevailing factor reducing the image quality of CBCT in minimally invasive spine surgery. In CBCT, conventional metal artifact reduction algorithms pay more attention to the inpainting of the metal traces, but metal segmentation is also challenging. Despite the current success in image segmentation with deep learning, the substantial expense associated with annotating metal traces in the projection domain makes most of these approaches impractical for this task. To address this, we propose a Hessian-incorporated U-Net (HU-Net) for CBCT projection-domain metal segmentation with guidance from SAM. The proposed method has been tested on both digital phantom data and clinical CBCT data. According to the experimental results, our method has demonstrated notable improvement in the segmentation of metal traces across both datasets. This paper presents a feasible approach for metal trace segmentation in the projection domain with deep learning and has the potential to be applied in clinical applications.

关键词： Deep learning Image quality Image segmentation Minimally invasive surgery Mechatronics Metals Phantoms

来源：评论

学校读者我要写书评

暂无评论

Does Thermal Really Always Matter for RGB-T Salient Object Detection?

arXiv

引用

arXiv 2022年

作者： Cong, Runmin Zhang, Kepu Zhang, Chen Zheng, Feng Zhao, Yao Huang, Qingming Kwong, Sam The Institute of Information Science Beijing Jiaotong University Beijing100044 China The Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China The Department of Computer Science City University of Hong Kong China The Department of Computer Science and Technology Southern University of Science and Technology Shenzhen518055 China The Research Institute of Trustworthy Autonomous Systems Shenzhen518055 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518055 China The City University of Hong Kong Shenzhen Research Institute Shenzhen51800 China

In recent years, RGB-T salient object detection (SOD) has attracted continuous attention, which makes it possible to identify salient objects in environments such as low light by introducing thermal image. However, most of the existing RGBT SOD models focus on how to perform cross-modality feature fusion, ignoring whether thermal image is really always matter in SOD task. Starting from the definition and nature of this task, this paper rethinks the connotation of thermal modality, and proposes a network named TNet to solve the RGB-T SOD task. In this paper, we introduce a global illumination estimation module to predict the global illuminance score of the image, so as to regulate the role played by the two modalities. In addition, considering the role of thermal modality, we set up different cross-modality interaction mechanisms in the encoding phase and the decoding phase. On the one hand, we introduce a semantic constraint provider to enrich the semantics of thermal images in the encoding phase, which makes thermal modality more suitable for the SOD task. On the other hand, we introduce a two-stage localization and complementation module in the decoding phase to transfer object localization cue and internal integrity cue in thermal features to the RGB modality. Extensive experiments on three datasets show that the proposed TNet achieves competitive performance compared with 20 state-of-the-art methods. The code and results can be found from the link of https://***/proj_***. © 2022, CC BY-NC-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Gait Phase Classification Based on sEMG Signals Using Long Short-Term Memory for Lower Limb Exoskeleton Robot

引用

IOP Conference Series: Materials Science and Engineering 2020年第1期853卷

作者： Ye Yuan Ziming Guo Can Wang Shengcai Duan Lufeng Zhang Xinyu Wu Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences CAS Key Laboratory of Human-Machine Intelligence-Synergic Systems Shenzhen Institutes of Advanced Technology Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University.

In this work, we present a Long Short-Term Memory Model (LSTMM) for gait phase classification based on sEMG signals to control the lower limb exoskeleton robot which can recognize 2 phases (Stand and Swing) of leg phases between the foot and ground. This model only needs four sEMG signals to control the lower limb exoskeleton robot helping the hemiplegia patient walking. Compared with the existing methods, the proposed model not only avoids the complex sensor systems but also enhances the accuracy of gait phase classification. The experimental results first verify the availability of sEMG data acquisition system on the lower limb exoskeleton robot made by the Shenzhen Institutes of advanced Technologies (SIAT) by quantify the system with gold standard optoelectronic system Vicon, then show that the proposed LSTMM is significantly higher on prediction accuracy and has better robustness for gait phase classification to control the lower limb exoskeleton robot with different speeds. Finally, the maximum accuracy of LSTMM on the gait phase classification is 97.89%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study on moving target detection to passive radar based on FM broadcast transmitter

引用

Chinese Journal of Systems Engineering and Electronics 2007年第3期000卷

作者： Zhu Jiabing Tao Liang Hong Yi Education Ministry Key Lab of Intelligent Computing and Signal Processing Anhui Univ.Hefei 230039P.R.China Inst.of Signal Processing East China Research Inst.of Electronic EngineeringHefei 230031P.R.China Education Ministry Key Lab of Intelligent Computing and Signal Processing Anhui Univ.Hefei 230039P.R.China

Target detection by a noncooperative illuminator is a topic of general interest in the electronic warfare *** of all,direct-path interference(DPI)suppression which is the technique of bottleneck of moving target detection by a noncooperative frequency modulation(FM) broadcast transmitter is analyzed in this article;Secondly,a space-time-frequency domain synthetic solution to this problem is introduced:Adaptive nulling array processing is considered in the space domain,DPI cancellation based on adaptive fractional delay interpolation(AFDI)technique is used in planned time domain,and long-time coherent integration is utilized in the frequency domain;Finally,an experimental system is planned by considering FM broadcast transmitter as a noncooperative illuminator,Simulation results by real collected data show that the proposed method has a better performance of moving target detection.

关键词： passive radar direct path interference adaptive beamforming adaptive fractional delay interpolation long-time coherent integration.

来源：评论

学校读者我要写书评

暂无评论

Study on Sensitization Mechanism of Novel Magnetorheological Composite Pdms Thin Film Based on Enhanced Magneto-Mechanical Effect

SSRN

引用

SSRN 2023年

作者： Sang, Shengbo Tan, Qiuyun Jiang, Jiaolin Wu, Kaile Xiao, Pengli Zhao, Dong Guo, Xing Yang, Zhuoqing Dong, Xiushan Ge, Yang Shanxi Key Laboratory of Micro Nano Sensors & Artificial Intelligence Perception College of Information and Computer Taiyuan University of Technology Taiyuan030024 China Key Lab of Advanced Transducers and Intelligent Control System Ministry of Education Taiyuan University of Technology Taiyuan030024 China Shanghai200240 China Shanxi Academy of Medical Sciences China Shanxi Research Institute of 6D Artificial Intelligence Biomedical Science Taiyuan030024 China

High sensitivity is key to expand the range of bio-detection, especially in realizing biological detection on single molecular level. Herein, we introduce a novel magnetorheological membrane with enhanced magneto-mechanical effect into the biosensor. Specifically, we made the magnetorheological composite PDMS film (MREF) strengthened by magnetostrictive particles (MSP), and the anisotropic TbDyFe-PDMS can be magnetically deformed to 90 °with 5.8 emu/g, which possesses an initial tensile modulus 55% higher than isotropic. In particular, the modified MR effect equations were proposed considering magnetic dipole interaction and nonlinear magnetostrictive pre-strain of MSP. Such formulae indicate that the enhanced MR effect of MSP-MREF is greatly determined by Ms, remanence, and the flux linkage-like structure. In addition, finite element simulations were carried out to validate and complementarily demonstrate the nonlinear magneto-mechanical behaviors of MSP-MREF theoretically. Finally, the biosensor based on MSP-MREF was fabricated to detect the low concentrations of human serum albumin (HSA), and its sensitivity is around 4 times that of the conventional biosensor. Furthermore, it exhibits high reliability in detecting HSA in real human urine samples, making it the ideal candidate as a practical and effective way for the detection of biomolecules at low concentrations in the future. © 2023, The Authors. All rights reserved.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Modulating p-type doping of two-dimensional material palladium diselenide

引用

Nano research 2024年第4期17卷 3232-3244页

作者： Jiali Yang Yu Liu En-Yang Wang Jinbo Pang Shirong Huang Thomas Gemming Jinshun Bi Alicja Bachmatiuk Hao Jia Shu-Xian Hu Chongyun Jiang Hong Liu Gianaurelio Cuniberti Weijia Zhou Mark H Rümmeli Institute for Advanced Interdisciplinary Research(iAIR) University of JinanJinan 250022China Institute for Materials Chemistry Leibniz Institute for Solid State and Materials Research Dresden(IFW Dresden)20 Helmholtz StrasseDresden 01069Germany State Key Lab of Transducer Technology Shanghai Institute of Microsystem and Information TechnologyChinese Academy of SciencesShanghai 200050China College of Energy Soochow Institute for Energy and Materials Innovations Soochow UniversitySuzhou 215006China Key Laboratory of Advanced Carbon Materials and Wearable Energy Technologies of Jiangsu Province Soochow UniversitySuzhou 215006China School of Integrated Circuits University of Chinese Academy of SciencesBeijing 101408China Institute of Microelectronics of Tianjin Binhai New Area Tianjin 300451China Institute of Microelectronics Chinese Academy of SciencesBeijing 100029China Lukasiewicz Research Network PORT Polish Center for Technology DevelopmentStablowicka 147Wroclaw 54-066Poland School of Mathematics and Physics University of Science and Technology BeijingBeijing 100083China College of electronic information and optical engineering Nankai UniversityTianjin 300350China Centre of Polymer and Carbon Materials Polish Academy of SciencesM.Curie Sklodowskiej 34Zabrze 41-819Poland Center for Energy and Environmental Technologies VŠB-Technical University of Ostrava17.Listopadu 15Ostrava 70833Czech Republic State Key Laboratory of Crystal Materials Center of Bio&Micro/Nano Functional MaterialsShandong UniversityJinan 250100China Dresden Center for Computational Materials Science Technische Universität DresdenDresden 01062Germany Dresden Center for Intelligent Materials(GCL DCIM) Technische Universität DresdenDresden 01062Germany Institute for Materials Science and Max Bergmann Center of Biomaterials Technische Universität DresdenDresden 01069Germany Center for Advancing Electronics Dresden Technische Universität DresdenDresden 01069Germany

The van der Waals heterostructures have evolved as novel materials for complementing the Si-based semiconductor ***-10 noble metal dichalcogenides(e.g.,PtS_(2),PtSe_(2),PdS_(2),and PdSe_(2))have been listed into two-dimensional(2D)materials toolkit to assemble van der Waals *** them,PdSe_(2) demonstrates advantages of high stability in air,high mobility,and wide tunable ***,the regulation of p-type doping of PdSe_(2) remains unsolved problem prior to fabricating p–n junction as a fundamental platform of semiconductor ***,a quantitative method for the controllable doping of PdSe_(2) is yet to be *** this study,the doping level of PdSe_(2) was correlated with the concentration of Lewis acids,for example,SnCl_(4),used for *** the transfer characteristics,the threshold voltage(the gate voltage corresponding to the minimum drain current)increased after SnCl_(4) soaking ***_(2) transistors were soaked in SnCl_(4) solutions with five different *** threshold voltages from the as-obtained transfer curves were extracted for linear fitting to the threshold voltage versus doping concentration correlation *** study provides in-depth insights into the controllable p-type doping of PdSe_(2).It may also push forward the research of the regulation of conductivity behaviors of 2D materials.

关键词： two-dimensional(2D)materials Lewis acid treatment p-type doping field-effect transistors transfer characteristic

来源：评论

学校读者我要写书评

暂无评论

Bilingual Word Embedding with Sentence Combination CNN for 1-to-N Sentence Alignment 20

Bilingual Word Embedding with Sentence Combination CNN for 1...

引用

Proceedings of the 4th International Conference on Natural Language processing and information Retrieval

作者： Xinyuan Ren Xiangling Fu Xuesi Zhou Chunsheng Liu Songfeng Gao Lei Peng School of Software Engineering Beijing University of Posts and Telecommunications Beijing China and Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China Department of Electronic Engineering Tsinghua University Hai Dian Beijing China and Multimedia Signal and Intelligent Information Processing Lab Tsinghua University Hai Dian Beijing China BUPT and Huarong Joint lab of Smart Finance Beijing P. R. China and HuaRong RongTong (Beijing) Technology Co. Ltd Beijing P. R. China

ISBN: (纸本)9781450377607

Sentence alignment, as one of the most active and fundamental tasks in the field of natural language processing (NLP), is usually realized in two categories of methods. One is traditional methods which are firstly proposed, the other, which are adopted later, is based on the Neural Network method. Presently, under the limitation that the existing mainstream data corpora are mostly in the form of 1-to-1, the alignment models with relatively good performance mainly apply to the cases of 1-to-1 sentence alignment. However, under the circumstance that a sentence contains too much information, 1-to-N sentence alignment can actually have a better effect on sentence translation tasks, compared with the 1-to-1 form, since it is more flexible and can reduce the complexity of the original sentence. As a result, we attempt to exploit neural networks with relatively good performance in the cases of 1-to-1 to fit in the cases of 1-to-N. In this paper, a novel 1-N Bilingual word Embedding with Sentence Combination CNN Improved Framework (1-NBESCC) is proposed in order to align 1-to-N sentences more precisely. Experiments show that our proposed model performs as good as the traditional methods such as BLEUALIGN in 1-to-1 situation, but much better in 1-to-N situation.

关键词： Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

CoS2/V2O3 Heterostructure with Coffee Ground Derived Carbon as Superior Composite Anodes of Sodium-Ion Batteries

SSRN

引用

SSRN 2023年

作者： Xue, Yongqi Wu, Jun Cheng, Zhiqun Xu, Congxin Cai, Yurong Ni, Wenbin Zhou, Xiaochong College of Electronics and Information Hangzhou Dianzi University Hangzhou310018 China The Key Laboratory of Advanced Textile Materials and Manufacturing Technology of Ministry of Education National Engineering Lab for Textile Fiber Materials and Processing Technology School of Materials Science and Engineering Zhejiang Sci-Tech University Hangzhou310018 China Huzhou Horizontal Na Energy Technology Co. Ltd Chengye Intelligent Center No. 819 Xisaishan Road Longxi Street Huzhou313000 China

The poor ion transport kinetics and serious volumetric change of transition metal sulfides hinder their electrochemical applications. In this study, we introduced a heterostructure between CoS2 and V2O3 as an anode of sodium-ion batteries (SIBs) via a feasible hydrothermal method combining with a biomass carbon derived from coffee grounds (CG). The as-prepared CoS2/V2O3-CG composite retained a reversible capacity of 464.5 mAh g-1 after 300 cycles at 0.5 A g-1, exhibited an excellent rate capability of up to 8 A g-1 and a remarkable long-cycling life of over 2,000 cycles at 2 A g-1 with a capacity decay rate of less than 0.041% per cycle. The kinetic analysis indicated that CoS2/V2O3-CG composite exhibited a superior capacitive behavior, making it a high Na+ diffusion coefficient in SIBs. The enhanced electrochemical performances of composite can be primarily attributed to the CoS2/V2O3 heterostructure and porous biomass-derived carbon, which offers a built-in electric field and a large surface area, and effectively alleviates the volumetric expansion effect. © 2023, The Authors. All rights reserved.

关键词： Anodes

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：