检索结果-内蒙古大学图书馆

A Method for Extracting Electronic Medical Record Entities by Fusing Multichannel Self-Attention Mechanism with Location Relationship Features 9th

A Method for Extracting Electronic Medical Record Entities b...

引用

9th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2023

作者： Xu, Hongyan Wang, Hong Feng, Yong Wang, Rongbing Zhang, Yonggang College of Information Liaoning University Shenyang110036 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

ISBN: (纸本)9789819959709

With the implementation of the "Internet+" strategy, electronic medical records are generally applied in the medical field. Deep mining of electronic medical record content data is an effective means to obtain medical knowledge and analyse patients’ states, but the existing methods for extracting entities from electronic medical records have problems of redundant information, overlapping entities, and low accuracy rates. Therefore, this paper proposes an entity extraction method for electronic medical records based on the network framework of BERT-BiLSTM, which incorporates a multichannel self-attention mechanism and location relationship features. First, the text input sequence was encoded using the BERT-BiLSTM network framework, and the global semantic information of the sentence was mined more deeply using the multichannel self-attention mechanism. Then, the position relation characteristic was used to extract the local semantic message of the text, and the position relation characteristic of the word and the position embedding matrix of the whole sentence were obtained. Next, the extracted global semantic information was stitched with the positional embedding matrix of the sentence to obtain the current entity classification matrix. Finally, the proposed method was validated on the dataset of Chinese medical text entity relationship extraction and the 2010i2b2/VA relationship corpus, and the experimental results indicate that the proposed method surpasses existing methods in terms of precision, recall, F1 value and training time. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

K-means on commodity GPUs with CUDA

K-means on commodity GPUs with CUDA

引用

2009 WRI World Congress on Computer Science and Information engineering, CSIE 2009

作者： Bai, Hong-Tao He, Li-Li Ouyang, Dan-Tong Li, Zhan-Shan Li, He College of Computer Science and Technology Jilin University 130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University 130012 China

ISBN: (纸本)9780769535074

K-means algorithm is one of the most famous unsupervised clustering algorithms. Many theoretical improvements for the performance of original algorithms have been put forward, while almost all of them are based on Single Instruction Single Data (SISD) architecture processors (CPUs), which partly ignored the inherent paralleled characteristic of the algorithms. In this paper, a novel Single Instruction Multiple Data (SIMD) architecture processors (GPUs) based k-means algorithm is proposed. In this algorithm, in order to accelerate compute-intensive portions of traditional k-means, both data objects assignment and k centroids recalculation are off-loaded to the GPU in parallel. We have implemented this GPU-based k-means on the newest generation GPU with Compute Unified Device Architecture (CUDA). The numerical experiments demonstrated that the speed of GPU-based k-means could reach as high as 40 times of the CPU-based k-means. © 2008 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Improving incremental diagnosis with choosing measurement order

Improving incremental diagnosis with choosing measurement or...

引用

2010 International Conference of Information Science and Management engineering, ISME 2010

作者： Zhao, Xiangfu Ouyang, Dantong College of Mathematics Physical and Information Engineering Zhejiang Normal University Jinhua China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China

ISBN: (纸本)9780769541327

There may be many groups of candidate results after the step of candidate generation in model-based diagnosis. Hwee Tou Ng proposed the Inc-Diagnose approach to further reduce the candidate results. However, the efficiency of Inc-Diagnose may not be very good. Firstly, we give some correction of Inc-Diagnosis by applying it to a real example. Then, we propose an improved approach with choosing the order of measurements for incremental diagnosis. Example results show that our approach has better efficiency. © 2010 IEEE.

关键词： Incremental diagnosis Measurement order Model-based diagnosis

来源：评论

学校读者我要写书评

暂无评论

Crossed-Time Delay Neural Network for Speaker Recognition 1

引用

27th International Conference on MultiMedia Modeling, MMM 2021

作者： Chen, Liang Liang, Yanchun Shi, Xiaoshu Zhou, You Wu, Chunguo Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun130012 China Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education School of Computer Zhuhai College of Jilin University Zhuhai519041 China

ISBN: (数字)9783030678326

ISBN: (纸本)9783030678319

Time Delay Neural Network (TDNN) is a well-performing structure for deep neural network-based speaker recognition systems. In this paper we introduce a novel structure, named Crossed-Time Delay Neural Network (CTDNN) to enhance the performance of current TDNN for speaker recognition. Inspired by the multi-filters setting of convolution layers from convolution neural networks, we set multiple time delay units with different context size at the bottom layer and construct a multilayer parallel network. The proposed CTDNN gives significant improvements over original TDNN on both speaker verification and identification tasks. It outperforms in VoxCeleb1 dataset in verification experiment with a 2.6% absolute Equal Error Rate improvement. In few shots condition, CTDNN reaches 90.4% identification accuracy, which doubles the identification accuracy of original TDNN. We also compare the proposed CTDNN with another new variant of TDNN, Factorized-TDNN, which shows that our model has a 36% absolute identification accuracy improvement under few shots condition. Moreover, the proposed CTDNN can handle training with a larger batch more efficiently and hence, utilize calculation resources economically. © 2021, Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A novel approach for modeling Direction Relations between Uncertain Regions

A novel approach for modeling Direction Relations between Un...

引用

2010 International Conference on Machine Vision and Human-Machine Interface, MVHI 2010

作者： Dong, Yiqun Liu, Dayou Wang, Fang Tian, Ye College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China

ISBN: (纸本)9780769540092

Conventional models based on crisp regions can not deal with the Direction Relations between Uncertain Regions (DRUR). Using broad boundary to represent the uncertain boundary, a novel approach is proposed based on model SK for modeling DRUR in this paper. DRUR are described as the combinations of basic cardinal direction relations, then we study the composition of DRUR, and a method is put forward for calculating this composition. © 2010 IEEE.

关键词： Board boundary Composition Direction relations Model SK Uncertain regions Plant uncertain Uncertainty Modeling Boundary

来源：评论

学校读者我要写书评

暂无评论

A study on parallel semantics of constraint logic rograms

A study on parallel semantics of constraint logic rograms

引用

International Conference on Machine Learning and Cybernetics, ICMLC 2005

作者： Sun, Ji.-Gui Zhang, Yong-Gang College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory for Symbolic Computation and Knowledge Engineering Ministry of Education Changchun 130012 China

ISBN: (纸本)078039092X

This paper presents two parallel semantics of constraint logic programs: multiset answer constraint semantics and game semantics, which differ entirely from the traditional semantics. When giving the first semantics, it adopts the s-semantics approach, whose aim is to find notions of models which really capture the operational semantics. And it defines the program equivalence based on multiset answer constraint. Then it investigates the game semantics and proves that it is consistent with traditional operational semantics. On the basis of these two semantics, programmers can comprehend the programs deeply and develop more sound parallel constraint logic programming systems. Finally, it gives the conclusions and future work. © 2005 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Solving constrained traveling salesman problems by genetic algorithms

引用

自然科学进展(英文版) 2004年第7期14卷 631-637页

作者： WU Chunguo LIANG Yanchun LEE Heowpueh LU Chun LIN Wuzhong College of Computer Science and Technology Jilin University Key Laboratory for Symbol Computation and Knowledge Engineering Ministry of Education of China Changchun 130012 China Institute of High Performance Computing Singapore 117528 Singapore Institute of High Performance Computing Singapore 117528 Singapore

Three kinds of constrained traveling salesman problems (TSP) arising from application problems, namely the open route TSP, the end-fixed TSP, and the path-constrained TSP, are proposed. The corresponding approaches based on modified genetic algorithms (GA) for solving these constrained TSPs are presented. Numerical experiments demonstrate that the algorithm for the open route TSP shows its advantages when the open route is required, the algorithm for the end-fixed TSP can deal with route optimization with constraint of fixed ends effectively, and the algorithm for the path-constraint could benefit the traffic problems where some cities cannot be visited from each other.

关键词： constrained traveling salesman problem genetic algorithm Hamiltonian path open route fixed end

来源：评论

学校读者我要写书评

暂无评论

Warburg Effects in Cancer and Normal Proliferating Cells:Two Tales of the Same Name

引用

Genomics, Proteomics & Bioinformatics 2019年第3期17卷 273-286页

作者： Huiyan Sun Liang Chen Sha Cao Yanchun Liang Ying Xu The China-Japan Union Hospital Jilin UniversityChangchun 130033China MOE Key Laboratory of Symbolic Computation and Knowledge Engineering College of Computer Science and TechnologyJilin UniversityChangchun 130012China Computational Systems Biology Lab Department of Biochemistry and Molecular Biology and Institute of BioinformaticsUniversity of GeorgiaAthensGA 30602USA Faculty of Health Sciences University of MacaoTaipaMacao SAR 999078China Department of Biostatistics School of MedicineIndiana UniversityIndianapolisIN 46202USA Zhuhai Laboratory of MOE Key Laboratory of Symbolic Computation and Knowledge Engineering Zhuhai College of Jilin UniversityZhuhai 519041China

It has been observed that both cancer tissue cells and normal proliferating cells(NPCs)have the Warburg *** goal here is to demonstrate that they do this for different *** accomplish this,we have analyzed the transcriptomic data of over 7000 cancer and control tissues of 14 cancer types in TCGA and data of five NPC types in *** analyses reveal that NPCs accumulate large quantities of ATPs produced by the respiration process before starting the Warburg effect,to raise the intracellular pH from 6.8 to 7.2 and to prepare for cell division *** cell cycle starts,the cells start to rely on glycolysis for ATP generation followed by ATP hydrolysis and lactic acid release,to maintain the elevated intracellular pH as needed by cell division since together the three processes are pH *** cells go back to the normal respirationbased ATP production once the cell division phase *** comparison,cancer cells have reached their intracellular pH at 7.4 from top down as multiple acid-loading transporters are up-regulated and most acid-extruding ones except for lactic acid exporters are *** cells use continuous glycolysis for ATP production as way to acidify the intracellular space since the lactic acid secretion is decoupled from glycolysis-based ATP generation and is pH balanced by increased expressions of acid-loading ***-expression analyses suggest that lactic acid secretion is regulated by external,non-pH related ***,our data strongly suggest that the two cell types have the Warburg effect for very different reasons.

关键词： Cancer Warburg effect Fenton reaction Cell proliferation pH homeostasis

来源：评论

学校读者我要写书评

暂无评论

Blind identification of image copy-paste tampering based on logarithm polar coordinate transformation

Blind identification of image copy-paste tampering based on ...

引用

2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011

作者： Lv, A. Ying-Da Shen, B. Xuan-Jing Chen, C. Hai-Peng College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China

ISBN: (纸本)9781601321916

To detect image copy-paste tampering, an improved blind identification was proposed in this study. Firstly, according to gray-level and gray-structure, every couple of doubtful blocks can be located. Secondly, for each located couple of doubtful blocks, use logarithm polar coordinate transformation to translate the rotation and scaling in Cartesian coordinate system into translation in logarithm polar coordinate system;and use phase correlation method to obtain rotation angle, scaling size and position offset;and then, the tampered regions would be located roughly. Finally, use geometry method to accurately calculate the rotation angle, scaling size and position offset between the copy-paste regions, and according to these values, the tampered region can be located accurately. Experimental results showed that our algorithm can detect the copy-paste tampering, even with rotation and scaling transformation, and it can resist some post-processing, such as blurring, adding noise, and so on.

关键词： Rotation

来源：评论

学校读者我要写书评

暂无评论

Solving SAT problem with a revised hitting set algorithm

Solving SAT problem with a revised hitting set algorithm

引用

2010 2nd International Conference on Future Computer and Communication, ICFCC 2010

作者： Xu, Youjun Ouyang, Dantong Ye, Yuxin He, Jialiang College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

ISBN: (纸本)9781424458226

The satisfiability(SAT) problem is a core problem of artificial intelligence. Research findings in SAT are widely used in many areas. The main methods solving SAT problem are resolution principle, tableau calculus and extension rule. Besides methods mentioned above, we find that the SAT problem can be solved with hitting set algorithms. If a set of clause is satisfiable, there must be a hitting set of the clause set which containing no complementary pairs of literals. Algorithm NEWHS-tree is an efficient hitting set algorithm proposed by Ouyang. RNHST proposed in this paper is a revised algorithm in respect of NEWHS-tree. It judges the satisfiability of a clause set by confirming the existence of the set's hitting set without complementary pairs of literals. The test result shows that RNHST is an efficient algorithm. ©2010 IEEE.

关键词： Forestry

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：