检索结果-内蒙古大学图书馆

Trigger words detection by integrating attention mechanism into Bi-LSTM neural network—A case study in PubMED-wide trigger words detection for pancreatic cancer 17th

Trigger words detection by integrating attention mechanism i...

引用

17th China National conference on Computational Linguistics, CCL 2018 and 6th international Symposium on Natural Language Processing Based on Naturally Annotated Big Data, NLP-NABD 2018

作者： Zhou, Kaiyin Yao, Xinzhi Wang, Shuguang Kim, Jin-Dong Cohen, Kevin Bretonnel Chen, Ruiying Wang, Yuxing Xia, Jingbo College of Informatics Huazhong Agricultural University Wuhan China Hubei Key Laboratory of Agricultural Bioinformatics Wuhan China Tokyo Japan School of Medicine University of Colorado Denver Anschutz Medical Campus Aurora United States

ISBN: (纸本)9783030017156

A Bi-LSTM based encode/decode mechanism for named entity recognition was studied in this research. In the proposed mechanism, Bi-LSTM was used for encoding, an Attention method was used in the intermediate layers, and an unidirectional LSTM was used as decoder layer. By using element wise product to modify the conventional decoder layers, the proposed model achieved better F-score, compared with other three baseline LSTM-based models. For the purpose of algorithm application, a case study of causal gene discovery in terms of disease pathway enrichment was designed. In addition, the causal gene discovery rate of our proposed method was compared with another baseline methods. the result showed that trigger genes detection effectively increase the performance of a text mining system for causal gene discovery. © Springer Nature Switzerland AG 2018.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

ACM international conference Proceeding Series

ACM International Conference Proceeding Series

引用

6th international conference on bioinformatics and Computational Biology, ICBCB 2018

ISBN: (纸本)9781450363488

the proceedings contain 29 papers. the topics discussed include: a dynamic pooling approach to extract complete allele signal information in somatic copy number alternations detection;a computational framework to simultaneously quantify DNA methylation, somatic copy number alternation and DNA heterogeneity from low coverage plasma circulating DNA sequencing;synonymous permutation reveals selection for less out-of-frame stop codons;predicting intrinsically disordered proteins based on different feature teams;YeastSCI: a web tool integrating zinc cluster protein information of saccharomyces and candida;biased distribution of amino acid in intrinsically disordered proteins and regions;FlexSLiM: a novel approach for short linear motif discovery in protein sequences;leaf shape variation and its correlation to phenotypic traits of soybean in northeast China;predicting intrinsically disordered regions based on the structural bias of amino acid dimers;ECG signal de-noising using EEMD based on white noise decomposition;research of heart rate variability analysis system based on cloud model;a framework of an unconstrained sleep monitoring system;super-resolution based on noise resistance deep convolutional network;study on recognition method of label-free red and white cell using fecal microscopic image;and a method of constructing vertebral 3D statistical model based on Gaussian curvature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

17th China National conference on Computational Linguistics, CCL 2018 and 6th international Symposium on Natural Language Processing Based on Naturally Annotated Big Data, NLP-NABD 2018

17th China National Conference on Computational Linguistics,...

引用

17th China National conference on Computational Linguistics, CCL 2018 and 6th international Symposium on Natural Language Processing Based on Naturally Annotated Big Data, NLP-NABD 2018

ISBN: (纸本)9783030017156

the proceedings contain 33 papers. the special focus in this conference is on Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. the topics include: Knowledge graph embedding with logical consistency;an end-to-end entity and relation extraction network with multi-head attention;attention-based convolutional neural networks for Chinese relation extraction;a study on improving end-to-end neural coreference resolution;type hierarchy enhanced heterogeneous network embedding for fine-grained entity typing in knowledge bases;scientific keyphrase extraction: Extracting candidates with semi-supervised data augmentation;using a Chinese lexicon to learn sense embeddings and measure semantic similarity;revisiting correlations between intrinsic and extrinsic evaluations of word embeddings;question-answering aspect classification with hierarchical attention network;syntax enhanced research method of stylistic features;end-to-end task-oriented dialogue system with distantly supervised knowledge base retriever;Attention-based CNN-BLSTM networks for joint intent detection and slot filling;multi-perspective fusion network for commonsense reading comprehension;a hierarchical hybrid neural network architecture for Chinese text summarization;TSABCNN: Two-stage attention-based convolutional neural network for frame identification;linked document classification by network representation learning;a word embedding transfer model for robust text categorization;review headline generation with user embedding;a joint model for sentiment classification and opinion words extraction;network representation learning based on community and text features;addressing domain adaptation for Chinese word segmentation with instances-based transfer learning;learning to detect verbose expressions in spoken texts;Medical knowledge attention enhanced neural model for named entity recognition in Chinese EMR;coherence-based automated essay scoring using self-attentio

关键词：

来源：评论

学校读者我要写书评

暂无评论

6th international conference on Big Data Analytics, BDA 2018

6th International Conference on Big Data Analytics, BDA 2018

引用

6th international conference on Big Data Analytics, BDA 2018

ISBN: (纸本)9783030047795

the proceedings contain 29 papers. the special focus in this conference is on Big Data Analytics. the topics include: Automated credibility assessment of web page based on genre;cbI: Improving credibility of user-generated content on facebook;a parallel approach to detect communities in evolving networks;modeling sparse and evolving data;polystore data management systems for managing scientific data-sets in big data archives;MPP SQL query optimization with RTCG;big data analytics framework for spatial data;an ingestion based analytics framework for complex event processing engine in internet of things;An energy-efficient greedy mapreduce scheduler for heterogeneous hadoop YARN cluster;blockchain-powered big data analytics platform;Analysis of narcolepsy based on single-channel EEG signals;formal Methods, artificial intelligence, big-data analytics, and knowledge engineering in medical care to reduce disease burden and health disparities;*** based soil N-P-K prediction model for soil and crop specific data: A predictive modelling approach;deep neural network based image captioning;oversample based large scale support vector machine for online class imbalance problem;using crowd sourced data for music mood classification;applying big data intelligence for real time machine fault prediction;PRISMO: Priority based spam detection using multi optimization;malware detection using machine learning and deep learning;spatial co-location pattern mining;humble data management to big data analytics/science: A retrospective stroll;Fusion of game theory and big data for AI applications;distributed financial calculation framework on cloud computing environment;testing concept drift detection technique on data stream;homogenous ensemble of time-series models for indian stock market.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semi-automated Testing of an Architectural Floor Plan Retrieval Framework: Quantitative and Qualitative Comparison of Semantic pattern-Based Matching Approaches 1

引用

6th international conference on pattern recognition Applications and Methods (ICPRAM)

作者： Sabri, Qamer Uddin Bayer, Johannes Ayzenshtadt, Viktor Bukhari, Syed Saqib Althoff, Klaus-Dieter Dengel, Andreas German Res Ctr Artificial Intelligence Trippstadter Str 122 D-67663 Kaiserslautern Germany Tech Univ Kaiserslautern POB 3049 D-67663 Kaiserslautern Germany Univ Hildesheim Inst Comp Sci Samelsonpl 1 D-31141 Hildesheim Germany

ISBN: (数字)9783319936475

ISBN: (纸本)9783319936475;9783319936468

Early design phases in architecture deal with the conceptualization of a building. During these phases, a high-level description of a building (usually coming from a contractor of costumer) is iteratively turned into a first floor plan layout. One established method for architects to get inspiration is the search of references from former building projects. However, this search is usually conducted manually (and therefore labor-intensive) nowadays. Hence, an automated search for similar architectural concepts is desired. In the course of this paper, case-based reasoning and (in)exact graph matching are utilized to construct an endto-end system for floor plan retrieval, accessible by a refined version of our design-supporting web interface. In our approach, a floor plan is modeled as a graph, where each room is represented as a node and the relations between rooms are modeled as edges. We use a set of high-level abstractions, so-called semantic fingerprints, to generate simplified graphs that are simple to match. the retrieval process itself is performed by three systems (case-based reasoning, exact graph matching and inexact graph matching), whose results are unified internally. We conducted several tests to show the deployment ability of our system: firstly, we run a stress-test for determining the computational limits our system can handle. Secondly, we tested our system qualitatively and showed that each retrieval system is superior in at least one search scenario. this paper is an extended version of [1]. In the paper at hand, we introduce a new feature that maps components of search queries to results and demonstrate this function by the means of a case study. Finally, we conducted an extended literature comparison of the case-based system in this area.

关键词： Graph matching Subgraph matching Graph isomorphism Architectural floor plan Case-based reasoning pattern recognition Query-result mapping

来源：评论

学校读者我要写书评

暂无评论

Design and application of electronic tongue system for orange juice quality detection using internet of things

Design and application of electronic tongue system for orang...

引用

6th international-Federation-of-Automatic-Control (IFAC) conference on Bio-Robotics (BIOROBOTICS)

作者： Ma, Zeliang Yin, Tingjia Gui, Tingting Wang, Zhiqiang Sun, Xia Li, Caihong Guo, Yemin Shandong Univ Technol Coll Comp Sci & Technol Zibo 255049 Peoples R China Shandong Univ Technol Coll Agr Engn & Food Sci Zibo 255049 Peoples R China

Imitating the mechanism of human taste perception, an electronic tongue (ET) system for orange juice quality detection based on internet of things was developed. the system consists of three parts: hand-held detection telininal, wireless communication system and cloud service platfoun. During the detection, the hand-held detection telininal was used to obtain taste "fingerprint" data from various kinds of juices based on large pulse scanning potential, and then transmitted these data to a cloud service platfoun through a wireless communication system, as well as the pattern recognition methods were utilized to analyze the data. Finally, the results were compared with the built-in "fingerprint" database of the beverage on the cloud platfoun so as to obtain the brand or adulteration infounation of the tested juice. In this study, the developed ET system was further used for the identification of orange juice brand and purity detection. Linear discriminant analysis (LDA) was applied to the qualitative analysis of orange juice with different brand, and the support vector machine (SVM) was used to quantitative forecast of orange juice purity. the result indicated that the LDA can effectively differentiate samples of orange juice with different brand, which the identification accuracy reached 100%;the SVM model possess a good quantitative prediction accuracy for orange juice purity with the root mean square error (RMSE) in prediction set reaching 0.0172. this system possessed the advantages of fast detection, simple operation, low cost, high stability as well as the result was easy to query. (C) 2018, IFAC (international Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： internet of things electronic tongue pattern recognition orange juice quality

来源：评论

学校读者我要写书评

暂无评论

Recognize Assyrian cuneiform characters by virtual dataset 6

Recognize Assyrian cuneiform characters by virtual dataset

引用

6th international conference on Information and Communication Technology and Accessibility (ICTA)

作者： Rahma, Abdul Monem S. Saeid, Ali Adel Hussien, Muhsen J. Abdul Univ Technol Baghdad Dept Comp Sci Baghdad Iraq

ISBN: (纸本)9781538613528;9781538644607

Cuneiform symbols represent a complex problem in pattern recognition, in particular for OCR (optical character recognition) due to challenges related to cuneiform-like character distortion and font heterogeneity. this paper proposes new approaches to recognise Assyrian cuneiform characters using OCR to classify the symbols. as a new way to recognize the Assyrian letters by dealing with symbols of complex character. the dataset utilised consists of 16 patterns to reflect all probabilities associated with each cuneiform symbol related to their shape and directions, assuming each character consists of a set of symbols. Polygon approximation techniques are used to generate feature vectors for the classification tasks. the proposed method obtains classification ratios up to 91% depending on the algorithm used for the feature vector.

关键词： Cuneiform polygon approximation dataset pattern recognition OCR

来源：评论

学校读者我要写书评

暂无评论

A simultaneous topic and sentiment classification of tweets 1

引用

9th international conference on Soft Computing and pattern recognition, SoCPaR 2017

作者： Hassan, Doaa Department of Computers and Systems National Telecommunication Institute 5 Mahmoud El Miligy Street 6th district-Nasr City Cairo Egypt

ISBN: (数字)9783319763576

ISBN: (纸本)9783319763569

Social networks have been an emerging technology for communication among billions of users. One of the most popular social networks is Twitter. the popularity of Twitter comes from its simplicity since it allows users to exchange messages of short length that does not exceed 140 characters and takes the form of tweets. In this paper, we propose a model for performing a classification of tweets posted by the Twitter user based on a mixture of the topic and sentiment of those tweets. the proposed approach is new in that it creates a model that combines the processes of topic and sentiment classification of tweets simultaneously. therefore, with this model, one can categorize tweets according to their topics and simultaneously assign them into different sentiments categories. the topic of the tweets in the basic experiment of the proposed approach is classified into five main different categories including: "political", "commercials", "educational", "religious", and "sportive". Meanwhile, the sentiment of those tweets is classified into three main different categories including "positive", "negative", "neutral". the effectiveness of the proposed approach is demonstrated on a real dataset that consists of various extracted tweets with different categories of topics and opinions. the empirical results show that our approach is very powerful in categorizing tweets according to topics and simultaneously assigning them into different sentiments categories. © Springer international Publishing AG, part of Springer Nature 2018.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Facial Image Attributes Transformation via Conditional Recycle Generative Adversarial Networks

引用

Journal of Computer Science & Technology 2018年第3期33卷 511-521页

作者： Huai-Yu Li Wei-Ming Dong Bao-Gang Hu National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China

this study introduces a novel conditional recycle generative adversarial network for facial attribute transfor- mation, which can transform high-level semantic face attributes without changing the identity. In our approach, we input a source facial image to the conditional generator with target attribute condition to generate a face with the target attribute. then we recycle the generated face back to the same conditional generator with source attribute condition. A face which should be similar to that of the source face in personal identity and facial attributes is generated. Hence, we introduce a recycle reconstruction loss to enforce the final generated facial image and the source facial image to be identical. Evaluations on the CelebA dataset demonstrate the effectiveness of our approach. Qualitative results show that our approach can learn and generate high-quality identity-preserving facial images with specified attributes.

关键词： generative adversarial network image editing facial attributes transformation

来源：评论

学校读者我要写书评

暂无评论

Advanced Technology and Social Media Influence on Research, Industry and Community 1

引用

6th IFIP international conference on Computational Intelligence and Its Applications (CIIA)

作者： Alhajj, Reda Univ Calgary Dept Comp Sci Calgary AB Canada

ISBN: (数字)9783319897431

ISBN: (纸本)9783319897431;9783319897424

the rapid development in technology and social media has gradually shifted the focus in research, industry and community from traditional into dynamic environments where creativity and innovation dominate various aspects of the daily life. this facilitated the automated collection and storage of huge amount of data which is necessary for effective decision making. Indeed, the value of data is increasingly realized and there is a tremendous need for effective techniques to maintain and handle the collected data starting from storage to processing and analysis leading to knowledge discovery. this chapter will cite our accomplished works which focus on techniques and structures which could maximize the benefit from data beyond what is traditionally supported. In the listed published work, we emphasized data intensive domains which require developing and utilizing advance computational techniques for informative discoveries. We described some of our accomplishments, ongoing research and future research plans. the notion of big data has been addressed to show how it is possible to process incrementally available big data using limited computing resources. the benefit of various data mining and network modeling mechanisms for data analysis and prediction has been addressed with emphasize on some practical applications ranging from forums and reviews to social media as effective means for communication, sharing and discussion leading to collaborative decision making and shaping of future plans.

关键词： Social media Social networks Data analysis Big data Frequent pattern mining Clustering bioinformatics

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：