文本检测最近文章检索（2）

期刊

1）Rotated cascade R-CNN: A shape robust detector with coordinate regression
旋转叶栅R-CNN：具有坐标回归的形状鲁棒检测器
Yixing Zhu; Chixiang Ma; Jun Du;
National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of China; Hefei; Anhui;
ABSTRACT:Abstract(#br)General object detection task mainly takes axis-aligned bounding-boxes as the detection outputs. To address more challenging scenarios, such as curved text detection and multi-oriented object detection in aerial images, we propose a novel two-stage approach for shape robust object detection. In the first stage, a locally sliding line-based point regression (LocSLPR) approach is presented to estimate the outline of the object, which is denoted as the intersections of the sliding line… 更多
摘要（#br）一般目标检测任务主要以轴对齐的边界框作为检测输出。为了解决更具挑战性的场景，例如航空文本中的弯曲文本检测和多方向目标检测，我们提出了一种新颖的两阶段方法来进行形状鲁棒的目标检测。在第一阶段，提出了一种基于局部滑动线的点回归（LocSLPR）方法来估计对象的轮廓，该轮廓表示为滑动线与对象边界框的交点。为了充分利用信息，我们仅对部分坐标进行回归，并根据滑尺计算剩余坐标。我们发现，与分段方法相比，使用较少的参数，回归可以实现更高的精度。在第二阶段 基于旋转叶栅区域的卷积神经网络（RCR-CNN）逐渐使目标物体回归，从而可以进一步改善系统性能。实验表明，我们的方法在几个四边形物体检测任务中均达到了最先进的性能。例如，我们的方法在ICPR 2018多类型Web图像的稳健阅读竞赛中获得0.796分，在文本检测任务中我们获得了第一名。该方法在ICPR 2018航空图像目标检测竞赛的任务1上也达到了69.2％的mAP，这是我们最好的单一模型，我们也获得了第一名。此外，该方法的性能优于弯曲文本数据集（CTW1500）上先前发布的最佳记录。可以进一步改善我们系统的性能。实验表明，我们的方法在几个四边形物体检测任务中均达到了最先进的性能。例如，我们的方法在ICPR 2018多类型Web图像的稳健阅读竞赛中获得0.796分，在文本检测任务中我们获得了第一名。该方法在ICPR 2018航空图像目标检测竞赛的任务1上也达到了69.2％的mAP，这是我们最好的单一模型，我们也获得了第一名。此外，该方法的性能优于弯曲文本数据集（CTW1500）上先前发布的最佳记录。可以进一步改善我们系统的性能。实验表明，我们的方法在几个四边形物体检测任务中均达到了最先进的性能。例如，我们的方法在ICPR 2018多类型Web图像的稳健阅读竞赛中获得0.796分，在文本检测任务中我们获得了第一名。该方法在ICPR 2018航空图像目标检测竞赛的任务1上也达到了69.2％的mAP，这是我们最好的单一模型，我们也获得了第一名。此外，该方法的性能优于弯曲文本数据集（CTW1500）上先前发布的最佳记录。在ICPR 2018多类型Web图像的稳健阅读竞赛中，第796位获得了文本检测任务的第一名。该方法在ICPR 2018航空图像目标检测竞赛的任务1上也达到了69.2％的mAP，这是我们最好的单一模型，我们也获得了第一名。此外，该方法的性能优于弯曲文本数据集（CTW1500）上先前发布的最佳记录。在ICPR 2018多类型Web图像的稳健阅读竞赛中，第796位获得了文本检测任务的第一名。该方法在ICPR 2018航空图像目标检测竞赛的任务1上也达到了69.2％的mAP，这是我们最好的单一模型，我们也获得了第一名。此外，该方法的性能优于弯曲文本数据集（CTW1500）上先前发布的最佳记录。 还原

关键词：目标检测 文字检测； 航空影像； 弯曲的文字； 旋转级联R-CNN；
KEYWORDS:Object detection; Text detection; Aerial images; Curved text; Rotated cascade R-CNN;
JOURNAL:Pattern Recognition
SOURCE:外文期刊
DOI:10.1016/j.patcog.2019.106964
YEAR:2019
PUBLISHER:Elsevier Ltd
2）Opinion community detection and opinion leader detection based on text information and network topology in cloud environment
云环境下基于文本信息和网络拓扑的意见社区检测和意见领袖检测
Chunlin Li; Jingpan Bai; Lei Zhang; Hengliang Tang; Youlong Luo;
Department of Computer Science, Wuhan University of Technology, Wuhan 430063, PR China; Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai 200241, PR China; School of Information, Beijing Wuzi University, Beijing 101149, PR China;
ABSTRACT:Abstract(#br)With the rapid development of web technology, the social networks have become the largest information portals. In the social platforms, the text information can effectively reflect the user opinions or the public opinions for a certain entity, such as company, celebrity service, product and so on. Therefore, mining user opinions from social networks have become an imperative requirement for the service groups. In this paper, an opinion community detection method is proposed by consi… 更多
摘要：摘要（#br）随着网络技术的飞速发展，社交网络已成为最大的信息门户。在社交平台上，文本信息可以有效地反映特定实体（例如公司，名人服务，产品等）的用户意见或公众意见。因此，从社交网络挖掘用户意见已成为服务组的当务之急。提出了一种考虑用户内容相似度，时间相似度和用户拓扑结构的意见社区检测方法。实现了两个用户之间的集成相似度，包括内容相似度，时间相似度和用户的拓扑结构。然后，基于综合的相似性，检测意见社区。此外，为了识别意见领袖，提出了一种基于用户影响力和情感分析的意见领袖检测方法。具有相同主题的用户形成意见社区。同时，创建一个有向图来表达意见社区中用户之间的交互关系。然后，提出了用户影响力模型和情绪分析模型。此外，在情绪分析模型中还考虑了否定词的出现频率。然后，建立了针对意见社区中每个用户的影响力值的模型。影响力值最高的用户被视为意见领袖。最后，在分布式计算环境中评估了所提出算法的性能。同时，进行了广泛的实验。结果表明，我们提出的意见社区检测算法可以有效地检测意见社区。而且，提出的意见领袖检测算法可以显着地识别社交网络中的意见领袖。 还原
KEYWORDS:Social networks; Opinion community detection; Opinion leader detection; Cloud computing;
JOURNAL:Information Sciences
SOURCE:外文期刊
DOI:10.1016/j.ins.2019.06.060
YEAR:2019
PAGES:61-83
PUBLISHER:Elsevier Inc.
3）Effectiveness of mobile phone text messaging in improving glycaemic control among persons with newly detected type 2 diabetes
手机短信在改善新发现的2型糖尿病患者血糖控制中的有效性
Ramachandran Vinitha; Arun Nanditha; Chamukuttan Snehalatha; Krishnamoorthy Satheesh; Priscilla Susairaj; Arun Raghavan; Ambady Ramachandran;
India Diabetes Research Foundation and Dr. A. Ramachandran’s Diabetes Hospitals; Chennai; India;
ABSTRACT:Abstract(#br)Aims(#br)The aim of the study was to evaluate the effect of text messaging as a tool to improve glycaemic control among newly diagnosed T2D patients in a 2 year period.(#br)Methods(#br)This is a multicentric, randomised controlled trial conducted in 2 states of India. The primary outcome was improvement in glycaemia measured by an HbA1c value of ≤7% (53 mmol/mol) with intervention. The secondary outcomes were changes in biochemical, dietary parameters and physical activity. Acceptab… 更多
摘要：摘要（Augs）目的（#br）该研究的目的是评估短信在2年内作为改善初诊T2D患者血糖控制的工具的效果。（＃br）方法（#br）这是在印度两个州进行的多中心，随机对照试验。主要结果是干预后HbA1c值≤7％（53 mmol / mol）测得的血糖改善。次要结果是生化，饮食参数和体育活动的变化。评估了短信的可接受性。入选诊断时HbA1c值≥6.5％（48 mmol / mol）的人。总共招募了248名平均年龄为43.3±8.7岁的参与者。对照组（n = 122）的参与者接受标准护理，干预组（n = 126）的参与者每周接受三次定制的短信。两组均在研究开始时接受了个人建议。（#br）结果（#br）两组的基线特征相似。与基线值相比，两组在24个月时均显示血压和血糖变量显着降低。干预组也显示LDLc明显降低。多变量分析表明，HbA1c的降低与干预措施有关。结论文本消息传递可以通过个人授权和持续的行为改变来改善血糖控制。干预组也显示LDLc明显降低。多变量分析表明，HbA1c的降低与干预措施有关。结论文本消息传递可以通过个人授权和持续的行为改变来改善血糖控制。干预组也显示LDLc明显降低。多变量分析表明，HbA1c的降低与干预措施有关。结论文本消息传递可以通过个人授权和持续的行为改变来改善血糖控制。 还原
KEYWORDS:Short messaging service; Newly diagnosed type 2 diabetes; Glycaemic control; MHealth; HbA1c;
JOURNAL:Diabetes Research and Clinical Practice
SOURCE:外文期刊
DOI:10.1016/j.diabres.2019.107919
YEAR:2019
PUBLISHER:Elsevier B.V.
4）Detecting substance-related problems in narrative investigation summaries of child abuse and neglect using text mining and machine learning
使用文本挖掘和机器学习在儿童虐待和忽视的叙述性调查摘要中发现与物质相关的问题
Brian E. Perron; Bryan G. Victor; Gregory Bushman; Andrew Moore; Joseph P. Ryan; Alex Jiahong Lu; Emily K. Piellusch;
Child and Adolescent Data Lab, University of Michigan, School of Social Work, 1080 S University Ave, Ann Arbor, MI, 48109, United States; Indiana University School of Social Work, 902 West New York Street Indianapolis, Indiana, 46202, United States; University of Michigan, School of Information, 105 S State St, Ann Arbor, MI, 48109, United States;
ABSTRACT:Abstract(#br)Background(#br)State child welfare agencies collect, store, and manage vast amounts of data. However, they often do not have the right data, or the data is problematic or difficult to inform strategies to improve services and system processes. Considerable resources are required to read and code these text data. Data science and text mining offer potentially efficient and cost-effective strategies for maximizing the value of these data.(#br)Objective(#br)The current study tests the … 更多
摘要：摘要（#br）背景（#br）州儿童福利机构收集，存储和管理大量数据。但是，它们通常没有正确的数据，或者数据存在问题或难以告知改善服务和系统流程的策略。需要大量资源来读取和编码这些文本数据。数据科学和文本挖掘为最大程度地提高这些数据的价值提供了潜在的有效且具有成本效益的策略。（＃br）目标（#br）本研究测试了使用文本挖掘从非结构化文本中提取信息以更好地理解实质的可行性。有关被虐待或被忽视的家庭之间的相关问题。（＃br）方法（#br）一家州儿童福利机构提供了有关虐待和被忽视儿童的调查的书面摘要。专家审查员根据案例工作者是否发现了与物质有关的问题，对2956年的调查摘要进行了编码。这些编码文件用于开发，训练和验证可以自动执行编码的计算机模型。（＃br）结果（#br）根据专家评审人员的判断，一组计算机模型的准确率超过90％ 。计算机模型和专家审阅者之间的Fleiss kappa估计值超过.80，表明专家审阅者评级可以与计算机模型互换。从非结构化文本数据中提取有意义的见解的有效解决方案。 还原
KEYWORDS:Text mining; Machine learning; Data science; Text classification; Child welfare; Substance misuse;
JOURNAL:Child Abuse & Neglect
SOURCE:外文期刊
DOI:10.1016/j.chiabu.2019.104180
YEAR:2019
PUBLISHER:Elsevier Ltd
5）Hot Events Detection of Stock Market Based on Time Series Data of Stock and Text Data of Network Public Opinion
基于股票时间序列数据和网络舆情文本数据的股市热点事件检测
作者:
Beibei Cao
作者背景:
Department of Publishing and Dissemination, Shanghai Publishing and Printing College, Shanghai, China
DOI:10.4236/jdaip.2019.74011
文章关键词:N/A
原文摘要:With the highly integration of the Internet world and the real world, Internet information not only provides real-time and effective data for financial investors, but also helps them understand market dynamics, and enables investors to quickly identify relevant financial events that may lead to stock market volatility. However, in the research of event detection in the financial field, many studies are focused on micro-blog, news and other network text information. Few scholars have studied the characteristics of financial time series data. Considering that in the financial field, the occurrence of an event often affects both the online public opinion space and the real transaction space, so this paper proposes a multi-source heterogeneous information detection method based on stock transaction time series data and online public opinion text data to detect hot events in the stock market. This method uses outlier detection algorithm to extract the time of hot events in stock market based on multi-member fusion. And according to the weight calculation formula of the feature item proposed in this paper, this method calculates the keyword weight of network public opinion information to obtain the core content of hot events in the stock market. Finally, accurate detection of stock market hot events is achieved.

随着Internet世界与现实世界的高度集成，Internet信息不仅为金融投资者提供了实时有效的数据，还帮助他们了解市场动态，并使投资者能够快速识别可能导致股票下跌的相关金融事件。市场动荡。但是，在金融领域的事件检测研究中，许多研究集中在微博客，新闻和其他网络文本信息上。很少有学者研究金融时间序列数据的特征。考虑到在金融领域，事件的发生通常会影响在线舆论空间和实际交易空间，为此，本文提出了一种基于股票交易时间序列数据和在线舆论文本数据的多源异构信息检测方法，以检测股票市场的热点事件。该方法采用离群检测算法，基于多成员融合提取股市热点事件的时间。并根据本文提出的特征项的权重计算公式，计算网络舆情信息的关键词权重，得到股市热点事件的核心内容。最终，实现了对股票市场热点事件的准确检测。并根据本文提出的特征项的权重计算公式，计算网络舆情信息的关键词权重，得到股市热点事件的核心内容。最终，实现了对股票市场热点事件的准确检测。并根据本文提出的特征项的权重计算公式，计算网络舆情信息的关键词权重，得到股市热点事件的核心内容。最终，实现了对股票市场热点事件的准确检测。
6）
Text emotion detection in social networks using a novel ensemble classifier based on Parzen Tree Estimator (TPE)
使用基于Parzen Tree Estimator（TPE）的新型集成分类器在社交网络中进行文本情感检测
作者： Fereshteh Ghanbari-Adivi, Mohammad Mosleh
作者单位： 1Department of Computer Engineering, Dezful Branch, Islamic Azad University
刊名： Neural Computing and Applications, 2019, Vol.31 (12), pp.8971-8983
来源数据库： Springer Nature Journal
DOI： 10.1007/s00521-019-04230-9
关键词： Sentiment analysis; Emotion classification; Ensemble classifier; Doc2Vector algorithm;
英文摘要： Abstract(#br)The texts often express the emotions of the writers or cause emotions in the readers. In recent years, the development of the social networks has made emotional analysis of texts into an attractive topic for research. A sentiment analysis system for automatic detection of fine-grained emotions in text consists of three main parts of preprocessing, feature extraction and classification. The main focus of this paper is on presenting a novel ensemble classifier that is consisted of 1500 of k-Nearest Neighbor, Multilayer Perceptron and Decision Tree basic classifiers, which is able to systematically distinguish different fine-grained emotions between regular and irregular sentences with a proper accuracy. Moreover, Tree-structured Parzen Estimator is employed to tune parameters of the basic classifiers. The preprocessing and feature extraction operations are performed by natural language processing tools (Tokenization and Lemmatization) and Doc2Vector algorithm, respectively. Three different sets of ISEAR, OANC and CrowdFlower are used to evaluate the proposed method, which consists of regular and irregular sentences. The evaluation results show that accuracies of the proposed ensemble classifier are 99.49 and 88.49% in the detection of regular and irregular sentences, respectively.
摘要（#br）文本经常表达作者的情感或引起读者的情感。近年来，社交网络的发展使文本的情感分析成为一个有吸引力的研究主题。一种用于自动检测文本中细粒度情绪的情感分析系统，包括预处理，特征提取和分类三个主要部分。本文的主要重点是提出一种新颖的整体分类器，该分类器由1500个k最近邻，多层感知器和决策树基本分类器组成，该分类器能够通过使用正确的准确性。此外，采用树状结构的Parzen估计器来调整参数基本分类器。预处理和特征提取操作分别由自然语言处理工具（令牌化和引词化）和Doc2Vector算法执行。该方法由ISEAR，OANC和CrowdFlower三个不同的集合评估，该方法由规则句子和不规则句子组成。评估结果表明，提出的集成分类器在规则和不规则句子检测中的准确率分别为99.49％和88.49％。
7）User group based emotion detection and topic discovery over short text
基于用户组的情感检测和短文本上的主题发现
作者： Jiachun Feng, Yanghui Rao, Haoran Xie, Fu Lee Wang, Qing Li
刊名： World Wide Web, 2019(prepublish), pp.1-35
来源数据库： Springer Nature Journal
DOI： 10.1007/s11280-019-00760-3
8）
Detecting substance-related problems in narrative investigation summaries of child abuse and neglect using text mining and machine learning.
使用文本挖掘和机器学习在儿童虐待和忽视的叙述性调查摘要中检测与物质相关的问题。
Perron Brian E; Victor Bryan G; Bushman Gregory; Moore Andrew; Ryan Joseph P; Lu Alex Jiahong; Piellusch Emily K;
Child and Adolescent Data Lab, University of Michigan, School of Social Work, 1080 S University Ave, Ann Arbor, MI, 48109, United States. Electronic address: [email protected].; Indiana University School of Social Work, 902 West New York Street Indianapolis, Indiana, 46202, United States.; University of Michigan, School of Information, 105 S State St, Ann Arbor, MI, 48109, United States.;
ABSTRACT:BACKGROUND(#br)State child welfare agencies collect, store, and manage vast amounts of data. However, they often do not have the right data, or the data is problematic or difficult to inform strategies to improve services and system processes. Considerable resources are required to read and code these text data. Data science and text mining offer potentially efficient and cost-effective strategies for maximizing the value of these data.(#br)OBJECTIVE(#br)The current study tests the feasibility o… 更多
KEYWORDS:Child welfare; Data science; Machine learning; Substance misuse; Text classification; Text mining;
JOURNAL:Child abuse & neglect
SOURCE:外文期刊
DOI:10.1016/j.chiabu.2019.104180
YEAR:2019
PAGES:104180
PUBLISHER:Pubmed
10）Automated Misspelling Detection and Correction in Persian Clinical Text.
波斯语临床文本中的自动拼写错误检测和更正
Yazdani Azita; Ghazisaeedi Marjan; Ahmadinejad Nasrin; Giti Masoumeh; Amjadi Habibe; Nahvijou Azin;
Department of Health Information Technology, School of Management and Information Sciences, Shiraz University of Medical Sciences, Shiraz, Iran.; Health Human Resources Research Center, School of Management and Information Sciences, Shiraz University of Medical Sciences, Shiraz, Iran.; Department of Health Information Management, School of Allied Medical Sciences, Tehran University of Medical Sciences(TUMS), Tehran, Iran.; Advanced Diagnostic and Interventional Radiology Research Center (ADIR), Tehran University of Medical Sciences (TUMS), Tehran, Iran.; Medical Imaging Center, Cancer Research Institute, Imam Khomeini Hospital, Tehran, Iran.; Breast Cancer Research Center, Cancer Institute, Tehran University of Medical Sciences (TUMS), Tehran, Iran.; Human Resource Department, Imam Hospital, Tehran University of Medical Sciences (TUMS), Tehran, Iran.; Cancer Research Center, Cancer Institute of Iran, Tehran University of;
ABSTRACT:Accurate electronic health records are important for clinical care, research, and patient safety assurance. Correction of misspelled words is required to ensure the correct interpretation of medical records. In the Persian language, the lack of automated misspelling detection and correction system is evident in the medicine and health care. In this article, we describe the development of an automated misspelling detection and correction system for radiology and ultrasound’s free texts in the Per… 更多
摘要：准确的电子健康记录对于临床护理，研究和患者安全保证至关重要。需要纠正拼写错误的单词，以确保正确理解医疗记录。用波斯语，在医学和卫生保健中明显缺乏自动拼写错误检测和纠正系统。在本文中，我们描述了针对波斯语放射学和超声免费文本的自动拼写错误检测和纠正系统的开发。为了实现我们的目标，我们使用了n-gram语言模型以及与腹部和骨盆超声，头颈部超声和乳房超声报告相关的三种不同类型的自由文本。我们的系统对放射学和超声的自由文本的检测性能高达90.29％，校正精度为88.56％。结果表明，在临床报告中可以进行高质量的拼写纠正。该系统还在文档编制过程和成像部门的报告最终批准过程中节省了大量资金。
KEYWORDS:N-gram language model; Natural language processing; Radiology reporting; Spelling correction; Ultrasound;
JOURNAL:Journal of digital imaging
SOURCE:外文期刊
DOI:10.1007/s10278-019-00296-y
YEAR:2019
PUBLISHER:Pubmed
11）Evaluation of Research Trends in Knowledge Management: A Hybrid Analysis through Burst Detection and Text Clustering
作者:
Babak Sohrabi,Iman Raeesi Vanani,Seyed Mohammad Jafar Jalali,Ehsan Abedin
作者背景:N/A
DOI:10.1142/S0219649219500436
文章关键词:Knowledge management,Burst detection analysis,Text clustering,Scientometrics
原文摘要:This paper aims to analyze the content of validated journal articles related to Knowledge Management (KM) in more than 18,000 papers of the Web of Science (WoS) database and then provide the most recent specific trends in KM field using text mining and burst detection to help researchers invest in the most challenging and fruitful areas of KM research domain. The method for finding the recent trend of KM includes the following steps: Conducting searches and collecting the publication data from WoS; using a hybrid analysis through burst detection and text clustering; also enriching and analyzing the results in order to achieve an overall perspective about the KM position and the popularity among researchers. This study could be valuable for researchers and KM specialists as well as managers as they may study the history of a subject by getting the structure of its scientific productions, so as to purposefully plan and determine the research priorities in KM.
本文旨在分析Web of Science（WoS）数据库的18,000多篇论文中与知识管理（KM）相关的经过验证的期刊文章的内容，然后使用文本挖掘和突发检测来提供KM领域的最新特定趋势，以期帮助研究人员在KM研究领域最具挑战性和成果丰硕的领域进行投资。查找KM最近趋势的方法包括以下步骤：进行搜索并从WoS收集发布数据；通过突发检测和文本聚类使用混合分析；还可以丰富和分析结果，以便对KM的位置和研究人员的受欢迎程度有一个整体的了解。
12）联合边界框校准的自然场景文本检测
方承志火兴龙程宥铖
南京邮电大学电子与光学工程学院
摘要：针对自然场景下多方向文本对象提出一种基于深度学习的文本检测方法。该方法在设计锚框时剥离锚框的方向特征但保留其长宽比特征，在覆盖相同长宽比范围时，锚框设计数量减少，从而缓解采样密集时正负样本类别失衡的影响。另外，在方法的后处理阶段，提出一种边界框校准算法，该算法利用最大稳定极值区域（MSER）获取字符边缘信息，通过基于规则的逻辑判断，对边界框进行收缩或膨胀操作，从而达到边界框校准目的。通过在公开数据集ICDAR2015上的测试与比较，验证了所提边界框校准算法的有效性。
基金：国家自然科学基金面上基金项目(No.61271334,No.61073115)；
关键词：文本检测; 自然场景; 类别失衡; 边界框校准;
分类号：TP391.1;TP18
13）Applying a deep learning-based sequence labeling approach to detect attributes of medical concepts in clinical text.
应用基于深度学习的序列标记方法来检测临床文本中医学概念的属性
Xu Jun; Li Zhiheng; Wei Qiang; Wu Yonghui; Xiang Yang; Lee Hee-Jin; Zhang Yaoyun; Wu Stephen; Xu Hua;
The University of Texas School of Biomedical Informatics, 7000 Fannin St Suite, Houston, TX, 600, USA.; College of Computer Science and Technology, Dalian University of Technology, Dalian, China.; Departments of Health Outcomes and Policy, College of Medicine, University of Florida, Gainesville, Florida, USA.; The University of Texas School of Biomedical Informatics, 7000 Fannin St Suite, Houston, TX, 600, USA. [email protected].;
ABSTRACT:BACKGROUND(#br)To detect attributes of medical concepts in clinical text, a traditional method often consists of two steps: named entity recognition of attributes and then relation classification between medical concepts and attributes. Here we present a novel solution, in which attribute detection of given concepts is converted into a sequence labeling problem, thus attribute entity recognition and relation classification are done simultaneously within one step.(#br)METHODS(#br)A neural archite… 更多
摘要：背景技术为了检测临床文本中医学概念的属性，传统方法通常包括两个步骤：命名属性的实体识别，然后医学概念​​与属性之间的关系分类。在这里，我们提出了一种新颖的解决方案，其中将给定概念的属性检测转换为序列标记问题，从而在一个步骤中同时完成属性实体的识别和关系分类。（＃br）METHODS（#br）结合双向的神经结构采用长短期记忆网络和条件随机字段（Bi-LSTMs-CRF）可以有效地检测各种医学概念属性对。然后，我们将基于深度学习的序列标记方法与传统的两步系统进行了比较，以完成三种不同的属性检测任务：疾病修饰符， 还原
KEYWORDS:Clinical notes; Information extraction; Natural language processing;
JOURNAL:BMC medical informatics and decision making
SOURCE:外文期刊
DOI:10.1186/s12911-019-0937-2
YEAR:2019
PAGES:236
PUBLISHER:Pubmed
14）Applying a deep learning-based sequence labeling approach to detect attributes of medical concepts in clinical text
基于深度学习的序列标记方法在医学概念属性检测中的应用
作者： Jun Xu, Zhiheng Li, Qiang Wei, Yonghui Wu, Yang Xiang, Hee-Jin Lee, Yaoyun Zhang, Stephen Wu, Hua Xu
作者单位： 1The University of Texas School of Biomedical Informatics, 7000 Fannin St Suite, 600, Houston, TX, USA
2College of Computer Science and Technology, Dalian University of Technology, Dalian, China
3Departments of Health Outcomes and Policy, College of Medicine, University of Florida, Gainesville, Florida, USA
刊名： BMC Medical Informatics and Decision Making, 2019, Vol.19 (Suppl 11), pp.385-518
来源数据库： Springer Nature Journal
DOI： 10.1186/s12911-019-0937-2
关键词： Information extraction; Natural language processing; Clinical notes;
英文摘要： Abstract(#br)Background(#br)To detect attributes of medical concepts in clinical text, a traditional method often consists of two steps: named entity recognition of attributes and then relation classification between medical concepts and attributes. Here we present a novel solution, in which attribute detection of given concepts is converted into a sequence labeling problem, thus attribute entity recognition and relation classification are done simultaneously within one step. Methods(#br)A neural architecture combining bidirectional Long Short-Term Memory networks and Conditional Random fields (Bi-LSTMs-CRF) was adopted to detect various medical concept-attribute pairs in an efficient way. We then compared our deep learning-based sequence labeling approach with traditional two-step…
15）Automatically detect diagnostic patterns based on clinical notes through Text Mining通过文本挖掘基于临床笔记自动检测诊断模式
João Ribeiro; Júlio Duarte; Filipe Portela; Manuel F. Santos;
Department of Information Systems, University of Minho, Campus de Azurém, Guimarães 4800-058, Portugal; Centro Algoritmi, University of Minho, Campus de Azurém, Guimarães 4800-058, Portugal;
ABSTRACT:Abstract(#br)The importance of standardized treatment for patients is huge because it can reduce waiting times, costs in hospitals and make treatment more effective for patients. According to these patterns, the creation of a tool that can make the admission and interpretation of free text will become an important step in the medical field. For the analysis of the unstructured text, the “RapidMiner” tool was used. Following the text analysis, the word frequency technique will be used in the repo… 更多
KEYWORDS:Text Mining; Text Analysis;
JOURNAL:Procedia Computer Science
SOURCE:外文期刊
DOI:10.1016/j.procs.2019.11.027
YEAR:2019
PAGES:684-689
PUBLISHER:Elsevier B.V.
16）Detection of medical text semantic similarity based on convolutional neural network基于卷积神经网络的医学文本语义相似度检测
作者： Tao Zheng, Yimei Gao, Fei Wang, Chenhao Fan, Xingzhi Fu, Mei Li, Ya Zhang, Shaodian Zhang, Handong Ma
来源数据库： Springer Nature Journal
DOI： 10.1186/s12911-019-0880-2
17）A hybrid approach to detecting technological recombination based on text mining and patent network analysis
基于文本挖掘和专利网络分析的技术重组检测方法
作者： Xiao Zhou, Lu Huang, Yi Zhang, Miaomiao Yu
作者单位： 1School of Economics and Management, Xidian University
2School of Management and Economics, Beijing Institute of Technology
3Centre for Artificial Intelligence, Faculty of Engineering and Information Technology, University of Technology Sydney
刊名： Scientometrics, 2019, Vol.121 (2), pp.699-737
来源数据库： Springer Nature Journal
DOI： 10.1007/s11192-019-03218-5
关键词： Patent network analysis; The structure of science revolutions; Bibliometrics; Text mining; Technological recombination; Artificial intelligence;
英文摘要： Abstract(#br)Detecting promising technology groups for recombination holds the promise of great value for R&D managers and technology policymakers, especially if the technologies in question can be detected before they have been combined. However, predicting the future is always easier said than done. In this regard, Arthur’s theory (The nature of technology: what it is and how it evolves, Free Press, New York, 2009) on the nature of technologies and how science evolves, coupled with Kuhn’s theory of scientific revolutions (Kuhn in The structure of scientific revolutions, 1st edn, University of Chicago Press, Chicago, p 3, 1962), may serve as the basis of a shrewd methodological framework for forecasting recombinative innovation. These theories help us to set out quantifiable criteria and…
18）Detection of Diplophonation in Audio Recordings of German Standard Text Readings.
Aichinger Philipp; Schoentgen Jean;
Division of Phoniatrics-Logopedics, Department of Otorhinolaryngology, Medical University of Vienna, Vienna, Austria. Electronic address: [email protected].; Department of Bio-, Electro-and Mechanical Systems (BEAMS), Faculty of Applied Sciences, Université libre de Bruxelles, Brussels, Belgium.;
ABSTRACT:OBJECTIVES(#br)Diplophonia is a common symptom of voice disorder that is in need of objectification. We investigated whether diplophonia can be detected from audio recordings of text readings by means of dedicated audio signal processing, ie, a descendant of a formerly published “Diplophonia Diagram.”(#br)STUDY DESIGN(#br)Diagnostic study.(#br)METHODS(#br)Forty subjects were included who had been clinically rated in the past as diplophonic. For each subject, the audio signal of the German standa… 更多
KEYWORDS:Audio recordings; Detection; Diplophonia; Running speech; Signal processing; Standard text readings;
JOURNAL:Journal of voice : official journal of the Voice Foundation
SOURCE:外文期刊
DOI:10.1016/j.jvoice.2018.06.00
YEAR:2019
PAGES:949.e1-949.e10
PUBLISHER:Pubmed