检索结果-南通市图书馆

Distinct but correct: generating diversified and entity-revised medical response

Science China(Information Sciences) 2024年第3期67卷 94-113页

作者： Bin li Bin SUN shutao li Encheng CHEN Hongru liU Yixuan WENG Yongping BAI Meiling HU College of Electrical and Information Engineering Hunan University School of Mathematics Sun Yat-sen University JD Technology National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of Sciences Xiangya Hospital of Central South University Teaching and Research Section of Clinical Nursing Xiangya Hospital of Central South University

Medical dialogue generation(MDG) is applied for building medical dialogue systems for intelligent consultation. Such systems can communicate with patients in real time, thereby improving the efficiency of clinical diagnosis. However, predicting correct entities and correctly generating distinct responses remain a great challenge. Inspired by actual doctors’ responses to patients, we consider MDG a two-stage task: entity prediction and dialogue generation. For entity prediction, we design an ent-mac post pre-training strategy by leveraging external medical entity knowledge to enhance the pre-trained model. For dialogue generation, we propose an entity-aware fusion MDG method in which predicted entities are integrated into the dialogue generation model through different encoding fusion mechanisms, using information from different sources. Because the diverse beam search algorithm can produce responses with entities that deviate from the predicted entities, an entity-revised diverse beam search is proposed to correct the entities entailed in the generated responses and make the generated responses more distinct. The experimental results on the China Conference on Knowledge Graph and Semantic Computing 2021(A/B tests) and the International Conference on Learning Representations 2021(online test) datasets show that the proposed method outperforms several state-of-the-art methods, which demonstrates its practicability and effectiveness.

关键词： medical entity prediction ent-mac post pre-training strategy entity-aware fusion medical dialogue generation encoding fusion mechanism entity-revised diverse beam search

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Analysis of The Correlation Between inhA Gene Mutation and Resistance to Protionamide in Drug-Resistant Mycobacterium Tuberculosis

引用

Journal of Clinical and Nursing Research 2024年第4期8卷 132-136页

作者： Xulin Huang Tian Zheng shutao li Xinjiang Uygur Autonomous Region Infectious Disease Hospital(Sixth People’s Hospital of the Autonomous Region) Urumqi 830063China The Eighth Affiliated Hospital of Xinjiang Medical University Urumqi 830000China

Objective: To investigate the characteristics of katG and inhA gene mutations in multidrug-resistant tuberculosis (MDR-TB), pre-extensively drug-resistant tuberculosis (preXDR-TB), and their correlation with resistance to protionamide (Pto). Methods: A total of 229 patients with MDR-TB and pre-XDR-TB diagnosed in the Eighth Affiliated Hospital of Xinjiang Medical University from January 2020 to February 2024 were selected to analyze the characteristics of katG and inhA mutations in MTB clinical isolates and their correlation with Pto resistance. Results: The mutation rate of katG (with or without inhA mutation) was 85.2%. The mutation rates in MDR-TB and pre-XDR-TB were 87.4% (125/143) and 81.4% (70/86), respectively. The mutation rate of inhA (including katG mutation) was 14.8% (34/229), which was 12.6% (18/143) and 18.6% (16/86) in MDR-TB and pre-XDR-MTB, respectively. There was no difference in mutation (P > 0.05). Conclusion: The total resistance rate to Pto in 229 strains was 8.7% (20/229), which was 8.4% (12/143) and 9.3% (8/86) in MDR-TB and pre-XDR-TB, respectively. Among the inhA mutant strains, 13 were resistant to the Pto phenotype, and the resistance rate was 65% (13/20). In MDR-TB and pre-XDR-TB strains resistant to Pto, inhA gene mutations occurred in 66.7% (6/9) and 63.6% (7/11), respectively. The resistance rates of MDR-MTB and pre-XDR-TB strains without inhA gene mutation to Pto were 2.4% (3/125) and 5.7% (4/70), respectively.

关键词： Tuberculosis Anti-multiple drug resistance Prothionamide Gene Mutations

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

考虑晶体取向的Al_(0.3)CoCrFeNi高熵合金动态力学性能研究

引用

爆炸与冲击 2024年第3期44卷 2-26页

作者：陈嘉琳李述涛陈叶青军事科学院国防工程研究院北京100036

鉴于高熵合金材料(high-entropy alloy,HEA)在高应变率动态响应下呈现不同的破坏模式及力学性能,其潜在机理从宏观角度已不能够完全解释,需从微观角度研究其动态响应过程中的原子结构变化、位错分布变化、演变机理及变形机制,为优化HEA... 详细信息

鉴于高熵合金材料(high-entropy alloy,HEA)在高应变率动态响应下呈现不同的破坏模式及力学性能,其潜在机理从宏观角度已不能够完全解释,需从微观角度研究其动态响应过程中的原子结构变化、位错分布变化、演变机理及变形机制,为优化HEA防护材料的加工工艺、制备方法等提供参考。利用分子动力学模拟的方法,设计了[100]、[110]和[111]等3种取向结构的Al_(0.3)CoCrFeNi高熵合金在不同应变率下的压缩、拉伸及冲击试验,分析了动态响应过程中原子结构变化、位错分布变化、演变机理及变形机制。压缩试验中:[110]取向结构的Al_(0.3)CoCrFeNi高熵合金的屈服强度最高,[111]的次之,[100]的最低;[100]取向结构的Al_(0.3)CoCrFeNi高熵合金主要的变形机制为孪晶变形,[110]的为滑移变形,[111]的为位错变形。拉伸试验中:[111]取向结构的Al_(0.3)CoCrFeNi高熵合金的屈服强度最高,[100]的次之,[110]的最低;[100]取向结构Al_(0.3)CoCrFeNi高熵合金拉伸过程中孪晶结构较多,[110]取向结构的Al_(0.3)CoCrFeNi高熵合金产生较规则的密排六方结构滑移面,[111]取向结构的Al_(0.3)CoCrFeNi高熵合金不会产生任何滑移面。随着应变率的升高,3种取向结构的Al_(0.3)CoCrFeNi高熵合金压缩和拉伸屈服强度均大幅度提高,对应伸长量增大。较低应变率(1×109 s^(−1))下的塑性变形机制主要为滑移变形,但滑移系较少;中应变率(1×10^(10)s^(−1))下的塑性变形机制是以滑移为主的变形机制,但滑移系较多;高应变率(1×10^(11)s^(−1))下的塑性变形机制是由原子排列无序化的非晶原子诱导的变形。[110]取向结构的Al_(0.3)CoCrFeNi高熵合金的抗冲击性能最好,与其具有最高的屈服强度,并且在屈服结束阶段也能保持最高的应力有关。

关键词：晶体取向高熵合金变形机制微观演变分子动力学

来源：

维普期刊数据库

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

适应复杂区域的时序SAR影像洪水监测与分析

引用

遥感学报 2024年第2期28卷 346-358页

作者：李聪妤刘家奇刘欣鑫李树涛康旭东湖南大学电气与信息工程学院长沙410082

洪涝灾害对中国沿湖沿江地带的国家经济和人民财产威胁巨大。针对洪涝灾害期间光学影像质量低,单幅SAR (Synthetic Aperture Radar)影像水体提取多依赖经验阈值且可靠性不足等问题,本文提出了一种适应复杂区域的时序SAR影像洪水监测方... 详细信息

洪涝灾害对中国沿湖沿江地带的国家经济和人民财产威胁巨大。针对洪涝灾害期间光学影像质量低,单幅SAR (Synthetic Aperture Radar)影像水体提取多依赖经验阈值且可靠性不足等问题,本文提出了一种适应复杂区域的时序SAR影像洪水监测方法。为获取完整的洪水淹没区域,首先结合影像序列的统计分析结果,设计了两个归一化差异指数——突出临时洪水的淹没范围提取指数SREI (Submerged Range Extraction Index)和突出矮植被覆盖的植被区淹没范围提取指数SRVEI (Submerged Range in Vegetation area Extraction Index);然后,根据同一区域植被季候性分布较为稳定的前提,给出了阈值的自适应选取方式;最后,考虑中国湖泊周围地物特点,构建了适应的后处理过程,优化提取区域,形成了洪水淹没区域提取与监测的详细流程和通用框架。本文以东洞庭湖流域为主要研究区域验证了方法的提取精度,并在此基础上进行了2020年东洞庭湖流域洪涝灾害态势分析和洪水淹没地物分析,展示了方法在洪涝灾害监测评估上的应用性能。另外,本文还将该方法应用于东洞庭湖流域往年数据,进行了汛期洪水淹没范围年际分析,并添加了同年鄱阳湖洪水淹没区域的实验,验证了方法时空应用的稳定性。相关实验结果表明,本文方法对洪水淹没区域的提取精度高,用户依赖性低,可跨越时空地应用于不同洪水淹没区域监测场景,且可以初步区分不同属性的洪水淹没范围,能够为本文涉及区域及其他区域的洪涝灾害监测、评估和预警提供一定的参考。

关键词：洪涝灾害合成孔径雷达时序监测水文遥感 SAR 洞庭湖

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Black phosphorus-based heterostructures for photocatalysis and photoelectrochemical water splitting

引用

Journal of Energy Chemistry 2022年第4期31卷 745-779页

作者： shutao li Yihe Zhang Hongwei Huang Beijing Key Laboratory of Materials Utilization of Nonmetallic Minerals and Solid Wastes and School of Materials Science and Technology China University of GeosciencesBeijing 100083China

Semiconductor-based photocatalytic and photoelectrochemical(PEC) processes can convert solar energy into high-density chemical energy or for the treatment of environmental pollutants, which are ideal ways to deal with environmental and energy crises. The development of high-efficiency photocatalysts and photoelectrodes is the key to the in-depth development and practical application of the two *** phosphorus(BP) has excellent physicalcochemical properties such as adjustable band gap, high carrier mobility, large specific surface area and anisotropy, making it one of the most promising ***-based heterostructure can not only realize the effective separation of photogenerated carriers but also improve the stability of BP, and is widely used in photocatalytic and PEC reactions. In this review, we first introduce the crystal structure, band structure, anisotropy, and preparation of BP with different dimensions(bulk, zero-dimension and two-dimension). Then, according to the transfer path of the photogenerated carriers and the components, the BP-based heterostructures are divided into type I heterojunction, type II heterojunction, Z-scheme heterojunction, S-scheme heterojunction, BP/carbonbased material heterostructure, BP/metal heterostructure and multi-component *** are the diverse photocatalytic applications of BP-based heterostructure, such as water splitting and CO_(2)reduction, N_(2)fixation, pollutant degradation, photothermal and photodynamic ***, some concluding views and opinions are stated on the challenges and opportunities faced by the further development of BP-based heterostructures in photocatalysis and PEC water splitting.

关键词： Black phosphorus Heterostructure Photocatalysis Photoelectrochemical water splitting

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

带壳装药毁伤元威力参数计算方法

引用

振动与冲击 2024年第13期43卷 25-34页

作者：张生李述涛王振清陈叶青军事科学院国防工程研究院北京100036 哈尔滨工程大学航天与建筑工程学院哈尔滨150001

带壳装药爆炸后将产生冲击波、破片等毁伤元,提高毁伤元威力参数计算精度对于武器破坏效应和工程防护研究都具有重要意义。为提高破片与冲击波威力参数的计算精度,通过分析带壳装药爆炸能量的分布规律,基于修正的能量守恒方程提出了一... 详细信息

带壳装药爆炸后将产生冲击波、破片等毁伤元,提高毁伤元威力参数计算精度对于武器破坏效应和工程防护研究都具有重要意义。为提高破片与冲击波威力参数的计算精度,通过分析带壳装药爆炸能量的分布规律,基于修正的能量守恒方程提出了一种更精确的破片初速计算公式;采用等效药量转换方法来计算带壳装药爆炸产生冲击波的等效药量,通过分析带壳装药初始冲击波的形成过程,建立了冲击波威力参数的理论计算模型,通过试验数据验证了计算模型的科学性和可靠性;通过已建立的理论模型推导得出两种毁伤元重叠时与爆源距离的计算公式,并量化分析了影响因素。研究表明,该计算方法的精度优于传统的毁伤元威力参数计算方法,破片初速、冲击波超压峰值、波阵面到达时间与试验的误差分别为3.0%、4.9%、1.1%;破片弹幕与冲击波波阵面重叠时的运动距离与炸药能量(炸药爆热)成正比,与壳体厚度(装药质量比)成反比。

关键词：带壳装药破片冲击波威力参数

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Learning the external and internal priors for multispectral and hyperspectral image fusion

引用

Science China(Information Sciences) 2023年第4期66卷 64-78页

作者： shutao li Renwei DIAN Haibo liU College of Electrical and Information Engineering Hunan University School of Robotics Hunan University

Recently, multispectral image(MSI) and hyperspectral image(HSI) fusion has been a popular topic in high-resolution HSI acquisition. This fusion leads to a challenging underdetermined problem, which image priors are used to regularize, aiming at improving fusion accuracy. To fully exploit HSI priors, this paper proposes two kinds of priors, i.e., external priors and internal priors, to regularize the fusion *** external prior represents the general image characteristics and is learned from abundant training data by using a Gaussian denoising convolutional neural network(CNN) trained in the additional gray images. An internal prior represents the unique characteristics of the HSI and MSI to be fused. To learn the external prior, we first segment the MSI into several superpixels and then enforce a low-rank constraint for each superpixel, which can well model local similarities in the HSI. In addition, to model a low-rank property in the spectral mode, the high-resolution HSI is decomposed into a low-rank spectral basis and ***, we formulate the fusion as an external and internal prior-regularized optimization problem, which is efficiently tackled through the alternating direction method of multipliers. Experiments on simulated and real datasets demonstrate the superiority of the proposed method.

关键词： multispectral and hyperspectral image fusion external and internal prior learning high-resolution hyperspectral imaging

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Self-supervised learning-based oil spill detection of hyperspectral images

引用

Science China(Technological Sciences) 2022年第4期65卷 793-801页

作者： DUAN PuHong XIE ZhuoJun KANG XuDong li shutao College of Electrical and Information Engineering Hunan UniversityChangsha 410082China Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province Changsha 410082China

Oil spill monitoring in remote sensing field has become a very popular technology to detect the spatial distribution of polluted ***,previous studies mainly focus on the supervised detection technologies,which requires a large number of high-quality training *** solve this problem,we propose a self-supervised learning method to learn the deep neural network from unlabelled hyperspectral data for oil spill detection,which consists of three parts:data augmentation,unsupervised deep feature learning,and oil spill detection ***,the original image is augmented with spectral and spatial transformation to improve robustness of the self-supervised ***,the deep neural networks are trained on the augmented data without label information to produce the high-level semantic ***,the pre-trained parameters are transferred to establish a neural network classifier to obtain the detection result,where a contrastive loss is developed to fine-tune the learned parameters so as to improve the generalization ability of the proposed *** performed on ten oil spill datasets reveal that the proposed method obtains promising detection performance with respect to other state-of-the-art hyperspectral detection approaches.

关键词： hyperspectral image self-supervised learning data augmentation oil spill detection contrastive loss

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

新疆结核病患者N-乙酰基转移酶2基因分型特征分析

引用

新疆医学 2024年第5期54卷 527-529,540页

作者：黄旭林李树涛新疆医科大学第八附属医院乌鲁木齐830049

目的研究新疆结核病患者N-乙酰基转移酶2基因(NAT2)多态性分布特点。方法纳入诊断为肺结核的132例患者为研究对象,应用多通道荧光定量分析仪测定NAT2基因多态性。所获取的数据采用χ^(2)检验,比较各组间基因型分布差异,以P0.05)。结论... 详细信息

目的研究新疆结核病患者N-乙酰基转移酶2基因(NAT2)多态性分布特点。方法纳入诊断为肺结核的132例患者为研究对象,应用多通道荧光定量分析仪测定NAT2基因多态性。所获取的数据采用χ^(2)检验,比较各组间基因型分布差异,以P0.05)。结论我区结核病患者NAT2基因多态性以中间乙酰化型为主,NAT2基因多态性在不同性别、年龄段及地区的结核患者中的分布无显著差异。

关键词：结核病 N-乙酰基转移酶2 基因多态性异烟肼

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Graph-matching-based character recognition for Chinese seal images

引用

Science China(Information Sciences) 2019年第9期62卷 37-50页

作者： Bin SUN Shaojun HUA shutao li Jun SUN College of Electrical and Information Engineering Hunan University Information Department Fujitsu Research and Develop Center

Recognizing characters in Chinese seal images is important when researching ancient cultural artworks because the seals may contain critical historical information. However, owing to large intraclass variance and a limited number of training samples, recognizing such characters in Chinese seals is ***, this study proposes a graph-matching-based method to recognize characters in historical Chinese seal images. In the proposed method, a Chinese seal character is first modeled as a graph representing its underlying geometric structure. Then, two affinity matrices that measure the similarity of nodes and edge pairs are calculated with their local features. Finally, a correspondence matrix is calculated using a graph matching algorithm and the most similar reference is selected as the recognition result. Compared with several existing classification methods for seal image recognition, the proposed graph-matching-based method achieves better results, particularly in the case of limited samples.

关键词： graph model Chinese seal character recognition graph matching

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：