A method for improving the accuracy of automatic indexing of Chinese-English mixed documents

Purpose: The thrust of this paper is to present a method for improving the accuracy of automatic indexing of Chinese-English mixed documents.Design/methodology/approach: Based on the inherent characteristics of Chinese-English mixed texts and the cybernetics theory,we proposed an integrated control method for indexing documents. It consists of 'feed-forward control','in-progress control' and 'feed-back control',aiming at improving the accuracy of automatic indexing of Chinese-English mixed documents. An experiment was conducted to investigate the effect of our proposed method.Findings: This method distinguishes Chinese and English documents in grammatical structures and word formation rules. Through the implementation of this method in the three phases of automatic indexing for the Chinese-English mixed documents,the results were encouraging. The precision increased from 88.54% to 97.10% and recall improved from97.37% to 99.47%.Research limitations: The indexing method is relatively complicated and the whole indexing process requires substantial human intervention. Due to pattern matching based on a bruteforce(BF) approach,the indexing efficiency has been reduced to some extent.Practical implications: The research is of both theoretical significance and practical value in improving the accuracy of automatic indexing of multilingual documents(not confined to Chinese-English mixed documents). The proposed method will benefit not only the indexing of life science documents but also the indexing of documents in other subject areas.Originality/value: So far,few studies have been published about the method for increasing the accuracy of multilingual automatic indexing. This study will provide insights into the automatic indexing of multilingual documents,especially Chinese-English mixed documents.

Multi-source information fused generative adversarial network model and data assimilation based history matching for reservoir with complex geologies

For reservoirs with complex non-Gaussian geological characteristics,such as carbonate reservoirs or reservoirs with sedimentary facies distribution,it is difficult to implement history matching directly,especially for the ensemble-based data assimilation methods.In this paper,we propose a multi-source information fused generative adversarial network(MSIGAN)model,which is used for parameterization of the complex geologies.In MSIGAN,various information such as facies distribution,microseismic,and inter-well connectivity,can be integrated to learn the geological features.And two major generative models in deep learning,variational autoencoder(VAE)and generative adversarial network(GAN)are combined in our model.Then the proposed MSIGAN model is integrated into the ensemble smoother with multiple data assimilation(ESMDA)method to conduct history matching.We tested the proposed method on two reservoir models with fluvial facies.The experimental results show that the proposed MSIGAN model can effectively learn the complex geological features,which can promote the accuracy of history matching.

Underwater Image Bidirectional Matching for Localization Based on SIFT

为识别的目的 SWATH (小 Waterplane 区域双胞胎的赫尔) 严厉有效地并且完善 SWATH 轮船鈥檚 表演的察觉技术，这份报纸基于规模论述新奇双向图象登记策略和 mosaicing 技术不变的特征变换(筛) 算法。建议方法能帮助我们观察与为分析 SWATH 的控制鳍的性能的一个大视觉角度严厉。筛是规模，旋转和照明的最有效的本地特征之一不变。然而，在这个算法有一些假火柴率。以在水下机器视觉，仅仅由获得一个精确火柴率罐头，我们发现一在水下机器人很快并且识别目标的地点。第一，因此，火柴比率原则的选择在这份报纸被提出；第二，双向登记算法的一些优点被分析单向性的匹配方法的特征结束。最后，一自动在水下图象拼接方法根据图象的固定尺寸，然后边被建议鈥檚 重叠节被主要部件分析算法合并。试验性的结果完成更好的登记和光滑的 mosaicing 效果，证明建议方法是有效的。

Automatic Recognition Method for Optical Measuring Instruments Based on Machine Vision

Based on a comprehensive study of various algorithms, the automatic recognition of traditional ocular optical measuring instruments is realized. Taking a universal tools microscope(UTM) lens view image as an example, a 2-layer automatic recognition model for data reading is established after adopting a series of pre-processing algorithms. This model is an optimal combination of the correlation-based template matching method and a concurrent back propagation(BP) neural network. Multiple complementary feature extraction is used in generating the eigenvectors of the concurrent network. In order to improve fault-tolerance capacity, rotation invariant features based on Zernike moments are extracted from digit characters and a 4-dimensional group of the outline features is also obtained. Moreover, the operating time and reading accuracy can be adjusted dy-namically by setting the threshold value. The experimental result indicates that the newly developed algorithm has optimal recognition precision and working speed. The average reading ratio can achieve 97.23%. The recognition method can automatically obtain the results of optical measuring instruments rapidly and stably without modifying their original structure, which meets the application requirements.

THE INFLUENCE OF SPECKLE ON HIGH RESOLUTION RANGE PROFILE RECOGNITION BASED ON THE MATCHING SCORE

Template database is the key to radar automation target recognition based on High Resolution Range Profile (HRRP). From the traditional perspective, average HRRP is a valid template for it can represent each HRRP without scatterer Moving Through Range Cell (MTRC). However, template database based on this assumption is always challenged by measured data. One reason is that speckle happens in the frame without scatterer MTRC. Speckle makes HRRP fluctuate sharply and not match well with the average HRRP. We precisely introduce the formation mechanism of speckle. Then, we make an insight into the principle of matching score. Based on the conclusion, we study the properties of matching score between speckled HRRP and the average HRRP. The theoretical analysis and Monte Carlo experimental results demonstrate that speckle makes HRRP not to match well with the average HRRP according to the energy ratio of speckled scatterers. On the assumption of ideal scattering centre model, speckled HRRP has a matching score less than 85% with the average HRRP if speckled scatterers occupy more than 50% energy of the target.

城市轨道交通全自动运行线路多专业速度控制与匹配设计研究

城市轨道交通多专业间的协调性是决定能否充分实现预期能力、发挥投资效益的关键环节,列车运行速度是其中一个重要方面,是城市轨道交通技术装备、技术标准、运营管理水平的重要标志。针对不同专业速度控制存在的重叠防护问题,通过剖析通信、信号、车辆、线路、环境等对全自动运行(FAO)线路列车运行速度的限制,提出列车自动运行(ATO)模式、列车自动防护(ATP)模式、蠕动模式和洗车模式4种典型运行模式下的速度匹配控制方案,讨论了根据线路等级速度拟定正线区间结构设计速度、车辆构造速度、车辆超速防护触发速度、车辆最大动态包络线计算速度、最高ATP顶篷速度、最高ATO目标速度的方法,并给出多专业匹配设计关键速度建议值。同时借助仿真手段,结合不同站间距设置与最短时间速度曲线计算,进一步针对速度等级为80,100 km/h以及120 km/h的线路分别讨论了站间距的匹配设计,建议三者站间距分别不少于1.0,1.4 km以及2.5 km。开展多专业速度控制与匹配设计的优化,有助于最大化发挥系统和设备性能,保证线路整体运营水平。

BIM模型编码可变性检验与自动匹配方法研究

为解决BIM元素变更导致的Web-BIM系统数据库与BIM元素无法匹配的问题,本研究首先根据各类BIM文件的特点,选择Rvt文件作为编辑BIM文件,选择Gltf文件作为Web端加载文件。对BIM模型的编码可变性进行了验证,结果表明对BIM构件尺寸修改、属性修改、位置移动等操作均不会改变构件的编码;若对BIM构件进行删除,该构件会被赋予新的编码,但其他构件的编码均不会被影响。本研究提出一种BIM模型变更前后自动匹配方法,通过建立元素识别和跟踪数据库、元素匹配算法、用户交互及确认、更新质量信息、定期检查等步骤,可以实现BIM模型变更前后Web端与BIM元素的匹配,为建筑项目的管理提供了有力的工具。

左氧氟沙星致心律失常的发生特点和危险因素分析

目的 了解大样本住院人群中左氧氟沙星致心律失常的发生特点、临床表现和相关危险因素。方法 借助“临床药品不良事件主动监测与智能评估警示系统-Ⅱ”(ADE-ASAS-Ⅱ),回顾性监测2019年使用左氧氟沙星的住院患者电子病历信息,获得发生心律失常患者的相关数据,采用倾向性评分匹配法选取未发生心律失常患者,通过单因素和多因素条件logistic回归分析左氧氟沙星导致心律失常的危险因素。结果12 879例使用左氧氟沙星人群的相关心律失常发生率为1.64%,其中65岁及以上人群发生率为3.22%;主要表现为期外收缩(0.84%)、心动过速(0.63%)、QT间期延长(0.44%),无尖端扭转型室性心动过速和室颤等严重心律失常。多因素条件logistic回归分析结果显示,用药疗程较长[OR=1.030,95%CI(1.009,1.050),P=0.004]和静脉给药[OR=2.392,95%CI(1.478,3.870),P <0.001]是左氧氟沙星致心律失常的独立危险因素。结论 左氧氟沙星引起的心律失常较为常见,分布类型多样,其中QT间期延长为偶见;临床应用时,应更多关注静脉用药的老年患者,并尽量避免长疗程用药。

基于单目视觉的散堆铆钉识别与定位技术

针对自动送钉过程中散堆铆钉识别与定位困难的问题,提出一种基于单目视觉的识别与定位方法。通过研究铆钉的反射光强获得钉杆的灰度分布规律,以参数化的方式构造了铆钉模板,并提出基于灰度匹配的铆钉识别算法。将单目视觉与激光位移传感器结合获取铆钉的空间位置,同时为解决单目视觉在测量不同深度下的铆钉位置存在原理性误差的问题,研究了一种重复定位拍照的测量方法,使真空吸嘴与钉杆中心的最大位置偏差由7.86 mm降低到0.87 mm。实验表明,灰度匹配算法的铆钉识别准确率在85%以上,并能适应30%~70%的照明亮度变化。使用该方法的机器人抓钉节拍最长为3.32 s,可留有充足的时间将铆钉输送至自动钻铆设备,满足自动钻铆设备的需求。

基于双输入输出卷积神经网络代理模型的油藏自动历史拟合研究

传统油藏自动历史拟合方法需进行多次计算耗时的油藏数值模拟,而深度学习代理模型可以实现高效且精度近似的油藏数值模拟替代计算。在基于深度学习代理模型的油藏自动历史拟合方法中,通常将采用油藏自动历史拟合方法进行调整的油藏不确定性参数作为深度学习代理模型的输入参数。现有的深度学习代理模型常为单一输入输出的神经网络模型架构,并未考虑油藏自动历史拟合方法需要对多个油藏不确定性参数进行调整,且需要训练多个深度学习代理模型以实现对油藏含水饱和度场分布及压力场分布的预测。为此,提出了一种基于双输入输出卷积神经网络代理模型的油藏自动历史拟合方法,将油藏渗透率场分布及相对渗透率参数作为输入,使用双输入输出卷积神经网络同时对油藏含水饱和度场分布及压力场分布进行预测,利用Peaceman方程计算产量,并耦合到多重数据同化集合平滑器(ES-MDA)方法中,对油藏渗透率场分布及相对渗透率参数进行反演更新,实现较为高效的油藏自动历史拟合求解。研究结果表明:双输入输出卷积神经网络代理模型在指定时间步的油藏含水饱和度场分布、压力场分布的预测精度均为93%以上。相较于传统油藏自动历史拟合方法,基于双输入输出卷积神经网络代理模型的油藏自动历史拟合方法避免了多次调用油藏数值模拟器的计算耗时问题,提高了拟合效率。

Research on Quantitative Identification of Three-Dimensional Connectivity of Fractured-Vuggy Reservoirs

The fractured-vuggy carbonate oil resources in the western basin of China are extremely rich.The connectivity of carbonate reservoirs is complex,and there is still a lack of clear understanding of the development and topological structure of the pore space in fractured-vuggy reservoirs.Thus,effective prediction of fractured-vuggy reservoirs is difficult.In view of this,this work employs adaptive point cloud technology to reproduce the shape and capture the characteristics of a fractured-vuggy reservoir.To identify the complex connectivity among pores,fractures,and vugs,a simplified one-dimensional connectivity model is established by using the meshless connection element method(CEM).Considering that different types of connection units have different flow characteristics,a sequential coupling calculation method that can efficiently calculate reservoir pressure and saturation is developed.By automatic history matching,the dynamic production data is fitted in real-time,and the characteristic parameters of the connection unit are inverted.Simulation results show that the three-dimensional connectivity model of the fractured-vuggy reservoir built in this work is as close as 90%of the fine grid model,while the dynamic simulation efficiency is much higher with good accuracy.

大坝安全监测数据异常识别模型簇研究

监测数据异常识别是大坝运行安全在线监测的前提和基础。单一识别方法难以实现高效准确识别,而RREW模型对规律不佳与单台阶数据序列容易漏判且计算效率低。为此,提出了基于卷积神经网络的一维VGG数据异常识别模型,建立了由统计回归、稳健回归、一维VGG识别模型等模型库和Pauta准则、MZ准则等判别准则库共同构成的大坝安全数据异常识别模型簇,并构建了不同数据类型与异常识别模型及预警准则的匹配机制。工程校验表明:一维VGG模型对不同序列长度、不同台阶占比的数据序列均具有较好的识别效果,能有效弥补传统回归模型和稳健回归模型的不足,由前述3种模型及两种准则共同构建的异常识别模型簇可实现海量数据异常的在线精准、快速识别,为大坝安全在线监测提供可靠的数据支持。

相似异源指纹研究进展及展望

指纹鉴定错案的发生引发了对指纹证据科学性要求的提高,伴随着指纹数据库的不断扩增,指纹相似异源问题已经成为指纹检验领域的重要研究内容之一,其对指纹鉴定标准的构建具有重要意义,也给指纹鉴定带来风险和挑战。本文首先介绍相似异源指纹的研究背景以及概念,然后从相似异源指纹的产生原因和鉴定错误率两方面展开综述,最后结合研究现状对其未来的发展趋势提出几点展望,以期补充指纹鉴定基础理论,为指纹证据的量化评价提供一定的参考。

基于点云匹配的智能工厂室内定位算法研究

针对智能工厂中的无人叉车系统需要精准的室内定位来满足装卸货工序的需求,研究了基于SLAM的定位算法以及基于反光柱的两种激光点云数据匹配定位算法,分析了这两种方法的优势和问题,并提出了一种新的融合定位算法。算法以高精度的反光柱定位算法为核心,通过SLAM定位来弥补反光柱数量不足时的系统延迟和精度损失问题,从而实现了一套连续、稳定、可靠的室内定位系统,其定位精度可以满足无人叉车日常工作的需求,也可以直接用于具体的工业生产流程中。

LIMS系统中标准管理模块的创新与应用

随着信息技术的不断进步,实验室信息管理系统(LIMS)在标准管理方面的创新应用日益显现。本文重点探讨了两大创新点:一是通过精细化设计的互联网爬虫技术,实现标准数据的自动采集、解析与实时更新;二是引入深度置信网络(DBN)框架,构建智能匹配模型,为用户提供精准的标准推荐服务。这两项技术的融合应用,不仅提升了LIMS系统的智能化水平,也为实验室标准管理带来了革命性的变革。

一种毫米波雷达里程计自主定位技术

本文通过研究毫米波雷达的数据基本特性,提出了一种毫米波雷达里程计自主定位技术。该方法通过特征匹配的方式,对毫米波雷达图像提取AKAZE特征点,并基于雷达图像自身所具备的几何先验信息,提出了3种匹配约束条件,从而大大降低了特征点误匹配率,保证了传感器位姿和里程计解算的可靠性。在牛津雷达机器人数据集上的试验结果表明,本文方法在不引入局部建图和回环检测等优化策略的情况下,水平位移相对定位误差和航向角误差可分别降低至6.8%和0.89(°)/m,单帧的定位时间仅为0.081 s,为恶劣环境下的室内外导航定位提供了新的思路。

基于视觉扫描生成巡检任务的机器人巡检方法

目前工业场景巡检机器人的巡检点设置是人员手动设置的。考虑到现场环境复杂,通常巡检点的数量庞大,设置任务耗费大量人力和时间,且一旦巡检点的设备改变,还得人工增加或删除巡检点,提出基于自动视觉扫描生成巡检任务的机器人巡检方法,利用机器人扫描环境的视频流,将所有图片送入到YOLOv4目标检测网络进行解析和筛选,并运用SIFT匹配方式去掉重复目标,可以自动生成复杂现场设备的巡检点。在隧道电缆的机器人巡检项目中应用此方法,相比于人工设置方式,提高效率90%以上。

基于双目系统的海面远距离测距研究

为适应未来无人船发展趋势,发现并定位海上远距离目标,采用YOLOV8和局部立体匹配方法,提出一种双目视觉远距离定位技术方案。首先对双目相机进行标定;然后采用YOLOV8算法对海上目标进行检测;进一步通过局部立体匹配,对两个相机检测目标进行局部特征提取和局部特征匹配;最后基于匹配结果,根据双目视觉原理计算所匹配目标的距离。实验结果表明:该技术方案对距离为100~300 m、300~500 m、500~700 m、700~900 m的目标测距平均精度分别为90%、84%、75%、60%,处理速度为20 PFS。与传统方法相比,所提方法直接聚焦海面目标,只对局部像素进行立体匹配,具有运行速度快、定位效果好的优势。

基于NLP的PS图像模板匹配智能识别算法

在PS图像模板匹配识别研究中,针对信息丢失严重,自身的全局运算能力需要进一步提高的问题,提出基于NLP的PS图像模板匹配智能识别算法。利用自然语言处理技术描述待识别目标方向特征,对目标方向码进行二进制压缩映射处理,同时应用窗口重叠机制,避免偏移现象出现,将压缩映射后的方向特征和输入的方向特征作匹配处理,实现对目标的精准识别。实验结果表明:设计的基于自然语言处理技术的智能识别算法在处理纹理特征比较少的目标时,识别信息较完整,能够精准匹配识别目标区域,全局运算能力得到了增强。

基于卫星立体影像的DSM数据自动提取试验

先简单介绍了DSM自动提取所用到的局部匹配算法、全局匹配算法和半全局匹配算法;其次进行了基于Inpho软件半全局匹配算法的卫星立体影像的DSM自动提取试验,探讨了从传感器类型和卫星影像分辨率2个方面对卫星立体影像DSM自动提取效果的影响,试验表明,更高分辨率的卫星立体影像、稳定且更高适配度的卫星传感器的卫星立体影像对DSM自动提取能取得更好的效果。