Wafer Defect Map Pattern Recognition Based on Improved ResNet

The defect detection of wafers is an important part of semiconductor manufacturing.The wafer defect map formed from the defects can be used to trace back the problems in the production process and make improvements in the yield of wafer manufacturing.Therefore,for the pattern recognition of wafer defects,this paper uses an improved ResNet convolutional neural network for automatic pattern recognition of seven common wafer defects.On the basis of the original ResNet,the squeeze-and-excitation(SE)attention mechanism is embedded into the network,through which the feature extraction ability of the network can be improved,key features can be found,and useless features can be suppressed.In addition,the residual structure is improved,and the depth separable convolution is added to replace the traditional convolution to reduce the computational and parametric quantities of the network.In addition,the network structure is improved and the activation function is changed.Comprehensive experiments show that the precision of the improved ResNet in this paper reaches 98.5%,while the number of parameters is greatly reduced compared with the original model,and has well results compared with the common convolutional neural network.Comprehensively,the method in this paper can be very good for pattern recognition of common wafer defect types,and has certain application value.

Multifractal Simulation of GeochemicalMap Patterns

Using a simple multifractal model based on the model De Wijs, various geochemical map patterns for element concentration values are being simulated. Each pattern is self-similar on the average in that a similar pattern can be derived by application of the multiplicative cascade model used to any small subarea on the pattern. In other experiments, the original, self-similar pattern is distorted by superimposing a 2-dimensional trend pattern and by mixing it with a constant concentration value model. It is investigated how such distortions change the multifractal spectrum estimated by means of the 3-step method of moments. Discrete and continuous frequency distribution models are derived for patterns that satisfy the model of De Wijs. These simulated patterns satisfy a discrete frequency distribution model that as upper bound has a continuous frequency distribution to which it approaches in form when the subdivisions of the multiplicative cascade model are repeated indefinitely. This limiting distribution is lognormal in the center and has Pareto tails. Potentially, this approach has important implications in mineral and oil resource evaluation.

Interpreting a period-adding bifurcation scenario in neural bursting patterns using border-collision bifurcation in a discontinuous map of a slow control variable

To further identify the dynamics of the period-adding bifurcation scenarios observed in both biological experiment and simulations with differential Chay model, this paper fits a discontinuous map of a slow control variable of Chay model based on simulation results. The procedure of period adding bifurcation scenario from period k to period k ＋ 1 bursting （k = 1, 2, 3, 4） involved in the period-adding cascades and the stochastic effect of noise near each bifurcation point is also reproduced in the discontinuous map. Moreover, dynamics of the border-collision bifurcation is identified in the discontinuous map, which is employed to understand the experimentally observed period increment sequence. The simple discontinuous map is of practical importance in modeling of collective behaviours of neural populations like synchronization in large neural circuits.

Patterns of upper layer circulation variability in the South China Sea from satellite altimetry using the self-organizing map

Patterns of the South China Sea (SCS) circulation variability are extracted from merged satellite altimetry data from October 1992 through August 2004 by using the self-organizing map (SOM). The annual cycle, seasonal and inter-annual variations of the SCS surface circulation are identified through the evolution of the characteristic circulation patterns.The annual cycle of the SCS general circulation patterns is described as a change between two opposite basin-scale SW-NE oriented gyres embedded with eddies: low sea surface height anomaly (SSHA) (cyclonic) in winter and high SSHA (anticyclonic) in summer half year. The transition starts from July—August (January—February) with a high (low) SSHA tongue east of Vietnam around 12°~14° N, which develops into a big anticyclonic (cyclonic) gyre while moving eastward to the deep basin. During the transitions, a dipole structure, cyclonic (anticyclonic) in the north and anticyclonic (cyclonic) in the south, may be formed southeast off Vietnam with a strong zonal jet around 10°~12° N. The seasonal variation is modulated by the interannual variations. Besides the strong 1997/1998 event in response to the peak Pacific El Nio in 1997, the overall SCS sea level is found to have a significant rise during 1999~2001, however, in summer 2004 the overall SCS sea level is lower and the basin-wide anticyclonic gyre becomes weaker than the other years.

PATTERN MAPPING ON BETA-SPLINE SURFACES——BILINEAR MAPPING METHOD

Texture pattern mapping is one of the most important techniques for high quality image syn- thesis. It can largely enhance the visual richness of raster-scan images. In this paper is presented a new method of mapping planar texture pattern onto beta-spline curved surfaces——bilinear mapping method which can map planar texture pattern onto curved surfaces with less distortion, and also can fulfill the geometric transformation of the texture pattern on the curved surfaces by operating the pattern win- dow. It is valuable to both CAD/CAM in artistic field and computer graphics.

Self-organizing Map Method Based on Real Rough Sets Space and Its Application of Pattern Recognition

This paper presents a real rough sets space and corresponding concepts of real lower and upper approximation sets which correspond to the real-valued attributes. Therefore, the real rough sets space can be investigated directly. A rhombus neighborhood for SOM is proposed, and the combination of SOM and rough sets theory is explored. According to the distance between the weight of winner node and the input vector in the real rough sets space, new weight learning rules are defined. The modified method makes the classification of the output of SOM clearer and the intervals of different classes larger. Finally, an example based on fault identification of an aircraft actuator is presented, The result of the simulation shows that this method is right and effective.

《朝元图》人物服饰图案在现代女包设计中的创新应用

《朝元图》是六百多年前的壁画作品,是中国绘画史上的旷世之作。文章从壁画中的人物服饰图案切入,深入挖掘服饰图案的文化内涵与艺术价值。从现代设计学角度分析服饰图案的历史背景、艺术特征和传承价值,并详细阐述服饰图案的提取方法。在服饰图案的创新设计过程中,结合当代审美意识,将带有创新基因的服饰图案成功应用到现代皮革女包的设计中。文章深入剖析了现代女包设计中的实践环节,将产生的设计方案与设计思路进行分析与汇总,以期为现代设计师们提供可借鉴的应用经验。

Integrative Self-Organizing Map—A Mean Pattern Model

We propose an integrative self-organizing map (iSOM) for exploring differential expression patterns across multiple microarray experiments. The algorithm is based on the assumption that observed differential expressions are random samples of a mean pattern model which is unknowna priori. The learning mechanism of iSOM is similar to the conventional SOM. The mean pattern model which underlies the proposed iSOM models mean differential expressions using a one-dimension of mean differential expressions for the mean differential expressions. The feature map of an iSOM model can be used to reveal correlation between multiple medically/biologically related disease types or multiple platform experiments for one disease. We illustrate applications of iSOM using simulated data and real data.

景观功能视角下的西南山区农业景观格局演变研究——以重庆市石柱县为例

鉴于中国西南山区农业生态环境的脆弱性与敏感性,解析该地区农业景观时空演变特征对合理利用农业景观资源和保护生态环境具有重要的理论意义.以重庆市石柱县为例,采用景观利用图谱、地形位分布指数、景观转移矩阵等方法,从景观功能视角开展西南山区农业景观格局演变特征分析.研究表明:①农业景观呈现出“三增一减”的变化趋势,即生活型和拓展型农业景观面积呈增长态势,生态型农业景观面积呈波动变化趋势;生产型农业景观面积持续下降.农业景观变化主要表现为生产型向生态型、生活型、拓展型农业景观转化;生态型向生活型、生产型、拓展型农业景观转化.②石柱县生态型农业景观主要分布在高等级地形位,生产型农业景观逐渐向高程和坡度较高的地形位移动,生活型农业景观主要分布在低、中低等级地形位上,拓展型农业景观逐渐向较高地形位转移.③坡度、高程等是导致研究区农业景观格局演变的主要环境因素;而农业人口、农民人均纯收入、第一产业占比等是农业景观格局演变重要的人文驱动因素.

Spatiotemporal characteristics of the sea level anomaly in the Kuroshio Extension using a self-organizing map

Satellite altimeter SSH data in the Kuroshio Extension （KE） region gathered during the period January 1993 to December 2014 are analyzed using self-organizing map （SOM） analysis. Four spatial patterns （SOM1, SOM2, SOM3, and SOM4） are extracted, and the corresponding time series are used to characterize the variation of the sea level anomaly. Except in some individual months, SOM1 and SOM2 with single-branch jet structures appear alternately during the periods 1993-1998 and 2002-2011. However, during 1999-2001 and 2012-2014, SOM3 and SOM4 with double-branch jet structures are dominant.The sea level anomalies exhibit interannual variations, while the KE stream demonstrates decadal variation. For SOM1, the change in the KE path is less evident, although the KE jet is strong and narrow. For SOM2, the KE jet is weakened and widened and its jet axis moves towards the southwest. Compared with the SOM3, for SOM4 the trough and ridge in the upstream KE region are deeper in the northeast-southwest direction, and accompanied by a jet weakening and splitting.This study shows that SOM analysis is a useful approach for characterizing KE variability.

面向关系特性建模的知识图谱表示学习研究综述

知识图谱表示学习技术可以将符号化的知识图谱转换为实体和关系的数值化表示,进而有效结合各类深度学习模型以赋能知识增强的下游应用。相较于实体,关系充分体现了知识图谱中的语义信息,建模关系的各类特性对知识图谱表示学习的性能非常关键。首先,针对一对一、一对多、多对一和多对多的复杂映射特性,梳理基于关系感知映射的模型、基于特定表示空间的模型、基于张量分解的模型和基于神经网络的模型;接着,面向建模对称、反对称、逆反和组合特性的多种关系模式,总结基于改进张量分解的模型、基于改进关系感知映射的模型和基于旋转操作的模型;其次,面向建模实体间隐含的层次关系,介绍基于辅助信息的模型、基于双曲空间的模型和基于极坐标系的模型。最后,针对稀疏知识图谱和动态知识图谱等更加复杂的情况,从融合多模态信息的知识图谱表示学习、规则增强的关系模式建模和针对动态知识图谱表示学习的关系特性建模等方面,讨论该领域研究的未来发展方向。

旅游产业嵌入的乡村生计空间基因图谱构建与格局分析——以山东省马套村为例

空间资源是农户赖以存续与发展以及参与产业利益分配的基础,在面向乡村旅游空间资本化过程中,重新界定乡村生计空间的内涵与范畴是确立农户权力与价值的资本依据。该文以旅游产业嵌入乡村生计空间为背景,以空间“基因图谱”的研究范式对乡村生计空间进行解析与整合,建立了包含地理物质空间、经济价值空间与社会文化空间3个维度的乡村生计空间基因系统。以山东省马套村为实证研究对象,对生计空间基因系统进行具象与实践,建立乡村生计空间基因库,并将各类基因元投影于乡村地理空间,归纳3类生计空间基因元的空间分布特征,得出马套村生计空间呈现出经济价值空间与社会文化空间相对独立、村域空间级差地租效应加剧、文化空间社会属性缺失、居民空间权能较弱等空间失配问题,提出在旅游产业驱动下村域生计空间优化的策略和建议。

叶序排布凹坑旋成体表面设计及磨削的研究

为了在旋成体上磨削出叶序排布凹坑结构化表面,基于叶序排布理论对旋成体曲面划分出结构化单元;设计出叶序排布凹坑旋成体表面的三维模型,并分析结构化单元凹坑的拓扑特征变化量,给出了球形磨头磨削凹坑表面的策略。最后通过计算机仿真获得了磨削加工中主轴不同角度方向和叶序排布系数对结构化凹坑表面的影响规律,并进行了初步磨削实验。结果表明:此磨削方法可以实现叶序排布凹坑旋成体表面的加工,随着叶序排布系数减小,凹坑在旋成体表面上排布更加稀疏;当球形磨头绕不同轴线旋转磨削时,在凹坑内部可形成纵向纹理、横向纹理和同心圆纹理。

一种基于MPS和ISOMAP的空间数据重建方法

在空间数据重建过程中,条件数据对重建结果影响较大,在仅有少量条件数据的情况下,重建结果常常出现较多的不确定性,此时适合采用不确定性插值方法重建空间数据.作为目前不确定性插值的主流方法之一,多点信息统计法(multiple-point statistics,MPS)可以从训练图像提取模式的本质特征,然后将这些特征复制到待模拟区域.由于传统采用线性降维的MPS方法无法有效处理非线性数据,因此将等距特征映射(isometric mapping,ISOMAP)应用到MPS方法,以实现对非线性数据的降维.提出基于MPS和ISOMAP的空间数据重建方法,通过模式库构建、模式降维、模式分类、模式提取等步骤能够较为准确地重构出未知的空间数据,为MPS处理非线性空间数据提供了新思路.实验结果表明:该方法所重建的空间数据具有与训练图像相似的结构特征.

基于知识图谱的香格里拉藏区民居装饰可视化分析

香格里拉藏区被誉为“离天堂最近的地方”,民居建筑装饰不仅是藏族悠久历史传统文化的现实印证,而且是藏族建筑文化的重要组成部分,其在装饰图案纹样上尤为绚丽多姿,向人们展示着神秘的美感。文章从装饰题材、纹样、装饰手法上进行总结分析,将CNKI数据库内有关藏族民居装饰领域的中文文献整合得出其发展历程的时区图,以保护和发扬藏族民居装饰艺术以及藏族民居建筑装饰传统文化为目的,为其传承和发展提出理论依据,从而促使香格里拉藏区民居装饰焕发新活力展现新的独特魅力。

机器学习在西北太平洋热带气旋生成前期大尺度环流场分型与识别中的应用

基于1979~2020年6~11月的热带气旋最佳路径(IBTrACS)和欧洲中期天气预报中心的第五代再分析(ERA5)资料,本文根据以热带气旋(TC)生成位置为中心的850 hPa水平风场特征,采用自组织映射网络(SOM)将西北太平洋TC生成前期的低层大尺度环流场分为5型:季风辐合型(MC)、季风涡旋型(MG)、强季风槽型(SMT)、弱季风槽型(WMT)及东风波型(EW)。MC型TC生成于副热带高压南侧辐合带中,占比最高;MG、SMT与WMT三型的TC生成受季风槽相关的气旋性切变或辐合区影响;EW型TC由东风波增幅发展生成,占比最小。在对历史资料分型的基础上,为选取合适的机器学习方法用于TC环流型的自动识别,本文还对比分析了支持向量机(SVM)、k近邻(KNN)及随机森林(RF)三种方法的识别效果,结果表明:SVM的准确率达0.965,对五类环流型识别的召回率和精确率均达到0.94以上,对样本不均衡问题不敏感,并且对样本量的敏感性分析显示其在有限样本量下即可充分学习各型的环流场特征,识别效果明显优于KNN和RF。

基于Map Reduce的序列模式挖掘算法

传统数据挖掘算法在处理海量数据集时计算能力有限。为解决该问题,提出一种基于Map Reduce的分布式序列模式挖掘算法MR PrefixSpan。在PrefixSpan算法的基础上,对模式挖掘任务进行分割,利用Map函数处理由不同前缀得到的序列模式,并行构造投影数据库,从而提高挖掘效率及简化搜索空间。采用Reduce函数对中间结果进行规约,得到全局序列模式。在Hadoop集群上的实验结果表明,MR PrefixSpan能减少数据库扫描时间,具有较高的并行加速比和较好的可扩展性。

《辅行诀》与《脏腑标本虚实寒热用药式》中肝木疾病临床表现及治疗用药的异同点分析

目的《辅行诀》与《脏腑标本虚实寒热用药式》均采用五脏虚实辨证作为理论架构,本文比较两者关于肝木疾病辨证用药的异同点,为“汤液经法图”的现代应用和理论融入提供依据。方法收集《辅行诀》与《脏腑标本虚实寒热用药式》关于肝木疾病辨证论治章节的临床症状表现和治疗药物信息,数据标准化后拆分成独立的语义概念进行比较,计算相符度。最终拆分成24个独立症状与《辅行诀》比较并计算相符度,用药药味依据“汤液经法图”五味补泻五脏规律进行定味和标记,并计算与补肝泻肝缓肝的“辛酸甘”味相符度。结果《脏腑标本虚实寒热用药式》肝木疾病包含24个症状,其中17个症状与《辅行诀》相符,相符度为70.8%,共有症状包括头痛、多怒、两胁肿痛等,《脏腑标本虚实寒热用药式》独有症状如卵缩、寒热虐等。同时,《脏腑标本虚实寒热用药式》包含76个肝木病治疗中药,其中辛味、酸味和甘味药总和占比为71.05%。结论《脏腑标本虚实寒热用药式》与《辅行诀》关于肝木疾病临床症状和治疗药物的认识有许多相同之处,相似度高达70%,两者可能具有相同的起源。五脏虚实+五味补泻辨证论治体系具有真实历史背景和临床实践价值。

多种混合格式CAD水深数据的智能识别提取

在CAD水深测量成果图中,水深往往以分离的文本方式标注,其整数、小数、小数点、负号等各部分相互分离且形式多样,这给水深信息提取工作带来了很大的困难。本文基于空间数据关联规则挖掘思想,建立空间布局拓扑表,采用人工神经网络学习和分类识别方法,智能识别和提取水深数据。此方法无需预先指定格式及其他参数,创新性实现了多种混合格式水深数据的自动化、智能化识别提取,且准确率高、速度快,在工程领域具有一定应用前景和推广价值。

基于统计分析和系统聚类的道路格网模式识别

从格网模式道路网的基本特征出发,即格网模式的道路网中纵横交错的道路线相互近似正交,组成大小不一,且相互嵌套的格网单元。从城市地图上采集到100个区域的道路网作为研究对象,通过100个研究区域的大量实测数据,统计出格网模式道路网的所有道路线夹角值,并求出他们的平均值和标准差,利用非监督的聚类方法,识别出格网模式的道路网。本文方法效率高且易于运用在工程实践中,克服了以往的识别方法约束条件多、通用性受到限制的不足。