Forward heuristic breadth-first reasoning based on rule match for biomass hybrid soft-sensor modeling in fermentation process

Biomass is a key parameter in fermentation process, directly influencing the performance of the fermentation system as well as the quality and yield of the targeted product. Hybrid soft-sensor modeling is a good method for on-line estimation of biomass. Structure of hybrid soft-sensor model is a key to improve the estimating accuracy. In this paper, a forward heuristic breadth-first reasoning approach based on rule match is proposed for constructing structure of hybrid model. First, strategy of forward heuristic reasoning about facts is introduced, which can reason complex hybrid model structure in the event of few known facts. Second, rule match degree is defined to obtain higher esti- mating accuracy. The experiment results of Nosiheptide fermentation process show that the hybrid modeling process can estimate biomass with higher accuracy by adding transcendental knowledge and partial mechanism to the process.

基于图卷积与规则匹配的单兵动作识别

针对基于骨架数据的动作识别方法存在语义理解方面不足,以及骨架数据获取不全导致识别准确率较低的问题,本文提出了一种基于融合语义分析的图卷积与规则匹配的单兵动作识别方法。首先,使用OpenPose姿态估计模型对士兵作战视频进行骨骼关键点提取;然后,根据有效骨骼关键点提取情况,动态选择基于目标检测模型(You Only Look Once,YOLO)的单兵动作识别方法或基于图卷积的动作识别方法;最后,针对图卷积网络置信度不高的判别结果引入规则匹配算法进一步完成单兵动作识别判定。实验结果表明,与时空图卷积网络(Spatial Temporal Graph Convolutional Networks,ST-GCN)算法和双流自适应图卷积网络(Two-Stream Adaptive Graph Convolutional Networks,2s-AGCN)算法相比,该方法在单兵动作识别任务中准确率分别提高了约38%与11%。

空中目标作战意图识别研究综述

随着战争形式的不断演变和武器装备的更新换代,空中战场态势日益复杂,迅速准确地识别目标作战意图是战场态势评估的一项重要内容,可以为指挥员的决策提供辅助信息,有利于掌握战争主动权。首先介绍了目标意图识别的基本概念及相关模型,界定了目标意图和意图识别的定义概念,从作战指挥决策流程和信息融合流程2个方面确定了目标意图识别的地位和重要性;其次目标特征和意图空间分别作为意图识别的输入属性和识别框架,是意图识别的基础并对此进行了综述;然后综述规则和模板匹配、证据理论、贝叶斯网络、传统机器学习和神经网络等5类常见的目标意图识别方法,介绍了每种识别方法的基本机理和识别过程,总结了其优缺点;最后对比分析了5类目标作战意图识别方法的性能,并对其未来研究方向进行了展望。

More efficient ontology matching algorithm for integrating heterogeneous web resources

To improve the performance of the ontology matching process, a more efficient ontology matching algorithm, which can effectively eliminate unnecessary operations of matching entities, is proposed. By the theoretical analysis and proof, a set of matching rules are summarized for depicting inherent relations among matching results of entities. Based on these rules, the proposed algorithm can reuse the matching results of two entities to directly determine the matching results of their adjacent entities. Thereby, redundant operations of matching adjacent entities can be avoided, which can improve the performance of the whole matching process. The experimental results show that, compared with related algorithms, the proposed algorithm has high matching accuracy and can remarkably reduce the consuming time of the whole matching process. So, the proposed algorithm is more competent for the large-scale ontology matching which often occurs in the practical heterogeneous web resources integration project.

网络安全中一种基于规则匹配的入侵检测方法

入侵检测方法在网络安全防线中承担监测网络异常流量、识别主机内部潜在威胁等至关重要的任务。然而,现有的入侵检测方法仍然面临一些挑战,如在收集和分析数据时对系统性能的损耗过大,导致许多入侵检测系统性能不高。此外,网络拥塞等导致的数据丢包问题,使得数据完整性受到影响,间接影响入侵检测的效率和检测结果的准确性。为了应对这一挑战,有效提高系统效率和检测的准确性,文章提出一种基于规则匹配的入侵检测方法。该方法由数据收集、特征提取、异常检测3个步骤组成。模拟实验表明,该入侵检测方法能准确地监测和识别网络中的异常行为和潜在的安全威胁,并且实时监控流量行为,提高系统安全。

面向复杂电子设备线缆数字化集成设计制造

文中针对传统三维建模软件用于线缆设计时效率低、设计一致性差的问题,开展了基于CATIA定制开发平台的线缆数字化集成设计平台研究。通过建立连接器、线材、辅料等的数据库和基于知识的线缆物料匹配性映射规则,开发了针对柔性线缆和半刚性线缆的线缆路径快速设计模块;通过快速编辑控制点实现线缆路径的高频次快速迭代优化;最后采用自动输出模块实现线缆图纸和制造数据的快速生成,并将成型数据自动导入线缆成型系统和基于混合现实的线缆引导装配系统,实现线缆从设计到制造的模型贯通。通过上述研究实现了线缆组件从路径规划到详细设计和制造一体化的集成应用,使线缆设计效率提升了3倍以上。

基于深度学习与规则结合的海运货物邮件命名实体识别

针对海运货物邮件实体识别中存在识别精度不高、实体边界确定困难的问题,提出一种结合深度学习与规则匹配的识别方法。其中:深度学习方法是在BiLSTM-CRF(Bidirectional Long Short Term Memory-Conditional Random Field)模型的基础上添加词的字符级特征,并融入多头注意力机制以捕获邮件文本中长距离依赖;规则匹配方法则根据领域实体特点制定规则来完成识别。根据货物邮件特点将语料进行标注并划分为:货物名称、货物重量、装卸港口、受载期和佣金五个类别。在自建语料中设置多组对比实验,实验表明所提方法在海运货物邮件实体识别的F1值达到79.3%。

唐诗与唐乐的匹配规律初探——以七首唐诗与唐乐匹配为例

通过对传世唐谱与唐诗的诗乐匹配实践可以发现,七言诗更宜与4/4拍曲子匹配,五言诗更宜与2/4拍曲子匹配,六言诗更宜与4/4拍曲子匹配。七言诗句与4/4拍乐句匹配的标准模式为“■××○|×××○”,五言诗句与2/4拍乐句匹配的标准模式为“××|■×”,六言诗句与4/4拍乐句匹配的标准模式为“××××|×○×○”。标准模式外,诸诗乐匹配亦有所变化。不论“由乐以定词”,还是“选词以配乐”,唐诗与唐乐匹配的主导皆在诗而不在乐。其直接原因是诗句固定的朗诵音节节奏决定了乐句拍节节奏的被动、弹性适应,根本原因是诗句各音节朗诵时值长度对音节节奏产生的规定性,而诗句的意义节奏是对各音节朗诵时值长度限定的关键。

基于聚类和Apriori算法的苗族女上装色彩分析

苗族服饰元素是中国服饰文化的重要组成部分,其色彩搭配方式蕴含着极大的文化价值,展现了中国传统设计理念。以苗族女上装图像作为研究对象,对其色彩进行提取与分析。通过K-means聚类得到10个整体色、5个主色及10个辅色代表色,在HSV色彩空间下分析苗族服饰色彩分布,最后采用Apriori算法挖掘配色规则并建立配色网络。结果显示,苗族女上装以中低饱和、中低明度的红、黄、蓝色系为主,图案与主体色彩呈现出强烈对比。将配色关系应用到设计实践中,可促进苗族服饰色彩的传承与保护,为研究民族传统服饰色彩提供一定的借鉴和参考。

Rough Set Theory Based Approach for Fault Diagnosis Rule Extraction of Distribution System

As the first step of service restoration of distribution system,rapid fault diagnosis is a significant task for reducing power outage time,decreasing outage loss,and subsequently improving service reliability and safety.This paper analyzes a fault diagnosis approach by using rough set theory in which how to reduce decision table of data set is a main calculation intensive task.Aiming at this reduction problem,a heuristic reduction algorithm based on attribution length and frequency is proposed.At the same time,the corresponding value reduction method is proposed in order to fulfill the reduction and diagnosis rules extraction.Meanwhile,a Euclid matching method is introduced to solve confliction problems among the extracted rules when some information is lacking.Principal of the whole algorithm is clear and diagnostic rules distilled from the reduction are concise.Moreover,it needs less calculation towards specific discernibility matrix,and thus avoids the corresponding NP hard problem.The whole process is realized by MATLAB programming.A simulation example shows that the method has a fast calculation speed,and the extracted rules can reflect the characteristic of fault with a concise form.The rule database,formed by different reduction of decision table,can diagnose single fault and multi-faults efficiently,and give satisfied results even when the existed information is incomplete.The proposed method has good error-tolerate capability and the potential for on-line fault diagnosis.

An efficient embedding tree matching algorithm based on metaphoric dependency syntax tree

To find out all dependency relationships in which metaphors probably exist between syntax constituents in a given sentence,a dependency tree matching algorithm oriented to Chinese metaphor processing is proposed based on a research of unordered tree inclusion matching.In this algorithm,the pattern library is composed of formalization dependency syntax trees that are derived from large-scale metaphor sentences.These kinds of metaphor sentences are saved in the pattern library in advance.The main process of this algorithm is up-down searching and bottom-up backtracking revising.The algorithm discovers potential metaphoric structures in Chinese sentences from metaphoric dependency pattern library.Finally,the feasibility and efficiency of the new matching algorithm are further testified by the results of a series of experiments on dependency pattern library.Hence,accurate dependency relationships can be achieved through this algorithm.

面向系统可靠性保障的软件配置错误诊断仿真

为提高软件服务质量,满足系统的可靠性及高度可定制性要求,提出面向系统可靠性保障的软件配置错误诊断方法。以组件模块间可靠性为前提,结合系统对软件配置的要求,生成软件配置间的关联性,确定配置项值匹配与配置类型,根据相应诊断规则判断软件各节点输出的关系流是否存在错误,完成诊断全过程。实验表明,所提方法能够依据系统软件部分的各项参数诊断软件配置,且诊断结果与实际情况一致,检出率高,能够满足系统的实际应用需求。

Intelligent binary schema matching system in heterogeneity environment

For the past three decades, interoperability among heterogeneous systems had been a hard nut to crack due to the schematic and semantic perspectives that exist between objects. These systems were built under different data models. As such, levels of the local schemas are semantically very poor due to the limited expressiveness of traditional data models in which they were designed. Further more, most of the existing schema integration architectural components are inadequately equipped to handle the mapping schemas, especially when the semantics and structural conflicts are involved. This paper introduces an Intelligent Binary Schema Matching system (IBSMS), which exploits the phenomenon of making its components intelligent. That’s equipping its components such as translators and integrators with adequate knowledge about various data models. This allows the components acquire enough intelligence to maneuver or manipulate the correspondence between constructs from different models. In addition, the system has a Binary Matcher, which compares the attribute correspondences of various databases in a pairwise form, in order to establish the equivalences. With the establishment of the mappings, the users shall be able to access them (mappings) for their desired usage.

在线教育平台学习者的用户画像研究与构建

在大数据时代下的数据量呈指数级增长,基于统计模型的用户画像已经无法满足人们的个性化要求,利用学习行为数据绘制用户学习画像将成为未来教学模式的一种趋势。文章对在线学习者的日志和行为数据提取特征数据集,使用主流的大数据生态框架部署大数据离线批处理平台,并在此平台上构建学习者画像的标签体系以及使用规则匹配的机器学习算法完成用户画像模型的构建。与传统的用户画像相比,文中提出的标签模型和用户画像模型能挖掘出较为准确的学习者画像数据,以便为个性化推荐服务提供更好的支持。

动态匹配规则造成的变异——解析漠沙傣语塞擦组声母的复杂匹配现象

一般认为复杂时空层次的叠置是语言接触引发变异的主要机制。对漠沙傣语塞擦组声母复杂匹配现象的分析表明,动态匹配规则及其共同作用也是造成变异的重要原因。动态匹配规则包括:内部演变阶段对外来层的投射、目标语对外来层的投射、内部音系规则对外来层的制约、匹配残留造成的转换-类推规则,以及规则间的共同作用。

藏族传统图案中的民间习俗配色研究与分析

藏族少数民族特有的传统图案形象独具匠心。其所囊括的色彩形象变化万千,不同的配色法则表达着其特有的文化内涵,又产生更多的设计影响,本文即旨在从局部窥探和讨论这一问题。

《中医方剂大辞典》含黄芪今方用药规律数据挖掘

目的 通过分析《中医方剂大辞典》(第二版)含黄芪今方组方和应用规律,以期为临床用药和基础研究做出指导。方法 收集整理《中医方剂大辞典》中含黄芪的今方,利用Excel 2021构建临证方药数据库,使用SPSS Statistics 22.0、Cytoscape 3.8.1和IBM SPSS Modeler 18.0软件对其进行频次统计、关联规则和聚类分析等数据挖掘,分析含黄芪今方的主治疾病、证候、功效及组方规律。结果 根据纳入和排除标准,共统计了522首含黄芪的今方,其中涉及中药597种,主治140个,功效360个,证型119个,其中温性药和甘味药最多,归经以肝、脾、肾经为主,药物类型以补虚药最多,方剂类型以补益剂最多,剂型中汤剂最多。通过对522首含黄芪今方的分析,获取黄芪药物组合129组,基于黄芪的主治疾病,选择“虚劳”“痹病”“月经不调”进行聚类分析,显示出黄芪在不同疾病和不同配伍中发挥不同的功效。结论 《中医方剂大辞典》含黄芪的今方临床应用广泛,以补益气血为主,因此对黄芪今方进行数据挖掘,能进一步了解黄芪在现代临床应用中的进展,更加准确地体现出黄芪在临床中发挥的优势,从而找到最佳的配伍规律,为今后指导临床应用、基础研究和产品研发提供理论基础。

一种电力造价异常数据辨识算法

为了解决现有电力造价异常数据检测算法无法识别清单详情及清单与施工细节不符的问题,提出了一种基于规则匹配的电力造价异常数据辨识算法.利用K-means聚类算法实现了清单的初步分类和特征清单的提取,将特征清单的特征词作为清单类别特征.采用规则库对清单详情进行分词,并提取清单特征词,采用多项式贝叶斯算法计算出清单位于当前类别的概率.实验结果表明,所提出算法较传统异常数据检测算法的准确率提高了约10%.

基于统计学原理针灸治疗产后抑郁症文献的可视化分析

目的:对针灸治疗产后抑郁症的文献进行可视化分析,探索临床治疗该病证的辨证模式及配穴规律,为后续科研和临床诊治提供参考。方法:检索2006年1月-2021年12月中国知网数据库中针灸治疗产后抑郁症的文献。利用Cite Space、IBM SPSS Statistics 23、IBM SPSS Modeler 18.0,导入文献数据;进行文献、穴位关键词聚类、时区分析;研究其规律并建立知识结构。结果:纳入针灸治疗产后抑郁症关键词研究文献118篇,复筛后纳入穴位配伍规律研究文献59篇。“数据挖掘”“取穴规律”为高频关键词;相关文献关键词自2006年出现,由2007年起数量逐渐增多,反映此研究领域呈上升趋势发展。取穴时使用频次最高的穴位为太冲穴;所选经络频次最高的为足太阳膀胱经;关联性最强的穴位组合为太冲穴→足三里穴、三阴交穴→足三里穴和太冲穴→四神聪穴和足三里穴→血海穴。对频次≥5的24个腧穴进行聚类分析,分为3类。第一类为百会穴、中脘穴、印堂穴;第二类为心俞穴、肝俞穴、脾俞穴、肾俞穴、太溪穴、气海穴、关元穴、血海穴、膻中穴、行间穴、期门穴;第三类为足三里穴、三阴交穴、内关穴、太冲穴、合谷穴、四神聪穴、神门穴。结论:针灸治疗产后抑郁症的临床辨证以神志不宁、肝郁气滞、气血两虚为主。临床治疗主要根据醒神启闭针刺法、解郁调神针刺法的思路,联合特定穴配伍取穴。受限于样本容量质量,上述结论仍待进一步验证。

基于PR-ERNIE模型的航空安全风险量化分析

有效地利用实体识别技术识别出航空不安全信息中的风险要素,提升安全风险识别和评价能力,对于实现航空安全风险量化分析具有重要意义。为精准识别非结构化航空不安全信息中的风险要素,提出了一种融合先验规则和知识增强语义表示模型的实体识别模型,以大量航空不安全事件案例文本报告为分析对象,在自建标注语料上训练ERNIE模型,获取动态词向量,同时引入能够表达风险要素结构的规则进行优化。实验结果表明,模型在测试集上的精确率、召回率和F1值分别达到了92.5%、92.4%和92.4%,优于实验对比的其他模型。模型能够有效识别航空不安全信息中隐含的风险要素,为航空安全风险量化分析提供数据支持。