Knowledge Acquisition Based on Semantic Balance of Internal and External Knowledge
基于相似性负采样的知识图谱嵌入
DOI : 10.11992/tis.201811022网络出版地址: /kcms/detail/23.1538.TP.20190520.1347.006.html基于相似性负采样的知识图谱嵌入饶官军，古天龙，常亮，宾辰忠，秦赛歌，宣闻（桂林电子科技大学 广西可信软件重点实验室，广西 桂林 541004）摘 要：针对现有知识图谱嵌入模型通过从实体集中随机抽取一个实体来生成负例三元组，导致负例三元组质量较低，影响了实体与关系的特征学习能力。
研究了影响负例三元组质量的相关因素，提出了基于实体相似性负采样的方法来生成高质量的负例三元组。
在相似性负采样方法中，首先使用K-Means 聚类算法将所有实体划分为多个组，然后从正例三元组中头实体所在的簇中选择一个实体替换头实体，并以类似的方法替换尾实体。
通过将相似性负采样方法与TransE 相结合得到TransE-SNS 。
研究结果表明：TransE-SNS 在链路预测和三元组分类任务上取得了显著的进步。
关键词：知识图谱；表示学习；随机抽样；相似性负采样；K-Means 聚类；随机梯度下降；链接预测；三元组分类中图分类号：TP391 文献标志码：A 文章编号：1673−4785(2020)02−0218−09中文引用格式：饶官军, 古天龙, 常亮, 等. 基于相似性负采样的知识图谱嵌入[J]. 智能系统学报, 2020, 15(2): 218–226.英文引用格式：RAO Guanjun, GU Tianlong, CHANG Liang, et al. Knowledge graph embedding based on similarity negative sampling[J]. CAAI transactions on intelligent systems, 2020, 15(2): 218–226.Knowledge graph embedding based on similarity negative samplingRAO Guanjun ，GU Tianlong ，CHANG Liang ，BIN Chenzhong ，QIN Saige ，XUAN Wen(Guangxi Key Laboratory of Trusted Software, Guilin University ofElectronic Technology, Guilin 541004, China)Abstract : For the existing knowledge graph embedding model, the random extraction of an entity from the entity set results in the generation of lower-quality negative triples, and this affects the feature learning ability of the entity and the relationship. In this paper, we study the related factors affecting the quality of negative triples, and propose an entity similarity negative sampling method to generate high-quality negative triples. In the similarity negative sampling meth-od, all entities are first divided into a number of groups using the K-means clustering algorithm. Then, corresponding to each positive triple, an entity is selected to replace the head entity from the cluster, whereby the head entity is located in the positive triple, and the tail entity is replaced in a similar approach. TransE-SNS is obtained by combining the similar-ity negative sampling method with TransE. Experimental results show that TransE-SNS has made significant progress in link prediction and triplet classification tasks.Keywords : knowledge graph; representation learning; random sampling; similarity sampling; K-means clustering;stochastic gradient descent; link prediction; triple classification知识图谱(knowledge graph)的概念是谷歌在2012年正式提出的，主要用于提升搜索引擎性能。
Managing, mapping, and manipulating conceptual knowledge
1This research is supported in part by NASA under award No NCC 2-1035. Authors Leake and Wilson are currently at the Intelligent Informa-tion Laboratory at Northwestern University, on leave from Indiana University. They thank the Laboratory and the Northwestern Computer Sci-ence Department for their support. They also gratefully acknowledge the many contributions to this project by Mary Livingston and the ADTT team at NASA Ames and by James Newkirk at Indiana University.AbstractEffective knowledge management maintains the knowl-edge assets of an organization by identifying and cap-turing useful information in a usable form, and by sup-porting refinement and reuse of that information in ser-vice of the organization's goals. A particularly impor-tant asset is the “internal” knowledge embodied in the experiences of task experts that may be lost with shifts in projects and personnel. Concept Mapping provides a framework for making this internal knowledge explicit in a visual form that can easily be examined and shared. However, it does not address how relevant concept maps can be retrieved or adapted to new problems. CBR is playing an increasing role in knowledge re-trieval and reuse for corporate memories, and its capa-bilities are appealing to augment the concept mapping process. This paper describes ongoing research on a combined CBR/CMap framework for managing aero-space design knowledge. Its approach emphasizes in-teractive capture, access, and application of knowledge representing different experts' perspectives, and unob-trusive learning as knowledge is reused.IntroductionManaging the knowledge assets of an organiza-tion requires capturing and retaining useful knowledge and making it available in a usable form when it is needed in the future. This process is complicated by difficulties in acquiring and representing knowledge, in accessing relevant knowledge, and in reapplying prior lessons to new situations. These issues are particularly acute in capturing and utilizing “internal” knowledge as-sets embodied in the experiences of task experts. Different technologies offer different benefits for addressing these problems. Concept Maps (CMaps) (Novak & Gowin 1984) provide a framework for capturing experts' internal knowl-edge and making it explicit in a visual, graphical form that can be easily examined and shared. Concept mapping has been used for knowledge acquisition during the development of expert sys-tems (Ford et al. 1991), as the basis for the expla-nation component of expert systems (Ford, Cañas, & Adams-Webber 1992), and for knowledge preservation at NASA (Coffey, Moreman, & Dyer 1999).Procedures have been developed help guide CMap generation (e.g., (Jonassen, Beissner, & Yacci 1993)),and interactive tool shave been de-veloped to facilitate generation and manipulation of concept maps and map sharing over the Inter-net (Cañas et al. 1995). These tools support knowledge access through map browsing but not automatic retrieval of relevant maps from map archives or support for adaptation of retrieved CMaps. Such adaptation is important, for exam-ple, when a concept map represents a design that must be modified to fit new constraints. Case-based reasoning (CBR) is increasingly investi-gated as a knowledge management technique to support the retrieval and adaptation of prior cases (Becerra-Fernandez & Aha 1999; Klahr 1997), and retrieval and adaptation methods from CBR are promising to extend existing concept mapping tools. Conversely, using the concept mappingManaging, Mapping, and Manipulating Conceptual Knowledge 1Alberto J. CañasInstitute for Human and Machine CognitionUniversity of West Florida 40 South Alcaniz St. Pensacola, FL 32501 acanas@David B. Leake and David C. WilsonComputer Science Department L indley Hall, Indiana University150 S. Woodlawn Ave Bloomington, IN 47405 {leake,davwils}@process to capture cases may help CBR by fa-cilitating case engineering.Thus concept maps and case-based reasoning each address complementary parts of the knowl-edge management problem. This paper describes ongoing research on combining concept map-ping and CBR to leverage off their respective strengths. CBR provides support for the retrieval and application of CMaps, while CMaps and CMap tools provide mechanisms for capture and representation of hierarchical cases, browsing through the case organization to find alternative cases, and case examination. The combined framework provides interactive knowledge cap-ture and access, support for multiple conceptu-alizations of knowledge, and unobtrusive learn-ing as stored knowledge is applied to new situa-tionsConcept Mapping for Knowledge Cap-ture and SharingConcept maps represent meaningful relation-ships between concepts in the form of proposi-tions. Propositions are two or more concepts linked by words to form a semantic unit. In its simplest form, a concept map would contain just two concepts connected by a linking word to form a single proposition. For example, “Cen-taur is a rocket” would represent a simple map forming a valid proposition about the concepts “Centaur” and “Rocket.” A concept acquires additional meaning as more propositions include the concept. Thus, that the Centaur is a rocket, Centaur is powered by a turbopump, Centaur's role is as an upper stage, and so on, all expand the meaning of the concept Centaur. In this sense, concept maps represent meaning in a framework of embedded propositions. (Semantic nets are a form of concept map, but concept maps also include less constrained network rep-resentations.)Different content and structure are contained in concept maps depending on the contexts for which they are generated. Consequently, maps having similar concepts can vary from one con-text to another and can be highly idiosyncratic. The strength of concept maps lies in their ability to express a particular person's knowledge about a given topic in a specific context. Concept maps thus provide an elegant, easily understood repre-sentation of an expert's domain knowledge.The Institute for Human and Machine Cognition at the University of West Florida has developed software tools that extend the use of concept maps beyond knowledge capture and examina-tion, to serve as the browsing interface to a cor-porate memory of hierarchical concept maps and associated information resources. For example, the tools are currently being used in a NASA Lewis Center project to capture and preserve Senior Engineers' design expertise knowledge of launch vehicle systems integration for the Cen-taur/RL10 rocket system (Coffey, Moreman, & Dyer 1999). As part of this research project, a prototype browsable, multimedia model of the experts' domain knowledge was built, as illus-trated in Figure 1. The CMap tools allow icons to be associated with concepts, providing links to other concept maps or other explanatory me-dia (video, text, images, simulations, WWW pages, etc.), which may be distributed through-out the Internet. The tools also support ways in which the knowledge encoded in concept maps can be selectively shared among a community of users. Concept maps are hierarchical and may link to other maps over the Internet, enabling distributed teams to collectively develop and access complex maps. In addition, during the construction of concept maps, the tools allow users to designate sentences or propositions se-lected from CMaps for “publication” or sharing with other users. These propositions, or “claims,” are stored in a shared server, compos-ing a “knowledge soup” of assertions from mul-tiple sources. The system extracts from this in-formation the claims that other users chose to share and that are relevant to the claims the user published, providing information that may aid the user in constructing his or her own concept maps. The system also provides a process for commenting on or questioning these shared claims, querying other users about aspects that the user does not understand. This process facili-tates distributed discussion, refinement and use of concept maps, and the technology is currently being enhanced to develop a collaborative knowledge sharing environment for the NASA Astrobiology Institute.Combining CBR and CMapsWe are investigating the combination of CMapsand CBR for knowledge management to support aerospace design at NASA. Aerospace design is a complex task area in which “knowledge loss” as projects are discontinued or engineers retire is a profound problem. Previous efforts have been made at NASA to store and access textual re-ports of important lessons using standard com-mercial CBR tools (Bagg 1997). However, even when textual design records have been captured they may be hard to understand and reuse be-cause different experts conceptualize designs very differently. This has resulted in a push to capture design knowledge in the form of CMaps. Our interactive design support framework, DRAMA (Design Retrieval and Adaptation Mechanisms for Aerospace), is being developed in cooperation with the Advanced Design Tech-nologies Testbed project at NASA Ames Re-search Center. The goal is both to develop useful tools for aerospace design and to establish a general “knowledge-light” (Wilke et al. 1997) frame- work for interactive case-based design support systems.Motivations for combining CBR and Cmaps The integration of CBR with interactive CMap tools provides leverage for both the CBR and CMap systems. Existing CMap tools provide an interactive medium for representing and examin-ing designs, but their framework does not pro-vide search facilities to find relevant stored CMaps or advice on how to navigate hierarchi-cal CMap structures. Likewise, although the tools provide capabilities for interactively defin-ing new CMaps and manipulating their structure by adding, deleting, or substituting components, the tools provide little support for the decision-making that underlies the adaptation process. Consequently, their usefulness can be extended by the addition of automatic facilities for retriev-ing relevant CMaps, automated aids to navigat-ing CMaps and finding relevant information therein, and by aids to the reuse of existing CMaps.Conversely, case-based reasoning can leverage off the interactive case definition and revision capabilities of the CMap tools. CMaps can be used as a browsable structure for indexing cases, either simply, according to the nodes under which they are placed, or contextually, accord-Figure 1: Expert’s Domain Knowledge Model of the Centaur/RL-10 rocket system.ing to the user's perspective, reflected by the path taken to reach them. For example, different design cases indexed under “Boeing 777” might be appropriate to present to users depending on whether they reached that node by following links for hydraulic systems or links for avionics. Also, CMap tools provide a convenient method for entering case information in a middle form between textual descriptions (which are easy to input but hard to reason about) and rich struc-tured representations (which are hard to input but support complex reasoning). In our domain, the push to use concept mapping to understand the design process means that such cases will be available at low cost as “seed cases” for the CBR system. In addition, the CMap tools al-ready provide crucial functions for interactively generating, examining, and navigating the hier-archical structure of these cases.Using the CMap/CBR combination to sup-port knowledge access, reuse, and capture during designIn DRAMA, CMaps are used to represent two types of information. First, they represent hier-archies of aircraft and part types. Second, CMaps represent specific information about par-ticular designs such as their components and component relationships.The system treats the design process as generat-ing a CMap to describe each new design. Re-trieval and adaptation of relevant prior CMaps is an integral part of this process. A designer starts the design process by selecting a similar prior design as a starting point. The user may select this design either by using a traditional CBR retrieval tool for stored CMaps, or by interac-tively navigating through a set of concept maps providing alternative “views” of aircraft and air-craft component types, used to organize CMaps for specific aircraft. For example, suppose the designer is considering alternatives for increas-ing the fuel efficiency of a large airliner. The designer first navigates through the types of air-craft to select an aircraft, and selects a particular case—represented as a concept map—to adapt into the new design. The designer may adapt the specific design or may request that it be ab-stracted into a fill-in design template. Adaptation of design CMaps is supported by providing suggestions of relevant prior designs and enabling the user to browse CMaps to gather information to support the adaptation process. In our example, to revise the engine to increase fuel efficiency, the designer selects the engine node of the current aircraft as the part to adapt. If no CMap is already present for the component se-lected (e.g., the designer wishes to fill in a sketchy design by specifying its engine), the de-signer can use the interactive CMap tools to cre-ate a new CMap from scratch, or browse the CMaps for designs, import a design, and then adapt as desired. To help support adaptations e.g., to find a more fuel-efficient engine the de-signer may initiate a retrieval focused either on similar components (e.g., CMaps that show air-craft using similar engines), or similar contexts for the current type of component (e.g., CMaps that show the engines of similar aircraft). The result of the process is automatically saved as a new CMap for future use. Thus each design augments the corporate memory and provides additional starting points for future knowledge reuse.Significance of the approach CMaps as a medium for capture and representa-tion of experiences: Structured representations have been extensively studied within CBR. They provide much power but may require significant “case engineering” effort (Aha & Breslow 1997; Simoudis, Ford, & Cañas 1992). Work in textual case-based reasoning (Lenz & Ashley 1998) ap-plies CBR to information already stored in tex-tual form, but textual cases may be difficult to use. CMap representations are at a middle point between these alternatives: they include struc-tural information and are intended to concisely represent key concept properties, but may not use a standardized semantics. This makes them more difficult to manipulate autonomously than standardized representations but also easier to acquire when domain experts are called upon to encode their knowledge. DRAMA alleviates problems of differing representations in two ways. First, when a user draws a map and isabout to fill in a new link or node, it presents the user with menu of alternatives from previous maps. The user is not required to use links from this list, but when appropriate links are on the list this helps build a set of standard types over time. The second is simply the “retrieve and adapt” process itself: When new designs are generated by adaptation, significant portions of old representations are brought to new tasks, resulting in representations with similar struc-ture.Concept mapping as a form of design ration-ale captureMany projects have applied rule-based or model-based approaches to design rationale cap-ture, but encoding and updating the needed in-formation can be prohibitively expensive. Be-cause CMap design cases already capture an entire design as context, we believe that useful rationale capture can be achieved with fairly limited additional information: an annotation about why the designer chose a particular com-ponent, given the implicit context of the previ-ous components chosen. DRAMA enables de-signers to provide this information as a form of “weak explanation” of the type advocated by Gruber and Russell (1992), providing just enough information to guide a designer's own reasoning process.CMaps/CBR as interactive retrievalThe ability to browse through the CMap index-ing structures provides a convenient way for users to interactively search for cases. This is in the spirit of conversational case-based reasoning (CCBR) systems, which guide the retrieval process through an interactive dialogue of ques-tions (Aha & Breslow 1997), but here the user directly examines and traverses hierarchical or-ganizational structures.ConclusionConcept mapping is useful for knowledge man-agement as a vehicle for externalizing “internal” expert knowledge, to allow that knowledge to be examined, refined, and reused. CBR is useful for knowledge management in providing an easy-to-understand knowledge representation records of specific reasoning episodes—and methods for accessing relevant information and building up a corporate memory of experiences. The synergy of the two technologies provides a promising approach for addressing corporate “knowledge loss” by supporting the capture and reuse of ex-pert design experiences, helping to manage and maintain an important component of organiza-tional knowledge assets.ReferencesAha, D., and Breslow, L. 1997. Refining conver-sational case libraries. In Proceedings of the Second International Conference on Case-Based Reasoning, 267-278. Berlin: Springer Verlag. Bagg, T. 1997. RECALL: Reusable experience with case-based reasoning for automating les-sons learned./RECALL/homepg/reca ll.htm.Becerra-Fernandez, I., and Aha, D. 1999. Case-based problem solving for knowledge manage-ment systems. In Proceedings of the Twelfth An-nual Florida Artificial Intelligence Research Symposium. Menlo Park: AAAI. In press.Cañas, A.; Ford, K.; Brennan, J.; Reichherzer, T.; and Hayes, P. 1995. Knowledge construction and sharing in quorum. In World Conference on Artificial Intelligence in Education.Coffey, J.; Moreman, D.; and Dyer, J. 1999. In-stitutional memory preservation at NASA Lewis Research Center. In Proceedings of the HBCU/OMU Research Conference.Ford, K.; Cañas, A. J.; Jones, J.; Stahl, H.; No-vak, J.; and Adams-Webber, J. 1991. ICON-KAT: an integrated constructivist knowledge acquisition tool. Knowledge Acquisition 3. Ford, K. M.; Cañas, A. J.; and Adams-Webber, J. 1992. Participatory explanation: A new para-digm? In Proceedings of the Tenth European Conference on Artificial Intelligence Workshop on Expert Judgement, Human Error, and Intelli-gent Systems, 146-155.Gruber, T., and Russell, D. 1992. Generative design rationale: Beyond the record and replay paradigm. Knowledge Systems Laboratory KSL 92-59, Computer Science Department, Stanford University.Jonassen, D.; Beissner, K.; and Yacci, M. 1993. Explicit methods for conveying structural knowledge through concept maps. Hillsdale, NJ: Erlbaum. chapter 15, 155.Klahr, P. 1997. Knowledge management on a global scale. In Gaines, B.; Musen, M.; and Ut-hurusamy, R., eds., Proceedings of the 1997 Spring Symposium on Artificial Intelligence in Knowledge Management, 82-85. Stanford, CA: AAAI.Lenz, M., and Ashley, K., eds. 1998. Proceed-ings of the AAAI-98 Workshop on Textual Case-Based Reasoning. Menlo Park, CA: AAAI Press.Novak, J., and Gowin, D. 1984. Learning How to Learn. New York: Cambridge University Press.Simoudis, E.; Ford, K.; and Cañas, A. 1992. Knowledge acquisition in case-based reasoning: “...and then a miracle happens”. In Dankel, D., ed., Proceedings of the 1992 Florida AI Re-search Symposium. FLAIRS.Wilke, W.; Vollrath, I.; Altho, K.-D.; and Berg-mann, R. 1997. A framework for learning adap-tation knowledge based on knowledge light ap-proaches. In Proceedings of the Fifth German Workshop on Case-Based Reasoning.。
Senserelations语义关系
Semantic relationships are the foundation of language understanding. By analyzing semantic relationships, one can understand the meaning of words and sentences, and thus comprehend the meaning of the entire text.
要点一
要点二
Detailed description
Semantic conflict refers to the situation where two concepts or entities are contradictory or mutually exclusive in meaning and nature. For example, "peace" and "war" are conflicting because they represent opposite meanings and states.
Semantic relevance
Refers to the existence or attribute of one concept or entity containing the existence or attribute of another concept or entity.
Summary word
Statistical methods
Deep learning based methods
Summary: Based on deep learning methods, neural network models are used to recognize and calculate semantic relationships by learning semantic patterns from corpora.
知识图谱技术研究
知识图谱技术研究一、引言随着互联网技术的飞速发展，越来越多的数据被生成并且需要被处理，传统的数据处理方式已经无法满足现代业务的需求。
知识图谱技术则通过将大量信息以语义化的方式进行结构化并通过知识连接提供了一个新的处理方式。
二、知识图谱概述知识图谱（Knowledge Graph）是谷歌公司在2012年提出的一种基于知识库的新型搜索方式。
知识库是指一组组织结构化的知识，知识之间以语义的方式进行连接，从而构建了一个庞大的知识网络。
知识图谱提供了一种更加智能化的搜索方式，它不再仅仅是通过关键字的匹配来完成搜索，而是将用户的查询转化为语义问题，进而将此问题映射到知识图谱中，从而找到最佳答案。
三、知识图谱构建知识图谱的构建主要包括三个步骤：知识抽取、知识表示和知识存储。
1.知识抽取知识抽取是指从半结构化或非结构化的文本数据中，自动抽取出结构化的知识。
目前，知识抽取的研究主要集中在信息抽取和实体识别两个方面。
信息抽取是指从文本中识别出特定的信息类型，如人名、时间、地点等，然后将其组织为结构化的数据。
实体识别则是从文本中识别出具有名词性质的实体，如人、地点、组织等。
2.知识表示知识表示是指通过一定的方式将抽取出来的知识进行表示，以便于后续的处理和应用。
在知识表示的过程中，需要对数据进行清洗、分类、归纳、聚类等操作，并通过本体论体系构建出知识图谱的结构。
3.知识存储知识存储是指将表示完毕的知识进行存储，以便于后续的检索和使用。
知识存储主要采用图数据库来实现，其中常用的图数据库有Neo4j、Tinkerpop、JanusGraph等。
四、知识图谱应用知识图谱技术在各类领域中都有着广泛的应用，如智能客服、智能单元格、智能检索等。
下面将分别介绍几个应用案例：1.智能客服智能客服是一种基于知识图谱的人机交互系统。
此种系统可以分析从用户那里获取到的请求，同时又可以利用翻译技术和语义分析技术，自动生成针对请求的回答。
2.智能单元格智能单元格是一种基于知识图谱的电子表格系统。
知识表示方法的研究与分析
2012年第28期(总第43期)科技视界Science &Technology VisionSCIENCE &TECHNOLOGY VISION科技视界0引言知识表示是对知识的一种描述,或者说是一种约定,探索新的知识表示方法一直是人工智能研究的重要课题之一。
目前已有许多种知识表示方法。
例如,谓词逻辑、语义网络、产生式规则、框架、概念从属等。
这些方法对于描述特定领域的问题求解已经足够,且已得到广泛应用。
但是,从来没有人认为这些知识表示方法已经达到了最终的目的,因此知识表示仍是很久以来人工智能研究的中心课题。
对它的研究还需要相当深入的研究。
概念结构理论的出现为知识表示研究带来了一种新的思路。
本文正是从这个角度出发,在研究人工智能中知识基本概念、分类及传统知识表示方法基础上,主要研究概念图知识表示方法的基本理论及方法,通过实例阐述概念图知识表示方法的优点及其在实际工程中的应用。
1知识表示知识表示是人工智能研究的一个重要课题,无论应用人工智能技术解决什么问题,首先遇到的问题就是所涉及的各类知识如何加以表示。
研究知识表示的主要目的是为用户提供一种有利于进行逻辑推理,能够充分表示领域内知识和便于高效率进行程序设计的知识表示。
合理的知识表示,可以使问题的求解变得容易,并且有较高的求解效率。
一个好的知识表示方法应该具备以下的性质:1.1表达充分性能够将问题求解所需的知识正确有效的表达出来。
1.2推理有效性能够与高效的推理机制密切结合,支持系统的控制策略。
1.3操作维护性便于实现模块化,便于知识更新和知识库的维护。
1.4理解透明性知识表示便于人类理解,易读、易懂,便于知识的获取。
1.5良好访问性能够很好的接受访问并有效的利用所访问的知识对其进行有效的利用。
2传统知识表示方法基于前面所描述的知识表示方法所应具备的性质,目前普遍应用的传统知识表示方法主要有逻辑表示模式、基于规则的产生式系统、语义网、框架表示法、剧本表示法、脚本表示法等。
基于步态的机器学习模型识别遗忘型轻度认知障碍和阿尔茨海默病
·3857·•论著•基于步态的机器学习模型识别遗忘型轻度认知障碍和阿尔茨海默病陶帅1，韩星1，孔丽文1，汪祖民1，谢海群2*【摘要】 背景 随着老龄化社会的到来，与年龄密切相关的认知障碍(包括痴呆)的患病率明显增加。
先前的研究表明，具有不同认知能力的人群所表现的步态状态也不一样。
过去研究者们在研究遗忘型轻度认知障碍（aMCI）和阿尔茨海默病（AD）的步态时，使用了统计分析方法，对机器学习方法的使用较少。
目的 构建基于步态的机器学习模型识别aMCI 和AD，探索aMCI 和AD 之间的步态标志物，以便将其用作帮助诊断aMCI 患者和AD 患者的可能工具。
方法 于2018年12月至2020年12月，从国家康复辅具研究中心附属康复医院、佛山市第一人民医院、大连大学附属中山医院招募了102例受试者，按照筛选标准最终纳入98例受试者，其中55例为aMCI 患者，10例为AD 患者，33例为健康对照（HC）者。
使用可穿戴设备采集参与者在单任务（自由行走）、双任务（倍数7）和双任务（倒数100）时的步态参数。
使用随机森林算法（RF）和梯度提升决策树算法（GBDT）建立模型，10个步态参数作为预测变量，疾病状态（HC、aMCI、AD）作为响应变量，比较两种机器学习算法对3个疾病组的识别效果。
然后使用机器学习算法结合递归特征消除法（RFE）进行重要特征选择。
结果 三组年龄、性别、身高、体质量、鞋码比较，差异无统计学意义（P>0.05）；MMSE 评分、MoCA 评分比较，差异有统计学意义（P<0.05）。
自由行走测试时，aMCI 组和AD 组受试者步幅较HC 组短，足跟着地角度较HC 组小；AD 组步速较HC 组和aMCI 组受试者慢，足趾离地角度较HC 组小（P<0.05）。
双任务倍数7测试时，aMCI 组和AD 组受试者步速较HC 组慢，足趾离地角度和足跟着地角度较HC 组小；AD 组支撑时间较HC 组长，足趾离地角度较aMCI 组小（P<0.05）。
基于知识图谱的语义搜索引擎研究
基于知识图谱的语义搜索引擎研究随着互联网技术的不断发展，搜索引擎已成为人们获取信息的主要途径。
但是，传统的基于关键词的搜索方式已经无法满足人们日益增长的信息需求。
在这个背景下，基于知识图谱的语义搜索引擎逐渐出现并受到了广泛关注。
本文将围绕该主题进行探讨。
一、知识图谱的概念及发展知识图谱源于谷歌的“知识图谱”项目，它是一种用于表示语义化信息的结构化数据。
在知识图谱中，通过对现实世界中实体、关系、属性的描述，形成了一个从更广泛、抽象的层面上描述现实世界的机器可读的知识库。
知识图谱的发展可以追溯到20世纪60年代的人工智能研究中，它是一种通过将人类知识和机器逻辑结合起来来实现更智能化的处理能力的方式。
在过去的几年中，谷歌、微软、IBM等公司先后推出自己的知识图谱，同时一些知识图谱相关的技术公司也兴起。
这些公司主要通过利用结构化数据的方式，来更好地帮助客户研究和分析他们所涉及的领域，例如物联网、医疗保健等领域。
近年来，随着人工智能技术的快速发展，基于知识图谱的应用也越来越广泛，其中一些最为有影响力的应用如智能语音助手和智能问答系统就是基于知识图谱。
二、传统搜索引擎的局限性将搜索引擎应用于寻找信息时，最重要的是关键词。
搜索引擎系统会根据搜索关键词在数据库中匹配结果，并展示在用户页面中。
然而，单一的关键词语可能携带着不丰富的信息，且存在歧义性问题。
例如，在搜索关键词“苹果”时，系统很难判断是指水果还是科技公司。
而在涉及到复杂的问题时，搜索引擎系统还需要理解内容上下文，并分析相关的语义、逻辑和常识，进而给出更准确的结果，而这种理解是传统搜索引擎所缺乏的。
因此，传统搜索引擎的局限性在如何理解应用领域的知识和怎样对结果进行语义表示这两个方面体现得最为明显。
三、基于知识图谱的语义搜索引擎早期的基于知识图谱的搜索引擎主要是针对谷歌的知识图谱进行了应用。
通过结合这些应用，用户可以使搜索引擎系统更好地理解他们的搜索需求。
Knowledge-acquisition
Knowledge acquisition is a method of learning, first proposed by Aristotle in his seminal work"Organon". Aristotle proposed that the mind at birth is a blank slate, or tabula rasa. As a blank slate it contains no knowledge of the objective, empirical universe, nor of itself.知识获取是一种学习的方法，是由亚里士多德在他"推论法"的半监督工作中首次提出的。
亚里士多德认为生下来时大脑就像是一块白板或者一张白纸。
作为一块白板，不包括任何的客观知识，先验领域，及本身。
知识获取是一种学习方法，第一次由亚里士多德在他的开创性的著作《推理法》中提出。
亚里士多德提出，大脑在出生时是一个白板。
就像白板那样，它没有容纳任何关于客观的、经验主义的宇宙的知识，抑或是关于它自己的知识。
"Knowing subject" is often the description of a mind with acquired knowledge. A human mind cannot be a "knowing subject" until it has "acquired knowledge". "Acquired" in this sense can be either an adjective, as in "that which has been acquired"; or a verb, as in the act of acquisition.)“认知主体”是经常用于描述已经获取知识的大脑。
- 1、下载文档前请自行甄别文档内容的完整性，平台不提供额外的编辑、内容补充、找答案等附加服务。
- 2、"仅部分预览"的文档,不可在线预览部分如存在完整性等问题,可反馈申请退款(可完整预览的文档不适用该条件!)。
- 3、如文档侵犯您的权益，请联系客服反馈,我们会尽快为您处理(人工客服工作时间：9:00-18:30)。
Abstract. This paper presents a strategy to handle incomplete knowledge during acquisition process. The goal of this research is to develop formal tools that benefit the law of semantic balance. The assumption is used that a situation inside the object’s boundary in some world should be in balance with a situation outside it. It means that continuous cognition of an object aspires to a complete knowledge about it and knowledge about internal structure of the object will be in balance with knowledge about relationships of the object with other objects in its environment. It is supposed that one way to discover incompleteness of knowledge about some object is to measure and compare knowledge about its internal and external structures in an environment. If there exist differences between the internal and the external semantics of an object, then these differences can be used to derive more knowledge about the object to make knowledge complete. The knowledge refinement process is done step-by-step as a continuous evolution of a knowledge base. Each step consists first automatic analysis of semantic balance which is then followed by attempts to derive knowledge that will balance differences between internal and external semantics of the object. This paper describes an algebra that is used to describe the internal and external semantics of an object and to derive unknown part of it. The results presented are mostly the
This paper deals with a cognition strategy based on semantic model of world. It describes one refinement technique to handle incompleteness of knowledge in acquisition process. Knowledge base refinement is now one of the central problems of expert systems (Willkins [12]). It needs a fundamental research using basic concepts of philosophy and cognitive science. The main focus of this paper is to describe and apply one of the fundamental philosophic principles - “Balance in Nature” in terms of semantic networks to define the strategy of improving knowledge during a cognition process. The goal of this research is to develop formal metasemantic algebra that benefits the law of semantic balance, i.e. there should be balance between the internal and external semantics of an object in the possible world (WORLD in short onwards in this paper). If this semantic law holds in the WORLD and there exists any difference between the internal and the external semantics of an object, then this difference can be used to acquire more knowledge about the object. The refinement proceeds step-by-step as a continuous evolution of
Knowledge Acquisition Based on Semantic Balance of Internal and External Knowledge
Vagan Y. Terziyan, Seppo Puuronen
Department of Computer Science and Information Systems, University of Jyvaskyla, P.O.Box 35, FIN-40351, Jyvaskyla, Finland e-mail: {vagan, sepi}@jytko.jyu.fi
knowledge base, where each step includes two substeps: first substep makes automatic analysis of semantic balance and if the situation is not in balance then the second substep attempts to derive knowledge that will reestablish balance. Knowledge base refinement as a method to improve an incorrect, inconsistent, and incomplete domain theory has also been suggested by Willkins [12]. His ODYSSEUS system refines knowledge bases of advanced rule-based systems. It learns by watching apprentice. His refinement program tries to construct an explanation of an observed action of an expert. Context of explanation allows to generate candidate of knowledge base repairs. ODYSSEUS system is designed for use with heuristic classification using hypothesis-directed reasoning. A processing stage prior to apprenticeship learning removes an inconsistent knowledge from the domain theory, which is responsible for deterioration of the performance of the system due to sociopathic interactions between elements of the domain theory. Sociopathicity implies that some kind of global refinement for the acquired knowledge is essential for machine learning. Current books in formal semantics widely use approaches based on fundamental conceptual research in philosophy and cognitive psychology. For example Larson and Segal [6] give equal weight to philosophical, empirical, and formal discussions. They study a particular human cognitive competence governing the meanings of words and phrases. They argue that speakers have unconscious knowledge of the semantic rules of their language. Knowledge of meanings is both the semantics of domain attributes (properties and relations) and learning technology how to derive semantics of inconsistent and incomplete meanings. During last several years one can see the growth of interest to semantic models of World (Li [7]). The reason seems to be in extremely fast development of global information networks. Study of large domains with numerous objects and groups of objects with relations requires possibilities to have closer considerations inside objects (their properties), outside objects (their external semantics), and both inside and outside considerations also for groups of objects. This kind of situations arises for example with WWW, the organization of which requires net-based semantic models and good technology of self-organization to handle problems of their complexity (Heylighen & Bollen [4]). One can interpret acquired knowledge only if “internal” part of it is in a conformity with “external” one. In other words these parts have to be in “balance”. Phenomena of balance is very important in understanding problems related to knowledge (Schultz, Mareschal & Schmidt [10]). It was used by Kamimura [5] to minimise incompleteness of internal and external knowledge represented in neural networks. Balance has to be taken into account in cooperative modeling and machine learning, according to Morik [8] and DeJong [2], in systems control according to Sen & Jugo [11]. The main focus of this paper is to describe in formal way and apply the fundamental philosophic principle of balance between internal and external semantics of a domain object. We use and further develop the formalism of metasemantic algebra (Puuronen & Terziyan [9]), (Bondarenko, Grebenyuk & Terziyan [1]), (Grebenyuk et al. [3]) to describe internal and external semantics of any single or compound object in a network and the formal use of the law of