一个基于知识库及其自动推理机制的ICAI(化学)系统

设计并实现了一种新型的ＩＣＡＩ系统。该系统以自动推理技术为基础,利用化学知识库,不仅实现了ＩＣＡＩ的知识集散功能,还成功地实现了知识揭示功能,不同于常垢ＩＣＡＩ的单纯检索－播放作用,该系统还具有化学用语层次上的人－机交互、基于自动推理的化学式与中文名称的双向翻译、化学问题求解等多多种智能功能。该系统还具有开放性,可以让用户在使用中调整系统的性能、补充存储的知识信息。该文比较了新型系统与流行的常规系     

一个基于知识库及自动推理机制的化学反应系统

提出了一种基于知识库及自动推理机制的化学反应系统,详细阐述了该自动推理系统的技术架构与算法实现.主要收集了无机化学知识,分析并提取相关化学反应规则,建立了相应的化学知识库,实现了由添加反应物到化学反应生成物的一系列自动推理过程.通过稀硫酸和铁反应实例表明,该系统对开发智能的虚拟实验平台,以及学生运用软件自主学习化学知识,掌握化学规律与现象,具有重要作用.     

GIS环境下制图自动综合

借助GIS的可视化以及GIS的空间分析工具,制图自动综合的研究进入了一个新阶段;一方面,GIS扩大了制图自动综合的内涵,另一方面,制图自动综合推动了GIS的发展;丰富了GIS的研究内容。实际上,制图自动综合应该是GSI系统的重要组成部分或应具有的重要功能。制图自动综合的研究手段和研究方法越来越丰富并取得了很大进展;在总结前人研究的基础上提出了GIS分层支持下的面向地理特征的自动综合,实验表明这种方法是可行的,但仍然存在诸多问题,这种方法的完善必须走基于知识综合的道路。     

Analogical Learning and Automated Rule Constructions

This paper describes some experiments of analogical learning and automated rule construction.The present investigation focuses on knowledge acquisition,learning by analyogy,and knowledge retention.The developed system initially learns from scratch,gradually acquires knowledge from its environment through trial-and-error interaction,incrementally augments its knowledge base,and analogically solves new tasks in a more efficient and direct manner.     

Supporting connectivism in knowledge based engineering with graph theory,filtering techniques and model quality assurance

Mass-customization has forced manufacturing companies to put significant efforts to digitize and automate their engineering and production processes. When new products are to be developed and introduced the production is not alone to be automated. The application of knowledge regarding how the product should be designed and produced based on customer requirements also must be automated. One big academic challenge is helping industry to make sure that the background knowledge of the automated engineering processes still can be understood by its stakeholders throughout the product life cycle.The research presented in this paper aims to build an infrastructure to support a connectivistic view on knowledge in knowledge based engineering. Fundamental concepts in connectivism include network formation and contextualization, which are here addressed by using graph theory together with information filtering techniques and quality assurance of CAD-models. The paper shows how engineering knowledge contained in spreadsheets, knowledge-bases and CAD-models can be penetrated and represented as filtered graphs to support a connectivistic working approach. Three software demonstrators developed to extract filtered graphs are presented and discussed in the paper.     

Profiling: From data to knowledge

Profiling is not about data but about knowledge. It provides a crucial technology in a society that is flooded with noise and information. Profiling is another term for sophisticated pattern recognition, and the enabling technology for Ambient Intelligence. It confronts us with a new type of inductive knowledge, inferred by means of automated algorithms. To the extent that decisions that impact our lives are based on such knowledge, we need to develop the means to make this knowledge accessible for individual citizens and provide them with the legal and technological tools to anticipate and contest such knowledge or challenge its application.     

Knowledge engineering for an intelligent case-based system for help desk operations

Help desks are computer-aided environments in customer support centers that provide frontline support to external and internal customers. The paper reports on an automated help desk system developed at an information technology company. With the proliferation of diverse software and hardware, the center provides support to a large variety of client systems. The number of calls increases while the turnover rate of employees is high, which means the cost of training escalates. The objective of this project is to develop an automated case-based help desk system to support both call center personnel and customers. The system would contribute to shortening the response time on incoming calls and reduce training time for new employees. The focus of the paper is on the knowledge engineering process of the system. We discuss in detail the knowledge acquisition, knowledge representation, system implementation and verification processes, and we emphasize the structured and automated development methods adopted.     

An approach for reverse engineering of design patterns

For the maintenance of software systems, developers have to completely understand the existing system. The usage of design patterns leads to benefits for new and young developers by enabling them to reuse the knowledge of their experienced colleagues. Design patterns can support a faster and better understanding of software systems. There are different approaches for supporting pattern recognition in existing systems by tools. They are evaluated by the Information Retrieval criteria precision and recall. An automated search based on structures has a highly positive influence on the manual validation of the results by developers. This validation of graphical structures is the most intuitive technique. In this paper a new approach for automated pattern search based on minimal key structures is presented. It is able to detect all patterns described by the GOF [15]. This approach is based on positive and negative search criteria for structures and is prototypically implemented using Rational Rose and Together.     

The three-state test for chaos detection in discrete maps

The three-state test (3ST) – a new approach for chaos detection in discrete chaotic maps is presented. The scheme is based on statistical analyses of patterns obtained from ascending sorting of the system states. In addition to its ability for clear discernment between chaotic, quasi-periodic and periodic dynamical systems, the detection of periods of stable cycles is also automated with 3ST. The method is directly applied on data series generated by chaotic maps and does not require a priori knowledge of the equations of the underlying system. It also presents the advantage of not having to depend on the nature of the vector field as well as its dimensionality and is computationally low cost. The effectiveness of the 3ST is confirmed using two well known and widely studied chaotic maps: the logistic map and the Henon 2D map.     

Evolutionary algorithms and de novo peptide design

One of the goals of computational chemistry is the automated de novo design of bioactive molecules. Despite significant progress in computational approaches to ligand design and efficient evaluation of binding energy, novel procedures for ligand design are required. Evolutionary computation provides a new approach to this design issue. This paper presents an automated methodology for computer-aided peptide design based on evolutionary algorithms. It provides an automatic tool for peptide de novo design, based on protein surface patches defined by user. Regarding the restrictive constrains of this problem a special emphasis has been made on the design of the evolutionary algorithms implemented.     

The Role of the Mizar Mathematical Library for Interactive Proof Development in Mizar

The Mizar system is one of the pioneering systems aimed at supporting mathematical proof development on a computer that have laid the groundwork for and eventually have evolved into modern interactive proof assistants. We claim that an important milestone in the development of these systems was the creation of organized libraries accumulating all previously available formalized knowledge in such a way that new works could effectively re-use all previously collected notions. In the case of Mizar, the turning point of its development was the decision to start building the Mizar Mathematical Library as a centrally-managed knowledge base maintained together with the formalization language and the verification system. In this paper we show the process of forming this library, the evolution of its design principles, and also present some data showing its current use with the modern version of the Mizar proof checker, but also as a rich corpus of semantically linked mathematical data in various areas including web-based and natural language proof presentation, maths education, and machine learning based automated theorem proving.     

基于知识发现的范例推理系统

1 引言范例推理(Case-Based Reasoning,CBR)是近十几年来人工智能中发展起来的区别于基于规则推理的一种推理模式,它是指借用旧的事例或经验来解决问题、评价解决方案、解释异常情况或理解新情况。CBR兴起的主要原因是传统的基于规则的系统存在诸多的缺点,如:在知识获取问题上存在困难,对于处理过的问题没有记忆而导致推理效率低下,不能有效地处理例外情况,整体性能较为脆弱等等,而CBR恰好能解决以上问题。     

Process knowledge based multi-class support vector classification (PK-MSVM) approach for surface defects in hot rolling

Random surface defects occur during the hot bar rolling of steels and are identified either by manual or by automated inspection techniques. Manual inspection techniques are purely based on the process knowledge of the inspector such as the location, type and kind of defects, and the primary sources of these defects. The automated techniques, to identify and classify the defects, rely on machine vision technologies and image processing algorithms based on support vector machines, wavelets, image processing and statistical inference. Both these approaches have their own advantages and limitations. To improve the accuracy of classification of these defects a process knowledge based support vector classification scheme is proposed (called PK-MSVM) which combines feature extraction task of automated inspection with the process knowledge. The defect observation data from the imaging sensor is transformed to include this process knowledge. Three attributes of the defects – length to width ratio, longitudinal location and transverse location- are used for this transformation are they are closely related to the thermo-mechanics of the rolling process. Different formulations of the multi-class support vector machines (MSVMs) are compared for this classification with or without process knowledge based transformation: one-against-one, one-against-all and Hastie’s algorithm of multi class SVM. It is found that the new approach (PK-MSVM) performs better than traditional MSVM for all the three formulations. For the best case, the performance sees a jump of more than 100%. Thus incorporating process knowledge in identification and classification does increase the reliability of inspection considerably.     

Interactive Correction and Recommendation for Computer Language Learning and Training

Active learning and training is a particularly effective form of education. In various domains, skills are equally important to knowledge. We present an automated learning and skills training system for a database programming environment that promotes procedural knowledge acquisition and skills training. The system provides meaningful knowledge-level feedback such as correction of student solutions and personalized guidance through recommendations. Specifically, we address automated synchronous feedback and recommendations based on personalized performance assessment. At the core of the tutoring system is a pattern-based error classification and correction component that analyzes student input in order to provide immediate feedback and in order to diagnose student weaknesses and suggest further study material. A syntax-driven approach based on grammars and syntax trees provides the solution for a semantic analysis technique. Syntax tree abstractions and comparison techniques based on equivalence rules and pattern matching are specific approaches.     

Automated knowledge acquisition for the surface-mount PWB assembly domain

The development of knowledge-based (or expert) systems for the surface-mount printed wiring board (PWB) assembly domain requires the understanding and regulation of several complex tasks. While the knowledge base in an expert system serves as a storehouse of knowledge primitives, its design and development is a bottleneck in the expert system development life-cycle. Therefore the development of an automated knowledge acquisition (KA) facility (or KA tool) would facilitate the implementation of expert systems for any domain. This paper describes an automated KA tool that helps to elicit and store information in domain-specific knowledge bases for surface-mount PWB assembly. A salient feature of this research is the acquisition of uncertain information.     

Premise Selection for Mathematics by Corpus Analysis and Kernel Methods

Smart premise selection is essential when using automated reasoning as a tool for large-theory formal proof development. This work develops learning-based premise selection in two ways. First, a fine-grained dependency analysis of existing high-level formal mathematical proofs is used to build a large knowledge base of proof dependencies, providing precise data for ATP-based re-verification and for training premise selection algorithms. Second, a new machine learning algorithm for premise selection based on kernel methods is proposed and implemented. To evaluate the impact of both techniques, a benchmark consisting of 2078 large-theory mathematical problems is constructed, extending the older MPTP Challenge benchmark. The combined effect of the techniques results in a 50 % improvement on the benchmark over the state-of-the-art Vampire/SInE system for automated reasoning in large theories.     

A case-based system for process planning

Process planning is the phase of manufacturing that is concerned with the selection, and sequencing of manufacturing operations necessary to transform an initial stock material into a finished part. It is a tedious operation that requires highly skilled and experienced personnel of which there is currently great shortage. To disseminate the costly expertise and to reduce process planning times, which tend to add high costs to small batch production, many automated computer systems have been introduced and applied. All these systems, though, require the supervision of an experienced human being and fail to capture the knowledge and reasoning behind process planning decisions. The causes of the lack of an efficient automatic system for process planning are the unique characteristics of the domain. In contrast to other areas where knowledge-based and expert systems have been applied, process planning demands the solution of several different planning problems before a final solution is achieved. Every change introduced to the previous world model creates a completely new world model with its own, new constraints and preconditions that nedd to be satisfied. This, in turn, affects the applicability of the knowledge to the new model.

To provide solutions to the above problems we have designed a prototypical knowledge-based system that uses the high level, dynamic memory structures of MOPs (Memory Organization Packages), meta-MOPs and TOPs (Thematic Organization Packets) to rearrange its knowledge according to its experiences and to predict and avoid errors. To model the dynamic, sharable knowledge and the constantly changing world model a knowledge-representation language named TOLTEC has been designed and used in the system. Furthermore, we propose a novel planning method based on abstract plans and constraints that can solve planning problems in uncertain domains given incomplete information.     

Knowledge acquisition and knowledge representation with class: the object-oriented paradigm

Knowledge acquisition and knowledge representation are the fundamental building blocks of knowledge-based systems (KBSs). How to efficiently elicit knowledge from experts and transform this elicited knowledge into a machine usable format is a significant and time consuming problem for KBS developers. Object-orientation provides several solutions to persistent knowledge acquisition and knowledge representation problems including transportability, knowledge reuse, and knowledge growth. An automated graphical knowledge acquisition tool is presented, based upon object-oriented principles. The object-oriented graphical interface provides a modeling platform that is easily understood by experts and knowledge engineers. The object-oriented base for the automated KA tool provides a representation independent methodology that can easily be mapped into any other object-oriented expert system or other object-oriented intelligent tools.     

FIELDED MACHINE LEARNING SYSTEM FOR VOCATIONAL COUNSELLING

A fielded machine learning system for vocational counselling is presented in which learning is based on adjustments of weights on links in a network. The system exemplifies how a specific representation, consisting of weights assigned to associations between keywords, enables the effective use of machine learning algorithms for acquiring and continually refining domain knowledge. The representation is designed for coping with the types of knowledge that can be found in weak theory domains, that is, knowledge too difficult to formalize because it is incomplete or vague. Knowledge acquisition and knowledge refinement processes are automated in order to efficiently decrease the effect of unreliable knowledge caused by unknown or unspecified biases inherent in the knowledge sources. The knowledge acquisition algorithms presented here are capable of coping with incomplete and vaguely defined domain knowledge. The knowledge refinement algorithms are used on-line to enable a continuous refinement of ill-defined domain knowledge.     

Knowledge based system for scheduling and control of an automated manufacturing cell

Cell Manager (Cm) is a prototype knowledge based system for real-time control and short-term planning of an automated manufacturing facility. It uses background of mathematical programming, simulation, and heuristic search. The Cm engine allows tracking of time related events and facts in discrete or continuous time. The use of Cm is illustrated on a cell that processes discrete batches of parts. There are four workstations and the material handling system consists of automated guided vehicles.