Narrow Results

Self-adaptation has been frequently employed in evolutionary computation. Angeline¹ defined three distinct adaptive levels which are: population, individual and component levels. Cultural Algorithms have been shown to provide a framework in which to model self-adaptation at each of these levels. Here, we examine the role that different forms of knowledge can play in the self-adaptation process at the population level for evolution-based function optimizers. In particular, we compare the relative performance of normative and situational knowledge in guiding the search process. An acceptance function using a fuzzy inference engine is employed to select acceptable individuals for forming the generalized knowledge in the belief space. Evolutionary programming is used to implement the population space. The results suggest that the use of a cultural framework can produce substantial performance improvements in execution time and accuracy for a given set of function minimization problems over population-only evolutionary systems.

We present in this paper an approach to providing cooperativeness in database querying using artificial intelligence techniques. The main focus is a cooperative interface that assists nonexperienced and casual users in extracting useful answers from a relational database. Our approach relies on an architecture that comprises two knowledge bases which store rules that describe the application domain and guide the process of query formulation and answering. A subset of SQL is used for expressing queries, and the cooperative interface relieves the user from knowing its full syntax and the structure of the database.

This paper proposes a computationally inexpensive algorithm that utilizes player data to optimize nonplayer character pathfinding in a competitive, multiplayer environment and focuses on imitating the player behavior. The algorithm’s input consists of player statistics gathered during the current and previous matches with additional time and space context, similar in design to influence maps. The input is then enriched with two additional, novel variables, allowing easy online fine-tuning of the output. The obtained result influences the final edge values of the map graph. Any known pathfinding algorithm that works with digraphs can then be utilized to control the agent. This paper contains exemplary results obtained when analyzing input on a map modeled after an existing map in the video game Unreal Tournament.

The control of small-scale systems using either knowledge-based or neural net methods is quite feasible. Large scale systems, however, introduce complexities in modeling and excessive computation time. This paper attacks these difficulties by breaking down the problem into a hierarchy of control contexts. The lowest level of this hierarchy is implemented as rule sets and/or neural networks. A method using "hints" is shown to greatly reduce training time in back-propagation neural nets.

In this paper, we propose a system aimed at interpreting 3-D scenes from 2-D image sequences in the case of scenes containing solid objects that can be described as being made up of polyhedral subparts. The major problems addressed are the definition of a suitable search strategy to reduce the computational complexity of the problem, and the exploitation of the information provided by motion analysis applied to the image sequence. The object models' representation is based on the definition of view classes. Experimental results on simple real scenes are presented.

Knowledge-based systems (KBSs) or expert systems (ESs) are able to solve problems generally through the application of knowledge representing a domain and a set of inference rules. In knowledge engineering (KE), the use of KBSs in the real world, three principal disadvantages have been encountered. First, the knowledge acquisition process has a very high cost in terms of money and time. Second, processing information provided by experts is often difficult and tedious. Third, the establishment of mark times associated with each project phase is difficult due to the complexity described in the previous two points. In response to these obstacles, many methodologies have been developed, most of which include a tool to support the application of the given methodology. Nevertheless, there are advantages and disadvantages inherent in KE methodologies, as well. For instance, particular phases or components of certain methodologies seem to be better equipped than others to respond to a given problem. However, since KE tools currently available support just one methodology the joint use of these phases or components from different methodologies for the solution of a particular problem is hindered. This paper presents KEManager, a generic meta-tool that facilitates the definition and combined application of phases or components from different methodologies. Although other methodologies could be defined and combined in the KEManager, this paper focuses on the combination of two well-known KE methodologies, CommonKADS and IDEAL, together with the most commonly-applied knowledge acquisition methods. The result is an example of the ad hoc creation of a new methodology from pre-existing methodologies, allowing for the adaptation of the KE process to an organization or domain-specific characteristics. The tool was evaluated by students at Carlos III University of Madrid (Spain).

This paper describes in full detail an analysis of two expert system shells: Level 5 Object and Kappa PC. The major components of these tools (knowledge representation, inference and control, developer interface, user interface and explanation facility, interface to external data sources, support and documentation) were studied and tested by means of small prototypes. Results and experiences of this work are given together with some software engineering remarks.

Regional Knowledge is useful in identifying patterns of relationships between variables, and it is particularly important in solving constrained global optimization problems. However, regional knowledge is generally unavailable prior to the optimization search. The questions here are: 1) Is it possible for an evolutionary system to learn regional knowledge during the search instead of having to acquire it beforehand? and 2) How can this regional knowledge be used to expedite evolutionary search? This paper defines regional schemata to provide an explicit mechanism to support the acquisition, storage and manipulation of regional knowledge. In a Cultural Algorithm framework, the belief space "contains" a set of these regional schemata, arranged in a hierarchical architecture, to enable the knowledge-based evolutionary system to learn regional knowledge during the search and apply the learned knowledge to guide the search. This mechanism can be used to guide the optimization search in a direct way, by "pruning" the infeasible regions and "promoting" the promising regions. Engineering problems with nonlinear constraints are tested and the results are discussed. It shows that the proposed mechanism is potential to solve complicated non-linear constrained optimization problems, and some other hard problems, e.g. the optimization problems with "ridges" in landscapes.

Knowledge-based engineering and computational intelligence are expected to become core technologies in the design and manufacturing for the next generation of space exploration missions. The literature is contradictory on how we are to assess such systems. Studies indicate significant disagreement regarding the amount of testing needed for system assessment. The sizes of standard black-box test suites are impractically large since the black-box approach neglects the internal structure of knowledge-based systems. On the contrary, practical results repeatedly indicate that only a few tests are needed to sample the range of behaviors of a knowledge-based program.

In this paper, we model testing as a search process over the internal state space of the knowledge-based system. When comparing different test suites, the test suite that examines larger portion of the state space is considered more complete. Our goal is to investigate the trade-off between the completeness criterion and the size of test suites. The results of testing experiment on tens of thousands of mutants of real-world knowledge based systems indicate that a very limited gain in completeness can be achieved through prolonged testing. The use of simple (or random) search strategies for testing appears to be as powerful as testing by more thorough search algorithms.

In developing knowledge-based systems, the process of collecting the knowledge from the experts, representing it in certain formats, and verifying it is required. It is however not easy to verify the formulated knowledge base by checking if a desired conclusion is derived by a sequence of inferring steps. This paper suggests a model of inference browsers by which the knowledge engineers may easily consult a sequence of inferring steps and verify the knowledge base. The suggested inference browser provides the environment in which the knowledge engineers may observe a sequence of inferring steps displayed in the graphical form, access directly the contents of the rules and the facts on the sequence, and observed a newly generated sequence of inferring steps when some of the rules or the facts are changed. Further, based on the graphically displayed inferring sequence, the inference browser itself detects the erroneous inferring step if it exists, analyzes it, and corrects the associated errors in the knowledge base. Finally the suggested inference browser is compared to other similar tools in terms of the facilities they provide.

In this paper, we present a development framework and verification methodologies for knowledge-based systems (KBSs) with real-time systems as our target system. The framework originates from an integration of three software development paradigms: rapid prototyping, operational specification, and transformational implementation. Based on this framework, we present RT-FRORL as a formal requirements specification language which exploits knowledge representation techniques as an aid in the specification, development, and verification of a KBS for real-time systems. RT-FRORL uses a combination of resolution refutation, anomaly detection matrix, and algorithms methods to verify a number of properties which might exist in KBSs. By incorporating RT-FROHL and its verification methods with the underlying framework, it lays a very strong foundation to deal with the current issues in KBSs verification.

This paper describes a generic, knowledge-based mechanism for selecting among a fixed set of alternatives. The mechanism, termed sponsor-selector has been used as a control mechanism in a number of different knowledge-based systems including problem-solver integration applications in routine design, diagnostic problem-solving, and navigational planning. For design, the DSPL language uses sponsor-selectors to select between alternate, fixed plans to determine the best approach for the design of an artifact. For diagnosis, the Peirce and TIPS system used sponsor-selectors as the overall control mechanism, determining which problem-solver, out of a group of problem-solving agents, to select under particular problem solving conditions. For navigation planning, the Router system used the sponsor-selector mechanism and the TIPS architecture to select between alternate problem-solving strategies. problem-solving approaches. We describe in this paper the general architecture of the sponsor-selector mechanism and how this mechanism was used in the 4 described systems, along with some performance measures and results.

Models are executable prototypes. Modeling is closely tied to simulation, which refers to the exercise of a model over a variable parametric space. Model simulations not only provide the engineer with feedback pertaining to the validity of a proposed design, but additionally allow competing designs to be compared on one or more parameters (i.e., sensitivity analysis). Models are defined from a base of several hundred primitive constructs. These constructs can define additional constructs hierarchically.

An expertⁿ–system was constructed, which retrieves software for reuse. This expert system is itself reusable and consists of many sub-systems – any one of which can invoke any other. A key feature is that any expertⁿ–system need never be modified, for purposes of reuse, once saved in a repository. Rather, it communicates all information back to the caller and lets the caller decide how and when to use it. Thus, blocks in an expertⁿ–system have very low coupling (i.e., no off-model connections). In addition, expertⁿ–systems are, as their name suggests, organized in a hierarchy. This means that very complex decision-making systems can be called into play with minimal effort. Growing the repository is equivalent to learning.

With the increases in the levels of automation and computerization, supervisory control systems are becoming increasingly common in commercial and military applications. A supervisory control system consists of one or more human operators interacting with highly automated components such as those seen in satellite ground control, flexible manufacturing systems, or nuclear power plants. Humans typically perform cognitively intense tasks such as monitoring, planning, real-time control, and troubleshooting, and are ultimately responsible for the safe and efficient operation of the overall system. Although developments on supervisory control have led to useful applications in interface design and automation, there is a scarcity of research that empirically evaluates human decision making in supervisory control through emulation of task performance using knowledge-based systems. In the context of dynamic planning involving simulated search and rescue missions using ground based autonomous robots and uninhabited aerial vehicles, we developed a knowledge-based system that mimics supervisory control performance. This paper describes the application domain, the details of the simulation model, and the implementation and assessment of a knowledge-based system that mimics human supervisory control performance.

The problem of assigning gates to aircraft that are due to arrive at an airport is one that involves a dynamic task environment. Airport gates can only be assigned if they are currently available, but deciding which gate to assign to which flight also involves satisfying multiple additional constraints. Once a solution has been found, new incoming flights will have approached the airspace of the airport in question, and these will require arrival gates to be assigned to them, so the entire process must be repeated. We have come up with a combined knowledge-based and evolutionary approach for performing the airport gate scheduling task. In this paper we present our model from a theoretical point of view, and then discuss a particular implementation of it for the scheduling of arrival gates in a specific airport and show some experimental results.

From an information systems perspective, the assessment of commercial websites can be assessed objectively or subjectively. From a business point of view, they can be assessed quantitatively or qualitatively. This paper describes taxonomy of website assessment approaches and proposes a knowledge-based system approach to evaluate commercial websites effectively. Given a large number of constantly evolving commercial websites on the Internet, our approach shows an efficient way of automatic assessment of commercial websites.

One of the ways of attaining higher productivity and profitability in machining processes is to enhance process supervision and control systems. Because of the nonlinear behavior and complexity of machining processes, researchers have used knowledge-based techniques to improve the performance of such systems. Their main reason for using this approach is that a suitable process model is indispensable for both automatic supervision and control, yet traditional approaches frequently fail to yield appropriate models of complex (nonlinear, time-varying, ill-defined) processes, such as machining certainly is, while knowledge-based methods provide novel tools for dealing with process complexity. One of the most powerful of these tools is fuzzy logic, which was the authors' chosen design approach. An overview is given of the main aspects of fuzzy logic and its application to modeling and control by means of the so-called Fuzzy Logic Device (FLD). Available methods suitable for process supervision are also reviewed, including pattern recognition and so-called intelligent supervision. Emphasis is placed on modeling by means of fuzzy clustering techniques. The machining process is typified with a systemic (input/output) approach, as is necessary for modeling and control purposes. Finally the authors' experience with successful applications of fuzzy logic to the modeling (fuzzy clustering) and control (fuzzy hierarchical control) of the machining process, implemented in a machining center, is presented. These thoroughly assessed real-world implementations corroborate the potential of knowledge-based techniques.

The problem of assembly process planning is critical for the automation and integration of production, due to the combinatorial complexity and the requirement of both flexibility and productivity. This chapter presents an integrated knowledgebased approach and system for automatic generation, evaluation and selection, and visualization of assembly sequences. In this chapter, information and knowledge about a product and its assembly processes is modeled and represented by using integrated object model and generic P/T net formalisms. The comprehensive knowledge-based integration coordinates design and assembly sequence planning in the complex interactions and domain knowledge between the technical and economical aspects. By using the integrated representational model, all feasible assembly sequences are generated by decomposing and reasoning the leveled feasible subassemblies, and represented through Petri net modeling. Both qualitative and quantitative constraints are then used to evaluate each assembly part and operation sequence individually and the entire sequences as well. Based on assemblability analysis and evaluation and predefined task time analysis, estimates are made for the assembly time and cost and operation's difficulty of product when each of these sequences is used. Some quantitative criteria such as assembly time and cost, operation difficulty and part priority index are applied to select the optimal assembly sequence. Finally, a prototype integrated knowledge-based assembly planning system is developed to achieve the integration of generation, evaluation and selection, and visualization of the assembly sequences.

This chapter shows how Fuzzy Pattern Matching techniques can be applied to the design of a knowledge-based system that can diagnose the most common faults of industrial rotating machinery through the evaluation of vibration data. The system is able to perform the tasks of Fault Detection, Fault Isolation and Fault Identification, and can handle the vagueness implicit in the diagnosis linguistic knowledge, as well as several sources for uncertainty that are generated during the vibration measurement process. Furthermore, a Genetic Algorithms-based module has also been included that, when enough fault data is available, has the ability to adapt some of the system's parameters in order to optimize its diagnosis performance.

The control of small-scale systems using either knowledge-based or neural net methods is quite feasible. Large scale systems, however, introduce complexities in modeling and excessive computation time. This paper attacks these difficulties by breaking down the problem into a hierarchy of control contexts. The lowest level of this hierarchy is implemented as rule sets and/or neural networks. A method using "hints" is shown to greatly reduce training time in back-propagation neural nets.