Economic evaluation of a new oil well is important for decision-making in the petroleum industry, and this evaluation is based on a good prediction on a well's production. However, it is difficult to accurately predict a well's production due to the complex subsurface conditions of reservoirs. The industrial standard approach is to use either curve-fitting methods or complex and time-consuming reservoir simulations. In this paper, an enhanced decision tree learning approach called neural-based decision tree (NDT) model is applied in an attempt to investigate its performance in predicting petroleum production. The primary strength of this model is that it can capture dependencies among attributes, and therefore, it is likely to provide an improved or more accurate prediction (Lee and Yen, 2002). This paper presents an application of the NDT model for petroleum prediction. Our models were developed based on the five most significant parameters that affect oil production: permeability, porosity, first shut-in pressure, residual oil and saturation of water. The five parameters were used as input variables, and oil production is the output variable for modeling. Four different models were generated in the modeling process, and each involves a different combination of parameters. First, an overall oil production model is developed using the three geoscience parameters of permeability, porosity and first shut-in pressure. Secondly, two different models, with different input parameters, were developed to predict production in the post-water flooding stage only. The results of the above models indicate that data-driven models may not be effective for classifying the data set. Hence, a trend model was developed in an attempt to improve the effectiveness and accuracy of the predictive model. The result shows that the trend model can provide an improved performance, and its performance is comparable to that of the artificial neural network.

Cognitive informatics (CI) is the transdisciplinary enquiry of cognitive and information sciences that investigates into the internal information processing mechanisms and processes of the brain and natural intelligence, and their engineering applications via an interdisciplinary approach. CI develops a coherent set of fundamental theories and denotational mathematics, which form the foundation for most information and knowledge based science and engineering disciplines such as computer science, cognitive science, neuropsychology, systems science, cybernetics, software engineering, knowledge engineering, and computational intelligence. This paper reviews the central doctrine of CI and its applications. The theoretical framework of CI is described on the architecture of CI and its denotational mathematic means. A set of theories and formal models of CI is presented in order to explore the natural and computational intelligence. A wide range of applications of CI are described in the areas of cognitive computers, cognitive properties of knowledge, simulations of human cognitive behaviors, cognitive complexity of software, autonomous agent systems, and computational intelligence.

This study describes the development of a dynamic knowledge-based reasoning-enhanced model predictive control system (KBRECS) for in-situ bioremediation processes. The automated control system balances the complex physical, chemical, and biological processes involved in the remediation process while minimizing overall cost of the entire remediation process. The control system includes an optimization subsystem and a monitoring subsystem. The optimization subsystem consists of a simulation model supported by an optimization function which is designed to generate a series of optimal control actions. The monitoring subsystem is a knowledge-based system which is designed to monitor and adjust the online control actions. The numerical simulation model describes the fate and transport of the subsurface contaminants. The optimization function is a constrained, nonlinear function that has been implemented using a genetic algorithm (GA). Intermediate genetic algorithm individuals are indexed and stored in the knowledge base, thereby reducing search times for values to replace the unqualified schemes used by the monitoring subsystem. The system was applied to a lab experiment and compared with the control system presented in [9]. The results indicated that the knowledge based reasoning system enhanced the control system by generating an appropriate control strategy and adjusting control actions promptly. This helps to enhance efficiency in control of the in-situ bioremediation process at petroleum-contaminated groundwater systems.

This paper presents the Knowledge Modeling System (KMS) and its application. The KMS supports users in formalizing and documenting knowledge elements acquired for development of knowledge-based systems. The system was developed based on a knowledge modeling technique called the Inferential Modeling Technique. It facilitates building an application ontology of a domain by explicitly structuring and formalizing both domain and task knowledge of any industrial problem domain. The system also supports knowledge sharing by converting the ontology into the Extensible Mark-Up Language (XML). The tool is compared against some other existing efforts at ontology construction support. Application of the KMS for constructing an application ontology in the domain of monitoring and control of a petroleum separation process is also presented.

An ontology is a comprehensive knowledge model that enables a developer to practice a "higher" level of reuse, namely knowledge reuse. To achieve knowledge reuse instead of software reuse, we propose forging a closer mapping between the knowledge and software models in the development process. In this paper, we first present UML as an ontology modeling language and then describe the Ontology-Domain-System approach to deriving a system model from a UML-based ontology model.

This paper presents the Object-Oriented Knowledge Engineering (OOKE) methodology and its application in developing an expert system. OOKE is an expert system development methodology which incorporates the conceptual modelling tool of Inferential Modelling Technique into the analysis model of the Object-Oriented Software Engineering methodology. It was applied to develop a supervisory and decision support system for monitor and control of a water distribution system called the Water Advisor. The expertise, heuristics and reasoning knowledge of experts were acquired and then formulated in a model building process using the OOKE into a conceptual model which became the basis for a prototype expert system.

Researchers have embraced a variety of machine learning (ML) techniques in their efforts to improve the quality of learning programs. The recent evolution of hybrid architectures for machine learning systems has resulted in several approaches that combine rule induction methods with case-based reasoning techniques to engender performance improvements over more traditional single-representation architectures. We briefly survey several major rule-induction and case-based reasoning ML systems. We then examine some interesting hybrid combinations of these systems and explain their strengths and weaknesses as learning systems. We present a balanced approach to constructing a hybrid architecture, along with arguments in favor of this balance and mechanisms for achieving a proper balance. Finally, we present some initial empirical results from testing our ideas and draw some conclusions based on those results.

Knowledge acquisition is a major bottleneck in the efficient development of knowledge-based systems because knowledge engineers are often faced with die difficult task of creating a conceptual model of a domain unfamiliar to them. In this paper, we propose a systematic technique which would help the knowledge engineer in this difficult modelling task. We discuss development of the knowledge modelling technique which involved a synthesis of both empirical observations obtained in a case study and theoretical insights gleaned from some artificial intelligence literature. The result of the juxtaposition is the formulation of a domain-independent categorization of knowledge types and inferences, which we called the inferential model. The model serves as a template of the types of knowledge in a model of expertise. Based on the model, we derived the inferential modelling technique which facilitates analysing verbal data elicited from an expert and configuring the data into a conceptual model. The technique is applied for analysis of knowledge obtained in the case study and we demonstrate its utility in organizing the elements of knowledge. Finally we suggest how the technique differs from other knowledge modelling approaches and some weaknesses in the present version of the model.

A novel inferential modeling technique (IMT) which aims to first clarify the domain ontology and inferences before proceeding onto the dynamic processing aspects of expertise is presented. The proposed model consists of the four levels of strategy, task, inference, and domain layers. The former two levels constitute the dynamic component and the latter two the static component. The static representation consists of the domain primitives and their interrelations, while the dynamic component represents a variety of tasks or activities which manipulate the domain entities in order to accomplish objectives. It is argued that the technique is useful as a tool in the elicitation and analysis phases of the development of a knowledge-based system. A preliminary application of the technique for constructing a knowledge-based system in the chemical engineering domain is described. >