Realizing active data warehouses with off‐the‐shelf database technology

Active data warehouses belong to a new category of decision support systems, which automate decision making for routine decision tasks and semi‐routine decision tasks. Just as active database systems extend conventional database systems with event–condition–action rules for integrity constraint enforcement or procedure execution, active data warehouses extend conventional data warehouses with analysis rules that mimic the work of an analyst during decision making. This paper demonstrates how analysis rules can be implemented on top of a passive relational data warehouse system by using commercially available database technology. Copyright © 2002 John Wiley & Sons, Ltd.     

Graph-based rules and transactions for parallel and active database systems

Active database management systems are becoming increasingly popular because of their relevance to several advanced and complex database applications. The need for user-defined execution orders (or control structures) for rules is well recognized by researchers of active database management systems. Priority-based approaches (e.g., numeric priorities) have been used to specify a desired control structure among rules. However, due to the fact that fixed priorities are assigned to rules, independent of different contexts in which they may be triggered, the existing approaches are not able to allow rules to be executed following different control structures when they are triggered by different events. More flexible and expressive control mechanisms are often needed for rules in advanced database applications such as CAD/CAM, CASE, CIM and flexible manufacturing systems. Since rules in database environments are executed in a transaction framework, an expressive transaction model is needed to model complex control structures among rulesuniformly. In this work, we separate the event part from the condition-action parts of a rule and associate it with a rule graph which represents a set of rules (actually a set of condition-action pairs) sharing the same control structure. Different rule graphs can be defined under different event specifications thereby enabling a set of rules to follow different control structures when triggered by different events. We also use an expressive graph-based transaction model to incorporate the control structures of rule graphs uniformly in a transaction framework. The proposed rule and transaction modeling and execution techniques have been implemented and verified on a shared-nothing multiprocessor computer nCUBE2. In this paper, we also describe the client-server architecture and different parallel transaction and rule execution techniques that have been used for the implementation. Finally, we analyze the speedup and scaleup of the implemented system.     

A hybrid system applied to epidemic screening

Although many knowledge-based systems (KBSs) focus on single-paradigm approaches to encoding knowledge (such as production rules), human experts rarely use a single type of knowledge to solve a real-world problem. A human expert usually combines a number of reasoning mechanisms. In recent years, rule-based reasoning (RBR), case-based reasoning (CBR) and model-based reasoning (MBR) have emerged as important and complementary reasoning methodologies in the intelligent systems area. For complex problem solving, it is useful to integrate RBR, CBR and MBR. In this paper, a hybrid epidemic screening KBS which integrates a deductive RBR system, an inductive CBR system and a quantitative MBR system is proposed. The system has been tested using real epidemic screening variables and data.     

A hybrid knowledge-based system applied to epidemic screening

Although many knowledge-based systems (KBSs) focus on single-paradigm approaches to encoding knowledge (such as production rules), experts rarely use a single type of knowledge in solving a problem. More often, an expert will apply a number of reasoning mechanisms. In recent years, rule-based reasoning (RBR), case-based reasoning (CBR) and model-based reasoning (MBR) have emerged as important and complementary reasoning methodologies in artificial intelligence. For complex problem solving, it is useful to integrate RBR, CBR and MBR. In this paper, a hybrid KBS which integrates a deductive RBR system, an inductive CBR system and a quantitative MBR system is proposed for epidemic screening. The system has been tested using real data, and results are encouraging.     

Towards Automated Case Knowledge Discovery in the M 2 Case-Based Reasoning System

In this paper we present the M ² Case-Based Reasoning (CBR) system. The M ² system addresses a number of issues that present methodologies for CBR systems have shied away from. We discuss techniques for removing the knowledge acquisition bottleneck when acquiring case knowledge. Here, case knowledge refers to the complementary knowledge structures, cases (more specific in nature) and adaptation rules (more general). We address the use of negative cases for updating the case knowledge as well as for refining the similarity measures. In particular we discuss in detail, showing experimental results, the use of Data Mining within the M ² system to build the case base from a database containing operational data, and discover adaptation rules. A methodology to monitor the competence of the CBR system and to utilize negative cases for updating the CBR system to enhance its competence is also discussed. The M ² CBR system also employs Rough Set and Fuzzy Set theories to further enhance its capabilities within real-world applications as well as providing a richer and truer model of human reasoning.     

ASHSD-II: A computational model for litigation support

Abstract: In this paper a hybrid knowledge-based system which exploits both rule-based reasoning (RBR) and case-based reasoning (CBR) is presented. The issues of RBR and CBR in general in the context of legal knowledge-based systems and legislation in rule form and previously-decided cases in an interconnected graph form are discussed. It is possible for the user to select either reasoning method (RBR or CBR), or indicate no preference. The rule base of this system consists of two types of rule. The first type of rule determines which options are legally applicable. The second type indicates how the courts are likely to act within the range of options available, which is determined by the first type of rule. When CBR is selected, the system uses the features of previously-decided cases to select the most similar cases to the situation that is described in the input and displays their details of decisions. In case of the selection of no preference option, the system applies RBR and CBR method separately, and then presents results based on an automated relative rating of the qualities of the RBR (based on the second type of rules) and CBR advice. These ideas have been implemented in a prototype system, known as A dvisory S upport for H ome S ettlement in D ivorce (ASHSD-II).     

Termination and confluence by rule prioritization

An active database system is a DBMS endowed with active rules, i.e., stored procedures activated by the system when specific events occur. The processing of active rules is characterized by two important properties: termination and confluence. We say that the processing of a set of active rules terminates if, given any initial active database state, the execution of the rules does not continue indefinitely; it is confluent if, for any initial database state, the final state is not influenced by the order of execution of the rules. Finding sufficient conditions for these properties to hold is a nontrivial problem, and the lack of a structured theory for the design of a system of active rules makes the analysis of the two properties more difficult. In this work, we translate a set of rules from any of the existing systems into an internal format; then, we translate the active rules into logical clauses, taking into account the system's execution semantics, and transfer to the active process known simple results about termination and determinism available in the literature for deductive rules.     

A logical foundation for the case‐based reasoning cycle

Case‐based reasoning (CBR) has drawn considerable attention in artificial intelligence (AI) fields with many successful applications in systems such as e‐commerce and multiagent systems. For the moment, research and development of CBR basically follows the traditional process model of CBR, i.e., the R⁴ model and problem space model introduced in 1994 and 1996, respectively. However, there has been no logical analysis for this popular CBR model. This article will fill this gap by providing a unified logical foundation for the CBR cycle. The proposed approach is based on an integration of traditional mathematical logic, fuzzy logic, and similarity‐based reasoning. At the same time, we examine the CBR cycle from the knowledge‐based (KB) viewpoint. The proposed logical approach can facilitate research and development of CBR. © 2003 Wiley Periodicals, Inc.     

ECA rule-based support for workflows

The use of event–condition–action (ECA) rules has transformed database systems from passive query-based data repositories to active sources of information delivery. In a similar fashion, ECA rules can be used to benefit workflow systems. In this paper, a software framework known as STEP workflow management facility is proposed in order to manage collaborative and distributed workflows and to provide interfaces to object management group-compliant product data management systems. Issues related to implementation using open standards such as CORBA are discussed. A key point underlying the framework is the flexibility it affords to users to re-configure the system according to evolving needs in collaborative product development.     

Multi-modal diagnosis combining case-based and model-based reasoning: a formal and experimental analysis

Integrating different reasoning modes in the construction of an intelligent system is one of the most interesting and challenging aspects of modern AI. Exploiting the complementarity and the synergy of different approaches is one of the main motivations that led several researchers to investigate the possibilities of building multi-modal reasoning systems, where different reasoning modalities and different knowledge representation formalisms are integrated and combined. Case-Based Reasoning (CBR) is often considered a fundamental modality in several multi-modal reasoning systems; CBR integration has been shown very useful and practical in several domains and tasks. The right way of devising a CBR integration is however very complex and a principled way of combining different modalities is needed to gain the maximum effectiveness and efficiency for a particular task. In this paper we present results (both theoretical and experimental) concerning architectures integrating CBR and Model-Based Reasoning (MBR) in the context of diagnostic problem solving. We first show that both the MBR and CBR approaches to diagnosis may suffer from computational intractability, and therefore a careful combination of the two approaches may be useful to reduce the computational cost in the average case. The most important contribution of the paper is the analysis of the different facets that may influence the entire performance of a multi-modal reasoning system, namely computational complexity, system competence in problem solving and the quality of the sets of produced solutions. We show that an opportunistic and flexible architecture able to estimate the right cooperation among modalities can exhibit a satisfactory behavior with respect to every performance aspect. An analysis of different ways of integrating CBR is performed both at the experimental and at the analytical level. On the analytical side, a cost model and a competence model able to analyze a multi-modal architecture through the analysis of its individual components are introduced and discussed. On the experimental side, a very detailed set of experiments has been carried out, showing that a flexible and opportunistic integration can provide significant advantages in the use of a multi-modal architecture.     

Exploring new roles for case-based reasoning in heterogeneous AI systems for medical decision support

Background Supporting medical decision making is a complex task, that offers challenging research issues to Artificial Intelligence (AI) scientists. The Case-based Reasoning (CBR) methodology has been proposed as a possible means for supporting decision making in this domain since the 1980s. Nevertheless, despite the variety of efforts produced by the CBR research community, and the number of issues properly handled by means of this methodology, the success of CBR systems in medicine is somehow limited, and almost no research product has been fully tested and commercialized; one of the main reasons for this may be found in the nature of the problem domain, which is extremely complex and multi-faceted. Materials and methods In this environment, we propose to design a modular architecture, in which several AI methodologies cooperate, to provide decision support. In the resulting context CBR, originally conceived as a well suited reasoning paradigm for medical applications, can extend its original roles, and cover a set of additional tasks. Results and conclusions As an example, in the paper we will show how CBR can be exploited for configuring the parameters relied upon by other (reasoning) modules. Other possible ways of deploying CBR in this domain will be the object of our future investigations, and, in our opinion, a possible research direction for people working on CBR in the health sciences.     

Managing Conflicts between Rules

Rules are used as a programming paradigm in several application domains, including active databases, planning, expert systems, and billing. For example, active databases have rules that execute upon the occurrence of particular events if specified condition predicates are satisfied. It is often the case that multiple rules are fireable when a particular event occurs. We propose a declarative mechanism to control the interaction and execution of multiple rules. The mechanism is based upon logical meta-rules that can express various types of relationships between rules. The meta-rules allow us to reason statically about the rule behavior. We can determine, in polynomial time, whether a rule will never execute, whether two rules can ever be executed together, and whether a rule system is guaranteed to have a unique execution set for all possible rules that become fireable. In this paper, we illustrate our techniques using rules in an active database. A system based upon the meta-rules and the static analysis presented here has been found to be of value in a billing application at AT & T to control interactions between discount plans.     

Autonomous objects: A natural model for complex applications

Object-oriented database systems are emerging as the next generation DBMSs for advanced applications, e.g., VLSI design, mechanical CAD/CAM, software engineering, etc. However, a close analysis indicates that the requirements imposed by these application domains cannot be met by an object-oriented model that relies purely onpassive objects. In this work we go beyond the conventionalsingle-thread-of-control paradigm of passive object models and propose a model ofactive objects which can autonomously initiate responses to environmental changes.Autonomous objects cooperate with each other by synchronous orasynchronous message passing—giving rise to themultiple-thread-of-control in such an environment. It is shown howevents—to which active objects react—can be incorporated into this model. We propose a nondeterministic computational model for the individual active objects that allows the autonomous reaction upon events. We show that this very sparse extension to an object-oriented model gives rise to several high-level features which can be controlled by events. The object-oriented paradigm allows one to isolate the rules according to which events are being raised. This leads to a potentially rather efficient execution model compared to existing relational concepts, which are typically globally-defined event trigger mechanisms.     

Intelligent databases: Old challenges and new opportunities

The evolution of existing information systems and a new wave of data-intensive applications are creating a strong demand for database-centered programming environments much more sophisticated and intelligent than those supported by current database systems. In this paper, we describe the contributions that deductive databases offer to the evolution of databases and information systems to satisfy said demands. In addition to all database essentials, deductive databases support rule-based logic-oriented languages that allow terse formulations of complete applications, along with reasoning and queries. Thus, they support a rule-based interface that eliminates the impedance mismatch problem (between programming language and query sublanguage) and elevates the design and development of database applications to the level of declarative, knowledge-based specifications. In this paper, we review the evolution of the enabling technology and architectures of deductive database prototypes; then we focus on their applications, as seen by the author through his experience with theLDL/LDL++ project. In particular, the paper describes the languages and the (bottom-up) execution technology used by the first generation of deductive database prototypes. Then the paper discusses how the experience with a first-generation system (LDL) guided the design and implementation of a second-generation prototype (LDL++).     

Data mining for case-based reasoning in high-dimensional biological domains

Case-based reasoning (CBR) is a suitable paradigm for class discovery in molecular biology, where the rules that define the domain knowledge are difficult to obtain and the number and the complexity of the rules affecting the problem are too large for formal knowledge representation. To extend the capabilities of CBR, we propose the mixture of experts for case-based reasoning (MOE4CBR), a method that combines an ensemble of CBR classifiers with spectral clustering and logistic regression. Our approach not only achieves higher prediction accuracy, but also leads to the selection of a subset of features that have meaningful relationships with their class labels. We evaluate MOE4CBR by applying the method to a CBR system called TA3 - a computational framework for CBR systems. For two ovarian mass spectrometry data sets, the prediction accuracy improves from 80 percent to 93 percent and from 90 percent to 98.4 percent, respectively. We also apply the method to leukemia and lung microarray data sets with prediction accuracy improving from 65 percent to 74 percent and from 60 percent to 70 percent, respectively. Finally, we compare our list of discovered biomarkers with the lists of selected biomarkers from other studies for the mass spectrometry data sets.     

Orthogonal relations for reasoning about posets

In large distributed systems, event abstraction becomes an important issue in order to represent interactions and reason at the right level of abstraction. Abstract events are collections of more elementary events, which provide a view of the system execution at an appropriate level of granularity. Understanding how two abstract events relate to each other is a fundamental problem for knowledge representation and reasoning in a complex system. In this paper, we study how two abstract events in a distributed system are related to each other in terms of the more elementary causality relation. Specifically, we analyze the ways in which two abstract events can be related to each other orthogonally, that is, identify all the possible mutually independent relations by which two such events could be related to each other. © 2002 Wiley Periodicals, Inc.     

A NEW APPROACH FOR THE INCREMENTAL DEVELOPMENT OF RETRIEVAL FUNCTIONS FOR CBR

We present a new approach to the effective development of complex retrieval components for case-based reasoning systems (CBR). Our approach goes beyond the traditional CBR approach by allowing an incremental refinement of an existing retrieval knowledge base during routine use of the system. The refinement takes place through a direct expert-system interaction while the expert is accomplishing their given tasks. We lend ideas from ripple-down rules (RDR), a proven method for the very effective and efficient acquisition of classification knowledge during the routine use of a knowledge-based system (KBS).

In our approach the expert is only required to provide explanations of why, for a given problem, a certain case should be retrieved. Incrementally a complex retrieval knowledge base as a composition of many simple retrieval functions is developed. This approach is effective with respect to both the development of highly tailored and complex retrieval knowledge bases for CBR as well as providing an intuitive and feasible approach for the expert. The approach has been implemented in our CBR system MIKAS (Menu construction using an Incremental Knowledge Acquisition System) that allows to automatically construct a menu that is strongly tailored to the individual requirements and food preferences of a client.     

3-Col problem modelling using simple kernel P systems

This paper presents the newly introduced class of (simple) kernel P systems ((s)kP systems) and investigates through a 3-colouring problem case study the expressive power and efficiency of kernel P systems. It describes two skP systems that model the problem and analyses them in terms of efficiency and complexity. The skP models prove to be more succinct (in terms of number of rules, objects, number of cells and execution steps) than the corresponding tissue P system, available in the literature, that solves the same problem, at the expense of a greater length of the rules.     

Reactive processing in ADOME-II: an extensible approach

A new approach for supporting reactive capability is described in the context of an advanced object-oriented database system called ADOME-II. Besides having a rich set of pre-defined composite event expressions and a well-defined execution model, ADOME-II supports an extensible approach to reactive processing so as to be able to gracefully accommodate dynamic applications’ requirements. In this approach, production rules combined with methods are used as a unifying mechanism to process rules, to enable incremental detection of composite events, and to allow new composite event expressions to be introduced into the system declaratively. This allows the definition of new production rules each time an extension of the model takes place. Methods of supporting new composite event expressions are described, and comparisons with other relevant approaches are also conducted. A prototype of ADOME-II has been constructed, which has as its implementation base an ordinary (passive) OODBMS and a production rule base system.