| 1994 Publications |
|
| Local Patching Produces Compact Knowledge Bases |
|
| P. Compton, P. Preston, B. Kang and T. Yip
|
| A Future for Knowledge Acquisition |
|
| Knowledge acquisition (KA) encompasses working with the expert to model the domain and a suitable problem solving method as preconditions for building a knowledge based system (KBS) and secondly working with the expert to populate the knowledge base. Ripple Down Rules (RDR) focuses on the second of these activities and allows an expert to populate a knowledge base (KB) without any knowledge engineering assistance. It is based on the idea that since the knowledge an expert provides is a justification of his or her judgment given in a specific context, this knowledge should only be used in the same context. Although the approach has been used for large single classification systems, it has the potential problem that the local nature of the knowledge may result in much repeated knowledge in the KB and much repeated knowledge acquisition. The study here attempts to quantitate and compare KB size and performance for systems built by experts with various levels of expertise and also inductively. The study also proposes a novel way of conducting such studies in that the different levels of expertise were achieved by using simulated experts. The conclusion from this study is that experts are likely to produce reasonably compact and efficient knowledge bases using the Ripple-Down Rule approach.
|
|
|
|
| New Paradigms for Expert Systems in Healthcare |
|
| Edwards G, P. Compton, B. Kang and P. Preston
|
| IVth Conference of the Health Informatics Association of New South Wales
|
|
| Decades of research have fostered a widely held expectation that expert systems (ES) will improve quality and efficiency in healthcare. In marked contrast to this vast body of literature is the tiny handful of systems in routine use. Obstacles to widespread dissemination of ES technology include the complexity of system maintenance and lack of acceptance by clinicians. We have devised and implemented a new strategy for ES, Ripple Down Rules (RDR), that creates new paradigms for both builders and users f medical ES.
|
|
|
|
| A Maintenance Approach to Case Based Reasoning |
|
| B. Kang and P. Compton
|
| Advances in Case-Based Reasoning : EWCBR-94 |
|
| The motivation for CBR is that knowledge comes mainly from experience, from dealing with cases. The goal of CBR is not to find knowledge in the knowledge base that applies to the present problem, but to find a case similar to the current case in a database of cases. This paper describes a methodology, ripple down rules (RDR), which allows a CBR system to be built without either induction or knowledge engineering and is well suited to maintenance. In essence, when the system fails to find the proper case to match with the present problem case, it asks the expert to identify the important features which differentiate the incorrectly retrieved case and the problem case. The problem case is added to the database and is indexed to be retrieved using the identified features only after the same incorrectly retrieved case is reached. This simple approach allows large systems to be easily built by unaided experts. RDR has been used for a large medical expert system (PEIRS) which is in routine use in a major teaching hospital's chemical pathology laboratory, providing clinical interpretations of data for diagnostic reports. PEIRS uses 2000 cases(rules), covers 20% of chemical pathology and is 95% accurate to date. It was built by pathologists without knowledge engineering assistance or skills. |
|
|
|
| Multiple Classification Ripple Down Rules |
|
| B. Kang and P. Compton
|
| Third Japanese Knowledge Acquisition for Knowledge-Based Systems Workshop |
|
| Ripple Down Rules (RDR) is an approach to building knowledge based systems (KBS) which allow an expert to build and maintain a KBS without the assistance of a knowledge engineer or knowledge engineering expertise. RDR allows for a KBS to be built whilst the system is in use, by correcting errors as they occur. Existing RDR inference methods provide a single classification for a set of data. This paper describes an extension to RDR, Multiple Classification Ripple Down Rules (MCRDR), which allows multiple independent classifications but has the same ease of use of RDR. RDR and MCRDR use a similar knowledge representation, similar inference methods and knowledge acquisition process. Where MCRDR classifications for a particular case are incorrect the KB can be corrected by attaching new rules as exceptions to the rules misclassifying the case. The MCRDR system uses expert knowledge to decide on the location as well as the composition of the rule. Validation is also more complex as many cases may need to be considered as possibly being misinterpreted by a new rule. Despite this increased complexity MCRDR knowledge acquisition is trivial and can be managed by an unaided expert. The approach has been evaluated by a series of simulation studies in which the role of human expert is replaced by a simulated expert using another KBS. These studies indicate MCRDR perform at least as well as RDR even in a single classification domain. It seems likely that as well as dealing with multiple classifications, MCRDR will provide a basis for building systems for other problems beyond simple classification but without requiring knowledge engineering assistance. |
|
|
|
| Verification and Validation with Ripple Down Rules |
|
| B. Kang, W. Gambetta and P. Compton
|
| Validation and Verification of Knowledge Based Systems (AAAI-94 Workshops) |
|
| Verification to ensure a system's consistency and validation to meet the user's criteria are essential elements in developing knowledge based systems(KBS) for real world use. The normal practice appears to assume that there will be initial knowledge acquisition attempting to build a complete system which will then be verified and validated. There may be a cycle through there steps till the system is complete. Maintenance is assumed to be a minor problem requiring the occasional repetition of the three stage process. This model is based on the assumption that an expert has complete knowledge and that by a suitable knowledge acquisition process this complete knowledge can be "extracted". It seems rather that experts are incapable of recounting how they reached a conclusion. Rather when asked a question they justify that their conclusion is correcting and their justification is tailored to the specific context of the inquiry. Experts are best at justifying why one conclusion is to be preferred over another.
This leads to a knowledge acquisition methodology, Ripple-down Rues(RDR), in which the knowledge base undergoes on-going development based on correcting errors. Each new correction or justification is used only in the context of the same mistake being made. The method allows the possibility of constraining the expert's choices to ensure that nay new knowledge added is valid and the KB structure ensures the knowledge is verified. This changes the notion of three stages of knowledge acquisition, verification and validation which are also repeated periodically during maintenance. The focus is on-going evolution of the KB with only validated verified knowledge being allowed. This provides a closer match with the normal evolution of human knowledge and expertise. It also provides a changed role for validation and verification in predetermining the structure of the KB and restricting the choices for the knowledge to be added .The overall approach has itself been validated by the development of a large medical expert system. This system has been developed while in routine use and has only involved experts without any knowledge engineering support or skill in its development. |
|
|
