Andrew Stranieri

A hybrid rule --- neural approach for the automation of legal reasoning in the discretionary domain of family law in Australia

Few automated legal reasoning systems have been developed in domains of law in which a judicial decision maker has extensive discretion in the exercise of his or her powers. Discretionary domains challenge existing artificial intelligence paradigms because models of judicial reasoning are difficult, if not impossible to specify. We argue that judicial discretion adds to the characterisation of law as open textured in a way which has not been addressed by artificial intelligence and law researchers in depth. We demonstrate that systems for reasoning with this form of open texture can be built by integrating rule sets with neural networks trained with data collected from standard past cases. The obstacles to this approach include difficulties in generating explanations once conclusions have been inferred, difficulties associated with the collection of sufficient data from past cases and difficulties associated with integrating two vastly different paradigms. A knowledge representation scheme based on the structure of arguments proposed by Toulmin has been used to overcome these obstacles. The system, known as Split Up, predicts judicial decisions in property proceedings within family law in Australia. Predictions from the system have been compared to those from a group of lawyers with favourable results.

ToolSHeD™: The development and evaluation of a decision support tool for health and safety in construction design

Purpose – The purpose of this paper is to describe an innovative information and decision support tool (ToolSHeD™) developed to help construction designers to integrate the management of OHS risk into the design process. The underlying structure of the prototype web‐based system and the process of knowledge acquisition and modelling are described. Design/methodology/approach – The ToolSHeD™ research and development project involved the capture of expert reasoning regarding design impacts upon occupational health and safety (OHS) risk. This knowledge was structured using an innovative method well‐suited to modelling knowledge in the context of uncertainty and discretionary decision‐making. Example “argument trees” are presented, representing the reasoning used by a panel of experts to assess the risk of falling from height during roof maintenance work. The advantage of using this method for modelling OHS knowledge, compared to the use of simplistic rules, is discussed Findings – The ToolSHeD™ prototype development and testing reveals that argument trees can represent design safety risk knowledge effectively. Practical implications – The translation of argument trees into a web‐based decision support tool is described and the potential impact of this tool in providing construction designers (architects and engineers) with easy and inexpensive access to expert OHS knowledge is discussed. Originality/value – The paper describes a new computer application, currently undergoing testing in the Australian building and construction industry. Its originality lies in the fact that ToolSHeD™ deploys argument trees to represent expert OHS reasoning, overcoming inherent limitations in rule‐based expert systems.

The integration of retrieval, reasoning and drafting for refugee law: a third generation legal knowledge based system

We identify an argument to be the basic unit of reasoning of a system that supports the construction of arguments and drafting of determinations in refugee law. Collaboration with the Refugee Review Tribunal of Australia has led to the development of a framework for argument construction that includes over 200 generic arguments. However, these arguments may not encompass all arguments used in any particular case. The construction of non-generic arguments involves the integration of information retrieval within reasoning. This retrieval is passage based from a wide variety of text sources. The framework also acts as the illocutionary structure in a document drafting process. In conceptualising this system we have found it useful to propose a classification of knowledge based systems in law.

The generic/actual argument model of practical reasoning

In this paper, we present a model of reasoning called the generic/actual argument model (GAAM). Reasoning within a discursive community can be represented with this model so that participant claims can be accommodated without recourse to combative metaphors such as attack or defeat. The model facilitates the comprehension of complex reasoning for humans as well as being a computational representation for machine modelling of reasoning. As such, the model naturally integrates machine inferences with human. The model has been the basis for the development of practical systems to support reasoning and deliberation in areas of law and organizational decision making. Here, we present a formal description of the model and identify some of its characteristics.

An approach for Ewing test selection to support the clinical assessment of cardiac autonomic neuropathy

OBJECTIVE This article addresses the problem of determining optimal sequences of tests for the clinical assessment of cardiac autonomic neuropathy (CAN). We investigate the accuracy of using only one of the recommended Ewing tests to classify CAN and the additional accuracy obtained by adding the remaining tests of the Ewing battery. This is important as not all five Ewing tests can always be applied in each situation in practice. METHODS AND MATERIAL We used new and unique database of the diabetes screening research initiative project, which is more than ten times larger than the data set used by Ewing in his original investigation of CAN. We utilized decision trees and the optimal decision path finder (ODPF) procedure for identifying optimal sequences of tests. RESULTS We present experimental results on the accuracy of using each one of the recommended Ewing tests to classify CAN and the additional accuracy that can be achieved by adding the remaining tests of the Ewing battery. We found the best sequences of tests for cost-function equal to the number of tests. The accuracies achieved by the initial segments of the optimal sequences for 2, 3 and 4 categories of CAN are 80.80, 91.33, 93.97 and 94.14, and respectively, 79.86, 89.29, 91.16 and 91.76, and 78.90, 86.21, 88.15 and 88.93. They show significant improvement compared to the sequence considered previously in the literature and the mathematical expectations of the accuracies of a random sequence of tests. The complete outcomes obtained for all subsets of the Ewing features are required for determining optimal sequences of tests for any cost-function with the use of the ODPF procedure. We have also found two most significant additional features that can increase the accuracy when some of the Ewing attributes cannot be obtained. CONCLUSIONS The outcomes obtained can be used to determine the optimal sequences of tests for each individual cost-function by following the ODPF procedure. The results show that the best single Ewing test for diagnosing CAN is the deep breathing heart rate variation test. Optimal sequences found for the cost-function equal to the number of tests guarantee that the best accuracy is achieved after any number of tests and provide an improvement in comparison with the previous ordering of tests or a random sequence.

The evaluation of legal knowledge based systems

Evaluation strategies to assess the effectiveness of legal knowledge based systems enable strengths and limitations of systems to be accurately articulated. This facilitates efforts in the research community to develop systems and also promotes the adoption of research prototypes in the commercial world. However, evaluation strategies for systems that operate in a domain as complex as law are difficult to specify. In this paper, we present an evaluation framework put forward by Reich and describe how this motivated the evaluation of our systems in Australian family law. Strategies surveyed include a comparison of linear regression with neural networks, user acceptance surveys, a comparison of system predictions with those from past cases, and a comparison of system outputs with those proposed by a panel of lawyers. Specific criteria for the evaluation of explanation facilities are also described.

Knowledge discovery in the Split Up project

Knowledge discovery techniques have not been applied extensively in legal domains despite potential benefits in the automated generation of legal knowledge from data. We suggest that more attention must be placed on the collection of data from cases that are ordinary and which are currently considered to be uninteresting for the full benefits of knowledge discovery to be realised. However, even with appropriate data, knowledge discovery techniques in law must deal with contradictory cases and must use statistical techniques in order to define error and estimate performance. We illustrate these points by describing the use of the cross validation resampling technique, our own error heuristic and the method we use for dealing with contradictions for the training of neural networks in the domain of property proceedings in Australian family law.

Predicting cardiac autonomic neuropathy category for diabetic data with missing values

Cardiovascular autonomic neuropathy (CAN) is a serious and well known complication of diabetes. Previous articles circumvented the problem of missing values in CAN data by deleting all records and fields with missing values and applying classifiers trained on different sets of features that were complete. Most of them also added alternative features to compensate for the deleted ones. Here we introduce and investigate a new method for classifying CAN data with missing values. In contrast to all previous papers, our new method does not delete attributes with missing values, does not use classifiers, and does not add features. Instead it is based on regression and meta-regression combined with the Ewing formula for identifying the classes of CAN. This is the first article using the Ewing formula and regression to classify CAN. We carried out extensive experiments to determine the best combination of regression and meta-regression techniques for classifying CAN data with missing values. The best outcomes have been obtained by the additive regression meta-learner based on M5Rules and combined with the Ewing formula. It has achieved the best accuracy of 99.78% for two classes of CAN, and 98.98% for three classes of CAN. These outcomes are substantially better than previous results obtained in the literature by deleting all missing attributes and applying traditional classifiers to different sets of features without regression. Another advantage of our method is that it does not require practitioners to perform more tests collecting additional alternative features.

Technologies for supporting reasoning communities and collaborative decision making: Cooperative approaches

Technologies for Supporting Reasoning Communities and Collaborative Decision Making: Cooperative Approaches includes chapters from diverse fields of enquiry including decision science, political science, argumentation, knowledge management, cognitive psychology and business intelligence.  Each chapter illustrates a perspective on group reasoning that ultimately aims to lead to a greater understanding of reasoning communities and inform technological developments.

Cost-analysis of teledentistry in residential aged care facilities.

Introduction The purpose of this research was to conduct a cost-analysis, from a public healthcare perspective, comparing the cost and benefits of face-to-face patient examination assessments conducted by a dentist at a residential aged care facility (RACF) situated in rural areas of the Australian state of Victoria, with two teledentistry approaches utilizing virtual oral examination. Methods The costs associated with implementing and operating the teledentistry approach were identified and measured using 2014 prices in Australian dollars. Costs were measured as direct intervention costs and programme costs. A population of 100 RACF residents was used as a basis to estimate the cost of oral examination and treatment plan development for the traditional face-to-face model vs. two teledentistry models: an asynchronous review and treatment plan preparation; and real-time communication with a remotely located oral health professional. Results It was estimated that if 100 residents received an asynchronous oral health assessment and treatment plan, the net cost from a healthcare perspective would be AU