Generality is predictive of prediction accuracy

During knowledge acquisition multiple alternative potential rules all appear equally credible. This paper addresses the dearth of formal analysis about how to select between such alternatives. It presents two hypotheses about the expected impact of selecting between classification rules of differing levels of generality in the absence of other evidence about their likely relative performance on unseen data. It is argued that the accuracy on unseen data of the more general rule will tend to be closer to that of a default rule for the class than will that of the more specific rule. It is also argued that in comparison to the more general rule, the accuracy of the more specific rule on unseen cases will tend to be closer to the accuracy obtained on training data. Experimental evidence is provided in support of these hypotheses. We argue that these hypotheses can be of use in selecting between rules in order to achieve specific knowledge acquisition objectives.

The development of a wisdom autonomic grid

It is not a simple matter to develop an integrative approach that exploits  synergies between knowledge management and knowledge discovery in   order to monitor and manage the full lifecycle of knowledge and provides  services quickly, reliably and securely. One of the main problems is the heterogeneity of the involved resources that represent knowledge. Data mining systems produce knowledge in a form meant to be understandable  to machines and on the other hand in knowledge management systems the  priority is placed on the readability and usability of knowledge by humans.  The Semantic Web is a promising platform to unify this heterogeneity and, in conjunction with novel techniques for Web Intelligence it could offer more  then just knowledge - wisdom. The Wisdom Autonomic Grid is an original proposal of a knowledge based Grid that is able to configure and reconfigure itself under varying and unpredictable conditions and optimize its working, performs something akin to healing and provides self-protection, as  visioned in the IBM Autonomic Computing initiative. This paper presents an original framework for creating advanced applications to integrate  knowledge discovery and knowledge management in the Autonomic Grid  and Web environments.

Benthic habitat mapping in coastal waters of south–east Australia

The Victorian Marine Mapping Project will improve knowledge on the location, spatial distribution, condition and extent of marine habitats and associated biodiversity in Victorian State waters. This information will guide informed decision making, enable priority setting, and assist in targeted natural resource management planning. This project entails benthic habitat mapping over 500 square kilometers of Victorian State waters using multibeam sonar, towed video and image classification techniques. Information collected includes seafloor topography, seafloor softness and hardness (reflectivity), and information on geology and benthic flora and fauna assemblages collectively comprising habitat. Computerized semi-automated classification techniques are also being developed to provide a cost effective approach to rapid mapping and assessment of coastal habitats.

Habitat mapping is important for understanding and communicating the distribution of natural values within the marine environment. The coastal fringe of Victoria encompasses a rich and diverse ecosystem representative of coastal waters of South-east Australia. To date, extensive knowledge of these systems is limited due to the lack of available data. Knowledge of the distribution and extent of habitat is required to target management activities most effectively, and provide the basis to monitor and report on their status in the future.

Evaluating the impact of an environmental education programme; an empirical study in Mexico.

This study draws on information from 11 in-depth interviews, two focus groups and 72 written questionnaires to evaluate an extra-curricular environmental education programme on forestry designed for preparatory school students from a small rural community in Mexico. Specifically, the study assessed the impact of the programme on the ecological knowledge of 72 students. Qualitative feedback suggests that students learnt about forestry, acquired greater awareness of the importance of conservation for the local environment and enjoyed the participatory teaching methods used in the programme. Quantitative results show a positive and significant association between the number of times a student participated in the programme and the student’s ecological knowledge. Students who participated in the programme once had a 16.3% higher knowledge on ecological concepts and knew, on average, 1.5 more local forest plants than students who never attended it (p<.001). Findings suggest that the inclusion of participatory environmental education programmes in preparatory schools would improve the acquisition of ecological knowledge. Further research could consider the consistency of the findings by replicating participatory methods presented here and by using an experimental research design.

Intelligent animal fibre identification and classification

To develop an objective and repeatable method of identification and classification of animal fibres, two different integrated systems were developed to mimic the human brain's ability to undertake feature extraction and discrimination of animal fibres. Both integrated systems are basically composed of an image processing system and an artificial neural network system.

Anaesthesia monitoring using fuzzy logic

Objective. Humans have a limited ability to accurately and continuously analyse large amount of data. In recent times, there has been a rapid growth in patient monitoring and medical data analysis using smart monitoring systems. Fuzzy logic-based expert systems, which can mimic human thought processes in complex circumstances, have indicated potential to improve clinicians' performance and accurately execute repetitive tasks to which humans are ill-suited. The main goal of this study is to develop a clinically useful diagnostic alarm system based on fuzzy logic for detecting critical events during anaesthesia administration. Method. The proposed diagnostic alarm system called fuzzy logic monitoring system (FLMS) is presented. New diagnostic rules and membership functions (MFs) are developed. In addition, fuzzy inference system (FIS), adaptive neuro fuzzy inference system (ANFIS), and clustering techniques are explored for developing the FLMS' diagnostic modules. The performance of FLMS which is based on fuzzy logic expert diagnostic systems is validated through a series of offline tests. The training and testing data set are selected randomly from 30 sets of patients' data. Results. The accuracy of diagnoses generated by the FLMS was validated by comparing the diagnostic information with the one provided by an anaesthetist for each patient. Kappa-analysis was used for measuring the level of agreement between the anaesthetist's and FLMS's diagnoses. When detecting hypovolaemia, a substantial level of agreement was observed between FLMS and the human expert (the anaesthetist) during surgical procedures. Conclusion. The diagnostic alarm system FLMS demonstrated that evidence-based expert diagnostic systems can diagnose hypovolaemia, with a substantial degree of accuracy, in anaesthetized patients and could be useful in delivering decision support to anaesthetists.

Using selective memory to track concept drift effectively

In this paper we describe a supervised learning algorithm that uses selective memory to track concept drift. Unlike previous methods to track concept drift that use window heuristics to adapt to changes, we present an improved approach that discriminates between the instances observed. The advantage of this method is that it allows the system to both adapt to and track drift more accurately as well as filter the noise in the data more effectively. We present the algorithm and compare its performance with FLORA a well known concept drift tracking algorithm.

Combination of decisions from a multiple neural network classifier system

In this paper, a study of the effectiveness of a multiple classifier system (MCS) in a medical diagnostic task is described. A hybrid network, based on the integration of a fuzzy ARTMAP and the probabilistic neural network, is employed as the basis of the MCS. Outputs from multiple networks are combined using some decision combination method to reach a final prediction. By using a real medical database, a set of experiments has been conducted to evaluate the performance of the MSC with different network configurations. The experimental results reveal the potential of the MCS as a useful decision support tool in the medical field.

Here where it lives … bioscleave

This essay introduces the work of Arakaw and Gins to interdisciplinary specialists and scholars and practitioners who are concerned with issues of art-science convergence. The co-authors discuss several points of view to the work of these artist-turned-architects and address the difficulties and challenges that their work represents in terms of the convergence and complexity of multiple dicourse and the practical challenges to embodied experience, technlogy-based approaches ot knowledge acquisition and perceptually-based learning environments.

Crime toolkits : the productisation of cybercrime

The productisation of crime toolkits is happening at an ever-increasing rate. Previous attacks that required indepth knowledge of computer systems can now be purchased online. Large scale attacks previously requiring months to setup a botnet can now be scheduled for a small fee. Criminals are leveraging this opportunity of commercialization, by compromising web applications and user's browser, to gain advantages such as using the computer's resources for launching further attacks, or stealing data such as identifying information. Crime toolkits are being developed to attack an increasing number of applications and can now be deployed by attackers with little technical knowledge. This paper surveys the current trends in crime toolkits, with a case study on the Zeus botnet. We profile the types of exploits that malicious writers prefer, with a view to predicting future attack trends. We find that the scope for damage is increasing, particularly as specialisation and scale increase in cybercrime.