Learn More
We have proposed replicator neural networks (RNNs) for outlier detection [8]. Here we compare RNN for out-lier detection with three other methods using both publicly available statistical datasets (generally small) and data mining datasets (generally much larger and generally real data). The smaller datasets provide insights into the relative strengths and(More)
BACKGROUND Flax (Linum usitatissimum L.) has been cultivated for around 9,000 years and is therefore one of the oldest cultivated species. Today, flax is still grown for its oil (oil-flax or linseed cultivars) and its cellulose-rich fibres (fibre-flax cultivars) used for high-value linen garments and composite materials. Despite the wide industrial use of(More)
BACKGROUND In our laboratory we use cultured chicory (Cichorium intybus) explants as a model to investigate cell reactivation and somatic embryogenesis and have produced 2 chicory genotypes (K59, C15) sharing a similar genetic background. K59 is a responsive genotype (embryogenic) capable of undergoing complete cell reactivation i.e. cell de- and(More)
We consider the problem of finding outliers in large multi-variate databases. Outlier detection can be applied during the data cleansing process of data mining to identify problems with the data itself, and to fraud detection where groups of outliers are often of particular interest. We use replicator neural networks (RNNs) to provide a measure of the(More)
BACKGROUND Quantitative real-time PCR (qRT-PCR) is currently the most accurate method for detecting differential gene expression. Such an approach depends on the identification of uniformly expressed 'housekeeping genes' (HKGs). Extensive transcriptomic data mining and experimental validation in different model plants have shown that the reliability of(More)
Plants are built of various specialized cell types that differ in their cell wall composition and structure. The cell walls of certain tissues (xylem, sclerenchyma) are characterized by the presence of the heterogeneous lignin polymer that plays an essential role in their physiology. This phenolic polymer is composed of different monomeric units - the(More)
There are many methods for finding association rules in very large data. However it is well known that most general association rule discovery methods find too many rules, which include a lot of uninteresting rules. Furthermore, the performances of many such algorithms deteriorate when the minimum support is low. They fail to find many interesting rules(More)
For universal health care systems such as that found in Australia, the health care budget constitutes one of the largest items for government expenditure. Identifying even small pockets of inefficiencies and wastage can have considerable impact (one percent of $30 billion is still a significant amount) and can result in shifting funds to where they are most(More)
Australia has a universal health insurance scheme called Medicare. Medicare payments for pathology services generate voluminous transaction data on patients, doctors and pathology laboratories. The Health Insurance Commission (HIC) currently uses predictive models to monitor compliance with regulatory requirements. The HIC commissioned a project to(More)