Habitat use by Darling Downs population of the grassland earless dragon: implications for conservation.

A population of the grassland earless dragon (Tympanocryptis pinguicolla) on the Darling Downs, Queensland, Australia, had been considered extinct until its recent rediscovery. We determined factors affecting grassland earless dragon abundance and prey availability in 3 habitats. Mean dragon body condition and prey numbers were higher in sorghum than grasslands and grass verges. Poisson regression analyses indicated that the dragon numbers were 10 times higher in sorghum, and that this may result from differences in prey numbers as well as other habitat conditions. Tracking data indicated selection of open versus closed microhabitat. Sorghum planted in rows provided alternating open and closed microhabitats for optimal thermoregulation conditions. Grasslands and grass verges were more uniformly shaded. Of individuals we tracked in the sorghum stubble, 85.7% used litter as overnight refuges. Litter was abundant in sorghum and sparse in grass habitats. The practices of minimum tillage and resting stubble strips possibly mitigate agricultural impacts on dragons and provide continuous access to suitable habitat. Changes in agricultural practices that affect the habitat suitability will potentially have detrimental impacts on the population. Our data suggest that conservation efforts be focused on maintaining suitability of habitats in crop fields. We recommend monitoring dragon abundance at control and trial sites of any new agricultural practices; this will provide opportunity to modify or stop undesirable practices before adoption by farmers. Conservation agencies may use our data as a baseline for monitoring long-term viability of the population.

The importance of forest area and configuration relative to local habitat factors for conserving forest mammals: A case study of koalas in Queensland, Australia

The loss and fragmentation of forest habitats by human land use are recognised as important factors influencing the decline of forest-dependent fauna. Mammal species that are dependent upon forest habitats are particularly sensitive to habitat loss and fragmentation because they have highly specific habitat requirements, and in many cases have limited ability to move through and utilise the land use matrix. We addressed this problem using a case study of the koala (Phascolarctos cinereus) surveyed in a fragmented rural-urban landscape in southeast Queensland, Australia. We applied a logistic modelling and hierarchical partitioning analysis to determine the importance of forest area and its configuration relative to site (local) and patch-level habitat variables. After taking into account spatial auto-correlation and the year of survey, we found koala occurrence increased with the area of all forest habitats, habitat patch size and the proportion of primary Eucalyptus tree species; and decreased with mean nearest neighbour distance between forest patches, the density of forest patches, and the density of sealed roads. The difference between the effect of habitat area and configuration was not as strong as theory predicts, with the configuration of remnant forest becoming increasingly important as the area of forest habitat declines. We conclude that the area of forest, its configuration across the landscape, as well as the land use matrix, are important determinants of koala occurrence, and that habitat configuration should not be overlooked in the conservation of forest-dependent mammals, such as the koala. We highlight the implications of these findings for koala conservation. (c) 2006 Elsevier Ltd. All rights reserved.

Incremental learning for interactive e-mail filtering

In this article, we propose a framework, namely, Prediction-Learning-Distillation (PLD) for interactive document classification and distilling misclassified documents. Whenever a user points out misclassified documents, the PLD learns from the mistakes and identifies the same mistakes from all other classified documents. The PLD then enforces this learning for future classifications. If the classifier fails to accept relevant documents or reject irrelevant documents on certain categories, then PLD will assign those documents as new positive/negative training instances. The classifier can then strengthen its weakness by learning from these new training instances. Our experiments’ results have demonstrated that the proposed algorithm can learn from user-identified misclassified documents, and then distil the rest successfully.

Interactive email filtering: Learning from misclassified examples

Learning from mistakes has proven to be an effective way of learning in the interactive document classifications. In this paper we propose an approach to effectively learning from mistakes in the email filtering process. Our system has employed both SVM and Winnow machine learning algorithms to learn from misclassified email documents and refine the email filtering process accordingly. Our experiments have shown that the training of an email filter becomes much effective and faster

Collaborative filtering on data streams

Collaborate Filtering is one of the most popular recommendation algorithms. Most Collaborative Filtering algorithms work with a static set of data. This paper introduces a novel approach to providing recommendations using Collaborative Filtering when user rating is received over an incoming data stream. In an incoming stream there are massive amounts of data arriving rapidly making it impossible to save all the records for later analysis. By dynamically building a decision tree for every item as data arrive, the incoming data stream is used effectively although an inevitable trade off between accuracy and amount of memory used is introduced. By adding a simple personalization step using a hierarchy of the items, it is possible to improve the predicted ratings made by each decision tree and generate recommendations in real-time. Empirical studies with the dynamically built decision trees show that the personalization step improves the overall predicted accuracy.

Time weight collaborative filtering

Collaborative filtering is regarded as one of the most promising recommendation algorithms. The item-based approaches for collaborative filtering identify the similarity between two items by comparing users' ratings on them. In these approaches, ratings produced at different times are weighted equally. That is to say, changes in user purchase interest are not taken into consideration. For example, an item that was rated recently by a user should have a bigger impact on the prediction of future user behaviour than an item that was rated a long time ago. In this paper, we present a novel algorithm to compute the time weights for different items in a manner that will assign a decreasing weight to old data. More specifically, the users' purchase habits vary. Even the same user has quite different attitudes towards different items. Our proposed algorithm uses clustering to discriminate between different kinds of items. To each item cluster, we trace each user's purchase interest change and introduce a personalized decay factor according to the user own purchase behaviour. Empirical studies have shown that our new algorithm substantially improves the precision of item-based collaborative filtering without introducing higher order computational complexity.

Filtering duplicate items over distributed data streams

In recent years many real time applications need to handle data streams. We consider the distributed environments in which remote data sources keep on collecting data from real world or from other data sources, and continuously push the data to a central stream processor. In these kinds of environments, significant communication is induced by the transmitting of rapid, high-volume and time-varying data streams. At the same time, the computing overhead at the central processor is also incurred. In this paper, we develop a novel filter approach, called DTFilter approach, for evaluating the windowed distinct queries in such a distributed system. DTFilter approach is based on the searching algorithm using a data structure of two height-balanced trees, and it avoids transmitting duplicate items in data streams, thus lots of network resources are saved. In addition, theoretical analysis of the time spent in performing the search, and of the amount of memory needed is provided. Extensive experiments also show that DTFilter approach owns high performance.