10,611 results for ResearchCommons@Waikato

  • Draft genome sequence of uncultured upland soil cluster gammaproteobacteria gives molecular insights into high-affinity methanotrophy

    Edwards, Collin R.; Onstott, Tullis C.; Miller, Jennifer M.; Wiggins, Jessica B.; Wang, We; Lee, Charles K.; Cary, S. Craig; Pointing, Stephen B.; Lau, Maggie C. Y. (2017)

    Journal article
    University of Waikato

    Aerated soils form the second largest sink for atmospheric CH₄. A nearcomplete genome of uncultured upland soil cluster Gammaproteobacteria that oxidize CH₄ at 2.5 ppmv was obtained from incubated Antarctic mineral cryosols. This first genome of high-affinity methanotrophs can help resolve the mysteries about their phylogenetic affiliation and metabolic potential.

    View record details
  • New Options for Hoeffding Trees

    Pfahringer, Bernhard; Holmes, Geoffrey; Kirkby, Richard Brendon (2007)

    Conference item
    University of Waikato

    Hoeffding trees are state-of-the-art for processing high-speed data streams. Their ingenuity stems from updating sufficient statistics, only addressing growth when decisions can be made that are guaranteed to be almost identical to those that would be made by conventional batch learning methods. Despite this guarantee, decisions are still subject to limited lookahead and stability issues. In this paper we explore Hoeffding Option Trees, a regular Hoeffding tree containing additional option nodes that allow several tests to be applied, leading to multiple Hoeffding trees as separate paths. We show how to control tree growth in order to generate a mixture of paths, and empirically determine a reasonable number of paths. We then empirically evaluate a spectrum of Hoeffding tree variations: single trees, option trees and bagged trees. Finally, we investigate pruning. We show that on some datasets a pruned option tree can be smaller and more accurate than a single tree.

    View record details
  • Finding new music: a diary study of everyday encounter with novel songs

    Cunningham, Sally Jo; Bainbridge, David; McKay, Dana (2007)

    Conference item
    University of Waikato

    This paper explores how we, as individuals, purposefully or serendipitously encounter 'new music' (that is, music that we haven’t heard before) and relates these behaviours to music information retrieval activities such as music searching and music discovery via use of recommender systems. 41 participants participated in a three-day diary study, in which they recorded all incidents that brought them into contact with new music. The diaries were analyzed using a Grounded Theory approach. The results of this analysis are discussed with respect to location, time, and whether the music encounter was actively sought or occurred passively. Based on these results, we outline design implications for music information retrieval software, and suggest an extension of 'laid back' searching.

    View record details
  • Experiments in Predicting Biodegradability

    Blockeel, Hendrik; Džeroski, Sašo; Kompare, Boris; Kramer, Stefan; Pfahringer, Bernhard; Van Laer, Wim (2004)

    Conference item
    University of Waikato

    This paper is concerned with the use of AI techniques in ecology. More specifically, we present a novel application of inductive logic programming (ILP) in the area of quantitative structure-activity relationships (QSARs). The activity we want to predict is the biodegradability of chemical compounds in water. In particular, the target variable is the half-life for aerobic aqueous biodegradation. Structural descriptions of chemicals in terms of atoms and bonds are derived from the chemicals' SMILES encodings. The definition of substructures is used as background knowledge. Predicting biodegradability is essentially a regression problem, but we also consider a discretized version of the target variable. We thus employ a number of relational classification and regression methods on the relational representation and compare these to propositional methods applied to different propositionalizations of the problem. We also experiment with a prediction technique that consists of merging upper and lower bound predictions into one prediction. Some conclusions are drawn concerning the applicability of machine learning systems and the merging technique in this domain and the evaluation of hypotheses.

    View record details
  • History-based visual mining of semi-structured audio and text

    Bouamrane, Matt-Mouley; Luz, Saturnino; Masoodian, Masood (2006)

    Conference item
    University of Waikato

    Accessing specific or salient parts of multimedia recordings remains a challenge as there is no obvious way of structuring and representing a mix of space-based and time-based media. A number of approaches have been proposed which usually involve translating the continuous component of the multimedia recording into a space-based representation, such as text from audio through automatic speech recognition and images from video (keyframes). In this paper, we present a novel technique which defines retrieval units in terms of a log of actions performed on space-based artefacts, and exploits timing properties and extended concurrency to construct a visual presentation of text and speech data. This technique can be easily adapted to any mix of space-based artefacts and continuous media.

    View record details
  • Accelerating Monte Carlo simulations with an NVIDIA® graphics processor

    Martinsen, Paul; Blaschke, Johannes; Künnemeyer, Rainer; Jordan, Robert (2009)

    Journal article
    University of Waikato

    Modern graphics cards, commonly used in desktop computers, have evolved beyond a simple interface between processor and display to incorporate sophisticated calculation engines that can be applied to general purpose computing. The Monte Carlo algorithm for modelling photon transport in turbid media has been implemented on an NVIDIA® 8800gt graphics card using the CUDA toolkit. The Monte Carlo method relies on following the trajectory of millions of photons through the sample, often taking hours or days to complete. The graphics-processor implementation, processing roughly 110 million scattering events per second, was found to run more than 70 times faster than a similar, single-threaded implementation on a 2.67 GHz desktop computer.

    View record details
  • Fast perceptron decision tree learning from evolving data streams

    Bifet, Albert; Holmes, Geoffrey; Pfahringer, Bernhard; Frank, Eibe (2010)

    Conference item
    University of Waikato

    Mining of data streams must balance three evaluation dimensions: accuracy, time and memory. Excellent accuracy on data streams has been obtained with Naive Bayes Hoeffding Trees—Hoeffding Trees with naive Bayes models at the leaf nodes—albeit with increased runtime compared to standard Hoeffding Trees. In this paper, we show that runtime can be reduced by replacing naive Bayes with perceptron classifiers, while maintaining highly competitive accuracy. We also show that accuracy can be increased even further by combining majority vote, naive Bayes, and perceptrons. We evaluate four perceptron-based learning strategies and compare them against appropriate baselines: simple perceptrons, Perceptron Hoeffding Trees, hybrid Naive Bayes Perceptron Trees, and bagged versions thereof. We implement a perceptron that uses the sigmoid activation function instead of the threshold activation function and optimizes the squared error, with one perceptron per class value. We test our methods by performing an evaluation study on synthetic and real-world datasets comprising up to ten million examples.

    View record details
  • Tourism to polluted lakes: issues for tourists and the industry. An empirical analysis of four Chinese lakes

    Ryan, Chris; Gu, Huimin; Chon, Kaye (2010)

    Journal article
    University of Waikato

    The paper seeks to address two specific questions. First, does the existence of polluted waters impact on the levels of satisfaction experienced by visitors to Chinese lakes? Second, does the local tourism industry (represented by a sample of hotel managers) correctly assess the importance of place attributes as assessed by visitors? The data presented are obtained from a sample of 913 visitors to four polluted lakes that are holiday or day visit locations and from 121 managers of hotels in those same areas. The evidence suggests that polluted areas can still function successfully as tourist locations because visitors in these instances view the lakescapes as part of a wider attraction that includes a built environment but that the hotel industry over-emphasises the importance of that built structure as a contributor to tourist place experience. Limitations to the research include the role played by an aesthetic gaze, which may have more importance within a Chinese culture than among Western counterparts because, particularly for the older Chinese, concepts of harmonization with nature are directed through the visual senses and references to classical literature rather than physical participation in water-based sports.

    View record details
  • Relational random forests based on random relational rules

    Anderson, Grant; Pfahringer, Bernhard (2009)

    Conference item
    University of Waikato

    Random Forests have been shown to perform very well in propositional learning. FORF is an upgrade of Random Forests for relational data. In this paper we investigate shortcomings of FORF and propose an alternative algorithm, R⁴F, for generating Random Forests over relational data. R⁴F employs randomly generated relational rules as fully self-contained Boolean tests inside each node in a tree and thus can be viewed as an instance of dynamic propositionalization. The implementation of R⁴F allows for the simultaneous or parallel growth of all the branches of all the trees in the ensemble in an efficient shared, but still single-threaded way. Experiments favorably compare R⁴F to both FORF and the combination of static propositionalization together with standard Random Forests. Various strategies for tree initialization and splitting of nodes, as well as resulting ensemble size, diversity, and computational complexity of R⁴F are also investigated.

    View record details
  • Promoting intercultural contact on campus: A project to connect and engage international and host students

    Campbell, Nittaya (2011)

    Journal article
    University of Waikato

    International students’ adjustment to living in an unfamiliar cultural environment and studying in a different educational system and language has been a topic of much research. Literature has shown that support from the host community could be the difference between a smooth transition and one fraught with problems and difficulties. This article describes a “buddy project” used in an intercultural communication class in which each student was a buddy for a newly arrived international student for a semester. The purpose of the project was to give social support to international students in the crucial first few months of their sojourn while at the same time complementing host students’ class-based theoretical learning with practical, meaningful experience with peers from another culture. The article discusses the outcomes, challenges, and students’ evaluations of the experiential learning exercise. Recommendations for future projects are outlined.

    View record details
  • Restaurant location in Hamilton, New Zealand: clustering patterns from 1996 to 2008

    Prayag, Girish; Landré, Martin; Ryan, Chris (2012)

    Journal article
    University of Waikato

    Purpose – The purpose of this study is to assess the evolution of restaurant locations in the city of Hamilton over a 12-year period (1996 to 2008) using GIS techniques. Retail theories such as central place, spatial interaction and principle of minimum differentiation are applied to the restaurant setting. Design/methodology/approach – A database of restaurants was compiled using the NZ yellow pages and contained 981 entries that consisted mainly of location addresses and types of cuisine. This paper focuses on locational patterns only. Findings – A process of geo-coding and clustering enabled the identification of two clustering periods over 12 years for city restaurants, indicating locational patterns of agglomeration within a short walking distance of the CBD and spill over effects to the north of the city. Research limitations/implications – The data do not allow statistical analysis of the variables causing the clustering but offer a visual description of the evolution. Explanations are offered on the possible planning regimes, retail provision and population changes that may explain this evolution. Practical implications – The findings allow identification of land use patterns in Hamilton city and potential areas where new restaurants could be developed. Also, the usefulness of geo-coded data in identifying clustering effects is highlighted. Originality/value – Existing location studies relate mostly to site selection criteria in the retailing industry while few have considered the evolution of restaurant locations in a specific geographic area. This paper offers a case study of Hamilton city and highlights the usefulness of GIS techniques in understanding locational patterns.

    View record details
  • The customer engagement/value interface: An exploratory investigation

    Hollebeek, Linda D. (2012)

    Journal article
    University of Waikato

    After generating significant interest among marketing practitioners, the customer engagement (CE) concept is rapidly gaining traction in the academic marketing literature. Although pioneering research has provided foundational insights in this emerging area, little is known regarding the ways in which CE may contribute to generating customer value (CV) and ensuing loyalty for utilitarian and hedonic brands. Addressing this research gap, this paper develops a conceptual model of the CE/CV interface for utilitarian and hedonic brands, which proposes: (i) The existence of a curvilinear relationship between CE/CV for utilitarian and hedonic brands; and (ii) Up to a focal brand-, category-, consumer-, and situation-specific optimum, growing CE generates greater CV increases for hedonic, than for utilitarian brands. By drawing on a sample of 14 consumers, depth-interviewing/focus group findings provided exploratory evidence for contentions (i) and (ii). The paper concludes with an overview of key research limitations and implications.

    View record details
  • Film-induced heritage site conservation: The case of echoes of the rainbow

    Pan, Steve; Ryan, Chris (2012)

    Journal article
    University of Waikato

    It has been contended that a link exists between films and the creation of tourist locations. A film can have an unintended consequence that leads to community actions and subsequent policy initiatives that are supportive of conservation of potential tourism cultural assets. This article analyses the processes by which one such film created a heightened awareness of the heritage values of a location setting in Hong Kong that led to changes in public policy. This case study highlights media’s role in shaping and changing public opinion. It examines through framing analysis the way in which public debate changed, thereby highlighting the way in which conservation activists and other stakeholders played out competing roles and the manner in which they sought to influence media coverage of the site. The article also points out the need to establish a set of consistent standards of conserving heritage sites rather than relying on a film to be the “savior.”

    View record details
  • Light requirements of Australian tropical vs. cool-temperate rainforest tree species show different relationships with seedling growth and functional traits

    Lusk, Christopher H.; Kelly, Jeff W.G; Gleason, Sean M. (2013)

    Journal article
    University of Waikato

    Background and Aims A trade-off between shade tolerance and growth in high light is thought to underlie the temporal dynamics of humid forests. On the other hand, it has been suggested that tree species sorting on temperature gradients involves a trade-off between growth rate and cold resistance. Little is known about how these two major trade-offs interact. Methods Seedlings of Australian tropical and cool-temperate rainforest trees were grown in glasshouse environments to compare growth versus shade-tolerance trade-offs in these two assemblages. Biomass distribution, photosynthetic capacity and vessel diameters were measured in order to examine the functional correlates of species differences in light requirements and growth rate. Species light requirements were assessed by field estimation of the light compensation point for stem growth. Results Light-demanding and shade-tolerant tropical species differed markedly in relative growth rates (RGR), but this trend was less evident among temperate species. This pattern was paralleled by biomass distribution data: specific leaf area (SLA) and leaf area ratio (LAR) of tropical species were significantly positively correlated with compensation points, but not those of cool-temperate species. The relatively slow growth and small SLA and LAR of Tasmanian light-demanders were associated with narrow vessels and low potential sapwood conductivity. Conclusions The conservative xylem traits, small LAR and modest RGR of Tasmanian light-demanders are consistent with selection for resistance to freeze–thaw embolism, at the expense of growth rate. Whereas competition for light favours rapid growth in light-demanding trees native to environments with warm, frost-free growing seasons, frost resistance may be an equally important determinant of the fitness of light-demanders in cool-temperate rainforest, as seedlings establishing in large openings are exposed to sub-zero temperatures that can occur throughout most of the year.

    View record details
  • Analysis of the flavonoid component of bioactive New Zealand mānuka (Leptospermum scoparium) honey and the isolation, characterisation and synthesis of an unusual pyrrole

    Chan, Ching Wan; Deadman, Benjamin Jade; Manley-Harris, Merilyn; Wilkins, Alistair L.; Alber, Dagmar G.; Harry, Elizabeth (2013)

    Journal article
    University of Waikato

    The flavonoid components of New Zealand mānuka (Leptospermum scoparium) honey have been quantified in a series of 31 honeys of varying non-peroxide antibacterial activity to clarify discrepancies between previous studies reported in the literature. Total flavonoid content was 1.16 mg/100 g honey. The principal flavonoids present were pinobanksin, pinocembrin, luteolin and chrysin and together these represented 61% of the total flavonoid content. 1, 2-formyl-5-(2-methoxyphenyl)-pyrrole, which was weakly correlated with the non-peroxide antibacterial activity, was isolated from the flavonoid fraction and separately synthesised. 1 did not display inhibitory activity against Staphylococcus aureus in vitro and thus the origin of the correlation, which is still unknown, is not a direct contribution.

    View record details
  • Pairwise meta-rules for better meta-learning-based algorithm ranking

    Sun, Quan; Pfahringer, Bernhard (2013-07)

    Journal article
    University of Waikato

    In this paper, we present a novel meta-feature generation method in the context of meta-learning, which is based on rules that compare the performance of individual base learners in a one-against-one manner. In addition to these new meta-features, we also introduce a new meta-learner called Approximate Ranking Tree Forests (ART Forests) that performs very competitively when compared with several state-of-the-art meta-learners. Our experimental results are based on a large collection of datasets and show that the proposed new techniques can improve the overall performance of meta-learning for algorithm ranking significantly. A key point in our approach is that each performance figure of any base learner for any specific dataset is generated by optimising the parameters of the base learner separately for each dataset.

    View record details
  • Diurnal fluctuations in seawater pH influence the response of a calcifying macroalga to ocean acidification

    Cornwall, Christopher E.; Hepburn, Christopher D.; McGraw, Christina M.; Currie, Kim I.; Pilditch, Conrad A.; Hunter, Keith A.; Boyd, Philip W.; Hurd, Catriona L. (2013)

    Journal article
    University of Waikato

    Coastal ecosystems that are characterized by kelp forests encounter daily pH fluctuations, driven by photosynthesis and respiration, which are larger than pH changes owing to ocean acidification (OA) projected for surface ocean waters by 2100. We investigated whether mimicry of biologically mediated diurnal shifts in pH—based for the first time on pH time-series measurements within a kelp forest—would offset or amplify the negative effects of OA on calcifiers. In a 40-day laboratory experiment, the calcifying coralline macroalga, Arthrocardia corymbosa, was exposed to two mean pH treatments (8.05 or 7.65). For each mean, two experimental pH manipulations were applied. In one treatment, pH was held constant. In the second treatment, pH was manipulated around the mean (as a step-function), 0.4 pH units higher during daylight and 0.4 units lower during darkness to approximate diurnal fluctuations in a kelp forest. In all cases, growth rates were lower at a reduced mean pH, and fluctuations in pH acted additively to further reduce growth. Photosynthesis, recruitment and elemental composition did not change with pH, but δ¹³C increased at lower mean pH. Including environmental heterogeneity in experimental design will assist with a more accurate assessment of the responses of calcifiers to OA.

    View record details
  • General second-rank correlation tensors for homogeneous magnetohydrodynamic turbulence

    Oughton, Sean; Rädler, K.-H.; Matthaeus, William H. (1997)

    Journal article
    University of Waikato

    The properties and structure of second-order (Cartesian) correlation tensors are derived for the general case of two solenoidal random vector fields. The theory is intended to describe homogeneous magnetohydrodynamic turbulence, with no assumed rotational or reflectional symmetries. Each correlation tensor can be written in terms of four scalar generating functions and the relationship of these functions to the potentials that generate the poloidal and toroidal components of the underlying vector fields is derived. The physical nature of the scalar functions is investigated and their true or pseudoscalar character is ascertained. In our general discussion we clarify several misleading statements dating back to Robertson’s original paper in the field [Proc. Camb. Philos. Soc. 36, 209 (1940)]. It is also shown that using the one-dimensional correlation function, it is possible to obtain spectral information on the induced electric field in directions perpendicular to the measurement direction.

    View record details
  • Handling numeric attributes in Hoeffding trees

    Pfahringer, Bernhard; Holmes, Geoffrey; Kirkby, Richard Brendon (2008)

    Conference item
    University of Waikato

    For conventional machine learning classification algorithms handling numeric attributes is relatively straightforward. Unsupervised and supervised solutions exist that either segment the data into pre-defined bins or sort the data and search for the best split points. Unfortunately, none of these solutions carry over particularly well to a data stream environment. Solutions for data streams have been proposed by several authors but as yet none have been compared empirically. In this paper we investigate a range of methods for multi-class tree-based classification where the handling of numeric attributes takes place as the tree is constructed. To this end, we extend an existing approximation approach, based on simple Gaussian approximation. We then compare this method with four approaches from the literature arriving at eight final algorithm configurations for testing. The solutions cover a range of options from perfectly accurate and memory intensive to highly approximate. All methods are tested using the Hoeffding tree classification algorithm. Surprisingly, the experimental comparison shows that the most approximate methods produce the most accurate trees by allowing for faster tree growth.

    View record details
  • Mining Arbitrarily Large Datasets Using Heuristic k-Nearest Neighbour Search

    Wu, Xing; Holmes, Geoffrey; Pfahringer, Bernhard (2008)

    Conference item
    University of Waikato

    Nearest Neighbour Search (NNS) is one of the top ten data mining algorithms. It is simple and effective but has a time complexity that is the product of the number of instances and the number of dimensions. When the number of dimensions is greater than two there are no known solutions that can guarantee a sublinear retrieval time. This paper describes and evaluates two ways to make NNS efficient for datasets that are arbitrarily large in the number of instances and dimensions. The methods are best described as heuristic as they are neither exact nor approximate. Both stem from recent developments in the field of data stream classification. The first uses Hoeffding Trees, an extension of decision trees to streams and the second is a direct stream extension of NNS. The methods are evaluated in terms of their accuracy and the time taken to find the neighbours. Results show that the methods are competitive with NNS in terms of accuracy but significantly faster.

    View record details