Computing and Mathematical Sciences Papers

This collection houses research from the School of Computing and Mathematical Sciences at the University of Waikato.

Recent Submissions

Now showing 1 - 5 of 1506
  • Item
    Predicting Steam Turbine Power Generation: A Comparison of Long Short-Term Memory and Willans Line Model
    (Journal Article, MDPI AG, 2024-01-10) Pasandideh, Mostafa; Taylor, Mathew; Tito, Shafiqur Rahman; Atkins, Martin John; Apperley, Mark
    This study focuses on using machine learning techniques to accurately predict the generated power in a two-stage back-pressure steam turbine used in the paper production industry. In order to accurately predict power production by a steam turbine, it is crucial to consider the time dependence of the input data. For this purpose, the long-short-term memory (LSTM) approach is employed. Correlation analysis is performed to select parameters with a correlation coefficient greater than 0.8. Initially, nine inputs are considered, and the study showcases the superior performance of the LSTM method, with an accuracy rate of 0.47. Further refinement is conducted by reducing the inputs to four based on correlation analysis, resulting in an improved accuracy rate of 0.39. The comparison between the LSTM method and the Willans line model evaluates the efficacy of the former in predicting production power. The root mean square error (RMSE) evaluation parameter is used to assess the accuracy of the prediction algorithm used for the generator’s production power. By highlighting the importance of selecting appropriate machine learning techniques, high-quality input data, and utilising correlation analysis for input refinement, this work demonstrates a valuable approach to accurately estimating and predicting power production in the energy industry.
  • Item
    Designing for Inaccessible People and Places
    (Conference Contribution, SPRINGER INTERNATIONAL PUBLISHING AG, 2021-01-01) Bowen, Judy; Hinze, Annika
    New Zealand forestry has the highest number of accidents and fatalities than any other NZ industry. Worker fatigue, work environment, and worker demographics all contribute to these high numbers. We have been investigating ways of tackling these problems using wearable and sensor-based technology. Two of the challenges faced by this project are: the personal nature of data collected by wearable technology and the lack of regular access to workers to take part in user-centered design activities. In this paper, we describe the use of Lean UX methods with proxy participants and proxy technology to explore key aspects of a proposed technical solution. We show that from these experimental studies, we were able to draw appropriate conclusions on which to base the development of a prototype designed to support forestry worker safety.
  • Item
    Hitting the target: stopping active learning at the cost-based optimum
    (Journal Article, Springer Science and Business Media LLC, 2022) Pullar-Strecker, Zac; Dost, Katharina; Frank, Eibe; Wicker, Jörg
    Active learning allows machine learning models to be trained using fewer labels while retaining similar performance to traditional supervised learning. An active learner selects the most informative data points, requests their labels, and retrains itself. While this approach is promising, it raises the question of how to determine when the model is ‘good enough’ without the additional labels required for traditional evaluation. Previously, different stopping criteria have been proposed aiming to identify the optimal stopping point. Yet, optimality can only be expressed as a domain-dependent trade-off between accuracy and the number of labels, and no criterion is superior in all applications. As a further complication, a comparison of criteria for a particular real-world application would require practitioners to collect additional labelled data they are aiming to avoid by using active learning in the first place. This work enables practitioners to employ active learning by providing actionable recommendations for which stopping criteria are best for a given real-world scenario. We contribute the first large-scale comparison of stopping criteria for pool-based active learning, using a cost measure to quantify the accuracy/label trade-off, public implementations of all stopping criteria we evaluate, and an open-source framework for evaluating stopping criteria. Our research enables practitioners to substantially reduce labelling costs by utilizing the stopping criterion which best suits their domain.
  • Item
    Balancing performance and energy consumption of bagging ensembles for the classification of data streams in edge computing
    (Journal Article, IEEE, 2022) Cassales, Guilherme; Gomes, Heitor Murilo; Bifet, Albert; Pfahringer, Bernhard; Senger, Herme
    In recent years, the Edge Computing (EC) paradigm has emerged as an enabling factor for developing technologies like the Internet of Things (IoT) and 5G networks, bridging the gap between Cloud Computing services and end-users, supporting low latency, mobility, and location awareness to delay-sensitive applications. An increasing number of solutions in EC have employed machine learning (ML) methods to perform data classification and other information processing tasks on continuous and evolving data streams. Usually, such solutions have to cope with vast amounts of data that come as data streams while balancing energy consumption, latency, and the predictive performance of the algorithms. Ensemble methods achieve remarkable predictive performance when applied to evolving data streams due to several models and the possibility of selective resets. This work investigates a strategy that introduces short intervals to defer the processing of mini-batches. Well balanced, our strategy can improve the performance (i.e., delay, throughput) and reduce the energy consumption of bagging ensembles to classify data streams. The experimental evaluation involved six state-of-art ensemble algorithms (OzaBag, OzaBag Adaptive Size Hoeffding Tree, Online Bagging ADWIN, Leveraging Bagging, Adaptive RandomForest, and Streaming Random Patches) applying five widely used machine learning benchmark datasets with varied characteristics on three computer platforms. As a result, our strategy can significantly reduce energy consumption in 96% of the experimental scenarios evaluated. Despite the trade-offs, it is possible to balance them to avoid significant loss in predictive performance.
  • Item
    Reading Lists Systems' pedagogical features: a comparative analysis
    (Conference Contribution, IEEE, 2023-06) Kumara, P. P. N. V.; Hinze, Annika; Vanderschantz, Nicholas; Timpany, Claire
    Reading Lists Systems are a pedagogical tool used in tertiary education to streamline the creation and management of course reading lists and make copyright compliance easier. This paper explores the design of current Reading Lists systems and how their features support the pedagogical needs of academics and students in tertiary education. A feature review combined with a comparative analysis approach was employed in our study. We analysed and compared Reading Lists systems and their features, implemented through Digital Libraries, that provide pedagogical support for academic teaching. As one of our outcomes, we identify the need to assist teachers to effectively use these tools in their daily practice.
All items in Research Commons are provided only to permit fair dealing for the purposes of research or private study. They are protected by copyright with all rights reserved unless otherwise indicated.