Computing and Mathematical Sciences Papers
This collection houses research from the Faculty of Computing and Mathematical Sciences at the University of Waikato.
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.
Recently Added
Subscribe (RSS 1.0)-
Transformers for multi-label classification of medical text: an empirical comparison
(Springer, 2021)Recent advancements in machine learning-based multi-label medical text classification techniques have been used to help enhance healthcare and aid better patient care. This research is motivated by transformers’ success ... -
Left restriction monoids from left E-completions
(Elsevier BV, 2022-05)Given a monoid S with E any non-empty subset of its idempotents, we present a novel one-sided version of idempotent completion we call left E-completion. In general, the construction yields a one-sided variant of a small ... -
Ordered Ehresmann semigroups and categories
(Taylor & Francis Inc, 2022-05-08)Ehresmann semigroups may be viewed as biunary semigroups equipped with domain and range operations satisfying some equational laws. Motivated by some of the main examples, we here define ordered Ehresmann semigroups, and ... -
Constellations with range and IS-categories
(2022)Constellations are asymmetric generalisations of categories. Although they are not required to possess a notion of range, many natural examples do. These include commonly occurring constellations related to concrete ... -
(F,G)-abundant semigroups
(Springer, 2022)On a semigroup S, define the equivalence relation F={(a,b)∈S×S∣∀x∈S:xa=x⇔xb=x}, and define G dually. We say S is F-abundant if there is an idempotent in every F-class, and similarly for G-abundance, and we say S is ... -
Habitat provision is a major driver of native bird communities in restored urban forests
(John Wiley & Sons Ltd, 2022)Urbanization, and the drastic loss of habitat it entails, poses a major threat to global avian biodiversity. Ecological restoration of urban forests is therefore increasingly vital for native bird conservation, but control ... -
On the latency impact of remote peering
(Springer, 2022)Internet Exchange Points (IXPs) play an essential role in the Internet, providing a fabric for thousands of Autonomous Systems (ASes) to interconnect. Initially designed to keep local traffic local, IXPs now interconnect ... -
Predicting glucose level with an adapted branch predictor
(Elsevier BV, 2022)Background and objective Diabetes mellitus manifests as prolonged elevated blood glucose levels resulting from impaired insulin production. Such high glucose levels over a long period of time damage multiple internal ... -
Experiments in cross-domain few-shot learning for image classification
(Informa UK Limited, 2022)Cross-domain few-shot learning has many practical applications. This paper attempts to shed light on suitable configurations of feature exactors and ‘shallow’ classifiers in this machine learning setting. We apply ResNet-based ... -
Methods for eliciting informative prior distributions: A critical review
(INFORMS, 2022)Eliciting informative prior distributions for Bayesian inference can often be complex and challenging. Although popular methods rely on asking experts probability-based questions to quantify uncertainty, these methods are ... -
Energy digital twin technology for industrial energy management: Classification, challenges and future
(Elsevier BV, 2022)Digitalisation of the process and energy industries through energy digital twin technology promises step-improvements in energy management and optimisation, better servicing and maintenance, energy-efficient design and ... -
GPUTreeShap: massively parallel exact calculation of SHAP scores for tree ensembles
(PeerJ, 2022)SHapley Additive exPlanation (SHAP) values (Lundberg & Lee, 2017) provide a game theoretic interpretation of the predictions of machine learning models based on Shapley values (Shapley, 1953). While exact calculation of ... -
Interaction modelling for IoT
(IEEE, 2021)Informal design artefacts allow end-users and nonexperts to contribute to software design ideas and development. In contrast, software engineering techniques such as modeldriven development support experts in ensuring ... -
Wearable technology for hazardous remote environments: Smart shirt and Rugged IoT network for forestry worker health
(Elsevier BV, 2022)This paper introduces the architecture and details of our wearable IoT solution for workplace health and safety in rugged outdoor environments. We focus on the specific requirements defined by the New Zealand forestry ... -
Sampling permutations for Shapley value estimation
(Microtome Publishing, 2022)Game-theoretic attribution techniques based on Shapley values are used to interpret blackbox machine learning models, but their exact calculation is generally NP-hard, requiring approximation methods for non-trivial models. ... -
Enhancing regulatory compliance by using artificial intelligence text mining to identify penalty clauses in legislation
(Full Court Press, 2018)As regulatory compliance (or compliance governance) becomes ever more challenging, attempts to engage IT solutions and especially artificial intelligence (AI) are on the rise. This paper suggest that regulatory compliance ... -
Perceptual improvements for Super-Resolution of Satellite Imagery
(IEEE, 2021)Super-resolution of satellite imagery poses unique challenges. We propose a hybrid method comprising two existing deep network super-resolution approaches, namely a feedforward network called DeepSUM, and ESRGAN, a GAN-based ... -
Using Coq to Enforce the Checks-Effects-Interactions Pattern in DeepSEA Smart Contracts
(2021)Using the DeepSEA system for smart contract proofs, this paper investigates how to use the Coq theorem prover to enforce that smart contracts follow the Checks-Effects-Interactions Pattern. This pattern is widely understood ... -
The 'DEEP' Landing Error Scoring System
(MDPI, 2020)The Landing Error Scoring System (LESS) is an injury-risk screening tool used in sports; but scoring is time consuming, clinician-dependent, and generally inaccessible outside of elite sports. Our aim is to evidence that ... -
Interpretable deep learning for surgical tool management
(Springer, 2021)This paper presents a novel convolutional neural network framework for multi-level classification of surgical tools. Our classifications are obtained from multiple levels of the model, and high accuracy is obtained by ...
