Engineering Science - Doctoral Theses

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 3 of 3
  • Item
    Development and evaluation of tools and methodologies for estimating behaviour and predicting training outcome of working dogs
    (University College Cork, 2023) Marcato, Marinara; Galvin, Paul; O'Flynn, Brendan; O'Mahony, Conor; Tedesco, Salvatore; INTERREG Programme (CALIN project); Science Foundation Ireland; Department of Agriculture, Food and the Marine, Ireland; European Regional Development Fund
    Background: The average training success rate in different dog industries is as low as 50% and the cost of training a guide dog is as high as 53,00 in Ireland. The key to reducing costs is in the assessment of trainee dogs for identifying likely to fail at an early stage. Objectives: This thesis aims to improve behavioural assessment methods by including machine learning methods to (1) predict future outcomes in trainee assistance dogs based on ratings and test batteries, and (2) estimate canine posture based on a recognition system specifically designed for working dogs. Methods: (1) Two standardised ratings were used, in particular, the Canine Behavioral Assessment and Research Questionnaire (C-BARQ) was completed by puppy raisers and the Monash Canine Personality Questionnaire - Revised (MCPQ-R) was answered by dog trainers. Rating data were independently analysed to investigate their relationship with training outcomes. The novel Assistance Dog Test Battery (ADTB) was designed to assess the suitability of trainee assistance dogs for assistance work during training. The test was conducted at 3 weeks - Data Collection 1 (DC1) - and 10 weeks - Data Collection 2 (DC2) - after the start of formal training to investigate the optimal timing to predict working outcomes. (2) Three Inertial Measurement Units (IMUs) were placed on the dogs in different positions (neck, back and chest) and five postures (walking, standing, sitting, lying down and body shake) were annotated. Advanced machine learning techniques were applied for the first time in this field to improve state-of-the-art posture prediction performance. Results: (1) The machine learning models achieved an area under the ROC of 0.84 and 0.85 when using the ratings C-BARQ and MCPQ-R to predict training outcome; and 0.74 and 0.84 when using the DC1 and DC2 of the ADTB to predict working outcomes, respectively. (2) The optimal canine posture classifier achieved an f1-weighted of 0.90. Conclusions: (1) These novel machine learning models provided the most effective early prediction of suitability for assistance work. The MCPQ-R and ADTB were demonstrated for the first time to be a reliable canine behavioural assessment method for estimating future outcomes in trainee dogs. (2) Comparison with previous work reveals a superior performance of the new canine posture estimation system for working
  • Item
    Performing women’s poetry: an evolving craft
    (University College Cork, 2023) Manning, Maria Hanora; Jenkins, Lee; Hanna, Adam; Irish Research Council
    This research project proposes to examine a current cohort of female poets employing performance techniques in their poetries, investigating how these poets continue to adapt and adopt the aesthetics of earlier poets. In recent years, the popularity of poetry in online communities has boomed, with an inevitable backlash to this poetic movement, criticising its contribution to poetry as a cultural form, such as Rebecca Watts’ PN Review article. Throughout this research, I aim to locate these poetries (often described as “digital” or “e- poetries”) along a continuum of performance, identifying the ways in which such a factor is evoked in both these new works and the work of earlier poets. Bearing in mind the theories John Miles Foley’s book Oral Literature and the Internet: Pathways of the Mind, which suggests the internet is a natural evolution of oral literature and spoken word poetries, I aim to connect the work of this cohort of poets with performance poets before them, examining the performative overlaps between oral and digital literatures. This project will interrogate the ways in which performance is enacted through a number of guises, from the sounds of orality and musicality, to the embodiment of performance by these poets. I aim to examine the creation of an aesthetic of performance among these women poets, paying particular attention to the ways the female body is performed in this work. Finally, I consider the social implications and contexts of such work, exploring the connections between poet and audience, the poetic persona and the performance of politics in these poetries. My research is primarily focused on work of poets disseminating their work chiefly through non-print methods, such as recording, performance, and social media, in the 21st Century. I will also examine the performance poetries of women poets in the 20th Century, examining the connections and creation ofa performance aesthetic, aiming to link the work of poets across these eras by examining a series of aspects of their poetics, such as the orality, the body, musicality, social engagement and public spheres of poetry.
  • Item
    Laser-induced graphene for electrochemical sensing applications
    (University College Cork, 2023) Vaughan, Eoghan; Iacopino, Daniela; Quinn, Aidan J.; Horizon 2020
    The fabrication of laser-induced graphene (LIG) allows rapid, inexpensive patterning of electrode designs onto various substrates. LIG is a material whose properties can be tuned by altering the fabrication process, to suit the desired application. In this thesis, LIG materials were developed using a low-power hobbyist visible laser system, for electrochemical sensing applications. Polyimide (PI) was studied initially as a precursor, with the resultant LIG electrodes showing excellent electrochemical properties. Then LIG electrodes were bio-modified for the sensitive detection of Interleukin 6. Bioplastic precursors, as an alternative to PI, were explored as a potential route to green-LIG devices. Chitosan-based sheets were graphitised, and the properties of this LIG were investigated. The electron transfer rates at such electrodes are promising for future device applications. Finally, cork is used as a LIG precursor. Electrochemical cork-LIG sensors showed remarkable properties, with rapid electron transfer rates and a low detection limit for Tyrosine and dopamine. The results contained in this thesis present fast, inexpensive and eco-friendly options for LIG electrochemical sensor development.