Welcome to ChesterRep - the University of Chester's Online Research Repository
ChesterRep is the University of Chester's institutional repository and an online platform designed to collate, store, and aid discoverability of research carried out at the university to the wider research community
For more information about how to submit material to ChesterRep, see our ChesterRep guides here. You can also find out more about our editorial and open access policies here. Please note that you must be a member of the University of Chester in order to view these pages.
Communities in DSpace
Select a community to browse its collections.
Alzheimer Brain Imaging Dataset Augmentation Using Wasserstein Generative Adversarial NetworkDeep learning models have evolved to be very efficient and robust for several computer vision applications. To harness the benefits of state-of-the-art deep networks in the realm of disease detection and prediction, it is imperative that high-quality datasets be made available for the models to train on. This work recognizes the dearth of training data (both in terms of quality and quantity of images) for using such networks for the detection of Alzheimer’s disease. It is proposed to employ a Wasserstein Generative Adversarial Network (WGAN) for generating synthetic images for augmentation of an existing Alzheimer brain image dataset. It is shown that the proposed approach is indeed successful in generating high-quality images for inclusion in the Alzheimer image dataset potentially making the dataset more suited for training high-end models.
FireNet-Tiny: Very-Low Parameter Count High Performance Fire Detection ModelIn daily life, fire threats result in significant costs on the ecological, social, and economic levels. It is essential to outfit the assets with fire prevention systems due to the sharp rise in the frequency of fire mishaps. To prevent such mishaps, several studies have been conducted to develop optimal and potent fire detection models. While the earliest methods were thermal/chemical in nature, image processing was later applied for identification of fire. More recent methods have taken advantage of the significant advancements in deep learning models for computer vision. However, in order to maintain a suitable inference time (leading towards real-time detection) and parameter count, the majority of deep learning models have to make trade-offs between their detection speed and detection performance (accuracy/recall/precision). The very lightweight convolution neural network we offer in this paper is specifically designed for the fire detection use case. The proposed model can be embedded in real-time fire monitoring equipment and could also prove potentially useful for future fire monitoring methods such as unmanned aerial vehicles (drones). By further diminishing the trainable parameter count of the model, the fire detection results obtained using the proposed FireNet-Tiny significantly outperform the prior low parameter count models. When tested against FireNet dataset, FireNet-Tiny, which only comprises 261,922 parameters, was shown to have an overall accuracy of 95.75%. In comparison, FireNet-v2 provided 94.95% accuracy with 318,460 parameters.
An Ultra-Energy-Efficient Reversible Quantum-Dot Cellular Automata 8:1 Multiplexer CircuitEnergy efficiency considerations in terms of reduced power dissipation are a significant issue in the design of digital circuits for very large-scale integration (VLSI) systems. Quantum-dot cellular automata (QCA) is an emerging ultralow power dissipation approach, distinct from traditional, complementary metal-oxide semiconductor (CMOS) technology, for building digital computing circuits. Developing fully reversible QCA circuits has the potential to significantly reduce energy dissipation. Multiplexers are fundamental elements in the construction of useful digital circuits. In this paper, a novel, multilayer, fully reversible QCA 8:1 multiplexer circuit with ultralow energy dissipation is introduced. The power dissipation of the proposed multiplexer is simulated using the QCADesigner-E version 2.2 tool, describing the microscopic physical mechanisms underlying the QCA operation. The results show that the proposed reversible QCA 8:1 multiplexer consumes 89% less energy than the most energy-efficient 8:1 multiplexer circuit previously presented in the literature
A critical autoethnographic study of the experience of the older secondary school teacher in England: a socio-political and emotional model of their Body without OrgansThis research explores the lives of ‘older’ secondary teachers as they inhabit an educational landscape that has changed significantly during their careers. It employs a postmodern critical autoethnographic methodology as a vehicle through which to examine their experiences, as professionals who now exist in a neoliberal, marketised model of education, where they have been commodified. The work focuses on how their experiences of education have moulded their values and identities and provides empirical evidence showing that maintaining these fundamentals is challenged and compromised in the educational landscape that they work in. There are imperatives for this study. The UK population is ageing, and people will be forced to work for longer in the future. However, professional challenges that older teachers face are driving them out of the profession prematurely. This is at a time of crisis in education, where there is a failure to recruit and retain teachers, so arresting the exodus of older teachers would partly address the significant, long-standing recruitment issue. The evidence demonstrates that older teachers experience a loss of voice and agency. They are subjected to performative regimes, that measure that which is readily measurable, in an education system that has a functionalist agenda, with an economic purpose. This regime quells their creative desires and limits their opportunities to collaborate and to share their significant knowledge and experience. Older teachers are not afforded the same promotion and developmental opportunities as younger teachers and are subject to ageist stereotypical assumptions about their continued ability to function at a high level in teaching. This is despite their will to continue to develop and seek new opportunities. The evidence demonstrates that they do not feel professionally valued, despite the wealth of experience that they have to offer, and the research reveals their voices and the significant emotional impact of this on them. Drawing on the work of Deleuze and Guattari (2013a, b) and my empirical evidence, I construct a socio-political model of the older teachers’ “Body without Organs”. This Vitruvian Teacher model incorporates aspects of their professional lives that sustain them, together with those that significantly challenge them. The critical narrative that emanates from the research gives rise to suggestions for sustaining these teachers in fulfilling careers.