507 research outputs found
Sort by
Measuring Confidence in Classification Decisions for Clinical Decision Support Systems: A Gaussian Bayes Optimization Approach
Get PDFThis thesis generally investigated various aspects of designing and developing Clinical Decision Support Systems (CDSSs), but in particular exploited machine learning techniques in supporting medical diagnosis decisions. Having reviewed the fundamental functional components of existing modern CDSSs, it shows that most such systems were lacking a trusted decision evaluation module that provides reliable information about decision strengths. Therefore a refined CDSS system framework was first proposed, which centralises the concept of confidence-based classification by coupling eventual decision outcomes with a level of decision reliability. Based on measure theory, a unified Decision Score measure of the decision reliability was introduced, which combines the decision outcomes in terms of positive or negative signs together with the decision strength in percentage values. Furthermore, the behaviour of the proposed decision score measure was investigated in more complex and diverse feature spaces of high dimensionality, where the challenges of the “curse of dimensionality” are encountered. Such challenge was handled by revisiting the problem under orthogonal projections of the feature space, and have developed a new measure in performing quantified evaluations on the decision score measure, known as the Decision Sensitivity measure. The key influencing factors for the sensitivity of decisions were found to include not only the dimensionality of the selected features, but also the standard deviation of each feature used in the transformed orthogonal space. After the basic concept of the decision score measure is established, this thesis further extended the uses of the decision score measure in a multiple classifiers setting. This thesis first reviewed the principles and rationales behind various well-established information fusion schemes and tested their strengths and limitations in adapting the proposed decision score measure. Moreover, a correlation-based decision fusion scheme was proposed in maximising the potentials of the decision score measure in complex scenarios. Based on the evaluation results across different datasets, it proves that fusion schemes improve the robustness of the decision models while maintaining a good level of diagnostic accuracy in general.
As clinical decision making normally faces new unseen cases and unpredictable challenges, it is essential to maintain a degree of adaptivity in a CDSS for post-deployment robustness of the system. Therefore, the last piece of the research reported in this thesis focused on investigating possible ways to refine the CDSS decision scores model in a time-efficient manner, spontaneously. In particular, this thesis reviewed several commonly used metrics and methods for monitoring and refining prediction models, and further adapted these methods to the proposed decision score measure
Vehicle Pair Activity Classification Using QTC and Long Short Term Memory Neural Network
Get PDFThe automated recognition of vehicle interaction is crucial for self-driving, collision avoidance and security surveillance applications. In this paper, we present a novel Long-Short Term Memory Neural Network (LSTM) based method for vehicle trajectory classification. We use Qualitative Trajectory Calculus (QTC) to represent the relative motion between a pair of vehicles. The spatio-temporal features of the interacting vehicles are captured as a sequence of QTC states and then encoded using one hot vector representation. Then, we develop an LSTM network to classify QTC trajectories that represent vehicle pairwise activities. Most of the high performing LSTM models are manually designed and require expertise in hyperparameter configuration. We adapt Bayesian Optimisation method to find an optimal LSTM architecture for classifying QTC trajectories of vehicle interaction. We evaluated our method on three different datasets comprising 7257 trajectories of 9 unique vehicle activities in different traffic scenarios. We demonstrate that our proposed method outperforms the state-of-the-art techniques. Further, we evaluated our approach with a combined dataset of the three datasets and achieved an error rate of no more than 1.79%. Though, our work mainly focuses on vehicle trajectories, the proposed method is generic and can be used on pairwise analysis of other interacting objects
'Fox Hunting and Classical Horsemanship as Social Performance of Elitism and Power: A Journey Across Time' (Ropa, ed)
No full textThis chapter juxtaposes the developments of foxhunting and classical horsemanship over time, using a performance framework to evaluate how they respectively communicated and continue to communicate messages about social status, group identity and social cohesion of the society in which they are placed. This chapter considers how social conditions shape and are shaped by these horsemanship pursuits, in explaining the different trajectories these have had over time. In the 21stcentury, classical horsemanship has a new prestige marker through inscription on the UNESCO list for intangible cultural heritage. In contrast, hunting live foxes has been banned since 2004through an Act of Parliament and a legal decision by the UK House of Lords, with the ban coming to stand for a triumph for democracy
From the Wings to the Stage and Beyond; Performance Anxiety and Flow in UK Vocational Dance Students
Get PDFProfessional dancers have described high levels of performance anxiety while also experiencing flow on stage. However, such research tends to capture one period of time in the performance experience and rarely focuses on vocational dance students. The current study samples vocational dance students at a UK performing arts school and captures their cognitive, somatic and emotional experiences from pre- to post-performance. Eleven interviews were conducted with female students aged between 15 and 17 years. Thematic analysis was employed and three themes identified:
Facilitative and Debilitative Anxiety in the Wings, Constructions of Anxiety and Flow on Stage, and After the Show; the Highs and the Lows. Findings produced an understanding of the psychological journey from pre- to post-performance. Students have the potential to manipulate
their cognitions to facilitate flow suggesting that dance schools can implement psychological techniques to manage anxiety and increase flow, thus enhancing well-being and performanc
Anomalous Viscosity of a Racemate: A Simple Experiment Demonstrating Chirally Induced Spin Selectivity
Get PDFIt has been known for over a century that racemic solutions of hydrogen-bonded compounds are less viscous than their component enantiomers, but this fact has so far remained unexplained. Here we confirm it using enantiomers of lactic acid and compare it to molecular dynamics (MD) simulations of lactic acid viscosity. The effect is absent in classical MD. We suggest that the anomalous viscosity of racemates may be due to a recently discovered magnetic intermolecular force due to spin-dependent charge reorganization
Automatic Convolutional Neural Network Architecture Search for Breast Lesion Classification from Ultrasound Images: An ENAS Bayesian Optimization Approach
Get PDFBreast cancer is one of the most common cancer types among women globally. Cancer detection/classification from medical images is a topic of vital importance because early cancer detection may allow patients to receive proper and timely treatment, significantly increasing their survival rates. Ultrasound imaging has been extensively used for various medical diagnostics by radiologists. Over the last ten years, sophisticated deep learning neural networks such as Convolutional Neural Networks (CNN) have been developed. Such deep learning neural networks tend to provide an “end-to-end” solution for image pattern recognition and have achieved impressive performance results for various applications. Deep convolutional neural networks have recently appeared in CAD systems due to their success in extracting effective image features.
CNN architecture design involves using many hyper-parameters. Creating a robust CNN architecture depends on finding an optimal combination between those hyper-parameters. Therefore, manually designing CNN architecture is time-consuming and leads to trial and error. Neural Architecture Search offers an alternative by automatically determining hyper-parameter settings for CNN architectures based on the dataset at hand. Efficient Neural Architecture Search (ENAS) is the efficient method for automatically designing CNN architecture. There has been no research in the literature - till that reported in this thesis - on using ENAS to search for CNN architecture for ultrasound images in general nor for breast lesion classification. In addition, there are only a few reported pieces of research on CNN architectures manually designed specifically for breast lesion classification from ultrasound images. These research works are based on only small datasets from one hospital in their modelling and testing processes.
This research aims to create an automatic designing CNN architecture approach for designing CNN architectures for classifying breast cancer from ultrasound images. This research investigates the effectiveness of one of the most popular methods, ENAS, for automatically searching for a convolutional neural network architecture. The research starts by adapting the ENAS framework to automatically search for optimal CNN architectures based on datasets of ultrasound images collected from different medical centres. The research then addresses the issue of model overfitting and generalisation of ENAS-based CNNs by using different data augmentation, reducing architecture complexity and training on an unbalanced number of images between benign and malignant classes. Furthermore, the ENAS framework is modified by expanding its search space by adding more operations suitable for ultrasound images such as different convolutional operations with different filter sizes. This modification improved the overall performance of produced CNN architecture by ENAS. We further enhanced the design of final CNN model which are based on optimal cells obtained by ENAS by adding a high-way connection to compensate features from early layers to the final set of feature maps.
Furthermore, this research deploys the Bayesian Optimisation method to further develop an ENAS-B framework to address the limitations of the existing ENAS framework in optimizing the CNN architecture layers and trainable hyper-parameters, promoting an end-to-end automatic CNN search for the intended purpose of breast lesion classification using ultrasound images. The research concludes that a CNN model of 5 layers with optimised hyper-parameters is a robust model that can outperform the state-of-the-art CNN models designed for breast lesion classification such as VGG-16, ResNet50, Inception-V3, XceptionNet, NasNet mobile, EfficentNetB0 and mobile Net-V2 methods with transfer learning. The work presented in this thesis provides a good guideline for scientists to design a robust CNN model that can generalise beyond internal testing datasets
FROM GOVERNMENT TO GOVERNANCE, FROM JUDICIARY TO…?
Get PDFIt is clear from the research on the political and legal constitutions around regulatory power that it is a complex picture. The question for this paper is whether there is a relationship between regulatory governance and institutions and the judiciaries, i.e. are they constrained by the rule of law in the same way as classical administration? The first part of this paper will start to chart out an expansion and contraction of judicial power in relation to executive powers. The second part will provide a comparison between England and France’s regulatory systems and their relationships to their respective judiciaries. The conclusion sets out to answer the main question of where the judiciary sits in an a complex political, economic and legal tapestry to control a hybrid institution that sits outside of a legal constitution
Parental Perspectives on Their Sons’ Motivation to Dance
Get PDFClements and Clegg present original data, from parent's of adolescent boys who dance, that considers the parental experiences of and the boys’ motivations to dance. Parents perceived their son’s as highly internally motivated to dance despite both the parents and the boys experiencing negative reactions from others. To facilitate their son’s engagement in dance, parents provided both psychological support, by enhancing resilience, alongside practical support in the form of finance and travel arrangements. Although parents expressed concern about injury and career stability they recognized the psychological benefits for their sons and the emotional positivity for themselves. The chapter’s findings capture the perceived impact of the interrelationship between age, gender, sexuality and socioeconomic status for adolescent male dancers
The Role of sentiment in the economy: 1920-1934
Get PDFThis paper investigates sentiment in the US economy from 1920 to 1934 using digitized articles from the Wall St Journal. We derive a monthly sentiment index and use a ten variable vector error correction model to identify sentiment shocks that are orthogonal to fundamentals. We show the timing and strength of these shocks and their resultant effects on the economy using historical decompositions. Intermittent impacts of up to fifteen percent on Industrial Production, ten percent on the S&P 500 and Bank loans and, thirty-seven basis points for the Credit risk spread, suggest a large role for sentiment
Bank Default Risk Propagation along Supply Chains: Evidence from the U.K.
Get PDFHow does banks’ default risk affect the probability of default of non-financial business-es? The literature has focused on the banks’ direct corporate customers. It fails to con-sider the role of supply chain relationships as a powerful channel for default risk conta-gion. Our paper fills this gap by analyzing the direct as well as the indirect impact of banks’ default risk on firms’ default risk in the U.K. Relying on Input-Output tables, we devise methods that enable us to examine this question in the absence of data on firm-to-firm linkages. To capture all potential propagation channels, we account for horizontal and vertical linkages, both between the firm and upstream industries (suppliers) and between the firm and downstream industries (customers). We further examine how trade credit and input specificity amplify or dampen the propagation of default risk. Our results show that increases in banks’ default risk from the banking crisis of 2007-2008 propagated strongly to U.K. non-financial firms via supply chains