Global ETD Search

1	The analysis and application of artificial neural networks for early warning systems in hydrology and the environment Duncan, Andrew Paul January 2014 (has links) Artificial Neural Networks (ANNs) have been comprehensively researched, both from a computer scientific perspective and with regard to their use for predictive modelling in a wide variety of applications including hydrology and the environment. Yet their adoption for live, real-time systems remains on the whole sporadic and experimental. A plausible hypothesis is that this may be at least in part due to their treatment heretofore as “black boxes” that implicitly contain something that is unknown, or even unknowable. It is understandable that many of those responsible for delivering Early Warning Systems (EWS) might not wish to take the risk of implementing solutions perceived as containing unknown elements, despite the computational advantages that ANNs offer. This thesis therefore builds on existing efforts to open the box and develop tools and techniques that visualise, analyse and use ANN weights and biases especially from the viewpoint of neural pathways from inputs to outputs of feedforward networks. In so doing, it aims to demonstrate novel approaches to self-improving predictive model construction for both regression and classification problems. This includes Neural Pathway Strength Feature Selection (NPSFS), which uses ensembles of ANNs trained on differing subsets of data and analysis of the learnt weights to infer degrees of relevance of the input features and so build simplified models with reduced input feature sets. Case studies are carried out for prediction of flooding at multiple nodes in urban drainage networks located in three urban catchments in the UK, which demonstrate rapid, accurate prediction of flooding both for regression and classification. Predictive skill is shown to reduce beyond the time of concentration of each sewer node, when actual rainfall is used as input to the models. Further case studies model and predict statutory bacteria count exceedances for bathing water quality compliance at 5 beaches in Southwest England. An illustrative case study using a forest fires dataset from the UCI machine learning repository is also included. Results from these model ensembles generally exhibit improved performance, when compared with single ANN models. Also ensembles with reduced input feature sets, using NPSFS, demonstrate as good or improved performance when compared with the full feature set models. Conclusions are drawn about a new set of tools and techniques, including NPSFS and visualisation techniques for inspection of ANN weights, the adoption of which it is hoped may lead to improved confidence in the use of ANN for live real-time EWS applications. 004
2	Chapter 1: In Search of Innate Leadership : Discovering, Evaluating and Understanding Innateness Morra, Erica, Zenker, Lisa January 2014 (has links) Every individual is born with different natural competencies that can be honed by both voluntary and involuntary environmental stimuli. The response our genotype decides to make, if any, towards those stimuli, determines how well our competencies develop. Each person’s coding and variations of genes will result in unique qualities in their phenotype, or physical structure. As a result, a person has various traits that are displayed through their behavior. DNA is genetically shown to express itself through traits by up to 75%. This leaves a sort of buffer of around 25%. This region is available for us to adapt to our environmental stimuli. Your innate qualities will not reach their full potential without stimulation from the environment, in a leadership case, with education and training and therefore it can be argued that environmental exposure is necessary to fully expose the potentials and capabilities of an individual, rather than instill a new skill or develop a talent that was not existent before. Innate leadership is not a permanent state, on the contrary, it is a continuously adaptive situation demanding contextual evolutionary changes or resignation from the subject occupying the role. When the needs and demands of a society or era outweigh the relevance of the innate leaders' traits and competencies, an evolution of leadership is needed to maintain a positive relationship between all parties involved. As a result, the innate leader will begin to lose their innateness in their role and unless they evolve and adapt (because the two actions are not the same) to new contextual needs, their tenure as leader will begin to be detrimental and counter-functional. What we want to put forward is a real, universal and constructive understanding of what makes a human happy, motivated and productive and how an innate person in context is a much better solution in the short and long run, for those around them when put to a task. genetic inheritability gene expression genetic determination gene mutation case study innatism traits leadership behaviour brain development brain function neural pathway neural coding SNP variation connectomics genomics heritability leadership theory DNA competencies environment education behavioural psychology genetics trait theory nature vs nurture dopamine neurotransmitters polygenetic traits Google Hitler personality innate leadership Morra Zenker

Search results

The analysis and application of artificial neural networks for early warning systems in hydrology and the environment

Chapter 1: In Search of Innate Leadership : Discovering, Evaluating and Understanding Innateness