Intratumoural heterogeneity complicates the molecular interpretation of biopsies, as multiple distinct tumour genomes are sampled and analysed at once. Ignoring the presence of these populations can lead to erroneous conclusions, and so a correct analysis must account for the clonal structure of the sample. Several methods to reconstruct tumour clonality from sequencing data have been proposed, spanning methods that either do not consider phylogenetic constraints or posit a perfect phylogeny. Models of the first type are typically latent feature models that can describe the observed data flexibly, but whose results may not be reconcilable with a phylogeny. The second type, instead, generally comprises non-parametric mixture models, with strict assumptions on the tumour’s evolutionary process. The focus of this dissertation is on the development of a phylogenetic latent feature model that can bridge the advantages of these two approaches, allowing deviations from a perfect phylogeny. The work is recounted by three statistical models of increasing complexity. First, I present a non-parametric model based on the Indian Buffet Process prior, and highlight the need for phylogenetic constraints. Second, I develop a finite, phylogenetic extension of the previous model, and show that it can outperform competing methods. Third, I generalise the phylogenetic model to arbitrary copy-number states. Markov chain Monte Carlo algorithms are presented to perform inference. The models are tested on datasets that include synthetic data, controlled biological data, and clinical data. In particular, the copy-number generalisation is applied to longitudinal circulating tumour DNA samples. Liquid biopsies that leverage circulating tumour DNA require sensitive techniques in order to detect mutations at low allele fractions. One method that allows sensitive mutation calling is the amplicon sequencing strategy TAm-Seq. I present bioinformatic tools to improve both the development of TAm-Seq amplicon panels and the analysis of its sequencing data. Finally, an enhancement of this method is presented and shown to detect mutations de novo and in a multiplexed manner at allele fractions less than 0.1%.

Statistical approaches are capable of underpinning strong models of musical structure, perception, and cognition. Multiple viewpoint systems are probabilistic models of sequential prediction that aim to capture the multidimensional aspects of a symbolic domain with predictions from multiple finite-context models combined in an information theoretically informed way. Information theory provides an important grounding for such models. In computational terms, information content is an empirical measure of compressibility for model evaluation, and entropy a powerful weighting system for combining predictions from multiple models. In perceptual terms, clear parallels can be drawn between information content and surprise, and entropy and certainty. In cognitive terms information theory underpins explanatory models of both musical representation and expectation. The thesis makes two broad contributions to the field of statistical modelling of music cognition: firstly, advancing the general understanding of multiple viewpoint systems, and, secondly, developing bottom-up, statistical learning methods capable of capturing higher order structure. In the first category, novel methods for predicting multiple basic attributes are empirically tested, significantly outperforming established methods, and refuting the assumption found in the literature that basic attributes are statistically independent from one another. Additionally, novel techniques for improving the prediction of derived viewpoints (viewpoints that abstract information away from whatever musical surface is under consideration) are introduced and analysed, and their relation with cognitive representations explored. Finally, the performance and suitability of an established algorithm that automatically constructs locally optimal multiple viewpoint systems is tested. In the second category, the current research brings together a number of existing statistical methods for segmentation and modelling musical surfaces with the aim of representing higher-order structure. A comprehensive review and empirical evaluation of these information theoretic segmentation methods is presented. Methods for labelling higher order segments, akin to layers of abstraction in a representation, are empirically evaluated and the cognitive implications explored. The architecture and performance of the models are assessed from cognitive and musicological perspectives.

This thesis investigates the relationship between prosody and formality in spoken Japanese, from the standpoints of both speech production and perception. The previous literature on this topic has often produced inconsistent or contradictory results (e.g. Loveday, 1981; Ofuka at al., 2000; Ito, 2001; Ito, 2002), and this thesis therefore seeks to address the research question of whether speakers and listeners use prosody in any predictable way when expressing or judging formality in spoken Japanese. Chapter 2 describes a pilot study which aimed to determine which prosodic variables were worth investigating in a larger corpus-based study. Speech of different levels of formality was elicited from subjects indirectly via the inclusion of indexical linguistic items in carrier sentences. Analysis of the relationship between mean f₀ and duration shows a significant correlation with the categories of formal and informal speech where both variables are higher in informal speech. Consequently, in Chapter 3 f₀ and articulation rate were analyzed in the corpus-based study. Corpus data for the study was collected via one-on-one conversations recorded at NINJAL in Tachikawa-shi, Japan. The speech data from the corpus was analyzed in order to test the hypothesis that the prosodic variables of mean f₀, articulation rate, and f₀ range would all be consistently higher in informal speech. Analysis using mixed effects models and a functional data analysis shows that all three prosodic variables are significantly higher in informal speech. These results were then used to inform the design of a speech perception study, which tested how manipulation of mean f₀, articulation rate, and f₀ range upwards or downwards affect listeners' judgments of de-lexicalized speech as formal or informal. Results show that manipulation of all three variables upwards or downward leads to listeners' judging recordings as more informal or formal respectively. However, manipulation of individual variables does not have a significant correlation with changes in listeners' judgements. This result led to the theory that categorization tasks in speech perception are probabilistic, with listeners accessing distributions of acoustic cues to the categories in order to make judgments. Chapter 5 of the thesis describes a probabilistic Bayesian model of formality formulated based on the theory of the cognitive process of category judgment described in Chapter 4, which attempts to predict a recording's level of formality based only on its prosody. Given information on the overall and speaker-specific distributions of the prosodic cues to the different levels of formality, the model is able to discriminate between categories at a rate better than chance (~63% accurate for formal speech, ~74% accurate for informal speech), performing better than human listeners - who could not predict formality based on only prosodic information at a rate above chance in the study in Chapter 4. The studies in this thesis show a consistent, significant relationship between prosody and formality in spoken Japanese in both speech production and perception, which can be modeled probabilistically using a Bayesian statistical framework.

Engine Management Systems (EMS) is getting more complicated each year with new functions being introduced due to tighter emission regulations of both air quality and CO2. This directly a ects the calibration process of a powertrain because the number of vehicle parameters has increased about 10 times in the last 10 years. Self-calibrating feature such as proposed in this thesis has the potential to increase the e ciency of calibrating a complex EMS. The feature is intended to adapt itself to the engine behaviour and performance by continuously updating its calibration maps as the engine is being operated. This process will reduce the needs for new calibration data and additional ne-tuning when an EMS is being carried over to a di erent vehicle. The self-calibrating feature automatically adjusts the air path calibration maps of an engine. It adjusts the air path setpoint maps in real-time for steady state operating conditions.

This thesis presents an assessment of the variation in solifluction occurrence, morphometry and movement rates in the Abisko region, northern Sweden. Variations in movement rates are analyzed both on a regional and local scale. The main methodological contributions of this thesis have been to provide new techniques of analyzing spatial and temporal variations of solifluction in order to detect long term temporal trends and to regionalize the variations in movement rates. The spatial analysis is achieved by using a combination of field measurements, GIS and remote sensing techniques and statistical analysis. The results are presented in six papers, focusing on the morphometry of solifluction landforms (paper I), the occurrence of permafrost (paper II), the spatial and temporal variations of lobe front movement rates using aerial photographs (paper III), the temporal, regional and local spatial variations in movement rates (paper IV – VI) and statistical modelling of the occurrence of solifluction landforms and calculation of geomorphic work (paper V and VI). The results show that, on a regional scale, vegetation patterns are a major control on the occurrence of turf-banked solifluction landforms, with high NDVI-values (vegetation) associated with the presence of forms. Elevation is also a major control on a regional scale with a decrease in lobe dimensions and movement rates with increased elevation. High soil moisture values are associated with larger landforms and increased movement rates. Movement rates are generally higher in the western part of the region and appear to increase with higher MAAT. Equally, geomorphic work is greatest in the western part of the region. The important controls on a local scale vary from site to site, but include vegetation, slope angle and soil moisture. The photo analysis indicates that annual movement rates of lobe fronts in Kärkevagge and Låktatjåkka valley over the period 1959-2000 ranges from not-detectable to 63mm/yr. The permafrost model shows probabilities >0.8 for permafrost at elevations above 1300 m a.s.l. in the western part of the region, decreasing to altitudes over 850 m a.s.l. in the eastern part of the region. Calculated geomorphic work suggests that solifluction is a significant denudational agent in the sub-Arctic mountains of northern Sweden, but less so than previously estimated.

Chronic Myeloid Leukemia is a kind of blood cancer with around 1 incidence per 100 000 persons/year. After the development of an effective treatment, imatinib, in the late 1990:s, the survival percentage has increased drastically. The high survival has turned the attention to different kinds of treatment responses, which in turn are good prognostic factors to future health status. In this thesis, the focus is on whether or not the patient has achieved a so called major molecular response after 12 month, or not. More precisely, the aim is to find prognostic factors to the 12 month response. In order to find prognostic factors for this binary response variable, a multivariate logistic regression analysis is conducted, with the goal of finding a parsimonious logistic model that describes the data. The analysis is done from a merged dataset from three earlier studies. The prognostic factors in the final model are treatment, 3 month response, and enlarged spleen. However, the residual analysis indicates that the model is incomplete, implying that further research needs to be done.

Precise measurements of corneal layer thickness are required to treat, evaluate risk of, and determine the progression of pathologies within the eye. The thickness measurements are typically acquired as 2d images, known as tomograms, from an optical coherence tomography (OCT) system. With the creation of ultra-high resolution OCT (UHROCT), there is active research in precisely measuring, in vivo, previously unresolvable corneal structures at arbitrary locations within the cornea to determine their relationship with corneal health. In order to obtain arbitrary corneal thickness measurements, existing reconstruction techniques require the cornea to be densely sampled so that a 3d representation can be interpolated from a stack of tomograms. Unfortunately, tomogram alignment relies solely on image properties such as pixel intensity, and does not constrain the reconstruction to corneal anatomy. Further, the reconstruction method cannot properly compensate for eye-motion. The deficiencies due to eye-motion are exacerbated due to the amount of time required in a single imaging session to acquire a sufficient number of tomograms in the region of interest. The proposed methodology is the first to incorporate models of the anatomy and the imaging system to address the limitations of existing corneal reconstruction methods. By constructing the model in such a way as to decouple anatomy from the imaging system, it becomes less computationally expensive to estimate model parameters. The decoupling provides an iterative methodology that can allow additional constraints to be introduced in the future. By combining sparsely sampled UHROCT measurements with a properly designed corneal model, reconstruction allows researchers to determine corneal layer thicknesses at arbitrary positions in both sampled and unsampled regions. The proposed methodology demonstrates an approach to decouple anatomy and physiology from measurements of a cornea, allowing for characterization of pathologies through corneal thickness measurements. Another significant contribution resulting from the corneal model allows five of the corneal layer boundaries to be automatically located and has already been used to process thousands of UHROCT tomograms. Recent studies using this method have also been used to correlate contact-lens wear to hypoxia and corneal layer swelling. While corneal reconstruction represents the main application of this work, the reconstruction methodology can be extended to other medical imaging domains and can even represent temporal changes in tissue with minor modifications to the framework.

This research examines the structure of safety climate in the manufacturing sector. It does so by examining and comparing attitudes to, and perceptions of, safety issues in two manufacturing organisations and one organisation involved in the supply of construction materials. The concept of safety climate, and the associated concept of safety culture, have been the subject of much research and theory building in recent years and this thesis builds on previous work. The research framework used here employed a mainly quantitative methodology in order to investigate the architecture of safety climate using structural modelling. Statistical modelling has been applied in other safety studies, often involving safety climate as one variable in a global description of safety systems. However it has rarely been used to model and describe the structure of safety climate as an indicator of safety culture, as in this research. The structure of safety climate described in this research is characterised by the interaction of organisational, group interaction, work environment and individual variables, which provide indicators of influences on individual levels of safety activity. Structural models of the data from all three participating organisations fitted the broad pattern of organisational variables influencing group and work environment variables, which, in turn influence individual variables. A more detailed comparison of organisational structures, however, highlighted slight differences between the two manufacturing organisations and more pronounced differences between these and the construction material supply organisation, suggesting that most elements in the structure of attitudes to safety described here are industry specific. These results are explained in terms of working environments. Differences in structure, consistent with job roles, were also apparent between occupational levels. The research, in line with previous work in the field, has highlighted the importance of management commitment to, and actions for, safety, as well as the role of individual responsibility in the promotion of safety activity. The work reported here has emphasised their importance in developing and maintaining an organisational culture for safety.

This thesis consists of two parts. The first part proposes a new model – the Markov-modulated Hawkes process with stepwise decay (MMHPSD) to investigate the seismicity rate. The MMHPSD is a self-exciting process which switches among different states, in each of which the process has distinguishable background seismicity and decay rates. Parameter estimation is developed via the expectation maximization algorithm. The model is applied to data from the Landers earthquake sequence, demonstrating that it is useful for modelling changes in the temporal patterns of seismicity. The states in the model can capture the behavior of main shocks, large aftershocks, secondary aftershocks and a period of quiescence with different background rates and decay rates. The state transitions can then explain the seismicity rate changes and help indicate if there is any seismicity shadow or relative quiescence. The second part of this thesis develops statistical methods to examine earthquake sequences possessing ancillary data, in this case groundwater level data or GPS measurements of deformation. For the former, signals from groundwater level data at Tangshan Well, China, are extracted for the period from 2002 to 2005 using a moving window method. A number of different statistical techniques are used to detect and quantify coseismic responses to P, S, Love and Rayleigh wave arrivals. The P phase arrivals appear to trigger identifiable oscillations in groundwater level, whereas the Rayleigh waves amplify the water level movement. Identifiable coseismic responses are found for approximately 40 percent of magnitude 6+ earthquakes worldwide. A threshold in the relationship between earthquake magnitude and well–epicenter distance is also found, satisfied by 97% of the identified coseismic responses, above which coseismic changes in groundwater level at Tangshan Well are most likely. A non-linear filter measuring short-term deformation rate changes is introduced to extract signals from GPS data. For two case studies of a) deep earthquakes in central North Island, New Zealand, and b) shallow earthquakes in Southern California, a hidden Markov model (HMM) is fitted to the output from the filter. Mutual information analysis indicates that the state having the largest variation of deformation rate contains precursory information that indicates an elevated probability for earthquake occurrence.

In this dissertation, we present and evaluate algorithms for statistical gas distribution modelling in mobile robot applications. We derive a representation of the gas distribution in natural environments using gas measurements collected with mobile robots. The algorithms fuse different sensors readings (gas, wind and location) to create 2D or 3D maps. Throughout this thesis, the Kernel DM+V algorithm plays a central role in modelling the gas distribution. The key idea is the spatial extrapolation of the gas measurement using a Gaussian kernel. The algorithm produces four maps: the weight map shows the density of the measurements; the confidence map shows areas in which the model is considered being trustful; the mean map represents the modelled gas distribution; the variance map represents the spatial structure of the variance of the mean estimate. The Kernel DM+V/W algorithm incorporates wind measurements in the computation of the models by modifying the shape of the Gaussian kernel according to the local wind direction and magnitude. The Kernel 3D-DM+V/W algorithm extends the previous algorithm to the third dimension using a tri-variate Gaussian kernel. Ground-truth evaluation is a critical issue for gas distribution modelling with mobile platforms. We propose two methods to evaluate gas distribution models. Firstly, we create a ground-truth gas distribution using a simulation environment, and we compare the models with this ground-truth gas distribution. Secondly, considering that a good model should explain the measurements and accurately predicts new ones, we evaluate the models according to their ability in inferring unseen gas concentrations. We evaluate the algorithms carrying out experiments in different environments. We start with a simulated environment and we end in urban applications, in which we integrated gas sensors on robots designed for urban hygiene. We found that typically the models that comprise wind information outperform the models that do not include the wind data.