Statistical methods for biomedical signal analysis and processing

Statistical modelling and statistical learning theory are two powerful analytical frameworks for analyzing signals and developing efficient processing and classification algorithms. In this thesis, these frameworks are applied for modelling and processing biomedical signals in two different contexts: ultrasound medical imaging systems and primate neural activity analysis and modelling. In the context of ultrasound medical imaging, two main applications are explored: deconvolution of signals measured from a ultrasonic transducer and automatic image segmentation and classification of prostate ultrasound scans. In the former application a stochastic model of the radio frequency signal measured from a ultrasonic transducer is derived. This model is then employed for developing in a statistical framework a regularized deconvolution procedure, for enhancing signal resolution. In the latter application, different statistical models are used to characterize images of prostate tissues, extracting different features. These features are then uses to segment the images in region of interests by means of an automatic procedure based on a statistical model of the extracted features. Finally, machine learning techniques are used for automatic classification of the different region of interests. In the context of neural activity signals, an example of bio-inspired dynamical network was developed to help in studies of motor-related processes in the brain of primate monkeys. The presented model aims to mimic the abstract functionality of a cell population in 7a parietal region of primate monkeys, during the execution of learned behavioural tasks.

Statistical methods for analysis and processing of medical ultrasound: applications to segmentation and restoration

In this thesis two major topics inherent with medical ultrasound images are addressed: deconvolution and segmentation. In the first case a deconvolution algorithm is described allowing statistically consistent maximum a posteriori estimates of the tissue reflectivity to be restored. These estimates are proven to provide a reliable source of information for achieving an accurate characterization of biological tissues through the ultrasound echo. The second topic involves the definition of a semi automatic algorithm for myocardium segmentation in 2D echocardiographic images. The results show that the proposed method can reduce inter- and intra observer variability in myocardial contours delineation and is feasible and accurate even on clinical data.

Analytical methods for evaluating the quality and the genuineness of olive oils

This Ph.D. thesis focuses on the investigation of some chemical and sensorial analytical parameters linked to the quality and purity of different categories of oils obtained by olives: extra virgin olive oils, both those that are sold in the large retail trade (supermarkets and discounts) and those directly collected at some Italian mills, and lower-quality oils (refined, lampante and “repaso”). Concurrently with the adoption of traditional and well-known analytical procedures such as gas chromatography and high-performance liquid chromatography, I carried out a set-up of innovative, fast and environmentally-friend methods. For example, I developed some analytical approaches based on Fourier transform medium infrared spectroscopy (FT-MIR) and time domain reflectometry (TDR), coupled with a robust chemometric elaboration of the results. I investigated some other freshness and quality markers that are not included in official parameters (in Italian and European regulations): the adoption of such a full chemical and sensorial analytical plan allowed me to obtain interesting information about the degree of quality of the EVOOs, mostly within the Italian market. Here the range of quality of EVOOs resulted very wide, in terms of sensory attributes, price classes and chemical parameters. Thanks to the collaboration with other Italian and foreign research groups, I carried out several applicative studies, especially focusing on the shelf-life of oils obtained by olives and on the effects of thermal stresses on the quality of the products. I also studied some innovative technological treatments, such as the clarification by using inert gases, as an alternative to the traditional filtration. Moreover, during a three-and-a-half months research stay at the University of Applied Sciences in Zurich, I also carried out a study related to the application of statistical methods for the elaboration of sensory results, obtained thanks to the official Swiss Panel and to some consumer tests.

Statistical learning of random probability measures

The study of random probability measures is a lively research topic that has attracted interest from different fields in recent years. In this thesis, we consider random probability measures in the context of Bayesian nonparametrics, where the law of a random probability measure is used as prior distribution, and in the context of distributional data analysis, where the goal is to perform inference given avsample from the law of a random probability measure. The contributions contained in this thesis can be subdivided according to three different topics: (i) the use of almost surely discrete repulsive random measures (i.e., whose support points are well separated) for Bayesian model-based clustering, (ii) the proposal of new laws for collections of random probability measures for Bayesian density estimation of partially exchangeable data subdivided into different groups, and (iii) the study of principal component analysis and regression models for probability distributions seen as elements of the 2-Wasserstein space. Specifically, for point (i) above we propose an efficient Markov chain Monte Carlo algorithm for posterior inference, which sidesteps the need of split-merge reversible jump moves typically associated with poor performance, we propose a model for clustering high-dimensional data by introducing a novel class of anisotropic determinantal point processes, and study the distributional properties of the repulsive measures, shedding light on important theoretical results which enable more principled prior elicitation and more efficient posterior simulation algorithms. For point (ii) above, we consider several models suitable for clustering homogeneous populations, inducing spatial dependence across groups of data, extracting the characteristic traits common to all the data-groups, and propose a novel vector autoregressive model to study of growth curves of Singaporean kids. Finally, for point (iii), we propose a novel class of projected statistical methods for distributional data analysis for measures on the real line and on the unit-circle.

Multi-pollutants impact on modern cement built heritage

It is well known that the deposition of gaseous pollutants and aerosols plays a major role in causing the deterioration of monuments and built cultural heritage in European cities. Despite of many studies dedicated to the environmental damage of cultural heritage, in case of cement mortars, commonly used in the 20th century architecture, the deterioration due to air multipollutants impact, especially the formation of black crusts, is still not well explored making this issue a challenging area of research. This work centers on cement mortars – environment interactions, focusing on the diagnosis of the damage on the modern built heritage due to air multi-pollutants. For this purpose three sites, exposed to different urban areas in Europe, were selected for sampling and subsequent laboratory analyses: Centennial Hall, Wroclaw (Poland), Chiesa dell'Autostrada del Sole, Florence (Italy), Casa Galleria Vichi, Florence (Italy). The sampling sessions were performed taking into account the height from the ground level and protection from rain run off (sheltered, partly sheltered and exposed areas). The complete characterization of collected damage layer and underlying materials was performed using a range of analytical techniques: optical and scanning electron microscopy, X ray diffractometry, differential and gravimetric thermal analysis, ion chromatography, flash combustion/gas chromatographic analysis, inductively coupled plasma-optical emission spectrometer. The data were elaborated using statistical methods (i.e. principal components analyses) and enrichment factor for cement mortars was calculated for the first time. The results obtained from the experimental activity performed on the damage layers indicate that gypsum, due to the deposition of atmospheric sulphur compounds, is the main damage product at surfaces sheltered from rain run-off at Centennial Hall and Casa Galleria Vichi. By contrast, gypsum has not been identified in the samples collected at Chiesa dell'Autostrada del Sole. This is connected to the restoration works, particularly surface cleaning, regularly performed for the maintenance of the building. Moreover, the results obtained demonstrated the correlation between the location of the building and the composition of the damage layer: Centennial Hall is mainly undergoing to the impact of pollutants emitted from the close coal power stations, whilst Casa Galleria Vichi is principally affected by pollutants from vehicular exhaust in front of the building.

"Making Sense of Figures": Statistics, Computing and Information Technologies in Agriculture and Biology in Britain, 1920s-1960s

Throughout the twentieth century statistical methods have increasingly become part of experimental research. In particular, statistics has made quantification processes meaningful in the soft sciences, which had traditionally relied on activities such as collecting and describing diversity rather than timing variation. The thesis explores this change in relation to agriculture and biology, focusing on analysis of variance and experimental design, the statistical methods developed by the mathematician and geneticist Ronald Aylmer Fisher during the 1920s. The role that Fisher’s methods acquired as tools of scientific research, side by side with the laboratory equipment and the field practices adopted by research workers, is here investigated bottom-up, beginning with the computing instruments and the information technologies that were the tools of the trade for statisticians. Four case studies show under several perspectives the interaction of statistics, computing and information technologies, giving on the one hand an overview of the main tools – mechanical calculators, statistical tables, punched and index cards, standardised forms, digital computers – adopted in the period, and on the other pointing out how these tools complemented each other and were instrumental for the development and dissemination of analysis of variance and experimental design. The period considered is the half-century from the early 1920s to the late 1960s, the institutions investigated are Rothamsted Experimental Station and the Galton Laboratory, and the statisticians examined are Ronald Fisher and Frank Yates.

Bayesian space-time data fusion for real-time forecasting and map uncertainty

Environmental computer models are deterministic models devoted to predict several environmental phenomena such as air pollution or meteorological events. Numerical model output is given in terms of averages over grid cells, usually at high spatial and temporal resolution. However, these outputs are often biased with unknown calibration and not equipped with any information about the associated uncertainty. Conversely, data collected at monitoring stations is more accurate since they essentially provide the true levels. Due the leading role played by numerical models, it now important to compare model output with observations. Statistical methods developed to combine numerical model output and station data are usually referred to as data fusion. In this work, we first combine ozone monitoring data with ozone predictions from the Eta-CMAQ air quality model in order to forecast real-time current 8-hour average ozone level defined as the average of the previous four hours, current hour, and predictions for the next three hours. We propose a Bayesian downscaler model based on first differences with a flexible coefficient structure and an efficient computational strategy to fit model parameters. Model validation for the eastern United States shows consequential improvement of our fully inferential approach compared with the current real-time forecasting system. Furthermore, we consider the introduction of temperature data from a weather forecast model into the downscaler, showing improved real-time ozone predictions. Finally, we introduce a hierarchical model to obtain spatially varying uncertainty associated with numerical model output. We show how we can learn about such uncertainty through suitable stochastic data fusion modeling using some external validation data. We illustrate our Bayesian model by providing the uncertainty map associated with a temperature output over the northeastern United States.

Analisi dei predittori e della traiettoria dello sviluppo neuromotorio a 24 mesi nei bambini very low birth weight

Neurodevelopment of preterm children has become an outcome of major interest since the improvement in survival due to advances in neonatal care. Many studies focused on the relationships among prenatal characteristics and neurodevelopmental outcome in order to identify the higher risk preterms’ subgroups. The aim of this study is to analyze and put in relation growth and development trajectories to investigate their association. 346 children born at the S.Orsola Hospital in Bologna from 01/01/2005 to 30/06/2011 with a birth weight of <1500 grams were followed up in a longitudinal study at different intervals from 3 to 24 months of corrected age. During follow-up visits, preterms’ main biometrical characteristics were measured and the Griffiths Mental Development Scale was administered to assess neurodevelopment. Latent Curve Models were developed to estimate the trajectories of length and of neurodevelopment, both separately and combined in a single model, and to assess the influence of clinical and socio-economic variables. Neurodevelopment trajectory was stepwise declining over time and length trajectory showed a steep increase until 12 months and was flat afterwards. Higher initial values of length were correlated with higher initial values of neurodevelopment and predicted a more declining neurodevelopment. SGA preterms and those from families with higher status had a less declining neurodevelopment slope, while being born from a migrant mother proved negative on neurodevelopment through the mediating effect of a being taller at 3 months. A longer stay in NICU used as a proxy of preterms’ morbidity) was predictive of lower initial neurodevelopment levels. At 24 months, neurodevelopment is more similar among preterms and is more accurately evaluated. The association among preterms’ neurodevelopment and physiological growth may provide further insights on the determinants of preterms’ outcomes. Sound statistical methods, exploiting all the information collected in a longitudinal study, may be more appropriate to the analysis.

The XENON1T experiment: Monte Carlo background estimation and sensitivity curves study

Despite the scientific achievement of the last decades in the astrophysical and cosmological fields, the majority of the Universe energy content is still unknown. A potential solution to the “missing mass problem” is the existence of dark matter in the form of WIMPs. Due to the very small cross section for WIMP-nuleon interactions, the number of expected events is very limited (about 1 ev/tonne/year), thus requiring detectors with large target mass and low background level. The aim of the XENON1T experiment, the first tonne-scale LXe based detector, is to be sensitive to WIMP-nucleon cross section as low as 10^-47 cm^2. To investigate the possibility of such a detector to reach its goal, Monte Carlo simulations are mandatory to estimate the background. To this aim, the GEANT4 toolkit has been used to implement the detector geometry and to simulate the decays from the various background sources: electromagnetic and nuclear. From the analysis of the simulations, the level of background has been found totally acceptable for the experiment purposes: about 1 background event in a 2 tonne-years exposure. Indeed, using the Maximum Gap method, the XENON1T sensitivity has been evaluated and the minimum for the WIMP-nucleon cross sections has been found at 1.87 x 10^-47 cm^2, at 90% CL, for a WIMP mass of 45 GeV/c^2. The results have been independently cross checked by using the Likelihood Ratio method that confirmed such results with an agreement within less than a factor two. Such a result is completely acceptable considering the intrinsic differences between the two statistical methods. Thus, in the PhD thesis it has been proven that the XENON1T detector will be able to reach the designed sensitivity, thus lowering the limits on the WIMP-nucleon cross section by about 2 orders of magnitude with respect to the current experiments.

Statistical mechanics formalism and methods for the analysis of real networks

This thesis provides a thoroughly theoretical background in network theory and shows novel applications to real problems and data. In the first chapter a general introduction to network ensembles is given, and the relations with “standard” equilibrium statistical mechanics are described. Moreover, an entropy measure is considered to analyze statistical properties of the integrated PPI-signalling-mRNA expression networks in different cases. In the second chapter multilayer networks are introduced to evaluate and quantify the correlations between real interdependent networks. Multiplex networks describing citation-collaboration interactions and patterns in colorectal cancer are presented. The last chapter is completely dedicated to control theory and its relation with network theory. We characterise how the structural controllability of a network is affected by the fraction of low in-degree and low out-degree nodes. Finally, we present a novel approach to the controllability of multiplex networks

Kernel Methods for Tree Structured Data

Machine learning comprises a series of techniques for automatic extraction of meaningful information from large collections of noisy data. In many real world applications, data is naturally represented in structured form. Since traditional methods in machine learning deal with vectorial information, they require an a priori form of preprocessing. Among all the learning techniques for dealing with structured data, kernel methods are recognized to have a strong theoretical background and to be effective approaches. They do not require an explicit vectorial representation of the data in terms of features, but rely on a measure of similarity between any pair of objects of a domain, the kernel function. Designing fast and good kernel functions is a challenging problem. In the case of tree structured data two issues become relevant: kernel for trees should not be sparse and should be fast to compute. The sparsity problem arises when, given a dataset and a kernel function, most structures of the dataset are completely dissimilar to one another. In those cases the classifier has too few information for making correct predictions on unseen data. In fact, it tends to produce a discriminating function behaving as the nearest neighbour rule. Sparsity is likely to arise for some standard tree kernel functions, such as the subtree and subset tree kernel, when they are applied to datasets with node labels belonging to a large domain. A second drawback of using tree kernels is the time complexity required both in learning and classification phases. Such a complexity can sometimes prevents the kernel application in scenarios involving large amount of data. This thesis proposes three contributions for resolving the above issues of kernel for trees. A first contribution aims at creating kernel functions which adapt to the statistical properties of the dataset, thus reducing its sparsity with respect to traditional tree kernel functions. Specifically, we propose to encode the input trees by an algorithm able to project the data onto a lower dimensional space with the property that similar structures are mapped similarly. By building kernel functions on the lower dimensional representation, we are able to perform inexact matchings between different inputs in the original space. A second contribution is the proposal of a novel kernel function based on the convolution kernel framework. Convolution kernel measures the similarity of two objects in terms of the similarities of their subparts. Most convolution kernels are based on counting the number of shared substructures, partially discarding information about their position in the original structure. The kernel function we propose is, instead, especially focused on this aspect. A third contribution is devoted at reducing the computational burden related to the calculation of a kernel function between a tree and a forest of trees, which is a typical operation in the classification phase and, for some algorithms, also in the learning phase. We propose a general methodology applicable to convolution kernels. Moreover, we show an instantiation of our technique when kernels such as the subtree and subset tree kernels are employed. In those cases, Direct Acyclic Graphs can be used to compactly represent shared substructures in different trees, thus reducing the computational burden and storage requirements.

Development of instrumental and sensory analytical methods of food obtained by traditional and emerging technologies

The consumer demand for natural, minimally processed, fresh like and functional food has lead to an increasing interest in emerging technologies. The aim of this PhD project was to study three innovative food processing technologies currently used in the food sector. Ultrasound-assisted freezing, vacuum impregnation and pulsed electric field have been investigated through laboratory scale systems and semi-industrial pilot plants. Furthermore, analytical and sensory techniques have been developed to evaluate the quality of food and vegetable matrix obtained by traditional and emerging processes. Ultrasound was found to be a valuable technique to improve the freezing process of potatoes, anticipating the beginning of the nucleation process, mainly when applied during the supercooling phase. A study of the effects of pulsed electric fields on phenol and enzymatic profile of melon juice has been realized and the statistical treatment of data was carried out through a response surface method. Next, flavour enrichment of apple sticks has been realized applying different techniques, as atmospheric, vacuum, ultrasound technologies and their combinations. The second section of the thesis deals with the development of analytical methods for the discrimination and quantification of phenol compounds in vegetable matrix, as chestnut bark extracts and olive mill waste water. The management of waste disposal in mill sector has been approached with the aim of reducing the amount of waste, and at the same time recovering valuable by-products, to be used in different industrial sectors. Finally, the sensory analysis of boiled potatoes has been carried out through the development of a quantitative descriptive procedure for the study of Italian and Mexican potato varieties. An update on flavour development in fresh and cooked potatoes has been realized and a sensory glossary, including general and specific definitions related to organic products, used in the European project Ecropolis, has been drafted.

Application of innovative methods of source apportionment in air contamination assessment

In this work, new tools in atmospheric pollutant sampling and analysis were applied in order to go deeper in source apportionment study. The project was developed mainly by the study of atmospheric emission sources in a suburban area influenced by a municipal solid waste incinerator (MSWI), a medium-sized coastal tourist town and a motorway. Two main research lines were followed. For what concerns the first line, the potentiality of the use of PM samplers coupled with a wind select sensor was assessed. Results showed that they may be a valid support in source apportionment studies. However, meteorological and territorial conditions could strongly affect the results. Moreover, new markers were investigated, particularly focusing on the processes of biomass burning. OC revealed a good biomass combustion process indicator, as well as all determined organic compounds. Among metals, lead and aluminium are well related to the biomass combustion. Surprisingly PM was not enriched of potassium during bonfire event. The second research line consists on the application of Positive Matrix factorization (PMF), a new statistical tool in data analysis. This new technique was applied to datasets which refer to different time resolution data. PMF application to atmospheric deposition fluxes identified six main sources affecting the area. The incinerator’s relative contribution seemed to be negligible. PMF analysis was then applied to PM2.5 collected with samplers coupled with a wind select sensor. The higher number of determined environmental indicators allowed to obtain more detailed results on the sources affecting the area. Vehicular traffic revealed the source of greatest concern for the study area. Also in this case, incinerator’s relative contribution seemed to be negligible. Finally, the application of PMF analysis to hourly aerosol data demonstrated that the higher the temporal resolution of the data was, the more the source profiles were close to the real one.

Local Trigonometric Methods for Time Series Smoothing.

The thesis is concerned with local trigonometric regression methods. The aim was to develop a method for extraction of cyclical components in time series. The main results of the thesis are the following. First, a generalization of the filter proposed by Christiano and Fitzgerald is furnished for the smoothing of ARIMA(p,d,q) process. Second, a local trigonometric filter is built, with its statistical properties. Third, they are discussed the convergence properties of trigonometric estimators, and the problem of choosing the order of the model. A large scale simulation experiment has been designed in order to assess the performance of the proposed models and methods. The results show that local trigonometric regression may be a useful tool for periodic time series analysis.