Optimal kernel development for real-time communications

The purpose of this research is to develop an optimal kernel which would be used in a real-time engineering and communications system. Since the application is a real-time system, relevant real-time issues are studied in conjunction with kernel related issues. The emphasis of the research is the development of a kernel which would not only adhere to the criteria of a real-time environment, namely determinism and performance, but also provide the flexibility and portability associated with non-real-time environments. The essence of the research is to study how the features found in non-real-time systems could be applied to the real-time system in order to generate an optimal kernel which would provide flexibility and architecture independence while maintaining the performance needed by most of the engineering applications. Traditionally, development of real-time kernels has been done using assembly language. By utilizing the powerful constructs of the C language, a real-time kernel was developed which addressed the goals of flexibility and portability while still meeting the real-time criteria. The implementation of the kernel is carried out using the powerful 68010/20/30/40 microprocessor based systems.

Using food intake records to estimate compliance with the Eatwell plate dietary guidelines

Funded by Scottish Government's Rural and Environment Science and Analytical Services (RESAS) Division Food Standards Agency, UK Biscuit, Cake, Chocolate and Confectionery Association, London, UK

Using food intake records to estimate compliance with the Eatwell plate dietary guidelines

Funded by Scottish Government's Rural and Environment Science and Analytical Services (RESAS) Division Food Standards Agency, UK Biscuit, Cake, Chocolate and Confectionery Association, London, UK

Bayesian Inference in Large-scale Problems

Many modern applications fall into the category of "large-scale" statistical problems, in which both the number of observations n and the number of features or parameters p may be large. Many existing methods focus on point estimation, despite the continued relevance of uncertainty quantification in the sciences, where the number of parameters to estimate often exceeds the sample size, despite huge increases in the value of n typically seen in many fields. Thus, the tendency in some areas of industry to dispense with traditional statistical analysis on the basis that "n=all" is of little relevance outside of certain narrow applications. The main result of the Big Data revolution in most fields has instead been to make computation much harder without reducing the importance of uncertainty quantification. Bayesian methods excel at uncertainty quantification, but often scale poorly relative to alternatives. This conflict between the statistical advantages of Bayesian procedures and their substantial computational disadvantages is perhaps the greatest challenge facing modern Bayesian statistics, and is the primary motivation for the work presented here.

Two general strategies for scaling Bayesian inference are considered. The first is the development of methods that lend themselves to faster computation, and the second is design and characterization of computational algorithms that scale better in n or p. In the first instance, the focus is on joint inference outside of the standard problem of multivariate continuous data that has been a major focus of previous theoretical work in this area. In the second area, we pursue strategies for improving the speed of Markov chain Monte Carlo algorithms, and characterizing their performance in large-scale settings. Throughout, the focus is on rigorous theoretical evaluation combined with empirical demonstrations of performance and concordance with the theory.

One topic we consider is modeling the joint distribution of multivariate categorical data, often summarized in a contingency table. Contingency table analysis routinely relies on log-linear models, with latent structure analysis providing a common alternative. Latent structure models lead to a reduced rank tensor factorization of the probability mass function for multivariate categorical data, while log-linear models achieve dimensionality reduction through sparsity. Little is known about the relationship between these notions of dimensionality reduction in the two paradigms. In Chapter 2, we derive several results relating the support of a log-linear model to nonnegative ranks of the associated probability tensor. Motivated by these findings, we propose a new collapsed Tucker class of tensor decompositions, which bridge existing PARAFAC and Tucker decompositions, providing a more flexible framework for parsimoniously characterizing multivariate categorical data. Taking a Bayesian approach to inference, we illustrate empirical advantages of the new decompositions.

Latent class models for the joint distribution of multivariate categorical, such as the PARAFAC decomposition, data play an important role in the analysis of population structure. In this context, the number of latent classes is interpreted as the number of genetically distinct subpopulations of an organism, an important factor in the analysis of evolutionary processes and conservation status. Existing methods focus on point estimates of the number of subpopulations, and lack robust uncertainty quantification. Moreover, whether the number of latent classes in these models is even an identified parameter is an open question. In Chapter 3, we show that when the model is properly specified, the correct number of subpopulations can be recovered almost surely. We then propose an alternative method for estimating the number of latent subpopulations that provides good quantification of uncertainty, and provide a simple procedure for verifying that the proposed method is consistent for the number of subpopulations. The performance of the model in estimating the number of subpopulations and other common population structure inference problems is assessed in simulations and a real data application.

In contingency table analysis, sparse data is frequently encountered for even modest numbers of variables, resulting in non-existence of maximum likelihood estimates. A common solution is to obtain regularized estimates of the parameters of a log-linear model. Bayesian methods provide a coherent approach to regularization, but are often computationally intensive. Conjugate priors ease computational demands, but the conjugate Diaconis--Ylvisaker priors for the parameters of log-linear models do not give rise to closed form credible regions, complicating posterior inference. In Chapter 4 we derive the optimal Gaussian approximation to the posterior for log-linear models with Diaconis--Ylvisaker priors, and provide convergence rate and finite-sample bounds for the Kullback-Leibler divergence between the exact posterior and the optimal Gaussian approximation. We demonstrate empirically in simulations and a real data application that the approximation is highly accurate, even in relatively small samples. The proposed approximation provides a computationally scalable and principled approach to regularized estimation and approximate Bayesian inference for log-linear models.

Another challenging and somewhat non-standard joint modeling problem is inference on tail dependence in stochastic processes. In applications where extreme dependence is of interest, data are almost always time-indexed. Existing methods for inference and modeling in this setting often cluster extreme events or choose window sizes with the goal of preserving temporal information. In Chapter 5, we propose an alternative paradigm for inference on tail dependence in stochastic processes with arbitrary temporal dependence structure in the extremes, based on the idea that the information on strength of tail dependence and the temporal structure in this dependence are both encoded in waiting times between exceedances of high thresholds. We construct a class of time-indexed stochastic processes with tail dependence obtained by endowing the support points in de Haan's spectral representation of max-stable processes with velocities and lifetimes. We extend Smith's model to these max-stable velocity processes and obtain the distribution of waiting times between extreme events at multiple locations. Motivated by this result, a new definition of tail dependence is proposed that is a function of the distribution of waiting times between threshold exceedances, and an inferential framework is constructed for estimating the strength of extremal dependence and quantifying uncertainty in this paradigm. The method is applied to climatological, financial, and electrophysiology data.

The remainder of this thesis focuses on posterior computation by Markov chain Monte Carlo. The Markov Chain Monte Carlo method is the dominant paradigm for posterior computation in Bayesian analysis. It has long been common to control computation time by making approximations to the Markov transition kernel. Comparatively little attention has been paid to convergence and estimation error in these approximating Markov Chains. In Chapter 6, we propose a framework for assessing when to use approximations in MCMC algorithms, and how much error in the transition kernel should be tolerated to obtain optimal estimation performance with respect to a specified loss function and computational budget. The results require only ergodicity of the exact kernel and control of the kernel approximation accuracy. The theoretical framework is applied to approximations based on random subsets of data, low-rank approximations of Gaussian processes, and a novel approximating Markov chain for discrete mixture models.

Data augmentation Gibbs samplers are arguably the most popular class of algorithm for approximately sampling from the posterior distribution for the parameters of generalized linear models. The truncated Normal and Polya-Gamma data augmentation samplers are standard examples for probit and logit links, respectively. Motivated by an important problem in quantitative advertising, in Chapter 7 we consider the application of these algorithms to modeling rare events. We show that when the sample size is large but the observed number of successes is small, these data augmentation samplers mix very slowly, with a spectral gap that converges to zero at a rate at least proportional to the reciprocal of the square root of the sample size up to a log factor. In simulation studies, moderate sample sizes result in high autocorrelations and small effective sample sizes. Similar empirical results are observed for related data augmentation samplers for multinomial logit and probit models. When applied to a real quantitative advertising dataset, the data augmentation samplers mix very poorly. Conversely, Hamiltonian Monte Carlo and a type of independence chain Metropolis algorithm show good mixing on the same dataset.

Role of Hydrological Process Representation on Erosion, Deposition, and Sediment Yield Estimate

Soil erosion by water is a major driven force causing land degradation. Laboratory experiments, on-site field study, and suspended sediments measurements were major fundamental approaches to study the mechanisms of soil water erosion and to quantify the erosive losses during rain events. The experimental research faces the challenge to extent the result to a wider spatial scale. Soil water erosion modeling provides possible solutions for scaling problems in erosion research, and is of principal importance to better understanding the governing processes of water erosion. However, soil water erosion models were considered to have limited value in practice. Uncertainties in hydrological simulations are among the reasons that hindering the development of water erosion model. Hydrological models gained substantial improvement recently and several water erosion models took advantages of the improvement of hydrological models. It is crucial to know the impact of changes in hydrological processes modeling on soil erosion simulation.

This dissertation work first created an erosion modeling tool (GEOtopSed) that takes advantage of the comprehensive hydrological model (GEOtop). The newly created tool was then tested and evaluated at an experimental watershed. The GEOtopSed model showed its ability to estimate multi-year soil erosion rate with varied hydrological conditions. To investigate the impact of different hydrological representations on soil erosion simulation, a 11-year simulation experiment was conducted for six models with varied configurations. The results were compared at varied temporal and spatial scales to highlight the roles of hydrological feedbacks on erosion. Models with simplified hydrological representations showed agreement with GEOtopSed model on long temporal scale (longer than annual). This result led to an investigation for erosion simulation at different rainfall regimes to check whether models with different hydrological representations have agreement on the soil water erosion responses to the changing climate. Multi-year ensemble simulations with different extreme precipitation scenarios were conducted at seven climate regions. The differences in erosion simulation results showed the influences of hydrological feedbacks which cannot be seen by purely rainfall erosivity method.

Integrity-Based Kernel Malware Detection

Kernel-level malware is one of the most dangerous threats to the security of users on the Internet, so there is an urgent need for its detection. The most popular detection approach is misuse-based detection. However, it cannot catch up with today's advanced malware that increasingly apply polymorphism and obfuscation. In this thesis, we present our integrity-based detection for kernel-level malware, which does not rely on the specific features of malware. We have developed an integrity analysis system that can derive and monitor integrity properties for commodity operating systems kernels. In our system, we focus on two classes of integrity properties: data invariants and integrity of Kernel Queue (KQ) requests. We adopt static analysis for data invariant detection and overcome several technical challenges: field-sensitivity, array-sensitivity, and pointer analysis. We identify data invariants that are critical to system runtime integrity from Linux kernel 2.4.32 and Windows Research Kernel (WRK) with very low false positive rate and very low false negative rate. We then develop an Invariant Monitor to guard these data invariants against real-world malware. In our experiment, we are able to use Invariant Monitor to detect ten real-world Linux rootkits and nine real-world Windows malware and one synthetic Windows malware. We leverage static and dynamic analysis of kernel and device drivers to learn the legitimate KQ requests. Based on the learned KQ requests, we build KQguard to protect KQs. At runtime, KQguard rejects all the unknown KQ requests that cannot be validated. We apply KQguard on WRK and Linux kernel, and extensive experimental evaluation shows that KQguard is efficient (up to 5.6% overhead) and effective (capable of achieving zero false positives against representative benign workloads after appropriate training and very low false negatives against 125 real-world malware and nine synthetic attacks). In our system, Invariant Monitor and KQguard cooperate together to protect data invariants and KQs in the target kernel. By monitoring these integrity properties, we can detect malware by its violation of these integrity properties during execution.

Litter basket installed in a mangrove forest to estimate litterfall productivity, Shark River Slough

This material is based upon work supported by the National Science Foundation through the Florida Coastal Everglades Long-Term Ecological Research program under Cooperative Agreements #DBI-0620409 and #DEB-9910514. This image is made available for non-commercial or educational use only.

Estimation of Sample Size and Power For Quantile Regression

Quantile regression (QR) was first introduced by Roger Koenker and Gilbert Bassett in 1978. It is robust to outliers which affect least squares estimator on a large scale in linear regression. Instead of modeling mean of the response, QR provides an alternative way to model the relationship between quantiles of the response and covariates. Therefore, QR can be widely used to solve problems in econometrics, environmental sciences and health sciences. Sample size is an important factor in the planning stage of experimental design and observational studies. In ordinary linear regression, sample size may be determined based on either precision analysis or power analysis with closed form formulas. There are also methods that calculate sample size based on precision analysis for QR like C.Jennen-Steinmetz and S.Wellek (2005). A method to estimate sample size for QR based on power analysis was proposed by Shao and Wang (2009). In this paper, a new method is proposed to calculate sample size based on power analysis under hypothesis test of covariate effects. Even though error distribution assumption is not necessary for QR analysis itself, researchers have to make assumptions of error distribution and covariate structure in the planning stage of a study to obtain a reasonable estimate of sample size. In this project, both parametric and nonparametric methods are provided to estimate error distribution. Since the method proposed can be implemented in R, user is able to choose either parametric distribution or nonparametric kernel density estimation for error distribution. User also needs to specify the covariate structure and effect size to carry out sample size and power calculation. The performance of the method proposed is further evaluated using numerical simulation. The results suggest that the sample sizes obtained from our method provide empirical powers that are closed to the nominal power level, for example, 80%.

Estimate of the (R)USLE rainfall erosivity factor from monthly precipitation data in mainland Spain

The need for continuous recording rain gauges makes it difficult to determine the rainfall erosivity factor (R-factor) of the (R)USLE model in areas without good temporal data coverage. In mainland Spain, the Nature Conservation Institute (ICONA) determined the R-factor at few selected pluviographs, so simple estimates of the R-factor are definitely of great interest. The objectives of this study were: (1) to identify a readily available estimate of the R-factor for mainland Spain; (2) to discuss the applicability of a single (global) estimate based on analysis of regional results; (3) to evaluate the effect of record length on estimate precision and accuracy; and (4) to validate an available regression model developed by ICONA. Four estimators based on monthly precipitation were computed at 74 rainfall stations throughout mainland Spain. The regression analysis conducted at a global level clearly showed that modified Fournier index (MFI) ranked first among all assessed indexes. Applicability of this preliminary global model across mainland Spain was evaluated by analyzing regression results obtained at a regional level. It was found that three contiguous regions of eastern Spain (Catalonia, Valencian Community and Murcia) could have a different rainfall erosivity pattern, so a new regression analysis was conducted by dividing mainland Spain into two areas: Eastern Spain and plateau-lowland area. A comparative analysis concluded that the bi-areal regression model based on MFI for a 10-year record length provided a simple, precise and accurate estimate of the R-factor in mainland Spain. Finally, validation of the regression model proposed by ICONA showed that R-ICONA index overpredicted the R-factor by approximately 19%.

Sedimentology, structure and age estimate of five continental slope submarine landslides, eastern Australia

Sedimentological and accelerator mass spectrometry (AMS) 14C data provide estimates of the structure and age of five submarine landslides (∼0.4–3 km3) present on eastern Australia's continental slope between Noosa Heads and Yamba. Dating of the post-slide conformably deposited sediment indicates sediment accumulation rates between 0.017 m ka–1 and 0.2 m ka–1, which is consistent with previous estimates reported for this area. Boundary surfaces were identified in five continental slope cores at depths of 0.8 to 2.2 m below the present-day seafloor. Boundary surfaces present as a sharp colour-change across the surface, discernible but small increases in sediment stiffness, a slight increase in sediment bulk density of 0.1 g cm–3, and distinct gaps in AMS 14C ages of at least 25 ka. Boundary surfaces are interpreted to represent a slide plane detachment surface but are not necessarily the only ones or even the major ones. Sub-bottom profiler records indicate that: (1) the youngest identifiable sediment reflectors upslope from three submarine landslides terminate on and are truncated by slide rupture surfaces; (2) there is no obvious evidence for a post-slide sediment layer draped over, or burying, slide ruptures or exposed slide detachment surfaces; and (3) the boundary surfaces identified within the cores are unlikely to be near-surface slide surfaces within an overall larger en masse dislocation. These findings suggest that these submarine landslides are geologically recent (<25 ka), and that the boundary surfaces are either: (a) an erosional features that developed after the landslide, in which case the boundary surface age provides a minimum age for the landslide; or (b) detachment surfaces from which slabs of near-surface sediment were removed during landsliding, in which case the age of the sediment above the boundary surface indicates the approximate age of landsliding. While an earthquake-triggering mechanism is favoured for the initiation of submarine landslides on the eastern Australian margin, further evidence is required to confirm this interpretation.

Sviluppo ed applicazione di tecniche di Multiple Kernel Learning per dati di neuroimaging

Questo lavoro di tesi riguarda lo studio e l’implementazione di un algoritmo di multiple kernel learning (MKL) per la classificazione e la regressione di dati di neuroimaging ed, in particolare, di grafi di connettività funzionale. Gli algoritmi di MKL impiegano una somma pesata di vari kernel (ovvero misure di similarità) e permettono di selezionare le features utili alla discriminazione delle istanze durante l’addestramento del classificatore/regressore stesso. L’aspetto innovativo introdotto in questa tesi è stato lo studio di un nuovo kernel tra grafi di connettività funzionale, con la particolare caratteristica di conservare l’informazione relativa all’importanza di ogni singola region of interest (ROI) ed impiegando la norma lp come metodo per l’aggiornamento dei pesi, al fine di ottenere soluzioni sparsificate. L’algoritmo è stato validato utilizzando mappe di connettività sintetiche ed è stato applicato ad un dataset formato da 32 pazienti affetti da deterioramento cognitivo lieve e malattia dei piccoli vasi, di cui 16 sottoposti a riabilitazione cognitiva tra un’esame di risonanza ma- gnetica funzionale di baseline e uno di follow-up. Le mappe di con- nettività sono state ottenute con il toolbox CONN. Il classificatore è riuscito a discriminare i due gruppi di pazienti in una configurazione leave-one-out annidata con un’accuratezza dell’87.5%. Questo lavoro di tesi è stato svolto durante un periodo di ricerca presso la School of Computer Science and Electronic Engineering dell’University of Essex (Colchester, UK).

Sugarcane leaf area estimate obtained from the corrected normalized difference vegetation index (NDVI)

v. 46, n. 2, p. 140-148, apr./jun. 2016.