Short-term wind power forecasting using Gaussian processes

Since wind has an intrinsically complex and stochastic nature, accurate wind power forecasts are necessary for the safety and economics of wind energy utilization. In this paper, we investigate a combination of numeric and probabilistic models: one-day-ahead wind power forecasts were made with Gaussian Processes (GPs) applied to the outputs of a Numerical Weather Prediction (NWP) model. Firstly the wind speed data from NWP was corrected by a GP. Then, as there is always a defined limit on power generated in a wind turbine due the turbine controlling strategy, a Censored GP was used to model the relationship between the corrected wind speed and power output. To validate the proposed approach, two real world datasets were used for model construction and testing. The simulation results were compared with the persistence method and Artificial Neural Networks (ANNs); the proposed model achieves about 11% improvement in forecasting accuracy (Mean Absolute Error) compared to the ANN model on one dataset, and nearly 5% improvement on another.

Special Classes of Orthogonal Polynomials and Corresponding Quadratures of Gaussian Type

MSC 2010: 33C47, 42C05, 41A55, 65D30, 65D32

Projected sequential Gaussian processes:a C++ tool for interpolation of large datasets with heterogeneous noise

Heterogeneous datasets arise naturally in most applications due to the use of a variety of sensors and measuring platforms. Such datasets can be heterogeneous in terms of the error characteristics and sensor models. Treating such data is most naturally accomplished using a Bayesian or model-based geostatistical approach; however, such methods generally scale rather badly with the size of dataset, and require computationally expensive Monte Carlo based inference. Recently within the machine learning and spatial statistics communities many papers have explored the potential of reduced rank representations of the covariance matrix, often referred to as projected or fixed rank approaches. In such methods the covariance function of the posterior process is represented by a reduced rank approximation which is chosen such that there is minimal information loss. In this paper a sequential Bayesian framework for inference in such projected processes is presented. The observations are considered one at a time which avoids the need for high dimensional integrals typically required in a Bayesian approach. A C++ library, gptk, which is part of the INTAMAP web service, is introduced which implements projected, sequential estimation and adds several novel features. In particular the library includes the ability to use a generic observation operator, or sensor model, to permit data fusion. It is also possible to cope with a range of observation error characteristics, including non-Gaussian observation errors. Inference for the covariance parameters is explored, including the impact of the projected process approximation on likelihood profiles. We illustrate the projected sequential method in application to synthetic and real datasets. Limitations and extensions are discussed. © 2010 Elsevier Ltd.

Semi-supervised Gaussian process latent variable model with pairwise constraints

In machine learning, Gaussian process latent variable model (GP-LVM) has been extensively applied in the field of unsupervised dimensionality reduction. When some supervised information, e.g., pairwise constraints or labels of the data, is available, the traditional GP-LVM cannot directly utilize such supervised information to improve the performance of dimensionality reduction. In this case, it is necessary to modify the traditional GP-LVM to make it capable of handing the supervised or semi-supervised learning tasks. For this purpose, we propose a new semi-supervised GP-LVM framework under the pairwise constraints. Through transferring the pairwise constraints in the observed space to the latent space, the constrained priori information on the latent variables can be obtained. Under this constrained priori, the latent variables are optimized by the maximum a posteriori (MAP) algorithm. The effectiveness of the proposed algorithm is demonstrated with experiments on a variety of data sets. © 2010 Elsevier B.V.

The kernel is in the least core for permutation games

Permutation games are totally balanced transferable utility cooperative games arising from certain sequencing and re-assignment optimization problems. It is known that for permutation games the bargaining set and the core coincide, consequently, the kernel is a subset of the core. We prove that for permutation games the kernel is contained in the least core, even if the latter is a lower dimensional subset of the core. By means of a 5-player permutation game we demonstrate that, in sense of the lexicographic center procedure leading to the nucleolus, this inclusion result can not be strengthened. Our 5-player permutation game is also an example (of minimum size) for a game with a non-convex kernel.

Statistical analysis and optimal classification of blood cell populations using Gaussian distributions

This dissertation develops a new figure of merit to measure the similarity (or dissimilarity) of Gaussian distributions through a novel concept that relates the Fisher distance to the percentage of data overlap. The derivations are expanded to provide a generalized mathematical platform for determining an optimal separating boundary of Gaussian distributions in multiple dimensions. Real-world data used for implementation and in carrying out feasibility studies were provided by Beckman-Coulter. It is noted that although the data used is flow cytometric in nature, the mathematics are general in their derivation to include other types of data as long as their statistical behavior approximate Gaussian distributions. ^ Because this new figure of merit is heavily based on the statistical nature of the data, a new filtering technique is introduced to accommodate for the accumulation process involved with histogram data. When data is accumulated into a frequency histogram, the data is inherently smoothed in a linear fashion, since an averaging effect is taking place as the histogram is generated. This new filtering scheme addresses data that is accumulated in the uneven resolution of the channels of the frequency histogram. ^ The qualitative interpretation of flow cytometric data is currently a time consuming and imprecise method for evaluating histogram data. This method offers a broader spectrum of capabilities in the analysis of histograms, since the figure of merit derived in this dissertation integrates within its mathematics both a measure of similarity and the percentage of overlap between the distributions under analysis. ^

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.^

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.

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.

The role of age and emotional valence in word recognition: an ex-Gaussian analysis

The aim of this work is to evaluate the roles of age and emotional valence in word recognition in terms of ex-Gaussian distribution components. In order to do that, a word recognition task was carried out with two age groups, in which emotional valence was manipulated. Older participants did not present a clear trend for reaction times. The younger participants showed significant statistical differences in negative words for target and distracting conditions. Addressing the ex-Gaussian tau parameter, often related to attentional demands in the literature, age-related differences in emotional valence seem not to have an effect for negative words. Focusing on emotional valence for each group, the younger participants only showed an effect on negative distracting words. The older participants showed an effect regarding negative and positive target words, and negative distracting words. This suggests that the attentional demand is higher for emotional words, in particular, for the older participants.

Dynamic classifiers for neonatal brain monitoring

Brain injury due to lack of oxygen or impaired blood flow around the time of birth, may cause long term neurological dysfunction or death in severe cases. The treatments need to be initiated as soon as possible and tailored according to the nature of the injury to achieve best outcomes. The Electroencephalogram (EEG) currently provides the best insight into neurological activities. However, its interpretation presents formidable challenge for the neurophsiologists. Moreover, such expertise is not widely available particularly around the clock in a typical busy Neonatal Intensive Care Unit (NICU). Therefore, an automated computerized system for detecting and grading the severity of brain injuries could be of great help for medical staff to diagnose and then initiate on-time treatments. In this study, automated systems for detection of neonatal seizures and grading the severity of Hypoxic-Ischemic Encephalopathy (HIE) using EEG and Heart Rate (HR) signals are presented. It is well known that there is a lot of contextual and temporal information present in the EEG and HR signals if examined at longer time scale. The systems developed in the past, exploited this information either at very early stage of the system without any intelligent block or at very later stage where presence of such information is much reduced. This work has particularly focused on the development of a system that can incorporate the contextual information at the middle (classifier) level. This is achieved by using dynamic classifiers that are able to process the sequences of feature vectors rather than only one feature vector at a time.

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.

Time series wind power forecasting based on variant Gaussian process and TLBO

Due to the variability and stochastic nature of wind power system, accurate wind power forecasting has an important role in developing reliable and economic power system operation and control strategies. As wind variability is stochastic, Gaussian Process regression has recently been introduced to capture the randomness of wind energy. However, the disadvantages of Gaussian Process regression include its computation complexity and incapability to adapt to time varying time-series systems. A variant Gaussian Process for time series forecasting is introduced in this study to address these issues. This new method is shown to be capable of reducing computational complexity and increasing prediction accuracy. It is further proved that the forecasting result converges as the number of available data approaches innite. Further, a teaching learning based optimization (TLBO) method is used to train the model and to accelerate
the learning rate. The proposed modelling and optimization method is applied to forecast both the wind power generation of Ireland and that from a single wind farm to show the eectiveness of the proposed method.