Semi-Supervised Classification Using Sparse Gaussian Process Regression

Gaussian Processes (GPs) are promising Bayesian methods for classification and regression problems. They have also been used for semi-supervised learning tasks. In this paper, we propose a new algorithm for solving semi-supervised binary classification problem using sparse GP regression (GPR) models. It is closely related to semi-supervised learning based on support vector regression (SVR) and maximum margin clustering. The proposed algorithm is simple and easy to implement. It gives a sparse solution directly unlike the SVR based algorithm. Also, the hyperparameters are estimated easily without resorting to expensive cross-validation technique. Use of sparse GPR model helps in making the proposed algorithm scalable. Preliminary results on synthetic and real-world data sets demonstrate the efficacy of the new algorithm.

Common underlying steering curves for motorcycles in steady turns

We study the steady turn behaviours of some light motorcycle models on circular paths, using the commercial software package ADAMS-Motorcycle. Steering torque and steering angle are obtained for several path radii and a range of steady forward speeds. For path radii much greater than motorcycle wheelbase, and for all motorcycle parameters including tyre parameters held fixed, dimensional analysis can predict the asymptotic behaviour of steering torque and angle. In particular, steering torque is a function purely of lateral acceleration plus another such function divided by path radius. Of these, the first function is numerically determined, while the second is approximated by an analytically determined constant. Similarly, the steering angle is a function purely of lateral acceleration, plus another such function divided by path radius. Of these, the first is determined numerically while the second is determined analytically. Both predictions are verified through ADAMS simulations for various tyre and geometric parameters. In summary, steady circular motions of a given motorcycle with given tyre parameters can be approximately characterised by just one curve for steering torque and one for steering angle.

A Multi-layer Perceptron based Non-linear Mixture Model to estimate class abundance from mixed pixels

Sub-pixel classification is essential for the successful description of many land cover (LC) features with spatial resolution less than the size of the image pixels. A commonly used approach for sub-pixel classification is linear mixture models (LMM). Even though, LMM have shown acceptable results, pragmatically, linear mixtures do not exist. A non-linear mixture model, therefore, may better describe the resultant mixture spectra for endmember (pure pixel) distribution. In this paper, we propose a new methodology for inferring LC fractions by a process called automatic linear-nonlinear mixture model (AL-NLMM). AL-NLMM is a three step process where the endmembers are first derived from an automated algorithm. These endmembers are used by the LMM in the second step that provides abundance estimation in a linear fashion. Finally, the abundance values along with the training samples representing the actual proportions are fed to multi-layer perceptron (MLP) architecture as input to train the neurons which further refines the abundance estimates to account for the non-linear nature of the mixing classes of interest. AL-NLMM is validated on computer simulated hyperspectral data of 200 bands. Validation of the output showed overall RMSE of 0.0089±0.0022 with LMM and 0.0030±0.0001 with the MLP based AL-NLMM, when compared to actual class proportions indicating that individual class abundances obtained from AL-NLMM are very close to the real observations.

A mixture model approach for formant tracking and the robustness of student's-t distribution

We address the problem of robust formant tracking in continuous speech in the presence of additive noise. We propose a new approach based on mixture modeling of the formant contours. Our approach consists of two main steps: (i) Computation of a pyknogram based on multiband amplitude-modulation/frequency-modulation (AM/FM) decomposition of the input speech; and (ii) Statistical modeling of the pyknogram using mixture models. We experiment with both Gaussian mixture model (GMM) and Student's-t mixture model (tMM) and show that the latter is robust with respect to handling outliers in the pyknogram data, parameter selection, accuracy, and smoothness of the estimated formant contours. Experimental results on simulated data as well as noisy speech data show that the proposed tMM-based approach is also robust to additive noise. We present performance comparisons with a recently developed adaptive filterbank technique proposed in the literature and the classical Burg's spectral estimator technique, which show that the proposed technique is more robust to noise.

Speeded up Gaussian mixture model algorithm for background subtraction

Adaptive Gaussian Mixture Models (GMM) have been one of the most popular and successful approaches to perform foreground segmentation on multimodal background scenes. However, the good accuracy of the GMM algorithm comes at a high computational cost. An improved GMM technique was proposed by Zivkovic to reduce computational cost by minimizing the number of modes adaptively. In this paper, we propose a modification to his adaptive GMM algorithm that further reduces execution time by replacing expensive floating point computations with low cost integer operations. To maintain accuracy, we derive a heuristic that computes periodic floating point updates for the GMM weight parameter using the value of an integer counter. Experiments show speedups in the range of 1.33 - 1.44 on standard video datasets where a large fraction of pixels are multimodal.

Interdependent cache analyses for better precision and safety

One of the challenges for accurately estimating Worst Case Execu-tion Time(WCET) of executables is to accurately predict their cache behaviour. Various techniques have been developed to predict the cache contents at different program points to estimate the execution time of memory-accessing instructions. One of the most widely used techniques is Abstract Interpretation based Must Analysis, which de-termines the cache blocks guaranteed to be present in the cache, and hence provides safe estimation of cache hits and misses. However,Must Analysis is highly imprecise, and platforms using Must Analysis have been known to produce blown-up WCET estimates. In our work, we propose to use May Analysis to assist the Must Analysis cache up-date and make it more precise. We prove the safety of our approach as well as provide examples where our Improved Must Analysis provides better precision. Further, we also detect a serious flaw in the original Persistence Analysis, and use Must and May Analysis to assist the Persistence Analysis cache update, to make it safe and more precise than the known solutions to the problem.

STUDENT'S-t MIXTURE MODEL BASED MULTI-INSTRUMENT RECOGNITION IN POLYPHONIC MUSIC

We address the problem of multi-instrument recognition in polyphonic music signals. Individual instruments are modeled within a stochastic framework using Student's-t Mixture Models (tMMs). We impose a mixture of these instrument models on the polyphonic signal model. No a priori knowledge is assumed about the number of instruments in the polyphony. The mixture weights are estimated in a latent variable framework from the polyphonic data using an Expectation Maximization (EM) algorithm, derived for the proposed approach. The weights are shown to indicate instrument activity. The output of the algorithm is an Instrument Activity Graph (IAG), using which, it is possible to find out the instruments that are active at a given time. An average F-ratio of 0 : 7 5 is obtained for polyphonies containing 2-5 instruments, on a experimental test set of 8 instruments: clarinet, flute, guitar, harp, mandolin, piano, trombone and violin.

Methods for Measuring Aggregate Costs of Conflict

This paper reviews the methods for measuring the economic cost of conflict. Estimating the economic costs of conflict requires a counterfactual calculation, which makes this a very difficult task. Social researchers have resorted to different estimation methods depending on the particular effect in question. The method used in each case depends on the units being analyzed (firms, sectors, regions or countries), the outcome variable under study (aggregate output, market valuation of firms, market shares, etc.) and data availability (a single cross-section, time series or panel data). This paper reviews existing methods used in the literature to assess the economic impact of conflict: cost accounting, cross-section methods, time series methods, panel data methods, gravity models, event studies, natural experiments and comparative case studies. The paper ends with a discussion of cost estimates and directions for further research.

Models in the implementation of the Water Framework Directive - benchmarking as part of the modelling proccess

The Water Framework Directive (WFD; European Commission 2000) is a framework for European environmental legislation that aims at improving water quality by using an integrated approach to implement the necessary societal and technical measures. Assessments to guide, support, monitor and evaluate policies, such as the WFD, require scientific approaches which integrate biophysical and human aspects of ecological systems and their interactions, as outlined by the International Council for Science (2002). These assessments need to be based on sound scientific principles and address the environmental problems in a holistic way. End-users need help to select the most appropriate methods and models. Advice on the selection and use of a wide range of water quality models has been developed within the project Benchmark Models for the Water Framework Directive (BMW). In this article, the authors summarise the role of benchmarking in the modelling process and explain how such an archive of validated models can be used to support the implementation of the WFD.

Phylogeny and speciation of the eastern Asian cyprinid genus Sarcocheilichthys

The genus Sarcocheilichthys is a group of small cyprinid fishes comprising 10 species/sub-species widely distributed in East Asia, which represents a valuable model for understanding the speciation of freshwater fishes in East Asia. In the present study, the molecular phylogenetic relationship of the genus Sarcocheilichthys was investigated using a 1140 bp section of the mitochondrial cytochrome b gene. Two different tree-building methods, maximum parsimony (MP) and Bayesian methods, yielded trees with almost the same topology, yielding high bootstrap values or posterior probabilities. The results showed that the genus Sarcocheilichthys consists of two large clades, clades I and II. Clade I contains Sarcocheilichthys lacustris, Sarcocheilichthys sinensis and Sarcocheilichthys parvus, with S. parvus at a basal position. In clade II, Sarcocheilichthys variegatus microoculus is at a basal position; samples of the widespread species, Sarcocheilichthys nigripinnis, form a large subclade containing another valid species Sarcocheilichthys czerskii. Sarcocheilichthys kiangsiensis is retained at an intermediate position. Since S. czerskii is a valid species in the S. nigripinnis clade, remaining samples of S. nigripinnis form a paraphyly. This speciation process is attributed to geographical isolation and special environmental conditions experienced by S. czerskii and stable environments experienced by the other S. nigripinnis populations. This type of speciation process was suggested to be very common. Samples of Sarcocheilichthys sinensis sinensis and Sarcocheilichthys sinensis fukiensis that did not form their own monophyletic groups suggest an early stage of speciation and support their sub-species status. Molecular clock analysis indicates that the two major lineages of the genus Sarcocheilichthys, clades I and II diverged c. 8.89 million years ago (mya). Sarcocheilichthys v. microoculus from Japan probably diverged 4.78 mya from the Chinese group. The northern-southern clades of S. nigripinnis began to diverge c. 2.12 mya, while one lineage of S. nigripinnis evolved into a new species, S. czerski, c. 0.34 mya. (C) 2008 The Authors Journal compilation (C) 2008 The Fisheries Society of the British Isles.

Optimized strong stability preserving IMEX Runge-Kutta methods

Esta es la versión no revisada del artículo: Inmaculada Higueras, Natalie Happenhofer, Othmar Koch, and Friedrich Kupka. 2014. Optimized strong stability preserving IMEX Runge-Kutta methods. J. Comput. Appl. Math. 272 (December 2014), 116-140. Se puede consultar la versión final en https://doi.org/10.1016/j.cam.2014.05.011

Finite mixture distributions, sequential likelihood and the EM algorithm

A popular way to account for unobserved heterogeneity is to assume that the data are drawn from a finite mixture distribution. A barrier to using finite mixture models is that parameters that could previously be estimated in stages must now be estimated jointly: using mixture distributions destroys any additive separability of the log-likelihood function. We show, however, that an extension of the EM algorithm reintroduces additive separability, thus allowing one to estimate parameters sequentially during each maximization step. In establishing this result, we develop a broad class of estimators for mixture models. Returning to the likelihood problem, we show that, relative to full information maximum likelihood, our sequential estimator can generate large computational savings with little loss of efficiency.