Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 52 for “"Expectation-maximization (EM) algorithm"”.

  1. Using the EM Algorithm to Estimate the Difference in Dependent Proportions in a 2 x 2 Table with Missing Data.

    … table when there are missing data. The Expectation-Maximization (EM) algorithm is used to obtain an estimate for the difference between correlated proportions. To obtain the standard error of this difference I employ a resampling technique known as bootstrapping. The performance of the …

    etsu Repository record for Using the EM Algorithm to Estimate the Difference in Dependent Proportions in a 2 x 2 Table with Missing Data. (opens in a new tab)

  2. Application of the EM Algorithm for Mixture Models

    … that identifies trajectories by using the Expectation-Maximization (EM) algorithm to fit semi-parametric mixtures of logistic distributions to longitudinal binary data. For performance comparison, we consider full maximization algo­ rithms (e.g. SAS procedure PROC TRAJ) and standard EM, as …

    uwo Repository record for Application of the EM Algorithm for Mixture Models (opens in a new tab)

  3. Unsupervised modeling of latent topics and lexical units in speech audio

    … discovers important words, phrases and topical themes present in an audio corpus. This system employs a segmental dynamic time warping (S-DTW) algorithm for acoustic pattern discovery in conjunction with a probabilistic model which treats the topic and pseudo-word identity of each discovered …

    mit Repository record for Unsupervised modeling of latent topics and lexical units in speech audio (opens in a new tab)

  4. Accelerated clustering through locality-sensitive hashing

    We obtain improved running times for two algorithms for clustering data: the expectation-maximization (EM) algorithm and Lloyd's algorithm. The EM algorithm is a heuristic for finding a mixture of k normal distributions in Rd that maximizes the probability of drawing n given data points. Lloyd's …

    mit Repository record for Accelerated clustering through locality-sensitive hashing (opens in a new tab)

  5. Planar detection using modified expectation maximization

    … an image pair is cast as an incomplete data problem where the parameters to be estimated are the ones that define the homographies induced by the planar regions in the scene. This incomplete data problem motivates the employment of the Expectation Maximization (EM) algorithm. Derivation of the EM

    missouri Repository record for Planar detection using modified expectation maximization (opens in a new tab)

  6. An EM algorithm for Lidar deconvolution

    … return from the observed return signal. The expectation-maximization (EM) algorithm has been used in signal deconvolution, to produce a maximum-likelihood estimate (MLE) for the original signal. We explain the benefits of the EM algorithm over other benchmark algorithms in Lidar …

    mit Repository record for An EM algorithm for Lidar deconvolution (opens in a new tab)

  7. Discriminative, generative, and imitative learning

    … machine learning and machine perception problems. Therein, one provides domain specific knowledge in terms of structure and parameter priors over the joint space of variables. Bayesian networks and Bayesian statistics provide a rich and flexible language for specifying this knowledge and …

    mit Repository record for Discriminative, generative, and imitative learning (opens in a new tab)

  8. Knowledge discovery and modeling in genomic databases

    … acceptor sites in vertebrate genes. The HMM system based on the developed models is fully trained using an expectation maximization (EM) algorithm and the system performance is evaluated using a 10-way cross-validation method. Experimental results show that the proposed HMM system achieves high …

    njit Repository record for Knowledge discovery and modeling in genomic databases (opens in a new tab)

  9. A Study of Reject Inference Techniques

    … average. To estimate these parameters, we usethe Expectation-Maximization (EM) algorithm wherein the data associated with therejected applicants is treated as missing completely at random. Simulated data derivedfrom actual case studies are used to assess the effectiveness of the mixture …

    alabama Repository record for A Study of Reject Inference Techniques (opens in a new tab)

  10. A Minimax Approach for Learning Gaussian Mixtures

    … a non-convex concave minimax optimization problem. We show that a Gradient Descent Ascent (GDA) method converges to an approximate stationary minimax point of the GAT-GMM optimization problem. In the benchmark case of a mixture of two symmetric, well-separated Gaussians, we further show this …

    mit Repository record for A Minimax Approach for Learning Gaussian Mixtures (opens in a new tab)

  11. Domain Adaptation with a Classifier Trained by Robust Pseudo-Labels

    … power, approaches based on deep learning algorithms have achieved remarkable results in solving computer vision classification problems. These performance improvements are achieved by assuming the source and target data are collected from the same probability distribution. However, this …

    vt Repository record for Domain Adaptation with a Classifier Trained by Robust Pseudo-Labels (opens in a new tab)

  12. Instrument Timbres and Pitch Estimation in Polyphonic Music

    … pieces of music by melody; automatic annotation algorithms seek to enable finer search criteria, such as instruments, genre, or meter. Score transcription systems strive for an abstract, compressed form of a piece of music understandable by composers and musicians. Much research still has to be …

    gatech Repository record for Instrument Timbres and Pitch Estimation in Polyphonic Music (opens in a new tab)

  13. Event detection in EEG signals for brain computer interface using expectation-maximation algorithm

    … electroencephalography (EEG)) and translating them into machine-understandable language. Most of the current BCI systems identify features of the brain signals and classify them according to a predefined criterion set by the classifying algorithm. The features of the brain signals can change over …

    strathclyde Repository record for Event detection in EEG signals for brain computer interface using expectation-maximation algorithm (opens in a new tab)

  14. Blind separation of noisy multivariate data using second-order statistics

    … non-stationarity of the underlying sources. The algorithm estimates the Second-Order separation transform A, the signal Order, and Noise, and is therefore referred to as SOON. SOON iteratively estimates: 1) k using a scree metric, and 2) the values of AP, G, and W using the …

    mit Repository record for Blind separation of noisy multivariate data using second-order statistics (opens in a new tab)

  15. Algorithms And Tools For Computational Analysis Of Human Transcriptome Using Rna-Seq

    … <p> We have developed two novel algorithms and tools and a computational workflow to interrogate human transcriptomes between healthy and diseased conditions. The first is a read count-based Expectation-Maximization (EM) algorithm and tool, which is called RAEM. It estimates …

    wayne-thes Repository record for Algorithms And Tools For Computational Analysis Of Human Transcriptome Using Rna-Seq (opens in a new tab)

  16. High-Dimensional Functional Graphs and Inference for Unknown Heterogeneous Populations

    … conditional dependence structure among random elements. We mainly focus on the following three research projects. The first project combines the strengths of FGMs with finite mixture of regression models (FMR) to overcome the challenges of estimating conditional dependence structures from …

    vt Repository record for High-Dimensional Functional Graphs and Inference for Unknown Heterogeneous Populations (opens in a new tab)

  17. Corporate Default Predictions and Methods for Uncertainty Quantifications

    … estimating parameters in the DFM, we derive an expectation maximization (EM) algorithm in explicit forms under necessary constraints. For multi-period default risks, we consider both the corporate-level and the market-level predictions. We also develop prediction interval (PI) procedures that …

    vt Repository record for Corporate Default Predictions and Methods for Uncertainty Quantifications (opens in a new tab)

  18. Some new Laplace-based probability distributions for modeling data with pronounced peaks combined with heavy tails and outliers

    … estimation through various computational schemes. This includes leveraging the Expectation Maximization (EM) algorithm and its variants, and addressing computational issues related to the models. We investigate the effectiveness of these estimation strategies on simulated data and demonstrate …

    unr Repository record for Some new Laplace-based probability distributions for modeling data with pronounced peaks combined with heavy tails and outliers (opens in a new tab)

  19. State-space models for stream networks

    … of this exact likelihood, a version of the expectation-maximization (EM) algorithm is presented that uses the Kalman Smoother to fill in missing values in the E-step, and maximizes the Gaussian likelihood for the completed dataset in the M-step. Several forms of dependence for discrete …

    colostate Repository record for State-space models for stream networks (opens in a new tab)

  20. Localized Feature Selection For Unsupervised Learning

    … In general, unsupervised feature selection algorithms conduct feature selection in a global sense by producing a common feature subset for all the clusters. This, however, can be invalid in clustering practice, where the local intrinsic property of data matters more, which implies that …

    wayne-thes Repository record for Localized Feature Selection For Unsupervised Learning (opens in a new tab)

Page 1 of 3