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 388 for “"Feature vectors"”.

  1. Mapping the structural landscape of protein families with geometric feature vectors

    This thesis describes two key results that can be used separately or in combination for protein function analysis. The Family-wise Analysis of SubStructural Templates (FASST) method uses all-against-all substructure comparison to determine family-wide sub-group organization by quantifying the …

    rice Repository record for Mapping the structural landscape of protein families with geometric feature vectors (opens in a new tab)

  2. Extracting Feature Vectors From Event-Related fMRI Data to Enable Machine Learning Analysis

    … of extracting summaries of events in fMRI for feature vector based machine learning. While they are both useful and robust, they are limited by the assumptions made in modeling. In this work, we examine a number of feature extraction techniques adjacent to linear models that account for or …

    vt Repository record for Extracting Feature Vectors From Event-Related fMRI Data to Enable Machine Learning Analysis (opens in a new tab)

  3. Low dimensional search for efficient texture synthesis

    … best pixel to use at the current position. The feature vectors used in the ANN search are typically between 100 and 300 dimensions. A large amount of research has examined how to reduce the number of feature vectors that need to be searched but very little has been done to speed up the actual …

    ubc Repository record for Low dimensional search for efficient texture synthesis (opens in a new tab) Download PDF for Low dimensional search for efficient texture synthesis (opens in a new tab)

  4. Feature network methods for machine learning

    We develop a graph structure for feature vectors in machine learning, which we denote as a feature network (FN); this is different from sample-based networks, in which nodes simply represent samples. FNs reveal the underlying relationship among feature vector components and re-represent features as …

    bu Repository record for Feature network methods for machine learning (opens in a new tab)

  5. Simultaneous reconstruction of spatial frequency fields and field sample locations

    … kriging estimate smooth interpolating fields for features measured at well-located points. In this thesis, we make a simultaneous reconstruction of interpolating spatial fields and measurement locations.</p> <p>We give models, and sample-based Bayesian inference, for estimating locations of …

    oxford Repository record for Simultaneous reconstruction of spatial frequency fields and field sample locations (opens in a new tab)

  6. Feature Selection in Image Databases

    … though the problem of determining the number of features required to provide an acceptable classification performance has been a topic of interest to the researchers in the pattern recognition community for a few decades, a formal method for solving this problem still does not exist. For …

    concordia Download PDF for Feature Selection in Image Databases (opens in a new tab)

  7. Forecasting Longitudinal Changes In Oropharyngeal Tumor Volume, Position, and Morphology During Image-Guided Radiation Therapy

    … and two morphology (size, shape, and position) feature vectors were used to describe 35 oropharyngeal gross tumor volumes (GTVs) during radiation therapy. The two morphology feature vectors comprised the coordinates of the GTV centroids and one of two shape descriptors. One shape descriptor was …

    uthsc Repository record for Forecasting Longitudinal Changes In Oropharyngeal Tumor Volume, Position, and Morphology During Image-Guided Radiation Therapy (opens in a new tab)

  8. Characteristic shape recognition with fuzzy dustering

    … based on this formulation to partition the input feature vectors into hyper-spheres. To illustrate the usefulness of improved FSC we have provided numerous examples in 2-D space. The idea has been extended to fuzzy ellipsoidal-shell clustering (rESC). A FESC algorithm has been proposed to …

    njit Repository record for Characteristic shape recognition with fuzzy dustering (opens in a new tab)

  9. Efficient Analytics for Large Implicit Correlation Networks

    … short length-k (on the order of thousands) feature vectors for every node in the network that describe the characteristic or behavior of that node. Edges between nodes are expressed as correlations, partial correlations or coherence between the corresponding feature vectors. If the number of …

    clemson Repository record for Efficient Analytics for Large Implicit Correlation Networks (opens in a new tab)

  10. Object Detection and Tracking for Creation of Interactive Videos

    … network. Specifically, we use GoogLeNet as a feature extractor, and then apply a long short-term memory (LSTM) network to further adjust the feature vectors extracted by GoogLeNet according to the context of the feature vectors of the previous frame. We feed the output of the LSTM to a …

    carleton Repository record for Object Detection and Tracking for Creation of Interactive Videos (opens in a new tab)

  11. ANALYSIS OF CELL MORPHOMETRIC PHENOTYPES BY DEEP LEARNING

    … ECM. We also demonstrate that SERNN-based feature vectors confer significant advantages in quantifying morphological differences over traditional geometric shape descriptors. Lastly, we also develop a generative framework to demonstrate the possibility of interpretation of deep …

    nus Repository record for ANALYSIS OF CELL MORPHOMETRIC PHENOTYPES BY DEEP LEARNING (opens in a new tab) Download file for ANALYSIS OF CELL MORPHOMETRIC PHENOTYPES BY DEEP LEARNING (opens in a new tab)

  12. Efficient processing of KNN and skyjoin queries

    … of each cluster to adaptively compress feature vectors into bit-strings. We also developed an efficient KNN search algorithm using MinMax Pruning or Partial MinDist Pruning method. Besides high-dimensional KNN query, we also extend the skyline operation to the Skyjoin query, which finds …

    nus Repository record for Efficient processing of KNN and skyjoin queries (opens in a new tab) Download file for Efficient processing of KNN and skyjoin queries (opens in a new tab)

  13. Advanced feature based techniques for landmine detection using ground penetrating radar

    … techniques for landmine detection. Two advanced feature based techniques are developed. One algorithm applies the clustering method based on the spectral feature vectors formed by the energy density spectra of return sensor signals, the idea behind is to find out whether there are some "hidden …

    missouri Repository record for Advanced feature based techniques for landmine detection using ground penetrating radar (opens in a new tab)

  14. Computational prediction of Ds transposon insertion sites in plants using DNA structural features

    … systems in plants, by exploring various DNA features and predicting insertion sites.</p> <p>A package named DnaFVP (DNA Feature Calculation, Visualization and Vector Preparation) was first developed for calculation, visualization and analysis of various DNA features, including nucleotide …

    iastate Repository record for Computational prediction of Ds transposon insertion sites in plants using DNA structural features (opens in a new tab)

  15. Discrete HMM isolated digit recognition

    … using an end-point algorithm, extraction of the feature vectors from the sampled speech signal, quantization of the feature vectors into a codebook of a particular size, and recognition of the spoken word using discrete Hidden Markov Modeling (HMM) of the words. We discuss the discrete HMM in …

    vt Repository record for Discrete HMM isolated digit recognition (opens in a new tab)

  16. Sparse Signal Deconvolution for Impurity Quantification in Oligonucleotide Mass Spectrometry

    … automated generation of a library containing features, plausible ions<br/>relating to an oligonucleotide, including modified synthetic oligonucleotides. For these ion features, multiple strategies of constructing feature vectors are explored; feature vectors are designed to accurately …

    bristol Repository record for Sparse Signal Deconvolution for Impurity Quantification in Oligonucleotide Mass Spectrometry (opens in a new tab) Download PDF for Sparse Signal Deconvolution for Impurity Quantification in Oligonucleotide Mass Spectrometry (opens in a new tab)

  17. Contributions to High-Dimensional Pattern Recognition

    … particularly targeted at problems in which the feature vectors are high-dimensional. Three pattern recognition scenarios are addressed, namely pattern classification, regression analysis and score fusion. For each of these, an algorithm for learning a statistical model is presented. In order to …

    upv Repository record for Contributions to High-Dimensional Pattern Recognition (opens in a new tab)

  18. Subsurface explosive hazard detection using MIMO forward-looking ground penetrating radar

    … Alarm locations have log-Gabor statistical features and spectral features, among others, extracted from multiple polarizations. The ability of these features to reduce the number of false alarms and increase the probability of detection is evaluated with data from an arid U.S. Army test …

    missouri Repository record for Subsurface explosive hazard detection using MIMO forward-looking ground penetrating radar (opens in a new tab)

  19. Autonomous star identification with neural networks

    … direct-match algorithms that pre-store the star feature vectors in a database. During recognition, the measurements are compared to the reference feature vectors in sequence or by using binary-tree search until a correct match is found. The computation time for the star recognition with …

    iastate Repository record for Autonomous star identification with neural networks (opens in a new tab)

  20. Susceptibility weighted image analysis methods for hypoxic-ischaemic encephalopathy prognosis

    … outcome by detecting and analysing vessel features in SWI images. In this research, a dataset of SWI images acquired from 42 infants with neonatal HIE is used for feature extraction. Firstly, the ridges representing the veins in the SWI images are detecting to obtain features including the …

    soton Download PDF for Susceptibility weighted image analysis methods for hypoxic-ischaemic encephalopathy prognosis (opens in a new tab)

Page 1 of 20