Loading...
Search for: manifold-learning
0.006 seconds

    Efficient multi-modal fusion on supergraph for scalable image annotation

    , Article Pattern Recognition ; Volume 48, Issue 7 , July , 2015 , Pages 2241-2253 ; 00313203 (ISSN) Amiri, S. H ; Jamzad, M ; Sharif University of Technology
    Elsevier Ltd  2015
    Abstract
    Different types of visual features provide multi-modal representation for images in the annotation task. Conventional graph-based image annotation methods integrate various features into a single descriptor and consider one node for each descriptor on the learning graph. However, this graph does not capture the information of individual features, making it unsuitable for propagating the labels of annotated images. In this paper, we address this issue by proposing an approach for fusing the visual features such that a specific subgraph is constructed for each visual modality and then subgraphs are connected to form a supergraph. As the size of supergraph grows linearly with the number of... 

    From local similarity to global coding: An application to image classification

    , Article Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Portland, OR ; 2013 , Pages 2794-2801 ; 10636919 (ISSN) Shaban, A ; Rabiee, H. R ; Farajtabar, M ; Ghazvininejad, M ; Sharif University of Technology
    2013
    Abstract
    Bag of words models for feature extraction have demonstrated top-notch performance in image classification. These representations are usually accompanied by a coding method. Recently, methods that code a descriptor giving regard to its nearby bases have proved efficacious. These methods take into account the nonlinear structure of descriptors, since local similarities are a good approximation of global similarities. However, they confine their usage of the global similarities to nearby bases. In this paper, we propose a coding scheme that brings into focus the manifold structure of descriptors, and devise a method to compute the global similarities of descriptors to the bases. Given a local... 

    Echocardiography frames quantification by empirical mode decomposition method

    , Article 2014 21st Iranian Conference on Biomedical Engineering, ICBME 2014, 26 November 2014 through 28 November 2014 ; November , 2014 , Pages 201-205 ; 9781479974177 (ISBN) Aliniazare, H ; Behnam, H ; Fatemizadeh, E ; Sani, Z. A ; Sharif University of Technology
    Institute of Electrical and Electronics Engineers Inc  2014
    Abstract
    In this study a new method is proposed for quantification of cardiac muscle motions in echocardiography frames based on empirical mode decomposition (EMD) and manifold learning method. EMD algorithm is able to extract intrinsic mode functions (IMF) from a signal. In the first bi-dimension intrinsic mode functions (BIMF) of echocardiography frames myocardial is shown with more details than the second BIMF and the second BIMF shows more details than the third BIMF. By using manifold learning method, quantification difference between each pair of consecutive frames in the first, second and third BIMF series (similarities between the frames were extracted). Acquired trajectories of three... 

    Manifold learning for ECG arrhythmia recognition

    , Article 2013 20th Iranian Conference on Biomedical Engineering, ICBME 2013 ; 2013 , Pages 126-131 Lashgari, E ; Jahed, M ; Khalaj, B ; Sharif University of Technology
    IEEE Computer Society  2013
    Abstract
    Heart is a complex system and we can find its function in electrocardiogram (ECG) signal. The records show high mortality rate of heart diseases. So it is essential to detect and recognize ECG arrhythmias. The problem with ECG analysis is the vast variations among morphologies of ECG signals. Premature Ventricular Contractions (PVC) is a common type of arrhythmia which may lead to critical situations and contains risk. This study, proposes a novel approach for detecting PVC and visualizing data with respect to ECG morphologies by using manifold learning. To this end, the Laplacian Eigenmaps - One of the reduction method and it is in the nonlinear category - is used to extract important... 

    Nonlinear blind source separation for sparse sources

    , Article European Signal Processing Conference, 28 August 2016 through 2 September 2016 ; Volume 2016-November , 2016 , Pages 1583-1587 ; 22195491 (ISSN) ; 9780992862657 (ISBN) Ehsandoust, B ; Rivet, B ; Jutten, C ; Babaie Zadeh, M ; Sharif University of Technology
    European Signal Processing Conference, EUSIPCO  2016
    Abstract
    Blind Source Separation (BSS) is the problem of separating signals which are mixed through an unknown function from a number of observations, without any information about the mixing model. Although it has been mathematically proven that the separation can be done when the mixture is linear, there is not any proof for the separability of nonlinearly mixed signals. Our contribution in this paper is performing nonlinear BSS for sparse sources. It is shown in this case, sources are separable even if the problem is under-determined (the number of observations is less than the number of source signals). However in the most general case (when the nonlinear mixing model can be of any kind and there... 

    Nonlinear Dimensionality Reduction via Path-Based Isometric Mapping

    , Article IEEE Transactions on Pattern Analysis and Machine Intelligence ; Volume 38, Issue 7 , 2016 , Pages 1452-1464 ; 01628828 (ISSN) Najafi, A ; Joudaki, A ; Fatemizadeh, E ; Sharif University of Technology
    IEEE Computer Society 
    Abstract
    Nonlinear dimensionality reduction methods have demonstrated top-notch performance in many pattern recognition and image classification tasks. Despite their popularity, they suffer from highly expensive time and memory requirements, which render them inapplicable to large-scale datasets. To leverage such cases we propose a new method called "Path-Based Isomap". Similar to Isomap, we exploit geodesic paths to find the low-dimensional embedding. However, instead of preserving pairwise geodesic distances, the low-dimensional embedding is computed via a path-mapping algorithm. Due to the much fewer number of paths compared to number of data points, a significant improvement in time and memory... 

    K/K-Nearest Neighborhood criterion for improving locally linear embedding

    , Article Proceedings of the 2009 6th International Conference on Computer Graphics, Imaging and Visualization: New Advances and Trends, CGIV2009, 11 August 2009 through 14 August 2009, Tianjin ; 2009 , Pages 392-397 ; 9780769537894 (ISBN) Eftekhari, A ; Moghaddam, H. A ; Babaie Zadeh, M ; Sharif University of Technology
    Abstract
    Spectral manifold learning techniques have recently found extensive applications in machine vision. The common strategy of spectral algorithms for manifold learning is exploiting the local relationships in a symmetric adjacency graph, which is typically constructed using k-nearest neighborhood (k-NN) criterion. In this paper, with our focus on locally linear embedding as a powerful and well-known spectral technique, shortcomings of k-NN for construction of the adjacency graph are first illustrated, and then a new criterion, namely k/K-nearest neighborhood (k/K-NN) is introduced to overcome these drawbacks. The proposed criterion involves finding the sparsest representation of each sample in... 

    K/K-nearest neighborhood criterion for improvement of locally linear embedding

    , Article 13th International Conference on Computer Analysis of Images and Patterns, CAIP 2009, Munster, 2 September 2009 through 4 September 2009 ; Volume 5702 LNCS , 2009 , Pages 808-815 ; 03029743 (ISSN); 3642037666 (ISBN); 9783642037665 (ISBN) Eftekhari, A ; Abrishami Moghaddam, H ; Babaie Zadeh, M ; Sharif University of Technology
    2009
    Abstract
    Spectral manifold learning techniques have recently found extensive applications in machine vision. The common strategy of spectral algorithms for manifold learning is exploiting the local relationships in a symmetric adjacency graph, which is typically constructed using k -nearest neighborhood (k-NN) criterion. In this paper, with our focus on locally linear embedding as a powerful and well-known spectral technique, shortcomings of k-NN for construction of the adjacency graph are first illustrated, and then a new criterion, namely k/K-nearest neighborhood (k/K-NN) is introduced to overcome these drawbacks. The proposed criterion involves finding the sparsest representation of each sample in... 

    Alzheimer’s disease early diagnosis using manifold-based semi-supervised learning

    , Article Brain Sciences ; Volume 7, Issue 8 , 2017 ; 20763425 (ISSN) Khajehnejad, M ; Habibollahi Saatlou, F ; Mohammadzade, H ; Sharif University of Technology
    Abstract
    Alzheimer’s disease (AD) is currently ranked as the sixth leading cause of death in the United States and recent estimates indicate that the disorder may rank third, just behind heart disease and cancer, as a cause of death for older people. Clearly, predicting this disease in the early stages and preventing it from progressing is of great importance. The diagnosis of Alzheimer’s disease (AD) requires a variety of medical tests, which leads to huge amounts of multivariate heterogeneous data. It can be difficult and exhausting to manually compare, visualize, and analyze this data due to the heterogeneous nature of medical tests, therefore, an efficient approach for accurate prediction of the... 

    Unsupervised domain adaptation via representation learning and adaptive classifier learning

    , Article Neurocomputing ; Volume 165 , 2015 , Pages 300-311 ; 09252312 (ISSN) Gheisari, M ; Baghshah Soleimani, M ; Sharif University of Technology
    Abstract
    The existing learning methods usually assume that training data and test data follow the same distribution, while this is not always true. Thus, in many cases the performance of these methods on the test data will be severely degraded. In this paper, we study the problem of unsupervised domain adaptation, where no labeled data in the target domain is available. The proposed method first finds a new representation for both the source and the target domain and then learns a prediction function for the classifier by optimizing an objective function which simultaneously tries to minimize the loss function on the source domain while also maximizes the consistency of manifold (which is based on... 

    Spatiotemporal registration and fusion of transthoracic echocardiography and volumetric coronary artery tree

    , Article International Journal of Computer Assisted Radiology and Surgery ; Volume 16, Issue 9 , 2021 , Pages 1493-1505 ; 18616410 (ISSN) Ghodsizad, T ; Behnam, H ; Fatemizadeh, E ; Faghihi Langroudi, T ; Bayat, F ; Sharif University of Technology
    Springer Science and Business Media Deutschland GmbH  2021
    Abstract
    Purpose: Cardiac multimodal image fusion can offer an image with various types of information in a single image. Many coronary stenosis, which are anatomically clear, are not functionally significant. The treatment of such kind of stenosis can cause irreversible effects on the patient. Thus, choosing the best treatment planning depend on anatomical and functional information is very beneficial. Methods: An algorithm for the fusion of coronary computed tomography angiography (CCTA) as an anatomical and transthoracic echocardiography (TTE) as a functional modality is presented. CCTA and TTE are temporally registered using manifold learning. A pattern search optimization algorithm, using...