Filters








3,970 Hits in 9.1 sec

Graph Regularized Sparse Coding for Image Representation

Miao Zheng, Jiajun Bu, Chun Chen, Can Wang, Lijun Zhang, Guang Qiu, Deng Cai
2011 IEEE Transactions on Image Processing  
In many real applications, the data is more likely to reside on a low-dimensional submanifold embedded in the high-dimensional ambient space.  ...  It is an unsupervised learning algorithm, which finds a basis set capturing high-level semantics in the data and learns sparse coordinates in terms of the basis set.  ...  Recently, there are several novel works on the design of the dictionary. One of the most efficient methods is the K-SVD method [28] .  ... 
doi:10.1109/tip.2010.2090535 pmid:21047712 fatcat:6rfbyic7kzf55nra5sdoydbrda

A Survey of Soft Computing Approaches in Biomedical Imaging

Manju Devi, Sukhdip Singh, Shailendra Tiwari, Subhash Chandra Patel, Melkamu Teshome Ayana, Jiawen Kang
2021 Journal of Healthcare Engineering  
We also studied and compared each approach used for other imaging modalities based on the certain parameter used for the system evaluation.  ...  Until now, various soft computing approaches have been proposed for medical applications.  ...  learning to avoid simple local minima and obtain good image quality. is approach obtains better performance than iterative reconstruction based on total variation and dictionary learning for both two-dimensional  ... 
doi:10.1155/2021/1563844 pmid:34394885 pmcid:PMC8356006 fatcat:uh6xrqpiyzej5jaepkpwxwzmvq

Collaborative representation-based classification of microarray gene expression data

Lizhen Shen, Hua Jiang, Mingfang He, Guoqing Liu, Bin Liu
2017 PLoS ONE  
In this paper, we propose a novel collaborative representation (CR)-based classification with regularized least square to classify gene data.  ...  In addition, compressive sensing approach is adopted to project the high-dimensional gene expression dataset to a lower-dimensional space which nearly contains the whole information.  ...  Thus, approaches based on machine learning, which can automatically acquire qualitatively interesting patterns from gene data, have been widely adopted [4] [5] [6] [7] .  ... 
doi:10.1371/journal.pone.0189533 pmid:29236759 pmcid:PMC5728509 fatcat:cac6l2vvfjhithdxduexvleygm

Composite measurements and molecular compressed sensing for highly efficient transcriptomics [article]

Brian Cleary, Le Cong, Eric Lander, Aviv Regev
2017 bioRxiv   pre-print
Here, we draw on a series of advances over the last decade in the field of mathematics to establish a rigorous link between biological structure, data compressibility, and efficient data acquisition.  ...  the interpretation of high-dimensional data.  ...  L.C. was supported by a CRI fellowship.  ... 
doi:10.1101/091926 fatcat:444rvou5zrc5pgr6djj4r75yge

Land cover classification in multispectral imagery using clustering of sparse approximations over learned feature dictionaries

Daniela I. Moody, Steven P. Brumby, Joel C. Rowland, Garrett L. Altmann
2014 Journal of Applied Remote Sensing  
We demonstrate our method on multispectral WorldView-2 data from a coastal plain ecosystem in Barrow, Alaska.  ...  We use a Hebbian learning rule to build spectral-textural dictionaries that are tailored for classification.  ...  Application of the methodology and continued development is supported by DOE's Office of Science, Biological and Environmental Research (BER) Program, through the Next Generation Ecosystem Experiment (  ... 
doi:10.1117/1.jrs.8.084793 fatcat:spdxm3aa6fexfe5jpvafdnco4u

HSR: L 1/2-regularized sparse representation for fast face recognition using hierarchical feature selection

Bo Han, Bo He, Tingting Sun, Tianhong Yan, Mengmeng Ma, Yue Shen, Amaury Lendasse
2015 Neural computing & applications (Print)  
In comparison with related work such as SRC and Gabor-feature based SRC (GSRC), experimental results on a variety of face databases demonstrate the great advantage of our method for computational cost.  ...  In this paper, we propose a novel method for fast face recognition called L1/2 Regularized Sparse Representation using Hierarchical Feature Selection (HSR).  ...  the low-dimensional features from the high-dimensional data.  ... 
doi:10.1007/s00521-015-1907-y fatcat:qlbhvzjnpjgw3k477gvzoiib2e

Multi-task Dictionary Learning based Convolutional Neural Network for Computer aided Diagnosis with Longitudinal Images [article]

Jie Zhang, Qingyang Li, Richard J. Caselli, Jieping Ye, Yalin Wang
2017 arXiv   pre-print
Then, we propose a novel unsupervised learning method, termed Multi-task Stochastic Coordinate Coding (MSCC), for learning different tasks by using shared and individual dictionaries and generating the  ...  To reach this goal, we innovate a CNN based deep learning multi-task dictionary learning framework to address the above challenges.  ...  [24] proposed a sparse coding model for MTL and transfer learning based on the generative methods, but it is not associated with deep learning model.  ... 
arXiv:1709.00042v1 fatcat:sciiul57vfey7k6mcyn7ilmb3i

2020 Index IEEE Transactions on Computational Imaging Vol. 6

2020 IEEE Transactions on Computational Imaging  
., TCI 2020 1297-1308 Novikov, A., see Moscoso, M., TCI 2020 87-94  ...  ., +, TCI 2020 1537-1547 Biological tissues Application of Subspace-Based Distorted-Born Iteration Method in Imaging Biaxial Anisotropic Scatterer.  ...  ., +, TCI 2020 682-696 Least squares approximations A Convex Formulation for Binary Tomography.  ... 
doi:10.1109/tci.2021.3054596 fatcat:puij7ztll5ai7alxrmqzsupcny

Spatio-Temporal Anomaly Detection for Industrial Robots through Prediction in Unsupervised Feature Space

Asim Munawar, Phongtharin Vinayavekhin, Giovanni De Magistris
2017 2017 IEEE Winter Conference on Applications of Computer Vision (WACV)  
Combining the learned features with a prediction system, we can detect irregularities in high dimensional data feed (e.g. video of a robot performing pick and place task).  ...  Spatio-temporal anomaly detection by unsupervised learning have applications in a wide range of practical settings.  ...  [7] proposed a unsupervised feature learning method that is novel and does not belong the above categories. It is based on training a convolutional neural networks with a pseudo training data.  ... 
doi:10.1109/wacv.2017.118 dblp:conf/wacv/MunawarVM17 fatcat:atj54eyvjjc6dk4p6bp6upodxa

Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification [article]

Shu Kong, Surangi Punyasena, Charless Fowlkes
2016 arXiv   pre-print
We propose a robust approach for performing automatic species-level recognition of fossil pollen grains in microscopy images that exploits both global shape and local texture characteristics in a patch-based  ...  We use these selected exemplars as a dictionary basis and propose a spatially-aware sparse coding method to match testing images for identification while maintaining global shape correspondence.  ...  To select the discriminative patches, we introduce a novel selection approach based on submodular maximization, which is very efficient and effective in practice.  ... 
arXiv:1605.00775v1 fatcat:tnyetri5bfeshf3mr6ircg5nny

Exploring a Siamese Neural Network Architecture for One-Shot Drug Discovery

Luis Torres, Nelson Monteiro, Jose Oliveira, Joel Arrais, Bernardete Ribeiro
2020 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE)  
The main objective of the study is to optimize the discovery of novel compounds based on a reduced set of candidate drugs.  ...  Deep neural networks offer a great predictive power when inferring the pharmacological properties and biological activities of small molecules in drug discovery applications.  ...  Acknowledgments Acknowledgments Um último agradecimento a todos os amigos e "família" de Coimbra por estarem sempre lá e me apoiarem nos momentos mais importantes.  ... 
doi:10.1109/bibe50027.2020.00035 fatcat:4knhi5fqq5hjbeyjuunzxx6phm

Population-scale three-dimensional reconstruction and quantitative profiling of microglia arbors

Murad Megjhani, Nicolas Rey-Villamizar, Amine Merouane, Yanbin Lu, Amit Mukherjee, Kristen Trett, Peter Chong, Carolyn Harris, William Shain, Badrinath Roysam
2015 Computer applications in the biosciences : CABIOS  
An over-complete dictionary-based model was learned for the image-specific local structure of microglial processes.  ...  more accurate based on the DIADEM metric.  ...  Ronald Coifman at Yale University for advice on harmonic co-clustering analysis. We also thank Ms. Audrey Cheong for manual reconstruction assistance, Mr.  ... 
doi:10.1093/bioinformatics/btv109 pmid:25701570 pmcid:PMC4481841 fatcat:i3hgc2pbzveqfj4sp65tr2q2zq

UProC: tools for ultra-fast protein domain classification

Peter Meinicke
2014 Computer applications in the biosciences : CABIOS  
UProC is by three orders of magnitude faster than profile-based methods and in a metagenome simulation study achieved up to 80% higher sensitivity on unassembled 100 bp reads.  ...  Motivation: With rapidly increasing volumes of biological sequence data the functional analysis of new sequences in terms of similarities to known protein families challenges classical bioinformatics.  ...  System and methods The protein sequence classification in UproC is based on a novel algorithm that we refer to as 'Mosaic Matching'.  ... 
doi:10.1093/bioinformatics/btu843 pmid:25540185 pmcid:PMC4410661 fatcat:ykeqts7pcnduvjgzuhdhvlsy4q

Representation in the (Artificial) Immune System

Chris McEwan, Emma Hart
2009 Journal of Mathematical Modelling and Algorithms  
Much of contemporary research in Artificial Immune Systems (AIS) has partitioned into either algorithmic machine learning and optimisation, or, modelling biologically plausible dynamical systems, with  ...  In this paper, we motivate and derive an alternative representational abstraction. To do so we consider the validity of shape-space from both the biological and machine learning perspectives.  ...  We begin with the ubiquitous fitting of a line by the method of least-squares y = X 0 w where X is an n ⇥ m column matrix of data vectors, w an n-dimensional weight vector (to be found), and y an m-dimensional  ... 
doi:10.1007/s10852-009-9104-6 fatcat:y2mk5jexcbfktijypqber4j5q4

Electroencephalogram based Detection of Deep Sedation in ICU Patients Using Atomic Decomposition

2018 IEEE Transactions on Biomedical Engineering  
This study was performed to evaluate how well states of deep sedation in ICU patients can be detected from the frontal electroencephalogram (EEG) using features based on the method of atomic decomposition  ...  Acknowledgments This material is based upon works supported by NIH-NINDS 1K23NS090900-01 (MBW, SBN), Andrew David Heitman Foundation (MBW), Rappaport Foundation (MBW).  ...  Nevertheless, rigorous application of all five elements of the data-driven approach has allowed machine learning approaches to successfully address numerous real-world applications.  ... 
doi:10.1109/tbme.2018.2813265 pmid:29993386 pmcid:PMC6424570 fatcat:dv3ublcif5fmtmlpi5w4nlj2s4
« Previous Showing results 1 — 15 out of 3,970 results