Filters








18,044 Hits in 8.3 sec

Output Fisher embedding regression

Moussab Djerrab, Alexandre Garcia, Maxime Sangnier, Florence d'Alché-Buc
2018 Machine Learning  
Numerical experiments on a wide variety of tasks (time series prediction, multi-output regression and multi-class classification) highlight the relevance of the approach for learning under limited supervision  ...  Based on a probabilistic modeling of training output data and the minimization of a Fisher loss, it requires to solve a pre-image problem in the prediction phase.  ...  Moussab Djerrab is supported by the Télécom ParisTech Machine Learning for Big Data Chair.  ... 
doi:10.1007/s10994-018-5698-0 fatcat:4eytutba6jhrdcrompn4fhv3gy

Neural Reversible Steganography with Long Short-Term Memory

Ching-Chun Chang, Chi-Hua Chen
2021 Security and Communication Networks  
State-of-the-art reversible steganographic schemes for digital images are based primarily on a histogram-shifting method in which the analytics module is often modelled as a pixel intensity predictor.  ...  ., noise reduction and super-resolution imaging).  ...  Module e previous coding module works under the assumption that a prediction mechanism has been developed and it is time to unveil and deliver the analytics module for estimating a reference image from  ... 
doi:10.1155/2021/5580272 fatcat:g3teymmqmjb35c23muvtl3htfi

Autocovariance structures for radial averages in small-angle X-ray scattering experiments

F. Jay Breidt, Andreea Erciulescu, Mark van der Woerd
2012 Journal of Time Series Analysis  
Across a range of experimental conditions and molecular types, spatial autocorrelation in the detector plane is present and is welldescribed by a stationary kernel convolution model.  ...  The twodimensional pattern is reduced to a one-dimensional curve through radial averaging; that is, by averaging across annuli on the detector plane.  ...  , averaged across all relevant time series from the differenced images.  ... 
doi:10.1111/j.1467-9892.2011.00779.x pmid:23355752 pmcid:PMC3551296 fatcat:bq57ze7kxrdwxgj2bpen33q6pe

Graph Signal Processing of Low and High-Order Dynamic Functional Connectivity Networks Using EEG Resting-State for Schizophrenia: A Whole Brain Breakdown [article]

Stavros I Dimitriadis
2019 bioRxiv   pre-print
Recently, a high-order version of FCG has emerged by estimating the correlations of the time series that describe the fluctuations of the functional strength of every pair of ROIs across experimental time  ...  At a second level, we estimated the laplacian transformations of both LO and HO-IDFCG and by calculating the temporal evolution of Synchronizability (Syn), four network metric time series (NMTSSyn) were  ...  Recently, a highorder version of FCG has emerged by estimating the correlations of the time series that describe the fluctuations of the functional strength of every pair of ROIs across experimental time  ... 
doi:10.1101/551671 fatcat:xuzbplj4argzzn5wa5lbzhoq4i

Video analysis based on volumetric event detection

Jing Wang, Zhi-Jie Xu
2010 International Journal of Automation and Computing  
This paper reports an innovative technique to transform original video frames to 3D volume structures denoted by spatial and temporal features.  ...  It then moves on to highlight the volume array structure in a so called "pre-suspicion" mechanism for later process.  ...  The identical multivariate kernel density estimation can then follow suit.  ... 
doi:10.1007/s11633-010-0516-6 fatcat:brwenzfjujbyxlk3djxk2t227q

An algorithm to separate touching grains based on Fourier series Approximation

S. B. Ghadge,
2014 IOSR Journal of Engineering  
An algorithm based on Fourier series approximation is proposed for separating touching grain kernels.  ...  Then pre-processing techniques are applied to threshold the required region and make the image smoother, and also to find the boundary points.  ...  kernel separation procedure for four grains: (a) original image showing multiple touching kernels; (b) Binary image (c) Pre-processed image (d) Fourier series approximation (red contours) of the boundary  ... 
doi:10.9790/3021-04630510 fatcat:pozygzhf2jcmvj4onrwjxozhru

Applicability of Convolutional Neural Networks for Calibration of Nonlinear Dynamic Models of Structures

Angela Lanning, Arash E. Zaghi, Tao Zhang
2022 Frontiers in Built Environment  
A convolutional neural network (CNN) architecture was used to calibrate these parameters by using the lateral load, displacement, and axial load time histories as input variables.  ...  Next, four CNNs were trained to evaluate the presentation of input data in time-domain and time-frequency domain.  ...  FIGURE 6 | 6 FIGURE 6 | Sample architecture for the TS-2D network using the time-series input and 2D kernel.  ... 
doi:10.3389/fbuil.2022.873546 doaj:6d63b66985db4ae891dd4ae16ea33465 fatcat:rgb4h2llqjgjhorvhhnsvftkmq

Scale-Space Splatting: Reforming Spacetime for Cross-Scale Exploration of Integral Measures in Molecular Dynamics

Juraj Palenik, Jan Byska, Stefan Bruckner, Helwig Hauser
2019 IEEE Transactions on Visualization and Computer Graphics  
These, however, by virtue of aggregation, hide structural information about the space/time localization of the studied phenomena.  ...  Our novel representation, based on partial domain aggregation, enables the construction of a continuous scale-space for discrete datasets and the simultaneous exploration of scales in both space and time  ...  Pinus, by Sips et al. [42] , is a multiscale visual analytics technique for finding patterns in time series data.  ... 
doi:10.1109/tvcg.2019.2934258 pmid:31403429 fatcat:47bnsp26d5b4bafbluq3eeyrvu

Connecting Beamforming and Kernel-based Noise Source Inversion

Daniel C Bowden, Korbinian Sager, Andreas Fichtner, Małgorzata Chmiel
2020 Geophysical Journal International  
For example, inversion frameworks can benefit from the numerous image enhancement tools developed by the beamforming community.  ...  These kernel-based approaches show great promise, both in mathematical rigour and in results, but are less physically intuitive and interpretable.  ...  Again, the appropriate time delays are estimated.  ... 
doi:10.1093/gji/ggaa539 fatcat:5roi77kkyrgdddn2u4qdc363uy

Revisiting the Past: Replicability of a Historic Long-Term Vegetation Dynamics Assessment in the Era of Big Data Analytics

David Frantz, Patrick Hostert, Philippe Rufin, Stefan Ernst, Achim Röder, Sebastian van der Linden
2022 Remote Sensing  
Over 10 years ago, Landsat time series analyses were inevitably limited to a few expensive images from carefully selected acquisition dates.  ...  We replicated this assessment using all available data paired with a time series method based on land surface phenology metrics.  ...  The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results.  ... 
doi:10.3390/rs14030597 fatcat:jpporeawufdf7pvvybvo4lnyme

ESTIMATING WATER LEVEL IN THE URMIA LAKE USING SATELLITE DATA: A MACHINE LEARNING APPROACH

M. Boueshagh, M. Hasanlou
2019 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Hence, the purpose of this paper is the Urmia Lake water level estimation during 2000–2006 using observed water level, snow cover, direct precipitation, and evaporation.  ...  For this purpose, Support Vector Regression (SVR), which is the most outstanding kernel method (with various kernel types), has been used.  ...  Figure 2 . 2 Urmia Lake basin in the northwest of Iran (Safaee et al., 2014) Figure 3 . 3 Water level time series, SC time series, precipitation time series and evaporation time series(2000 - 2006)  ... 
doi:10.5194/isprs-archives-xlii-4-w18-219-2019 fatcat:b75svspyjbb6lndudfj44q2bgm

Advancements in IR spectroscopic approaches for the determination of fungal derived contaminations in food crops

David McMullin, Boris Mizaikoff, Rudolf Krska
2014 Analytical and Bioanalytical Chemistry  
Infrared spectroscopy is a rapid, nondestructive analytical technique that can be applied to the authentication and characterization of food samples in high throughput.  ...  Economically important crops are infected by fungi that can severely reduce crop yields and quality and, in addition, produce mycotoxins.  ...  Automated sorting of intact wheat kernels was achieved by an NIR spectroscopic method that could differentiate samples at a 60 mg/kg DON threshold, which was correct 96 % of the time [25] .  ... 
doi:10.1007/s00216-014-8145-5 pmid:25258282 pmcid:PMC4305099 fatcat:f5bzkmtqj5h2tpmxssupp4vlle

Mixed Confidence Estimation for Iterative CT Reconstruction

David S. Perlmutter, Soo Mee Kim, Paul E. Kinahan, Adam M. Alessio
2016 IEEE Transactions on Medical Imaging  
We show that by splitting the image space into higher and lower confidence components, MCE can lower the estimator variance in both regions compared to conventional reconstruction.  ...  time.  ...  This work is supported by the National Institutes of Health under grants R01-HL109327 and R01-CA115870.  ... 
doi:10.1109/tmi.2016.2543141 pmid:27008663 pmcid:PMC5270602 fatcat:yqmzt2jagffxzn6f3r3re3zh4i

Kernel methods for fMRI pattern prediction

Yizhao Ni, Carlton Chu, Craig J. Saunders, John Ashburner
2008 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)  
The procedure involved correcting motion artifacts, spatial smoothing, removing low frequency drifts and applying multivariate linear and non-linear kernel methods.  ...  Two novel techniques are applied: one utilizes the Cosine Transform to remove low-frequency drifts over time and the other involves using prior knowledge about the spatial contribution of different brain  ...  The performance is measured by correlating the predicted task values with the actual "reference" feature time series data.  ... 
doi:10.1109/ijcnn.2008.4633870 dblp:conf/ijcnn/NiCSA08 fatcat:5t5bykhx7jhhzk4t4z4cvh2sqm

Statistical Machine Learning Methods and Remote Sensing for Sustainable Development Goals: A Review

Jacinta Holloway, Kerrie Mengersen
2018 Remote Sensing  
In the supplementary material, we also describe the necessary steps pre and post analysis for remote sensing data; the pre-processing and evaluation steps.  ...  The authors also thank and acknowledge Siu-Ming Tam for comments and guidance on the report, as Chair of the Task Team at the time the report was written.  ...  Acknowledgments: This paper is motivated by a United Nations Report the authors contributed a methodology chapter to as part of their role in the United Nations Satellite Imagery and Geospatial Data Task  ... 
doi:10.3390/rs10091365 fatcat:dnc5d73szjgk3lfn2c2kzsmbay
« Previous Showing results 1 — 15 out of 18,044 results