umu.sePublikationer
Ändra sökning
Länk till posten
Permanent länk

Direktlänk
BETA
Alternativa namn
Publikationer (10 of 101) Visa alla publikationer
Wang, J., Fonseca, R. M., Rutledge, K., Martin-Torres, J. & Yu, J. (2020). A Hybrid Statistical-Dynamical Downscaling of Air Temperature over Scandinavia using the WRF model. Advances in Atmospheric Sciences, 37, 57-74
Öppna denna publikation i ny flik eller fönster >>A Hybrid Statistical-Dynamical Downscaling of Air Temperature over Scandinavia using the WRF model
Visa övriga...
2020 (Engelska)Ingår i: Advances in Atmospheric Sciences, ISSN 0256-1530, E-ISSN 1861-9533, Vol. 37, s. 57-74Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

An accurate simulation of air temperature at local-scales is crucial for the vast majority of weather and climate applications. In this work, a hybrid statistical-dynamical downscaling method and a high-resolution dynamical-only downscaling method are applied to daily mean, minimum and maximum air temperatures to investigate the quality of local scale estimates produced by downscaling. These two downscaling approaches are evaluated using station observation data obtained from the Finnish Meteorological Institute (FMI) over a near-coastal region of western Finland. The dynamical downscaling is performed with the Weather Research and Forecasting (WRF) model, and the statistical downscaling method implemented is the Cumulative Distribution Function-transform (CDF-t). The CDF-t is trained using 20-years of WRF-downscaled Climate Forecast System Reanalysis (CFSR) data over the region at 3 km spatial resolution for the central month of each season. The performance of the two methods is assessed qualitatively, by inspection of quantile-quantile (Q-Q) plots, and quantitatively, through the Cramer-von Mises (CvM), mean absolute error (MAE), and root-mean-square Error (RMSE) diagnostics. The hybrid approach is found to provide significantly more skillful forecasts of the observed daily mean and maximum air temperatures than those of the dynamical-only downscaling (for all seasons). The hybrid method proved to be less computationally expensive, and also to give more skillful temperature forecasts (at least for the Finnish near-coastal region).

Ort, förlag, år, upplaga, sidor
Springer, 2020
Nyckelord
WRF, air temperature, CDF-t, hybrid statistical-dynamical downscaling, model evaluation, Scandinavian Peninsula.
Nationell ämneskategori
Sannolikhetsteori och statistik Meteorologi och atmosfärforskning
Forskningsämne
matematisk statistik
Identifikatorer
urn:nbn:se:umu:diva-162956 (URN)10.1007/s00376-019-9091-0 (DOI)
Projekt
WindCoE
Tillgänglig från: 2019-09-03 Skapad: 2019-09-03 Senast uppdaterad: 2020-01-07Bibliografiskt granskad
Wang, J., Zhou, Z. & Yu, J. (2020). Statistical inference for block sparsity of complex-valued signals. IET Signal Processing
Öppna denna publikation i ny flik eller fönster >>Statistical inference for block sparsity of complex-valued signals
2020 (Engelska)Ingår i: IET Signal Processing, ISSN 1751-9675, E-ISSN 1751-9683Artikel i tidskrift (Refereegranskat) Accepted
Abstract [en]

Block sparsity is an important parameter in many algorithms to successfully recover block-sparse signals under the framework of compressive sensing. However, it is often unknown and needs to be estimated. Recently there emerges a few research work about how to estimate block sparsity of real-valued signals, while there is, to the best of our knowledge, no research that has been done for complex-valued signals. In this study, we propose a method to estimate the block sparsity of complex-valued signal. Its statistical properties are obtained and verified by simulations. In addition, we demonstrate the importance of accurately estimating the block sparsity through a sensitivity analysis.

Ort, förlag, år, upplaga, sidor
Institution of Engineering and Technology, 2020
Nyckelord
Block sparsity; Complex-valued signals; Multivariate isotropic symmetric alpha-stable distributions
Nationell ämneskategori
Sannolikhetsteori och statistik Signalbehandling
Forskningsämne
matematisk statistik
Identifikatorer
urn:nbn:se:umu:diva-168016 (URN)10.1049/iet-spr.2019.0200 (DOI)
Tillgänglig från: 2020-02-10 Skapad: 2020-02-10 Senast uppdaterad: 2020-02-18
Zhou, Z. & Yu, J. (2019). A New Nonconvex Sparse Recovery Method for Compressive Sensing. Frontiers in Applied Mathematics and Statistics, 5, 1-11, Article ID 14.
Öppna denna publikation i ny flik eller fönster >>A New Nonconvex Sparse Recovery Method for Compressive Sensing
2019 (Engelska)Ingår i: Frontiers in Applied Mathematics and Statistics, ISSN 2297-4687, Vol. 5, s. 1-11, artikel-id 14Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

As an extension of the widely used ℓr-minimization with 0 < r ≤ 1, a new non-convex weighted ℓr − ℓ1 minimization method is proposed for compressive sensing. The theoretical recovery results based on restricted isometry property and q-ratio constrained minimal singular values are established. An algorithm that integrates the iteratively reweighted least squares algorithm and the difference of convex functions algorithmis given to approximately solve this non-convex problem. Numerical experiments are presented to illustrate our results.

Ort, förlag, år, upplaga, sidor
Frontiers Media S.A., 2019
Nyckelord
compressive sensing, nonconvex sparse recovery, iteratively reweighted least squares, difference of convex functions, q-ratio constrained minimal singular values
Nationell ämneskategori
Signalbehandling Matematik
Forskningsämne
signalbehandling; matematisk statistik
Identifikatorer
urn:nbn:se:umu:diva-157346 (URN)10.3389/fams.2019.00014 (DOI)
Forskningsfinansiär
Vetenskapsrådet, 340-2013-5342
Tillgänglig från: 2019-03-15 Skapad: 2019-03-15 Senast uppdaterad: 2019-03-20Bibliografiskt granskad
Bayisa, F., Zhou, Z., Cronie, O. & Yu, J. (2019). Adaptive algorithm for sparse signal recovery. Digital signal processing (Print), 87, 10-18
Öppna denna publikation i ny flik eller fönster >>Adaptive algorithm for sparse signal recovery
2019 (Engelska)Ingår i: Digital signal processing (Print), ISSN 1051-2004, E-ISSN 1095-4333, Vol. 87, s. 16s. 10-18Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

The development of compressive sensing in recent years has given much attention to sparse signal recovery. In sparse signal recovery, spike and slab priors are playing a key role in inducing sparsity. The use of such priors, however, results in non-convex and mixed integer programming problems. Most of the existing algorithms to solve non-convex and mixed integer programming problems involve either simplifying assumptions, relaxations or high computational expenses. In this paper, we propose a new adaptive alternating direction method of multipliers (AADMM) algorithm to directly solve the suggested non-convex and mixed integer programming problem. The algorithm is based on the one-to-one mapping property of the support and non-zero element of the signal. At each step of the algorithm, we update the support by either adding an index to it or removing an index from it and use the alternating direction method of multipliers to recover the signal corresponding to the updated support. Moreover, as opposed to the competing “adaptive sparsity matching pursuit” and “alternating direction method of multipliers” methods our algorithm can solve non-convex problems directly. Experiments on synthetic data and real-world images demonstrated that the proposed AADMM algorithm provides superior performance and is computationally cheaper than the recently developed iterative convex refinement (ICR) and adaptive matching pursuit (AMP) algorithms.

Ort, förlag, år, upplaga, sidor
Elsevier, 2019. s. 16
Nyckelord
sparsity, adaptive algorithm, sparse signal recovery, spike and slab priors
Nationell ämneskategori
Sannolikhetsteori och statistik Signalbehandling Medicinsk bildbehandling
Forskningsämne
matematisk statistik; signalbehandling
Identifikatorer
urn:nbn:se:umu:diva-146386 (URN)10.1016/j.dsp.2019.01.002 (DOI)000461266700002 ()2-s2.0-85060542792 (Scopus ID)
Projekt
Statistical modelling and intelligent data sampling in MRI and PET measurements for cancer therapy assessment
Forskningsfinansiär
Vetenskapsrådet, 340-2013-534
Anmärkning

Originally included in thesis in manuscript form

Tillgänglig från: 2018-04-07 Skapad: 2018-04-07 Senast uppdaterad: 2019-04-04Bibliografiskt granskad
Zhou, Z. & Yu, J. (2019). Adaptive estimation for varying coefficient modelswith nonstationary covariates. Communications in Statistics - Theory and Methods, 48(16), 4034-4050
Öppna denna publikation i ny flik eller fönster >>Adaptive estimation for varying coefficient modelswith nonstationary covariates
2019 (Engelska)Ingår i: Communications in Statistics - Theory and Methods, ISSN 0361-0926, E-ISSN 1532-415X, Vol. 48, nr 16, s. 4034-4050Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

In this paper, the adaptive estimation for varying coefficient models proposed by Chen, Wang, and Yao (2015) is extended to allowing for nonstationary covariates. The asymptotic properties of the estimator are obtained, showing different convergence rates for the integrated covariates and stationary covariates. The nonparametric estimator of the functional coefficient with integrated covariates has a faster convergence rate than the estimator with stationary covariates, and its asymptotic distribution is mixed normal. Moreover, the adaptive estimation is more efficient than the least square estimation for non normal errors. A simulation study is conducted to illustrate our theoretical results.

Ort, förlag, år, upplaga, sidor
Taylor & Francis, 2019
Nyckelord
Varying coefficient model, adaptive estimation, local linear fitting, non stationary covariates
Nationell ämneskategori
Sannolikhetsteori och statistik
Forskningsämne
matematisk statistik
Identifikatorer
urn:nbn:se:umu:diva-154754 (URN)10.1080/03610926.2018.1484483 (DOI)000473519800007 ()2-s2.0-85059303429 (Scopus ID)
Forskningsfinansiär
Vetenskapsrådet, 340-2013-534
Tillgänglig från: 2018-12-30 Skapad: 2018-12-30 Senast uppdaterad: 2019-08-06Bibliografiskt granskad
Leffler, K., Zhou, Z. & Yu, J. (2019). An extended block restricted isometry property for sparse recovery with non-Gaussian noise. Journal of Computational Mathematics
Öppna denna publikation i ny flik eller fönster >>An extended block restricted isometry property for sparse recovery with non-Gaussian noise
2019 (Engelska)Ingår i: Journal of Computational Mathematics, ISSN 0254-9409, E-ISSN 1991-7139Artikel i tidskrift (Refereegranskat) Epub ahead of print
Abstract [en]

We study the recovery conditions of weighted mixed ℓ2/ℓp minimization for block sparse signal reconstruction from compressed measurements when partial block supportinformation is available. We show theoretically that the extended block restricted isometry property can ensure robust recovery when the data fidelity constraint is expressed in terms of an ℓq norm of the residual error, thus establishing a setting wherein we arenot restricted to Gaussian measurement noise. We illustrate the results with a series of numerical experiments.

Ort, förlag, år, upplaga, sidor
Global Science Press, 2019
Nyckelord
Compressed sensing, block sparsity, partial support information, signal reconstruction, convex optimization
Nationell ämneskategori
Signalbehandling Sannolikhetsteori och statistik Beräkningsmatematik
Forskningsämne
matematisk statistik
Identifikatorer
urn:nbn:se:umu:diva-163366 (URN)10.4208/jcm.1905-m2018-0256 (DOI)
Forskningsfinansiär
Vetenskapsrådet
Tillgänglig från: 2019-09-17 Skapad: 2019-09-17 Senast uppdaterad: 2019-11-19
Wang, J., Zhou, Z., Garpebring, A. & Yu, J. (2019). Bayesian sparsity estimation in compressive sensing with application to MR images. Communications in Statistics: Case Studies, Data Analysis and Applications, 5(4), 415-431
Öppna denna publikation i ny flik eller fönster >>Bayesian sparsity estimation in compressive sensing with application to MR images
2019 (Engelska)Ingår i: Communications in Statistics: Case Studies, Data Analysis and Applications, ISSN 2373-7484, Vol. 5, nr 4, s. 415-431Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

The theory of compressive sensing (CS) asserts that an unknownsignal x ∈ CN can be accurately recovered from m measurements with m « N provided that x is sparse. Most of the recovery algorithms need the sparsity s = ||x||0 as an input. However, generally s is unknown, and directly estimating the sparsity has been an open problem. In this study, an estimator of sparsity is proposed by using Bayesian hierarchical model. Its statistical properties such as unbiasedness and asymptotic normality are proved. In the simulation study and real data study, magnetic resonance image data is used as input signal, which becomes sparse after sparsified transformation. The results from the simulation study confirm the theoretical properties of the estimator. In practice, the estimate from a real MR image can be used for recovering future MR images under the framework of CS if they are believed to have the same sparsity level after sparsification.

Ort, förlag, år, upplaga, sidor
Taylor & Francis Group, 2019
Nyckelord
Compressive sensing, sparsity, Bayesian hierarchical model, Matérn covariance, MRI
Nationell ämneskategori
Sannolikhetsteori och statistik Signalbehandling Medicinsk bildbehandling
Forskningsämne
matematisk statistik
Identifikatorer
urn:nbn:se:umu:diva-164952 (URN)10.1080/23737484.2019.1675557 (DOI)
Tillgänglig från: 2019-11-05 Skapad: 2019-11-05 Senast uppdaterad: 2019-12-16Bibliografiskt granskad
Pya Arnqvist, N., Ngendangenzwa, B., Nilsson, L., Lindahl, E. & Yu, J. (2019). Defect detection and classfiication: statistical learning approach - Part II.
Öppna denna publikation i ny flik eller fönster >>Defect detection and classfiication: statistical learning approach - Part II
Visa övriga...
2019 (Engelska)Rapport (Övrigt vetenskapligt)
Förlag
s. 56
Nyckelord
Statistical learning, probabilistic classification, defect detection, automated quality inspection
Nationell ämneskategori
Sannolikhetsteori och statistik Signalbehandling Bearbetnings-, yt- och fogningsteknik
Forskningsämne
matematisk statistik
Identifikatorer
urn:nbn:se:umu:diva-161255 (URN)
Forskningsfinansiär
Vinnova, 2015-03706
Tillgänglig från: 2019-07-01 Skapad: 2019-07-01 Senast uppdaterad: 2019-07-19Bibliografiskt granskad
Pya Arnqvist, N., Ngendangenzwa, B., Nilsson, L., Lindahl, E. & Yu, J. (2019). Efficient surface finish defect detection using reduced rank spline smoothers. In: CRoNoS & MDA 2019: . Paper presented at CRoNoS & MDA2019, Cyprus, April 14-16, 2019.
Öppna denna publikation i ny flik eller fönster >>Efficient surface finish defect detection using reduced rank spline smoothers
Visa övriga...
2019 (Engelska)Ingår i: CRoNoS & MDA 2019, 2019Konferensbidrag, Muntlig presentation med publicerat abstract (Refereegranskat)
Abstract [en]

One of the primary concerns of product quality control in the automotive industry is an automated detection of defects of small sizes on specular car body surfaces. A new statistical learning approach is presented for surface finish defect detection based on spline smoothing method for feature extraction and k-nearest neighbor probabilistic classifier. Rather than analyzing the natural images of the car body surfaces, the deflectometry technique is applied for image acquisition. Reduced rank cubic regression splines are used to smooth the pixel values while the effective degrees of freedom of the obtained smooths serve as components of the feature vector. A key advantage of the approach is that it allows us to reach near zero misclassification error when applying standard learning classifiers. We also propose the probability based performance evaluation metrics as alternatives to the conventional metrics. The usage of those provides the means for uncertainty estimation of the predictive performance of a classifier. Experimental classification results on the images obtained from the pilot system located at Volvo cab plant in Umea, Sweden, show that the proposed approach is much more efficient than compared methods.

Nationell ämneskategori
Sannolikhetsteori och statistik Signalbehandling
Forskningsämne
matematisk statistik
Identifikatorer
urn:nbn:se:umu:diva-158014 (URN)
Konferens
CRoNoS & MDA2019, Cyprus, April 14-16, 2019
Projekt
FIQA
Forskningsfinansiär
Vinnova, 2015-03706
Tillgänglig från: 2019-04-10 Skapad: 2019-04-10 Senast uppdaterad: 2019-04-16Bibliografiskt granskad
Wang, J., Zhou, Z. & Yu, J. (2019). Error bounds of block sparse signal recovery based on q-ratio block constrained minimal singular values. EURASIP Journal on Advances in Signal Processing, 2019, Article ID 57.
Öppna denna publikation i ny flik eller fönster >>Error bounds of block sparse signal recovery based on q-ratio block constrained minimal singular values
2019 (Engelska)Ingår i: EURASIP Journal on Advances in Signal Processing, ISSN 1687-6172, E-ISSN 1687-6180, Vol. 2019, artikel-id 57Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

In this paper, we introduce the q-ratio block constrained minimal singular values (BCMSV) as a new measure of measurement matrix in compressive sensing of block sparse/compressive signals and present an algorithm for computing this new measure. Both the mixed ℓ2/ℓq and the mixed ℓ2/ℓ1 norms of the reconstruction errors for stable and robust recovery using block basis pursuit (BBP), the block Dantzig selector (BDS), and the group lasso in terms of the q-ratio BCMSV are investigated. We establish a sufficient condition based on the q-ratio block sparsity for the exact recovery from the noise-free BBP and developed a convex-concave procedure to solve the corresponding non-convex problem in the condition. Furthermore, we prove that for sub-Gaussian random matrices, the q-ratio BCMSV is bounded away from zero with high probability when the number of measurements is reasonably large. Numerical experiments are implemented to illustrate the theoretical results. In addition, we demonstrate that the q-ratio BCMSV-based error bounds are tighter than the block-restricted isotropic constant-based bounds.

Ort, förlag, år, upplaga, sidor
Springer, 2019
Nyckelord
Compressive sensing, q-ratio block sparsity, q-ratio block constrained minimal singular value, Convex-concave procedure
Nationell ämneskategori
Signalbehandling Sannolikhetsteori och statistik Beräkningsmatematik
Forskningsämne
matematisk statistik
Identifikatorer
urn:nbn:se:umu:diva-165632 (URN)10.1186/s13634-019-0653-1 (DOI)000499457500002 ()
Forskningsfinansiär
Vetenskapsrådet, 340-2013-5342
Tillgänglig från: 2019-12-02 Skapad: 2019-12-02 Senast uppdaterad: 2020-01-09Bibliografiskt granskad
Projekt
Statistiska modeller och intelligenta datainsamlingsmetoder för MRI och PET mätningar med tillämpning för monitoring av cancerbehandling [2013-05342_VR]; Umeå universitet; Publikationer
Wang, J., Zhou, Z. & Yu, J. (2020). Statistical inference for block sparsity of complex-valued signals. IET Signal ProcessingZhou, Z. & Yu, J. (2019). Adaptive estimation for varying coefficient modelswith nonstationary covariates. Communications in Statistics - Theory and Methods, 48(16), 4034-4050Leffler, K., Zhou, Z. & Yu, J. (2019). An extended block restricted isometry property for sparse recovery with non-Gaussian noise. Journal of Computational MathematicsWang, J., Zhou, Z., Garpebring, A. & Yu, J. (2019). Bayesian sparsity estimation in compressive sensing with application to MR images. Communications in Statistics: Case Studies, Data Analysis and Applications, 5(4), 415-431Wang, J., Zhou, Z. & Yu, J. (2019). Enhanced block sparse signal recovery based on q-ratio block constrained minimal singular values. Wang, J., Zhou, Z. & Yu, J. (2019). Error bounds of block sparse signal recovery based on q-ratio block constrained minimal singular values. EURASIP Journal on Advances in Signal Processing, 2019, Article ID 57. Zhou, Z. & Yu, J. (2019). On q-ratio CMSV for sparse recovery. Signal Processing, 165, 128-132Zhou, Z. & Yu, J. (2019). Phaseless compressive sensing using partial support information. Optimization LettersWang, J., Zhou, Z. & Yu, J. (2019). Statistical inference for block sparsity of complex signals.
Organisationer
Identifikatorer
ORCID-id: ORCID iD iconorcid.org/0000-0001-5673-620x

Sök vidare i DiVA

Visa alla publikationer