Efficient recursive computational algorithms for multivariate t and multivariate unified skew-t distributions with applications to inference

Author(s):  
Mehdi Amiri ◽  
Yaser Mehrali ◽  
Narayanaswamy Balakrishnan ◽  
Ahad Jamalizadeh
Author(s):  
V.V. Kostenko ◽  
Yu.V. Vaulin ◽  
F.S. Dubrovin ◽  
O.Yu. Lvov

Буксируемый подводный модуль (БПМ) эффективно используется для решения задач, связанных с координированием подводных объектов, местоположение которых подлежит уточнению в процессе их детальногообследования. При этом большое значение имеет точность определения координат самого буксируемогомодуля относительно судна-буксировщика. Использование гидроакустических навигационных средств, вчастности систем с ультракороткой базой (ГАНС УКБ), ограничено вследствие помех, влияющих на качествосигналов в приемной антенне. Альтернативой служит метод определения координат БПМ на основе данныхтраекторных измерений параметров буксируемой системы. К числу последних относятся расчетные значенияпараметров кабеля связи в установившихся режимах буксировки, значения путевой скорости и путевого углабуксировщика, а также измеренные значения длины кабеля, глубины погружения и курса БПМ. В работе дансравнительный анализ различных вариантов вычислительных алгоритмов, позволяющих получить оценки точности определения координат БПМ в различных режимах стационарной буксировки и при наличии сбоев вработе навигационных средств.The towed underwater module (TUM) is a useful toolfor solving problems of the positioning of the underwaterobjects, the location of which must be clarified during its detailedinspection. Herewith, the accuracy of the determinationof the coordinates of the towed module itself relative tothe towing vessel is essential for such kind of problems. Theuse of underwater acoustic navigation means, the systemswith ultra-short baseline (USBL) in particular, are limiteddue to interference affecting the quality of the signals on thereceiving antenna. As an alternative, the method is proposedfor TUM positioning based on trajectory measurements ofparameters of the towed system, which may include calculatedvalues of communication cable parameters in steadystatetowing modes, values of ground speed and towing angle,as well as measured cable length, immersion depth, andTUM heading. The paper provides a comparative analysisof various versions of computational algorithms, which allowobtaining estimates of the TUM positioning accuracy indifferent modes of stationary towing and in the presence offailures in navigation systems operation.


Author(s):  
Nhan Phan-Thien ◽  
Sangtae Kim

This monograph describes various methods for solving deformation problems of particulate solids, taking the reader from analytical to computational methods. The book is the first to present the topic of linear elasticity in mathematical terms that will be familiar to anyone with a grounding in fluid mechanics. It incorporates the latest advances in computational algorithms for elliptic partial differential equations, and provides the groundwork for simulations on high performance parallel computers. Numerous exercises complement the theoretical discussions, and a related set of self-documented programs is available to readers with Internet access. The work will be of interest to advanced students and practicing researchers in mechanical engineering, chemical engineering, applied physics, computational methods, and developers of numerical modeling software.


2021 ◽  
pp. 105678952110286
Author(s):  
H Zhang ◽  
J Woody Ju ◽  
WL Zhu ◽  
KY Yuan

In a recent companion paper, a three-dimensional isotropic elastic micromechanical framework was developed to predict the mechanical behaviors of the innovative asphalt patching materials reinforced with a high-toughness, low-viscosity nanomolecular resin, dicyclopentadiene (DCPD), under the splitting tension test (ASTM D6931). By taking advantage of the previously proposed isotropic elastic-damage framework and considering the plastic behaviors of asphalt mastic, a class of elasto-damage-plastic model, based on a continuum thermodynamic framework, is proposed within an initial elastic strain energy-based formulation to predict the behaviors of the innovative materials more accurately. Specifically, the governing damage evolution is characterized through the effective stress concept in conjunction with the hypothesis of strain equivalence; the plastic flow is introduced by means of an additive split of the stress tensor. Corresponding computational algorithms are implemented into three-dimensional finite elements numerical simulations, and the outcomes are systemically compared with suitably designed experimental results.


2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Boris Kargoll ◽  
Alexander Dorndorf ◽  
Mohammad Omidalizarandi ◽  
Jens-André Paffenholz ◽  
Hamza Alkhatib

Abstract In this contribution, a vector-autoregressive (VAR) process with multivariate t-distributed random deviations is incorporated into the Gauss-Helmert model (GHM), resulting in an innovative adjustment model. This model is versatile since it allows for a wide range of functional models, unknown forms of auto- and cross-correlations, and outlier patterns. Subsequently, a computationally convenient iteratively reweighted least squares method based on an expectation maximization algorithm is derived in order to estimate the parameters of the functional model, the unknown coefficients of the VAR process, the cofactor matrix, and the degree of freedom of the t-distribution. The proposed method is validated in terms of its estimation bias and convergence behavior by means of a Monte Carlo simulation based on a GHM of a circle in two dimensions. The methodology is applied in two different fields of application within engineering geodesy: In the first scenario, the offset and linear drift of a noisy accelerometer are estimated based on a Gauss-Markov model with VAR and multivariate t-distributed errors, as a special case of the proposed GHM. In the second scenario real laser tracker measurements with outliers are adjusted to estimate the parameters of a sphere employing the proposed GHM with VAR and multivariate t-distributed errors. For both scenarios the estimated parameters of the fitted VAR model and multivariate t-distribution are analyzed for evidence of auto- or cross-correlations and deviation from a normal distribution regarding the measurement noise.


1980 ◽  
Vol 13 (2) ◽  
pp. 281-285 ◽  
Author(s):  
A. A. Aleksandrova ◽  
T. N. Smirnova

2021 ◽  
pp. 1-5
Author(s):  
Max A. Little

Parkinson’s disease is a complex and heterogeneous condition, and there are many gaps in the medical community’s scientific and practical understanding of the disease. Closing these gaps relies on objective data about symptoms and signs, collected over long durations. Smartphones contain sensor devices which can be used to remotely capture behavioral signals. From these signals, computational algorithms can distill metrics of symptom severity and progression. This brief review introduces the main concepts of the discipline, addressing the experimental, hardware and software logistics, and computational analysis. The article finishes with an exploration of future prospects for the technology.


2010 ◽  
Vol 21 (12) ◽  
pp. 1976-1984 ◽  
Author(s):  
Zhi Min Wang ◽  
Qing Song ◽  
Yeng Chai Soh ◽  
Kang Sim

Sign in / Sign up

Export Citation Format

Share Document