Efficient Statistical Model Research Articles

A simplified non-linear chemistry transport model for analyzing NO2 column observations: STILT–NOx

Abstract. Satellites monitoring air pollutants (e.g., nitrogen oxides; NOx = NO + NO2) or greenhouse gases (GHGs) are widely utilized to understand the spatiotemporal variability in and evolution of emission characteristics, chemical transformations, and atmospheric transport over anthropogenic hotspots. Recently, the joint use of space-based long-lived GHGs (e.g., carbon dioxide; CO2) and short-lived pollutants has made it possible to improve our understanding of emission characteristics. Some previous studies, however, lack consideration of the non-linear NOx chemistry or complex atmospheric transport. Considering the increase in satellite data volume and the demand for emission monitoring at higher spatiotemporal scales, it is crucial to construct a local-scale emission optimization system that can handle both long-lived GHGs and short-lived pollutants in a coupled and effective manner. This need motivates us to develop a Lagrangian chemical transport model that accounts for NOx chemistry and fine-scale atmospheric transport (STILT–NOx) and to investigate how physical and chemical processes, anthropogenic emissions, and background may affect the interpretation of tropospheric NO2 columns (tNO2). Interpreting emission signals from tNO2 commonly involves either an efficient statistical model or a sophisticated chemical transport model. To balance computational expenses and chemical complexity, we describe a simplified representation of the NOx chemistry that bypasses an explicit solution of individual chemical reactions while preserving the essential non-linearity that links NOx emissions to its concentrations. This NOx chemical parameterization is then incorporated into an existing Lagrangian modeling framework that is widely applied in the GHG community. We further quantify uncertainties associated with the wind field and chemical parameterization and evaluate modeled columns against retrieved columns from the TROPOspheric Monitoring Instrument (TROPOMI v2.1). Specifically, simulations with alternative model configurations of emissions, meteorology, chemistry, and inter-parcel mixing are carried out over three United States (US) power plants and two urban areas across seasons. Using the U.S. Environmental Protection Agency (EPA)-reported emissions for power plants with non-linear NOx chemistry improves the model–data alignment in tNO2 (a high bias of ≤ 10 % on an annual basis), compared to simulations using either the Emissions Database for Global Atmospheric Research (EDGAR) model or without chemistry (bias approaching 100 %). The largest model–data mismatches are associated with substantial biases in wind directions or conditions of slower atmospheric mixing and photochemistry. More importantly, our model development illustrates (1) how NOx chemistry affects the relationship between NOx and CO2 in terms of the spatial and seasonal variability and (2) how assimilating tNO2 can quantify systematic biases in modeled wind directions and emission distribution in prior inventories of NOx and CO2, which laid a foundation for a local-scale multi-tracer emission optimization system.

Novel Approach to Robust Concept Development for Offshore Floating Systems

This paper describes a new approach to the application of robust design optimisation to the development and selection of floating systems during concept and early-stage engineering. The basis of the approach is to combine a genetic algorithm with an efficient non-intrusive statistical model to allow both uncertainties in modelling (intrinsic uncertainty) and requirements (extrinsic uncertainty) to be accounted for within a Robust Design Framework that directs optimisation toward unique design solutions. A particular interpretation of the Pareto design objective space enables required levels of performance margin and meaningful measures of confidence in design objectives to be achieved. The approach can be used to provide a systematic series of optimal hull geometries (geosims) that meet the most likely variations in design requirements, and so mitigate the impact of change early in the design cycle. This paper follows on from and earlier publication (IJME648) on multi-objective, multi-discipline, optimisation and uses the same case study.

Subthreshold Delay Variation Model Considering Transitional Region for Input Slew

Subthreshold design provides the promising advantage of low power consumption at the cost of performance variation and even circuit failure. An accurate and efficient statistical timing model is crucial for timing analysis and performance optimization guidance. Prior works lack the consideration of the impact of slew time or the transitional region for input slew due to process variation and efficient approaches considering the impact of load capacitance and multiple process variations in complex gates, resulting in accuracy loss. In this work, an accurate end efficient gate delay variation model is analytically derived for various input slews and load capacitances. The transitional region between fast and slow input slew is efficiently partitioned with an adaptive error tolerance method so as to characterize timing variation by linear interpolation based on that for fast and slow input slew. In order to consider the impact of load capacitance, the relation between the sensitivity of step delay and the dominant threshold voltage variation is analytically derived. For complex gates, the multiple process variations for both parallel and stacking structures are equivalently expressed by threshold voltage variation from each transistor. The proposed model has been validated under advanced TSMC (Taiwan Semiconductor Manufacturing Company) 12 nm technology at subthreshold region and achieves excellent agreement with Monte Carlo SPICE (Simulation Program with Integrated Circuit Emphasis) simulation results with the max error less than 6.49% for standard deviation of gate delay and 4.63%/6.40% for max/min delay, demonstrating over 4 times precision improvement compared with competitive analytical models.

A Methodology for the Efficient Quantification of Parameter and Model Uncertainty

Abstract Complex structural systems often entail computationally intensive models that require efficient methods for statistical model calibration due to the high number of required model evaluations. In this paper, we present a Bayesian inference-based methodology for efficient statistical model calibration that builds upon the combination of the speed in the computation of a low-fidelity model with the accuracy of the computationally intensive high-fidelity model. The proposed two-stage method incorporates the adaptive Metropolis algorithm and a Gaussian process (GP)-based adaptive surrogate model as a low-fidelity model. In order to account for model uncertainty, we incorporate a GP-based discrepancy function into the model calibration. By calibrating the hyperparameters of the discrepancy function alongside the model parameters, we prevent the results of the model calibration to be biased. The methodology is illustrated by the statistical model calibration of a damping parameter in the modular active spring-damper system, a structural system developed within the collaborative research center SFB 805 at the Technical University of Darmstadt. The reduction of parameter and model uncertainty achieved by the application of our methodology is quantified and illustrated by assessing the predictive capability of the mathematical model of the modular active spring-damper system.

Radar cross section statistical characteristics of stealth aircraft using the Weibull‐generalized gamma mixture model

AbstractTo analyze the electromagnetic scattering characteristics of stealth targets, radar cross section (RCS) values of the typical stealth aircraft model are evaluated by electromagnetic simulation. Based on the RCS electromagnetic simulation results, RCS statistical histograms of the stealth aircraft model are created. For describing the RCS statistical characteristics of stealth aircrafts, a Weibull‐generalized gamma mixture distribution model is proposed in this study. Some special cases of the Weibull‐generalized gamma mixture distribution model are summarized. Utilizing the nonlinear least squares technique, fitting results of the proposed and conventional RCS distribution models for the RCS statistical characteristics of typical stealth aircarfts are compared. Mean square error test and R‐square () test results show that the proposed distribution model obtains better fitting results than the conventional RCS distribution models, which indicates that the proposed distribution model is a more efficient RCS statistical model.

Statistical insights into the water exchange process in the Yangtze-Poyang System: The YPWES model

Study RegionThe Yangtze-Poyang river-lake system (YPRLS) which includes the Poyang Lake, and the middle reach of Yangtze River basin. Study FocusThe water exchange in the YPRLS is complex and vital to the dynamic of it, thereby requiring well simulation. Nevertheless, existing numerical models have shortages in accuracy, efficiency and revealing potential relationships. Thus, for providing an accurate and efficient statistical model as a fundamental tool for investigating the effects of changing environment on the YPRLS, we developed the Yangtze-Poyang water exchange statistic (YPWES) model. In this study, the YPWES model was employed to simulate the water exchange in the YPRLS from 1971 to 2016 and improve our understanding of the backflow from the river to lake (BRL) in the YPRLS.New Hydrological Insights for the Region: Based on a physic-based lumped framework, the established YPWES model is basically more accurate and efficient than nine existing models. Meanwhile, 93% of the BRL event will occur when the value of discharge identification function (DIF) is 9.2–10.0 m, while the threshold range of the DIF corresponding to the BRL event occurrence was smaller after 2003 because the discharge-stage relationship changes with the Yangtze River streamflow when the BRL event occurs. Our work provides a valuable model and may help to investigate the cause and influence of the water exchange in the YPRLS.

An embedded element based 2D finite element model for the strength prediction of mineralized collagen fibril using Monte-Carlo type of simulations

A computationally efficient statistical model for the prediction of the strength of mineralized collagen fibril (a basic building block of bone) is presented by taking into account the uncertainties associated with the geometrical and material parameters of collagen and mineral phases. The mineral plates have been considered as one-dimensional bar elements embedded in the two-dimensional plane stress collagen matrix. The mineral phase is considered as linear elastic and a hyperelastic material model is adopted for the collagen phase. Further, the crack initiation and propagation in the collagen phase have been modeled using a damage plasticity approach. Different realizations of the arrangement of mineral plates have been generated to account for the associated geometrical uncertainties using an in-house MATLAB® code. Monte-Carlo type simulations have been performed on the different realizations of mineralized collagen fibril to predict its characteristic stress-strain response under tensile load. The characteristic strength of 3.64 GPa is obtained for mineralized collagen fibril using Weibull’s analysis which is found to be in agreement with the molecular dynamics simulation data and numerical studies reported in the past. A parameter sensitivity analysis concluded that mineral modulus has a significant effect on the overall tangent modulus of mineralized collagen fibril in large strain regime.

An efficient statistical model checker for nondeterminism and rare events

Statistical model checking avoids the state space explosion problem in verification and naturally supports complex non-Markovian formalisms. Yet as a simulation-based approach, its runtime becomes excessive in the presence of rare events, and it cannot soundly analyse nondeterministic models. In this article, we present modes: a statistical model checker that combines fully automated importance splitting to estimate the probabilities of rare events with smart lightweight scheduler sampling to approximate optimal schedulers in nondeterministic models. As part of the Modest Toolset, it supports a variety of input formalisms natively and via the Jani exchange format. A modular software architecture allows its various features to be flexibly combined. We highlight its capabilities using experiments across multi-core and distributed setups on three case studies and report on an extensive performance comparison with three current statistical model checkers.

Industrial issues and solutions to statistical model improvement: a case study of an automobile steering column

Statistical model improvement consists of model calibration, validation, and refinement techniques. It aims to increase the accuracy of computational models. Although engineers in industrial fields are expanding the use of computational models in the process of product development, many field engineers still hesitate to perform statistical model improvement due to its practical aspects. Therefore, this paper describes research aimed at addressing three practical issues that hinder statistical model improvement in industrial fields: (1) lack of experimental data for quantifying uncertainties of true responses, (2) numerical input variables for propagating uncertainties of the computational model, and (3) model form uncertainties in the computational model. Issues 1 and 2 deal with difficulties in uncertainty quantification of experimental and computational responses. Issue 3 focuses on model form uncertainties, which are due to the excessive simplification of computational modeling; simplification is employed to reduce the calculation cost. Furthermore, the paper outlines solutions to address these three issues, specifically: (1) kernel density estimation with estimated bounded data, (2–1) variance-based variable screening, (2–2) surrogate modeling, and (3) a model refinement approach. By examining the computational model of an automobile steering column, these techniques are shown to demonstrate efficient statistical model improvement. This case study shows that the suggested approaches can actively reduce the burden in statistical model improvement and increase the accuracy of computational modeling, thereby encouraging its use in industry.

An aggregated statistical approach for network flood detection using Gamma-Normal mixture modeling

In this paper, we propose a fast statistical anomaly detector at the aggregated-level for two types of anomalies: floods and flash crowds. The performance of the statistical anomaly detectors is significantly dependent on the accuracy of statistical modeling. Thus, we initially introduce a new efficient statistical model for the network traffic called Gamma Normal mixture (GNM). We study the compatibility of GNM and network traffic using different tests. Consequently, we design a novel anomaly detector based on using the generalized likelihood ratio test (GLRT) and GNM. Moreover, to more accurately determine the position of the anomalies, overlapped sliding windows have been applied in the aggregation step. To evaluate the performance of the proposed anomaly detector, we use receiver operating characteristics (ROC). Experimental results under public network traces, confirm the high efficiency of the proposed method. Also, the comparison of the proposed anomaly detector with its nearest competitor verifies the higher performance and lower computational load in utilizing the new strategy.

The Best Three Years of Your Life: A Prediction for Three-Year Graduation

The 3-year graduation rate is a rarely measured metric in higher education compared to its 4- or 6- year graduation rate counterparts. For the first time in college (FTIC) students to graduate in three years, they must come with certain skills, abilities, plans, supports, or motivations. This project considers two distinct but interrelated ways of using advanced and novel statistical models, the Log-linear Cognitive Diagnostic Model (LCDM) and the Logistic Regression model (LR), to look at both students’ ability to graduate in three years and the characteristics that contribute to this ability. The results indicate that the LCDM is a reliable and efficient statistical model that can provide accurate prediction of students’ ability to graduate early. In addition, student enrolled credit hours in the semester, transfer credit hours, student high school GPA, and student socioeconomic status (EFC) were statistically significant predictors contributing to three-year graduation. The significant interaction between students’ EFC status and transfer credit hours has a meaningfully practical impact on enrollment strategies and institutional policies. Future studies could use the same LCDM model to consider the degree to which these or other characteristics contribute to 4-, 5-, and 6-year graduation rates. Identification of these characteristics could have a policy, student support, and admissions implications. Additionally, the success of the LCDM model in predicting ability could be used for abilities unrelated to graduation, including the ability to pay off loans, succeed in an internship, or give back financially to a university.

Global Warming Prediction in India using Machine Learning

Long term global warming prediction can be of major importance in various sectors like climate related studies, agricultural, energy, medical and many more. This paper evaluates the performance of several Machine Learning algorithm (Linear Regression, Multi-Regression tree, Support Vector Regression (SVR), lasso) in problem of annual global warming prediction, from previous measured values over India. The first challenge dwells on creating a reliable, efficient statistical reliable data model on large data set and accurately capture relationship between average annual temperature and potential factors such as concentration of carbon dioxide, methane, nitrous oxide. The data is predicted and forecasted by linear regression because it is obtaining the highest accuracy for greenhouse gases and temperature among all the technologies which can be used. It was also found that CO2 is the plays the role of major contributor temperature change, followed by CH4, then by N20. After seeing the analysed and predicted data of the greenhouse gases and temperature, the global warming can be reduced comparatively within few years. The reduction of global temperature can help the whole world because not only human but also different animals are suffering from the global temperature.

Introducing an Efficient Statistical Model for Automatic Modulation Classification

Nowadays, Automatic Modulation Classification (AMC) plays an important role in many applications of cooperative and non-cooperative communication such as spectrum management, cognitive radio, intelligent modems, and interference identification. In this paper, a new robust AMC algorithm based on Generalized Autoregressive Conditional Heteroscedasticity (GARCH) model is proposed. Primarily, multi-level wavelet transform is applied on the received data samples. To select the efficient statistical model for wavelet coefficient description, the statistical characteristics of these coefficients are surveyed. The proposed analysis precisely illustrates that these coefficients have heteroscedasticity property which has not been mentioned before. Subsequently, to describe the wavelet coefficients, the heteroscedastic GARCH model is employed and its parameters are extracted as the features. Finally, the obtained features are applied to support vector machine (SVM) classifier to simultaneously determine the modulation type and constellation size. Eleven different types and sizes of the digital modulation schemes in various channels such as AWGN, flat fading and multipath fading in presence of common channel impairments are examined. The experimental results reveal the superior performance of the proposed method in comparison with the previously introduced approaches.

Saving energy by anticipating hot water production: identification of key points for an efficient statistical model integration

AbstractThis work aims to evaluate the energy savings that can be achieved in domestic hot water (DHW) production using consumption forecasting through statistical modeling. It uses our forecast algorithm and aims at investigating how it can improve energy efficiency depending on the system configuration. Especially, the influence of the DHW production type used is evaluated as well as the water tank insulation. To that end, real consumption measurements are used for model training. Then simulations are run on using TRNSYS software to compute the total energy consumption of DHW production systems over 1 year. Simulations are also based on real consumption measurements for realistic results. To appraise the energy savings, we compared simulations that consider either no forecast (reactive control), perfect forecast (to estimate the control ability to consider forecast), or the forecast provided by our algorithm. The measurements and simulations are run on 26 different but real dwellings to assess results variability. Several system configurations are also compared with varying thermal insulation indices for a complete benchmark of the approach so that an overall performance of the system and the anticipation strategy could be evaluated.

Model selection and application to high-dimensional count data clustering

EDCM, the Exponential-family approximation to the Dirichlet Compound Multinomial (DCM), proposed by Elkan (2006), is an efficient statistical model for high-dimensional and sparse count data. EDCM models take into account the burstiness phenomenon correctly while being many times faster than DCM. This work proposes the use of Minimum Message Length (MML) criterion for determining the number of components that best describes the data with a finite EDCM mixture model. Parameters estimation is based on the previously proposed Deterministic Annealing Expectation-Maximization (DAEM) approach. The validation of the proposed unsupervised algorithm involves different real applications: text document modeling, topic novelty detection and hierarchical image clustering. A comparison with results obtained for other information-theory based selection criteria is provided.

Evaluation of surface roughness during turning of Al-SiC and Al-SiC-Gr composites

Purpose In the current scenario, new materials are gaining popularity due to higher specific properties of strength and stiffness, increase in wear resistance, dimensional stability at higher temperature, etc. Subsequently, the need for precise machining has also been increased enormously. The purpose of this paper is to study the surface roughness during the turning of Al-10%SiC and Al-5%SiC-5%Gr composites under different cutting conditions. Design/methodology/approach Artificial neural network (ANN) has been effectively employed in solving problems with effortless computation in the areas such as fault diagnosis, process identification, property estimation, data smoothing and error filtering, product design and development, optimisation and estimation of activity coefficients. Response surface method is also used to analyse the problems involving a number of input parameters and their corresponding relationship between one or more measured dependent responses. Using Design Expert.8 evaluation software package, a simpler and more efficient statistical RSM model has been designed. RSM models are created by using 27 experimental data measurements obtained from different turning conditions of aluminium alloy composites. Findings In this work, the surface roughness during turning of Al-10%SiC and Al-5%SiC-5%Gr composites under different cutting conditions has been studied. The surface roughness value is proportional with the increase in feed rate and depth of cut while inversely proportional with the cutting speed. In all turning conditions, Al-10%SiC composite has lower surface roughness values than Al-5%SiC-5%Gr hybrid composite. An ANN and response surface models have been developed to predict the surface roughness of machined surface. The experimental results concur well with predicted models. Originality/value In the present trend, new materials are gaining popularity due to higher specific properties of strength and stiffness, increase in wear resistance, dimensional stability at higher temperature, etc. Subsequently, the need for precise machining has also been increased enormously. In this work, the surface roughness during turning of Al-10%SiC and Al-5%SiC-5%Gr composites under different cutting conditions has been studied.

An efficient Riemannian statistical shape model using differential coordinates: With application to the classification of data from the Osteoarthritis Initiative.

We propose a novel Riemannian framework for statistical analysis of shapes that is able to account for the nonlinearity in shape variation. By adopting a physical perspective, we introduce a differential representation that puts the local geometric variability into focus. We model these differential coordinates as elements of a Lie group thereby endowing our shape space with a non-Euclidean structure. A key advantage of our framework is that statistics in a manifold shape space becomes numerically tractable improving performance by several orders of magnitude over state-of-the-art. We show that our Riemannian model is well suited for the identification of intra-population variability as well as inter-population differences. In particular, we demonstrate the superiority of the proposed model in experiments on specificity and generalization ability. We further derive a statistical shape descriptor that outperforms the standard Euclidean approach in terms of shape-based classification of morphological disorders.

Linear Regression Analysis of Title Word Count and Article Time Cited using R

There is a common idea, that title variables like article title length would influence article citations. The aim of the present study was to investigating possible relationship between size of article title and number of article citations by minimizing scientometric variable biases. A dataset containing ~100,000 virological literatures was obtained from Web of Science InCiteTM database from 1997 to 2016. Variables, Title size (TWC), Year (YoP), Source (JS), and Publisher were selected. In addition number of times article is cited ‘Time Cited’ (TC) was retrieved from Web of Science InCiteTM. Linear regression analysis was performed between variables and TC using R for a possible prediction model for TC. Result has shown a robust standard error corrected linear regression with only 30.6% power of predictability. Furthermore, it was found that TC, YoP, and JS have meaningful potential in the linear model. Moreover, TC is negatively correlated with YoP, JS, and positively with TWC. As a result, size of article title, years passed since publication and the journal in which article accepted are good but not sufficient predictor of article citations. In addition, article is a multi-characteristic subject and other predictors can be supposed. However, we think that finding an efficient statistical linear predication model for TC, by increase of articles citation, is overwhelming.

Cyclic spectral analysis of electrocardiogram signals based on GARCH model

Abstract In this paper, the capability of Cyclic Spectral Density (CSD) is evaluated for ECG signal analyzing and a new feature generation method for them is presented. Although, the CSD presents a second-order statistical description in the frequency domain and reveals the hidden periodicity in EEG signals, it needs an efficient algorithm for calculating and also a suitable model for describing. By employing an efficient computational algorithm which is called the FFT accumulation method (FAM), the CSD of ECG signals can be computed. In this study, In order to choose an efficient statistical model for the Cyclic Spectral Analysis (CSA) coefficients of ECG signals, their statistical features are investigated at various regions of bi-frequency plane. It is revealed that the CSA coefficients are heteroscedastic and the Generalized Autoregressive Conditional Heteroscedasticity (GARCH) is a suitable model for them. Hence, The GARCH parameters of CSA sub-bands are calculated and are employed to classify the ECG using a support vector machine (SVM) classifier. Evidently, the results reveal that the performance of the new method in ECG classification outperforms the former studies.

Penalized weighted low-rank approximation for robust recovery of recurrent copy number variations.

BackgroundCopy number variation (CNV) analysis has become one of the most important research areas for understanding complex disease. With increasing resolution of array-based comparative genomic hybridization (aCGH) arrays, more and more raw copy number data are collected for multiple arrays. It is natural to realize the co-existence of both recurrent and individual-specific CNVs, together with the possible data contamination during the data generation process. Therefore, there is a great need for an efficient and robust statistical model for simultaneous recovery of both recurrent and individual-specific CNVs.ResultWe develop a penalized weighted low-rank approximation method (WPLA) for robust recovery of recurrent CNVs. In particular, we formulate multiple aCGH arrays into a realization of a hidden low-rank matrix with some random noises and let an additional weight matrix account for those individual-specific effects. Thus, we do not restrict the random noise to be normally distributed, or even homogeneous. We show its performance through three real datasets and twelve synthetic datasets from different types of recurrent CNV regions associated with either normal random errors or heavily contaminated errors.ConclusionOur numerical experiments have demonstrated that the WPLA can successfully recover the recurrent CNV patterns from raw data under different scenarios. Compared with two other recent methods, it performs the best regarding its ability to simultaneously detect both recurrent and individual-specific CNVs under normal random errors. More importantly, the WPLA is the only method which can effectively recover the recurrent CNVs region when the data is heavily contaminated.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-015-0835-2) contains supplementary material, which is available to authorized users.