Fit To Data Sets Research Articles

A Fitting Recognition Approach Combining Depth-Attention YOLOv5 and Prior Synthetic Dataset

To address power transmission lines (PTLs) traveling through complex environments leading to misdetections and omissions in fitting recognition using cameras, we propose a fitting recognition approach combining depth-attention YOLOv5 and prior synthetic dataset to improve the validity of fitting recognition. First, datasets with inspection features are automatically synthesized based on prior series data, achieving better results with a smaller data volume for the deep learning model and reducing the cost of obtaining fitting datasets. Next, a unique data collection mode is proposed using a developed flying-walking power transmission line inspection robot (FPTLIR) as the acquisition platform. The obtained image data in this collection mode has obvious time-space, stability, and depth difference, fusing the two data types in the deep learning model to improve the accuracy. Finally, a depth-attention mechanism is proposed to change the attention on the images with depth information, reducing the probability of model misdetection and omission. Test field experiments results show that compared with YOLOv5, the mAP5095 (mean average precision on step size 0.05 for thresholds from 0.5 to 0.95) of our depth-attention YOLOv5 model for fitting is 68.1%, the recall is 98.3%, and the precision is 98.3%. Among them, AP, recall, and precision increased by 5.2%, 4.8%, and 4.1%, respectively. Test field experiments verify the feasibility of the depth-attention YOLOv5. Line field experiments results show that the mAP5095 of our depth-attention YOLOv5 model for fittings is 64.6%, and the mAPs of each class are improved compared with other attention mechanisms. The inference speed of depth-attention YOLOv5 is 3 ms slower than the standard YOLOv5 model and 10 ms to 15 ms faster than other attention mechanisms, verifying the validity of the depth-attention YOLOv5. The proposed approach improves the accuracy of the fitting recognition on PTLs, providing a recognition and localization basis for the automation and intelligence of inspection robots.

Simple statistical models can be sufficient for testing hypotheses with population time-series data.

Time‐series data offer wide‐ranging opportunities to test hypotheses about the physical and biological factors that influence species abundances. Although sophisticated models have been developed and applied to analyze abundance time series, they require information about species detectability that is often unavailable. We propose that in many cases, simpler models are adequate for testing hypotheses. We consider three relatively simple regression models for time series, using simulated and empirical (fish and mammal) datasets. Model A is a conventional generalized linear model of abundance, model B adds a temporal autoregressive term, and model C uses an estimate of population growth rate as a response variable, with the option of including a term for density dependence. All models can be fit using Bayesian and non‐Bayesian methods. Simulation results demonstrated that model C tended to have greater support for long‐lived, lower‐fecundity organisms (K life‐history strategists), while model A, the simplest, tended to be supported for shorter‐lived, high‐fecundity organisms (r life‐history strategists). Analysis of real‐world fish and mammal datasets found that models A, B, and C each enjoyed support for at least some species, but sometimes yielded different insights. In particular, model C indicated effects of predictor variables that were not evident in analyses with models A and B. Bayesian and frequentist models yielded similar parameter estimates and performance. We conclude that relatively simple models are useful for testing hypotheses about the factors that influence abundance in time‐series data, and can be appropriate choices for datasets that lack the information needed to fit more complicated models. When feasible, we advise fitting datasets with multiple models because they can provide complementary information.

Theory and Applications of the Transmuted Continuous Bernoulli Distribution

Modern applied statistics naturally give rise to the continuous Bernoulli distribution (data fitting, deep learning, computer vision, etc). On the mathematical side, it can be viewed as a one-parameter distribution corresponding to a special exponential distribution restricted to the unit interval. As a matter of fact, manageable extensions of this distribution have great potential in the same fields. In this study, we motivate a transmuted version of the continuous Bernoulli distribution with the goal of analyzing proportional data sets. The feature of the created transmuted continuous Bernoulli distribution is an additional parameter that realizes a linear tradeoff between the min and max of two continuous random variables with the continuous Bernoulli distribution. The standard study process is respected: we derive some mathematical properties of the proposed distribution and adopt the maximum likelihood estimation technique in estimating the unknown parameters involved. A Monte Carlo simulation exercise was conducted to examine and confirm the asymptotic behavior of the obtained estimates. In order to show the applicability of the proposed distribution, three proportional data sets are analyzed and the results obtained are compared with competitive distributions. Empirical findings reveal that the transmuted continuous Bernoulli distribution promises more flexibility in fitting proportional data sets than its competitors.

Joint estimation of biogeochemical model parameters from multiple experiments: A bayesian approach applied to mercury methylation

To characterize complex biogeochemical systems, results from multiple experiments, where each targets a specific subprocess, are commonly combined. The resulting datasets are interpreted through the calibration of biogeochemical models for process inference and predictions. Commonly used calibration approaches of fitting datasets from individual experiments to subprocess models one at a time is prone to missing information shared between datasets and incomplete uncertainty propagation. We propose a Bayesian joint-fitting scheme addressing the above-mentioned concerns by jointly fitting all the available datasets, thus calibrating the entire biogeochemical model in one go using Markov Chain Monte Carlo (MCMC). The identification of null spaces in the parameter distributions from MCMC guided the simplification of certain subprocess models. For example, fast kinetic sorption was replaced by equilibrium sorption, and Monod demethylation was replaced by first-order demethylation. Joint fitting of datasets resulted in complete uncertainty propagation with parameter estimates informed by all available data.

Beware of scaling artefacts and implicit model characteristics when fitting soil water release and moisture capacity data

The primary objectives of this study were to: ( i) elucidate the impacts of nonlinear scale transformations on the shapes and parameter values of soil water release and moisture capacity curves; and ( ii) demonstrate how implicit characteristics of some established soil water release and moisture capacity models can impact model-data fits and estimates of model parameters. Nonlinear scale transformations of the tension head ( h) axis (e.g., log10 h, h1/2) were found to distort release and capacity curve shapes, create fictitious curve inflections and modes, and occasionally erase visual evidence of actual inflections and modes. The popular van Genuchten–Mualem and Assouline–Grant models were shown to always generate a release curve inflection and a capacity curve mode, even when inflections and modes did not exist in the data, and this in turn caused poor model-data fits in the critical near-saturated region. The van Genuchten model with four independently fitted parameters and the Dexter–Weibull model could accurately fit data sets with no inflection or mode, but this resulted in a physically unrealistic zero-angle intersection between the release curve and the water content axis. It was concluded that nonlinear h axis transforms should not be used when determining inflections, modes, pore size distributions, soil structure parameters, or soil quality indexes from soil water release and moisture capacity data-sets. It was also recommended that more flexible release curve models should be developed that do not assume the existence of inflections and modes, and also produce physically realistic angles of intersection between the water content axis and the fitted model.

Development of computational design for reliable prediction of dielectric strengths of perfluorocarbon compounds

The development of robust computational protocols capable of accurately predicting the dielectric strengths of eco-friendly insulating gas candidates is crucial; however, it lacks relevant efforts significantly. Consequently, a series of computational protocols are employed in this study to enable the computational prediction of polarizability and ionization energy of eco-friendly, perfluorinated carbon-based candidates, followed by the equation-based prediction of their dielectric strength. The validation process associated with the prediction of the afore-mentioned variables for selected datasets confirms the suitability of the B3LYP-based prediction protocol for reproducing experimental values. Subsequently, the validation of dielectric strength prediction outlines the following three conclusions. (1) The referenced equation adopted from a previous study is incapable of predicting the dielectric strengths of 137 organic compounds present in our database. (2) Parameterization of the coefficients in the referenced equation leads to the accurate prediction of the dielectric strengths. (3) Incorporation of a novel variable, viz. molecular weight, into the referenced equation combined with the parameterization of the coefficients leads to a robust protocol capable of predicting dielectric strengths with high efficiencies even with a significantly smaller fitting dataset. This implies the development of a comprehensive solution capable of accurately predicting the dielectric strengths of a substantially large dataset.

The Exponentiated Gumbel-Weibull {Logistic} Distribution with Application to Nigeria's COVID-19 Infections Data.

A new flexible univariate probability distribution was defined in this paper. The new distribution is so called the ‘exponentiated Gumbel–Weibull {logistic} distribution’ and it arose by using the exponentiated Gumbel distribution to generate a generalized Weibull distribution using the logit function or the quantile function of the logistic distribution as a link. The new distribution was observed to be both unimodal and bimodal as well as exhibits various shape and tail properties consistent with data arising from several real life phenomena. A detail study of its statistical properties was carried out and the maximum likelihood method was used in the estimation of its parameters. The new distribution was applied in fitting the reported daily number of infections due to the COVID-19 pandemic in Nigeria. Five other datasets were further used to ascertain the flexibility of the new distribution in fitting data sets with different statistical properties.

A novel extended model with versatile shaped failure rate: Statistical inference with Covid -19 applications

Statistical models perform an essential role in data analysis, and statisticians are constantly looking for novel or pretty recent statistical models to fit data sets across a broad variety of fields. In this study, we used modified Kies generalized transformation and the new power function to suggest an unique statistical model. We present and discuss a linear illustration of the density function. Theoretically, quantile function, characteristic function, stochastic ordering, mean, and moments are just a few of the structure properties we discuss. By defining an ideal statistical distribution for assessing the COVID-19 mortality rate, an attempt is performed to determine the model of COVID-19 spread in different nations like the United Kingdom and Italy. In some countries, the novel distribution have been shown to be more appropriate than existing competing models when fitted to COVID-19.

A novel extended Gumbel Type II model with statistical inference and Covid-19 applications

Statistical models play an important role in data analysis, and statisticians are constantly looking for new or relatively new statistical models to fit data sets across a wide range of fields. In this study, we used a new alpha power transformation and the Gumbel Type -II distribution to suggest an unique statistical model. The study contains a simulation analysis to determine the parameters’ efficiency. Two real-life data sets were utilized to demonstrate the use of novel alpha power Gumbel Type II (NAPGT-II) distribution. NAPGT-II distribution yields a better fit than Weibull, new alpha power exponential, exponentiated Gumbel Type-II, Gumbel Type-II and exponentiated generalized Gumbel Type-II distribution, as evidenced by the data.

Correlation of treatment time to target volume for GammaPod treatments: A simple second calculation.

PurposeThe GammaPod is a novel device for stereotactic breast treatments that employs 25 rotating Co‐60 sources while the patient is continuously translated in three axes to deliver a highly conformal dose to the target. There is no commercial software available for independent second calculations. The purpose of this study is to determine an efficient way to estimate GammaPod treatment times based on target volume and use it as a second calculation for patient‐specific quality assurance.MethodsFifty‐nine GammaPod (Xcision Medical Systems, LLC.) breast cancer patient treatments were used as the fitting dataset for this study. Similar to the Curie‐seconds concept in brachytherapy, we considered dose‐rate × time/(prescribed dose) as a function of target volumes. Using a MATLAB (Mathworks, Natick, MA, USA) script, we generated linear (with 95% confidence interval (CI)) and quadratic fits and tested the resulting equations on an additional set of 30 patients.ResultsWe found a strong correlation between the dose‐rate × time/(prescribed dose) and patients’ target volumes for both the linear and quadratic models. The linear fit was selected for use and using the polyval function in MATLAB, a 95% CI graph was created to depict the accuracy of the prediction for treatment times. Testing the model on 30 additional patients with target volumes ranging from 20 to 188 cc yielded treatment times from 10 to 25 min that in all cases were within the predicted CI. The average absolute difference between the predicted and actual treatment times was 1.0 min (range 0–3.3 min). The average percent difference was 5.8% (range 0%–18.4%).ConclusionThis work has resulted in a viable independent calculation for GammaPod treatment times. This method has been implemented as a spreadsheet that is ready for clinical use to predict and verify the accuracy of breast cancer treatment times.

PeerRank: Robust Learning to Rank With Peer Loss Over Noisy Labels

User-generated data are extensively utilized in learning to rank as they are easy to collect and up-to-date. However, the data inevitably contain noisy labels attributed to users’ annotation mistakes, lack of domain knowledge, system failure, etc., making building a robust model challenging. On account of the remarkable nature of deep neural networks in fitting datasets, the noisy labels significantly degrade the performance of learning-to-rank algorithms. To cope with this problem, previous studies have put forward several methods for label de-noising. However, they are either susceptible to the noise distribution on datasets, raising the demand for clean data or incurring more computational costs. Moreover, most of them are tough to extend to different scenarios. This paper proposes a simple yet effective framework named PeerRank that can be applied in broad applications such as click-through rate prediction and commercial web search in learning-to-rank tasks. PeerRank is a robust, effective, and adaptable framework that can couple with numerous models with theoretical guarantees. Extensive experiments on three public real-world datasets with thirteen point-wise base models and four semi-synthetic generation datasets with four pair-wise base models show the consistent improvement of PeerRank. The results comparing PeerRank with seven classic and state-of-the-art de-noising methods validate the advantages of PeerRank framework for learning to rank over noisy labels.

Locational Marginal Price Forecasting Using SVR-Based Multi-Output Regression in Electricity Markets

Electricity markets provide valuable data for regulators, operators, and investors. The use of machine learning methods for electricity market data could provide new insights about the market, and this information could be used for decision-making. This paper proposes a tool based on multi-output regression method using support vector machines (SVR) for LMP forecasting. The input corresponds to the active power load of each bus, in this case obtained through Monte Carlo simulations, in order to forecast LMPs. The LMPs provide market signals for investors and regulators. The results showed the high performance of the proposed model, since the average prediction error for fitting and testing datasets of the proposed method on the dataset was less than 1%. This provides insights into the application of machine learning method for electricity markets given the context of uncertainty and volatility for either real-time and ahead markets.

Covariance Generalized Linear Models: An Approach for Quantifying Uncertainty in Tree Stem Taper Modeling

Abstract A natural dependence among diameters measured within-tree is expected in taper data due to the hierarchical structure. The aim of this paper was to introduce the covariance generalized linear model (CGLM) framework in the context of forest biometrics for Pinus taeda stem form modeling. The CGLMs are based on marginal specification, which requires a definition of the mean and covariance components. The tree stem mean profiles were modeled by a nonlinear segmented model. The covariance matrix was built considering four strategies of linear combinations of known matrices, which expressed the variance or correlations among observations. The first strategy modeled only the variance of the diameters over the stem as a function of covariates, the second modeled correlation among observations, the third was defined based on a random walk model, the fourth was based on a structure similar to a mixed-effect model with a marginal specification, and the fourth was a traditional mixed-effect model. Mean squared error and bias showed that the approaches were similar for describing the mean profile for fitting and validation dataset. However, uncertainties expressed by confidence intervals of the relative diameters were significant and related to the matrix covariance structures of the CGLMs.

The Skewed-Elliptical Log-Linear Birnbaum–Saunders Alpha-Power Model

In this paper, the skew-elliptical sinh-alpha-power distribution is developed as a natural follow-up to the skew-elliptical log-linear Birnbaum–Saunders alpha-power distribution, previously studied in the literature. Special cases include the ordinary log-linear Birnbaum–Saunders and skewed log-linear Birnbaum–Saunders distributions. As shown, it is able to surpass the ordinary sinh-normal models when fitting data sets with high (above the expected with the sinh-normal) degrees of asymmetry. Maximum likelihood estimation is developed with the inverse of the observed information matrix used for standard error estimation. Large sample properties of the maximum likelihood estimators such as consistency and asymptotic normality are established. An application is reported for the data set previously analyzed in the literature, where performance of the new distribution is shown when compared with other proposed alternative models.

Heavy-Tailed Log-Logistic Distribution: Properties, Risk Measures and Applications

Heavy tailed distributions have a big role in studying risk data sets. Statisticians in many cases search and try to find new or relatively new statistical models to fit data sets in different fields. This article introduced a relatively new heavy-tailed statistical model by using alpha power transformation and exponentiated log-logistic distribution which called alpha power exponentiated log-logistic distribution. Its statistical properties were derived mathematically such as moments, moment generating function, quantile function, entropy, inequality curves and order statistics. Five estimation methods were introduced mathematically and the behaviour of the proposed model parameters was checked by randomly generated data sets and these estimation methods. Also, some actuarial measures were deduced mathematically such as value at risk, tail value at risk, tail variance and tail variance premium. Numerical values for these measures were performed and proved that the proposed distribution has a heavier tail than others compared models. Finally, three real data sets from different fields were used to show how these proposed models fitting these data sets than other many wells known and related models.

Optimization of fitness data monitoring system based on Internet of Things and cloud computing

In the service dimension, the construction of fitness science data supervision service mode is discussed. Based on the stakeholder theory, through the statistical analysis of the stakeholders of fitness science data supervision, three core stakeholders of the government, users and data service personnel are identified. Based on these three dimensions, we find out the core concepts of government policy model, user demand model and service model. At the same time, each dimension is deeply analyzed. Through the relationship analysis between these three dimensions, the user-oriented collaborative supervision service model of fitness scientific data is expected to guide the specific service practice of fitness scientific data supervision through the establishment of this model. In addition, an unsupervised learning method in machine learning, the isolation forest algorithm, is introduced to detect abnormal data; at the same time, using real fitness data sets, through comparative experiments with local anomaly factor algorithms, it is verified that the isolation forest algorithm has a good effect of anomaly detection; this article also uses redis cache to optimize the performance of the fitness data monitoring system, which solves the access pressure of the main database in a multi-user high-concurrency environment; Finally, the usability and stability of the system are verified by functional tests and stress tests.

ParaMol: A Package for Automatic Parameterization of Molecular Mechanics Force Fields.

The ensemble of structures generated by molecular mechanics (MM) simulations is determined by the functional form of the force field employed and its parameterization. For a given functional form, the quality of the parameterization is crucial and will determine how accurately we can compute observable properties from simulations. While accurate force field parameterizations are available for biomolecules, such as proteins or DNA, the parameterization of new molecules, such as drug candidates, is particularly challenging as these may involve functional groups and interactions for which accurate parameters may not be available. Here, in an effort to address this problem, we present ParaMol, a Python package that has a special focus on the parameterization of bonded and nonbonded terms of druglike molecules by fitting to ab initio data. We demonstrate the software by deriving bonded terms' parameters of three widely known drug molecules, viz. aspirin, caffeine, and a norfloxacin analogue, for which we show that, within the constraints of the functional form, the methodologies implemented in ParaMol are able to derive near-ideal parameters. Additionally, we illustrate the best practices to follow when employing specific parameterization routes. We also determine the sensitivity of different fitting data sets, such as relaxed dihedral scans and configurational ensembles, to the parameterization procedure, and discuss the features of the various weighting methods available to weight configurations. Owing to ParaMol's capabilities, we propose that this software can be introduced as a routine step in the protocol normally employed to parameterize druglike molecules for MM simulations.

New Topp Leone-G Family with Mathematical Properties and Applications

In the last few years, the Topp-Leone-G family has been regarded with various statistical applications. In this paper, efforts have been made to introduce a new family of distribution as an alternative to Topp-Leone-G distribution through a useful transformation with flexible hazard rate and greater reliability which we call new Topp-Leone-G (NTL-G) distribution. Some new special models and some statistical properties such as, expansions, probability weighted moments, moments and Rényi entropy are provided. The maximum likelihood method is used for estimating the model parameters. For the applied side, new models can be created in view of fitting data set. This last point is illustrated by consideration of the exponential distribution as baseline. A real data set is employed which represent the observations of ordered failure of some components. The obtained results show that, the NTL-G family is very competitive in comparison to other well implanted general families.

Fitting Method of Optimal Energy-Running Time Curve Based on Train Operation Data of an Urban Rail Section

Due to the complexity of the operation control of urban rail transit and diversity requirements for section running time standards, based on actual train operation data, this paper proposes a curve fitting method to find the interrelation between running time and energy consumption. According to features of the energy consumption-running time curve, the discriminant criterion of outliers is constructed to select the candidate fitting data set from the original data set. To fit the energy consumption-running time curve from two-dimensional scatter points, we propose a B-spline curve fitting method based on a genetic algorithm and the fitting method is proven to have high fitting accuracy and convergence speed. Furthermore, we propose an optimization method for the fitting curve based on dynamic adjustment of the fitting data set which is selected from the candidate fitting data set to obtain the optimal energy-running time curve. The validation of Guangzhou Metro's actual operation data shows that the energy-running time curve fitted and optimized by our method has lower energy and better continuity and smoothness and could be used for evaluation of train drivers’ performance and energy consumption of train operation diagram.

Covalent Docking and Molecular Dynamics Simulations Reveal the Resistance-Granting Mutations A237R/K in TEM Beta-Lactamase

The rate of modern drug discovery using experimental screening methods still lags far behind the rate at which pathogens mutate, highlighting the dire need for accurate and fast predictive simulations of macromolecular evolution. Particularly threatening, multidrug-resistant bacteria evade our defenses by expressing a series of resistance factors, the most famous of which is the 29 kilodaltons antibiotic cleaver, TEM beta-lactamase. Rising to this challenge, we applied biophysical simulations and predictions to identify two new resistance-conferring mutations in TEM and their respective modes of action. Using homology modeling and traditional all-atom molecular dynamics simulations, we predicted the structures of 50 TEM mutants, then deployed covalent docking to estimate their binding affinities against 85 beta-lactam-containing drugs to identify potential substrate specificity shifts. Finally, we used binding pose metadynamics and normal mode analyses to further scan the most promising results (validated against an empirical fitness dataset). This heuristic identified putative mechanisms for the previously-unreported, resistance-conferring mutations A237R and A237K. We also uncovered concerted structural rearrangements that could explain the specificity shifts observed in the clinically-entrenched mutations R164S/G/D. In addition to reaffirming the power of using simulations as molecular microscopes, our results could prove useful for guiding the rational design of next-generation beta-lactam antibiotics and bring the community closer to retaking the lead against the recurrent threat of multidrug-resistant pathogens.