检索结果-内蒙古大学图书馆

Safety performance functions for Two-Lane urban arterial segments

SAFETY SCIENCE 2023年第1期167卷

作者： Bartin, Bekir Ozbay, Kaan Xu, Chuan Ozyegin Univ Dept Civil Engn Nisantepe MahOrman Sok 34-36 TR-34794 Istanbul Turkiye NYU C2 SMART Ctr Tier 1 UTC USDOT Dept Civil & Urban Engn 15 MetroTech Ctr 6th Floor Brooklyn NY 11201 USA Southwest Jiaotong Univ Sch Transportat & Logist Natl United Engn Lab Integrated & Intelligent Tran 111 1st North Sect 2nd Ring Rd Chengdu Sichuan Peoples R China

This paper presents the calibration and development process of the safety performance function for the undivided two-lane urban and suburban arterial segments in New Jersey. Data requirements, the availability of required data, and the data processing and extraction methods are presented, along with detailed results of the calibration and development process. Negative binomial, Poisson, zero-inflated Poisson and Hurdle models were generated using the development database. The best model fit was based on likelihood ratio test, AIC and BIC statistics, Vuong test and rootograms. The test database was used to calculate the calibration factor for U2 segments. The predictions of the location-specific count models were then evaluated and compared to those of calibrated Highway Safety Manual model, using the test dataset. The validation test results showed that the negative binomial and hurdle models exhibited better performance in terms of absolute residuals and absolute Pearson residual statistics. This paper also shows the impact of crash location information on analyses results, and underlines that efforts made to manually extract the missing required data can easily be offset by the inaccuracies in crash frequency databases, and the thresholds used to identify intersection related crashes.

关键词： Safety performance functions Highway safety manual generalized linear models urban arterials Calibration factor

来源：评论

学校读者我要写书评

暂无评论

Objective model selection with parallel genetic algorithms using an eradication strategy

引用

CANADIAN JOURNAL OF STATISTICS-REVUE CANADIENNE DE STATISTIQUE 2024年第2期52卷 636-654页

作者： Plante, Jean-Francois Larocque, Maxime Ades, Michel HEC Montreal Dept Sci Decis Montreal PQ Canada iA Financial Grp Montreal PQ Canada Univ Quebec Montreal Dept Math Montreal PQ Canada

In supervised learning, feature selection methods identify the most relevant predictors to include in a model. For linear models, the inclusion or exclusion of each variable may be represented as a vector of bits playing the role of the genetic material that defines the model. Genetic algorithms reproduce the strategies of natural selection on a population of models to identify the best. We derive the distribution of the importance scores for parallel genetic algorithms under the null hypothesis that none of the features has predictive power. They, hence, provide an objective threshold for feature selection that does not require the visual inspection of a bubble plot. We also introduce the eradication strategy, akin to forward stepwise selection, where the genes of useful variables are sequentially forced into the models. The method is illustrated on real data, and simulation studies are run to describe its performance.

关键词： Feature selection generalized linear models genetic algorithms linear models machine learning model selection predictions

来源：评论

学校读者我要写书评

暂无评论

The spike-and-slab lasso and scalable algorithm to accommodate multinomial outcomes in variable selection problems

引用

JOURNAL OF APPLIED STATISTICS 2024年第11期51卷 2039-2061页

作者： Leach, Justin M. Yi, Nengjun Aban, Inmaculada Univ Alabama Birmingham Dept Biostat Birmingham AL USA Univ Alabama Birmingham Dept Biostat 1665 Univ Blvd Birmingham AL 35233 USA

Spike-and-slab prior distributions are used to impose variable selection in Bayesian regression-style problems with many possible predictors. These priors are a mixture of two zero-centered distributions with differing variances, resulting in different shrinkage levels on parameter estimates based on whether they are relevant to the outcome. The spike-and-slab lasso assigns mixtures of double exponential distributions as priors for the parameters. This framework was initially developed for linear models, later developed for generalized linear models, and shown to perform well in scenarios requiring sparse solutions. Standard formulations of generalized linear models cannot immediately accommodate categorical outcomes with > 2 categories, i.e. multinomial outcomes, and require modifications to model specification and parameter estimation. Such modifications are relatively straightforward in a Classical setting but require additional theoretical and computational considerations in Bayesian settings, which can depend on the choice of prior distributions for the parameters of interest. While previous developments of the spike-and-slab lasso focused on continuous, count, and/or binary outcomes, we generalize the spike-and-slab lasso to accommodate multinomial outcomes, developing both the theoretical basis for the model and an expectation-maximization algorithm to fit the model. To our knowledge, this is the first generalization of the spike-and-slab lasso to allow for multinomial outcomes.

关键词： Bayesian variable selection spike-and-slab generalized linear models multinomial outcomes elastic net

来源：评论

学校读者我要写书评

暂无评论

Count network autoregression

引用

JOURNAL OF TIME SERIES ANALYSIS 2024年第4期45卷 584-612页

作者： Armillotta, Mirko Fokianos, Konstantinos Vrije Univ Amsterdam Dept Econometr & Data Sci Amsterdam Netherlands Tinbergen Inst Amsterdam Netherlands Univ Cyprus Dept Math & Stat Nicosia Cyprus Univ Cyprus Dept Math & Stat Univ House Anastasios G Leventis 1 Panepistimiou CY-1678 Nicosia Cyprus

We consider network autoregressive models for count data with a non-random neighborhood structure. The main methodological contribution is the development of conditions that guarantee stability and valid statistical inference for such models. We consider both cases of fixed and increasing network dimension and we show that quasi-likelihood inference provides consistent and asymptotically normally distributed estimators. The article is complemented by simulation results and a data example.

关键词： generalized linear models increasing dimension link function multi-variate count time series quasi-likelihood

来源：评论

学校读者我要写书评

暂无评论

Mining frequent patterns with generalized linear model for traffic density analysis

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第12期82卷 18327-18352页

作者： Nair, Suja Chandrasekharan Elayidom, Sudheep Gopalan, Sasi Cochin Univ Sci & Technol Kochi Kerala India

Call Detail Record (CDR) is the detailed record of all the telephonic calls that pass through a telephone exchange or any other telecommunications equipment. It contains temporal and spatial data, and can also convey other information that would be helpful to the user. Large numbers of vehicles on roads creates substantial traffic, which makes it very difficult to maintain safety and control traffic especially in the urban areas. Several works were carried out in the past to estimate the traffic density. However, they were inappropriate and quite expensive, owing to the dynamics of the traffic flow. This paper proposes the use of CDR data to find the high traffic density zones (HTDZs). For prediction purpose, we mine the frequent patterns from CDR data to find the co-occurrence of the position associated with a mobile user. In addition, Recurrent neural Networks (RNN) using LSTM (Long Short-term memory) are used for the time series prediction. The proposed system helps the whole public not only the registered users by decreasing the accident rates. Statistical performance evaluation integrated with time series causality is done for the proposed system. The proposed system is evaluated over standard data sets and an accuracy of 96% is achieved and a root mean square value was obtained as 3.84 during prediction.

关键词： Traffic density analysis Call data record Frequent pattern mining Mobile network generalized linear models

来源：评论

学校读者我要写书评

暂无评论

Dropout Training is Distributionally Robust Optimal

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2023年第1期24卷 1-60页

作者： Blanchet, Jose Kang, Yang Olea, Jose Luis Montiel Nguyen, Viet Anh Zhang, Xuhui Stanford Univ Dept Management Sci & Engn Stanford CA 94305 USA Columbia Univ Dept Stat New York NY 10027 USA Cornell Univ Dept Econ Ithaca NY 14850 USA Chinese Univ Hong Kong Dept Syst Engn & Engn Management Hong Kong Peoples R China

This paper shows that dropout training in generalized linear models is the minimax solution of a two-player, zero-sum game where an adversarial nature corrupts a statistician's covariates using a multiplicative nonparametric errors-in-variables model. In this game, nature's least favorable distribution is dropout noise, where nature independently deletes entries of the covariate vector with some fixed probability 6. This result implies that dropout training indeed provides out-of-sample expected loss guarantees for distributions that arise from multiplicative perturbations of in-sample data. The paper makes a concrete recommendation on how to select the tuning parameter 6. The paper also provides a novel, parallelizable, unbiased multi-level Monte Carlo algorithm to speed-up the implementation of dropout training. Our algorithm has a much smaller computational cost compared to the naive implementation of dropout, provided the number of data points is much smaller than the dimension of the covariate vector.

关键词： generalized linear models generalization error distributionally robust opti-mization machine learning multi-level Monte Carlo

来源：评论

学校读者我要写书评

暂无评论

Gdaphen, R pipeline to identify the most important qualitative and quantitative predictor variables from phenotypic data

引用

BMC BIOINFORMATICS 2023年第1期24卷 1-18页

作者： Muniz Moreno, Maria del Mar Gaveriaux-Ruff, Claire Herault, Yann Univ Strasbourg CNRS UMR7104 INSERM U1258 Inst Genet Biol Moleculaire&Cellulaire IGBMC 1 Rue Laurent Fries F-67404 Illkirch Graffenstaden France Univ Strasbourg CNRS INSERM CELPHEDIAPHENOMIN Inst Clin Souris ICS 1 Rue Laurent Fries F-67404 Illkirch Graffenstaden France Univ Miami Miller Sch Med John P Hussman Inst Human Genom Miami FL 33136 USA

Background: In individuals or animals suffering from genetic or acquired diseases, it is important to identify which clinical or phenotypic variables can be used to discriminate between disease and non-disease states, the response to treatments or sexual dimorphism. However, the data often suffers from low number of samples, high number of variables or unbalanced experimental designs. Moreover, several parameters can be recorded in the same test. Thus, correlations should be assessed, and a more complex statistical framework is necessary for the analysis. Packages already exist that provide analysis tools, but they are not found together, rendering the decision method and implementation difficult for ***: We present Gdaphen, a fast joint-pipeline allowing the identification of most important qualitative and quantitative predictor variables to discriminate between genotypes, treatments, or sex. Gdaphen takes as input behavioral/clinical data and uses a Multiple Factor Analysis (MFA) to deal with groups of variables recorded from the same individuals or anonymize genotype-based recordings. Gdaphen uses as optimized input the non-correlated variables with 30% correlation or higher on the MFA-Principal Component Analysis (PCA), increasing the discriminative power and the classifier's predictive model efficiency. Gdaphen can determine the strongest variables that predict gene dosage effects thanks to the General linear Model (GLM)-based classifiers or determine the most discriminative not linear distributed variables thanks to Random Forest (RF) implementation. Moreover, Gdaphen provides the efficacy of each classifier and several visualization options to fully understand and support the results as easily readable plots ready to be included in publications. We demonstrate Gdaphen capabilities on several datasets and provide easily followable ***: Gdaphen makes the analysis of phenotypic data much easier for medical or preclinical be

关键词： R package Phenotypic data Clinical data Discrimination generalized linear models Random forest Imputation Model Prediction Machine learning Bootstrapping

来源：评论

学校读者我要写书评

暂无评论

Scale effect of landscape characteristics on undergrowth vegetation variance with different ecological traits

ECOLOGICAL FRONTIERS

引用

ECOLOGICAL FRONTIERS 2024年第6期44卷 1269-1279页

作者： Li, Zuzheng Wang, Tiangang Zhu, Jiangang Tian, Huixia Yang, Yanzheng Jin, Yingshan Chen, Bo Huang, Zhihao Han, Conghai Dai, Wei Zheng, Yi Lian, Zhenghua Wang, Yuerong Liang, Fang Lv, Da Cheng, Xiaoqin Beijing Acad Forestry & Landscape Architecture Beijing 100044 Peoples R China Beijing Forestry Univ Sch Ecol & Nat Conservat Beijing 100083 Peoples R China Beijing Jingxi Forest Farm Management Off Beijing 102300 Peoples R China Taiyuan Univ Sci & Technol Sch Environm & Resources Taiyuan 030024 Peoples R China Chinese Acad Sci Res Ctr Ecoenvironm Sci State Key Lab Urban & Reg Ecol Beijing 100085 Peoples R China Beijing Municipal Forestry & Pk Bur Beijing 101118 Peoples R China Miyun Dist Forestry & Pk Bur Beijing 101500 Peoples R China

Herbaceous understory vegetation plays a significant role in temperate forested ecosystems, with its diversity strongly dependent on both local and landscape conditions. However, the contribution of these factors across different spatial scales (e.g., scale effect) remains inadequately understood. The objective of this study was to determine the most important landscape and local characteristics influencing the species richness of the herb layer. We surveyed and sampled 53 sites in a mountainous forest within the Baihuashan National Nature Reserve of Beijing. Using generalized linear models, we investigated the simultaneous effect of local (e.g. tree density, average tree height, and cover of tree, shrub, and ground vegetation) and landscape (e.g. Area-weighted Mean Patch Size, Area-weighted Mean Euclidean Nearest Neighbor Distance, Area-weighted Mean Fractal Dimension Index, forest area, and shrubbery area) variables on the richness of species in the understory herb layer. Variation partitioning was used to examine the individual contribution of local and landscape variables. Our results identified 366 plant species from 95 families across 53 sampling sites. Significant differences in species richness were found among life forms, seed dispersal types, and habitat preferences (P < 0.001). Parsimonious models indicated that combining local and landscape factors at a 2 km scale explained the most variation in phanerophytes (R-2 = 0.658). Locally, average tree height significantly influenced the species richness of biotic dispersal, phanerophytes, and geophytes. At the landscape level, variables such as the Area-weighted Mean Fractal Dimension Index and farmland area significantly impacted plant community traits across different scales. Understanding these effects is crucial for developing effective sustainable forest ecosystem management strategies and for establishing robust ecological conservation policies.

关键词： Landscape characteristics Scale of effect Herbaceous understory vegetation generalized linear models

来源：评论

学校读者我要写书评

暂无评论

Robit regression in Stata

引用

STATA JOURNAL 2023年第3期23卷 658-682页

作者： Newson, Roger B. Falcaro, Milena Kings Coll London London England

Logistic and probit models are the most popular regression models for binary outcomes. A simple robust alternative is the robit model, which replaces the underlying normal distribution in the probit model with a Student's t distribution. The heavier tails of the t distribution (compared with the normal distribution) mean that model outliers are less influential. Robit regression models can be fit as generalized linear models with the link function defined as the inverse cumulative t distribution function with a specified number of degrees of freedom;they have been advocated as being particularly suitable for estimating inverse-probability weights and propensity scoring more generally. Here we describe a new command, robit, that implements robit regression in Stata.

关键词： st0724 robit xlink robit regression binary regression generalized linear models inverse-probability weights

来源：评论

学校读者我要写书评

暂无评论

Variation in the area of the polymictic Pampean shallow lakes and its relationship with precipitation

引用

ENVIRONMENTAL EARTH SCIENCES 2023年第24期82卷 1-13页

作者： Maestri, Maria Laura Ferrati, Rosana Monica Canziani, Graciela Ana Natl Univ Cent Buenos Aires Prov UNCPBA Multidisciplinary Inst Ecosyst & Sustainable Dev Pinto 399 RA-7000 Tandil Argentina Sci Res Commiss Prov Buenos Aires CICPBA Pinto 399 RA-7000 Tandil Argentina Natl Sci & Tech Res Council CONICET Godoy Cruz 2290C1425FQB Caba Argentina

The purpose of this study is to analyze the temporal dynamics of the free surface area of shallow lakes during the period 1984-2015 in the Pampas region, Argentina, using satellite image processing (Landsat 4 TM, Landsat 5 TM, Landsat 7 ETM+ and Landsat 8 OLI). The evolution of the free surface of five shallow lakes in two distinct basins of the province of Buenos Aires can be explained using generalized linear models (GLM) and taking as explanatory variables the accumulated precipitation and the number of rainfall days over a given period before the acquisition date of the satellite image. Accumulated precipitation and frequency of days with precipitation were calculated for 1, 7, 30, 90, and 180 days, as well as for 1, 2, 3, and 4 years, respectively. The results show that the explanatory variables linked to the memory of the system (3 and 4 years) contribute significantly in all cases to the reconstruction of the areas. In particular, long-term variables reconstruct accurately (R2 between 0.76 and 0.91) the area of the five shallow lakes for the period 2001-2015. The short-term explanatory variables (7 and 30 days) are also significant to the reconstruction of the variations observed in the first period (1984-2000) but only for the two lakes in the Southeastern basin (R2 = 0.70 and 0.94), while in the Center-South upper basin, only one of the lakes exhibits some short-term dependency in the second period (2001-2015) (R2 = 0.83).

关键词： Pampas shallow lakes Free surface area Precipitation Remote sensing generalized linear models

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：