检索结果-内蒙古大学图书馆

The spatially conscious machine learning model

STATISTICAL ANALYSIS AND DATA MINING 2020年第1期13卷 31-49页

作者： Kiely, Timothy J. Bastian, Nathaniel D. Northwestern Univ Dept Data Sci 339 East Chicago Ave Chicago IL 60611 USA

Successfully predicting gentrification could have many social and commercial applications;however, real estate sales are difficult to predict because they belong to a chaotic system comprised of intrinsic and extrinsic characteristics, perceived value, and market speculation. Using New York City real estate as our subject, we combine modern techniques of data science and machine learning with traditional spatial analysis to create robust real estate prediction models for both classification and regression tasks. We compare several cutting edge machine learning algorithms across spatial, semispatial, and nonspatial feature engineering techniques, and we empirically show that spatially conscious machine learning models outperform nonspatial models when married with advanced prediction techniques such as Random Forests, generalized linear models, gradient boosting machines, and artificial neural networks.

关键词： artificial neural networks feature engineering generalized linear models gradient boosting machine learning Random Forests real estate spatial analysis

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Radio Coverage Prediction in Urban Environments

引用

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 2020年第4期17卷 2117-2130页

作者： Mohammadjafari, Sanaz Roginsky, Sophie Kavurmacioglu, Emir Cevik, Mucahit Ethier, Jonathan Bener, Ayse Basar Ryerson Univ Data Sci Lab Toronto ON M5B 2K3 Canada

AIM: Having a reliable prediction model of radio signal strength is an essential tool for planning and designing a radio network. Given a geographic region, and associated power estimates linked to the transmitter placements, our objective is to develop machine learning models to predict the strength of the radio signals. BACKGROUND: The propagation model is often used to determine the optimal location of radio transmitters in order to optimize the power coverage in a geographic area of interest. However, it is often a costly operation to obtain the exact power measurements over a region for a given set of transmitter locations. Therefore, fast prediction methods are needed to estimate the power values given limited data. METHODOLOGY: We consider a dataset consisting of simulated power at each point in an environment for a given set of transmitter locations. We experiment with various machine learning models, namely, generalized linear models (GLMs), neural networks (NNs), and knearest neighbor (KNN), to estimate the power values for a given transmitter placement. We investigate various feature engineering approaches to enhance the predictive performance of the machine learning models. RESULTS: We observe that employed feature engineering methods such as polynomial degrees and transmitter to cluster distances significantly improve the prediction accuracy. In particular, GLM model performance notably improves thanks to these extracted features, where mean absolute error (MAE) is reduced around 77% from 11.37 dB to 2.55 dB. We note that KNN with k = 2 and DNN models perform better than NN and GLM. KNN has the best performance with an average MAE of 0.65dB and also substantially faster to train than NN/DNN models. In addition, our analysis shows that, to train a well-performing machine learning model, it is sufficient to use a dataset consisting of measurements at a fraction of the potential transmitter locations in a given region. CONCLUSIONS: Machine learning methods

关键词： Machine learning radio coverage transmitter placement k-nearest neighbor generalized linear models neural networks

来源：评论

学校读者我要写书评

暂无评论

Explainable Machine Learning for Early Assessment of COVID-19 Risk Prediction in Emergency Departments

引用

IEEE ACCESS 2020年 8卷 196299-196325页

作者： Casiraghi, Elena Malchiodi, Dario Trucco, Gabriella Frasca, Marco Cappelletti, Luca Fontana, Tommaso Esposito, Alessandro Andrea Avola, Emanuele Jachetti, Alessandro Reese, Justin Rizzi, Alessandro Robinson, Peter N. Valentini, Giorgio Univ Milan Dept Comp Sci Giovanni Degli Antoni I-20133 Milan Italy Univ Roma CINI Natl Lab Artificial Intelligence & Intellige I-00185 Rome Italy Univ Milan Data Sci Res Ctr I-20133 Milan Italy Politecn Milan Dipartimento Elettron Informaz & Bioingn I-20133 Milan Italy Fdn IRCCS Ca Granda Osped Maggiore Policlin Radiol Dept I-20122 Milan Italy Univ Milan Postgrad Sch Radiodiagnost I-20122 Milan Italy Fdn IRCCS Ca Granda Osped Maggiore Policlin Accident & Emergency Dept I-20122 Milan Italy Lawrence Berkeley Natl Lab Div Environm Genom & Syst Biol Berkeley CA 94720 USA Jackson Lab Genom Med Farmington CT 06032 USA

Between January and October of 2020, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus has infected more than 34 million persons in a worldwide pandemic leading to over one million deaths worldwide (data from the Johns Hopkins University). Since the virus begun to spread, emergency departments were busy with COVID-19 patients for whom a quick decision regarding in- or outpatient care was required. The virus can cause characteristic abnormalities in chest radiographs (CXR), but, due to the low sensitivity of CXR, additional variables and criteria are needed to accurately predict risk. Here, we describe a computerized system primarily aimed at extracting the most relevant radiological, clinical, and laboratory variables for improving patient risk prediction, and secondarily at presenting an explainable machine learning system, which may provide simple decision criteria to be used by clinicians as a support for assessing patient risk. To achieve robust and reliable variable selection, Boruta and Random Forest (RF) are combined in a 10-fold cross-validation scheme to produce a variable importance estimate not biased by the presence of surrogates. The most important variables are then selected to train a RF classifier, whose rules may be extracted, simplified, and pruned to finally build an associative tree, particularly appealing for its simplicity. Results show that the radiological score automatically computed through a neural network is highly correlated with the score computed by radiologists, and that laboratory variables, together with the number of comorbidities, aid risk prediction. The prediction performance of our approach was compared to that that of generalized linear models and shown to be effective and robust. The proposed machine learning-based computational system can be easily deployed and used in emergency departments for rapid and accurate risk prediction in COVID-19 patients.

关键词： COVID-19 Predictive models Machine learning Radio frequency Computational modeling Feature extraction Data models Associative tree Boruta feature selection clinical data analysis COVID-19 generalized linear models missing data imputation random forest classifier risk prediction

来源：评论

学校读者我要写书评

暂无评论

Probability inequalities for sums of NSD random variables and applications

引用

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS 2020年第2期49卷 281-306页

作者： Cai, Ting Hu, Hong Chang Hubei Normal Univ Sch Math & Stat Huangshi Hubei Peoples R China

In this paper, we obtain the exponential-type inequalities for maximal partial sums of negatively superadditive dependent (NSD) random variables, which extends the corresponding results for independent and negatively associated (NA) random variables. Using these inequalities, we further investigate the weak convergence of the M-estimators in the generalized linear model with NSD errors, which generalize and improve the corresponding results of the independent random errors to that of NSD random errors.

关键词： NSD random variable generalized linear models M-estimates weak convergence

来源：评论

学校读者我要写书评

暂无评论

An iterative algorithm for fitting nonconvex penalized generalized linear models with grouped predictors

引用

COMPUTATIONAL STATISTICS & DATA ANALYSIS 2012年第10期56卷 2976-2990页

作者： She, Yiyuan Florida State Univ Dept Stat Tallahassee FL 32306 USA

High-dimensional data pose challenges in statistical learning and modeling. Sometimes the predictors can be naturally grouped where pursuing the between-group sparsity is desired. Collinearity may occur in real-world high-dimensional applications where the popular l(1) technique suffers from both selection inconsistency and prediction inaccuracy. Moreover, the problems of interest often go beyond Gaussian models. To meet these challenges, nonconvex penalized generalized linear models with grouped predictors are investigated and a simple-to-implement algorithm is proposed for computation. A rigorous theoretical result guarantees its convergence and provides tight preliminary scaling. This framework allows for grouped predictors and nonconvex penalties, including the discrete 10 and the l(0) + l(2)' type penalties. Penalty design and parameter tuning for nonconvex penalties are examined. Applications of super-resolution spectrum estimation in signal processing and cancer classification with joint gene selection in bioinformatics show the performance improvement by nonconvex penalized estimation. (C) 2011 Elsevier B.V. All rights reserved.

关键词： Nonconvex penalties Group LASSO generalized linear models Spectral analysis Gene selection

来源：评论

学校读者我要写书评

暂无评论

Asymptotic Properties of Maximum Quasi-Likelihood Estimates in generalized linear models with "Working" Covariance Matrix and Adaptive Designs

引用

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS 2012年第19期41卷 3544-3561页

作者： Gao, Qi-Bing Lin, Jin-Guan Zhu, Chun-Hua Wu, Yao-Hua Southeast Univ Dept Math Nanjing 210096 Jiangsu Peoples R China Nanjing Normal Univ Sch Math Sci Nanjing Jiangsu Peoples R China Nanjing Audit Univ Dept Stat Nanjing Jiangsu Peoples R China Univ Sci & Technol China Dept Stat & Finance Hefei 230026 Peoples R China

In this article, for the generalized linear models (GLMs) with "working" covariance matrix and adaptive designs, we develop the asymptotic properties of maximum quasi-likelihood estimators (MQLEs) under some mild regular conditions. The existence of MQLEs in quasi-likelihood equation, the rate of convergence and asymptotic normality of MQLEs are presented. The results are illustrated by Monte-Carlo simulations.

关键词： Adaptive designs Asymptotic normality generalized linear models Maximum quasi-likelihood estimates "Working" Covariance Matrix

来源：评论

学校读者我要写书评

暂无评论

Fall incidence in hospitalized patients and prediction of its risk factors using a weighted Poisson model

引用

JOURNAL OF PUBLIC HEALTH-HEIDELBERG 2022年第12期30卷 2971-2980页

作者： Yaghoubi, Siamak Gooraji, Somayeh Ahmadi Habibi, Maryam Torkaman, Farideh Qazvin Univ Med Sci Rajaee Hosp Dept Anesthesia Clin Dev Unit Qazvin Iran Shahid Beheshti Univ Med Sci Dept Biostat Tehran Iran Qazvin Univ Med Sci Rajaee Hosp Dept Environm Hlth Clin Dev Unit Qazvin Iran Qazvin Univ Med Sci Velayat Hosp Dept Nursing Patient Safety Unit Qazvin Iran

Aim Falls in hospital as a major cause of disability and death threaten patients' safety and quality of life. We studied fall incidence in hospital, and predicted its risk factors using weighted Poisson (WP) model versus other models. Method This cross-sectional study was performed on the patients referred to two central hospitals in Qazvin, Iran between 2017 and 2019. The data were collected using the Morse scale and fall reporting forms in the hospital patient safety units (288 falls). Factors including age, gender, time of fall, fall location, cause of fall and its complications, drugs administrated, disease history, post-fall care measures, presence of companion, and length of hospital stay were assessed. The WP model was compared with other models. Results Fall incidence was 2.5 per 1000 patient days. Among them, 62.5% were elderly (mean age 65.7 +/- 19.21 yr). Using the WP model, age, gender, fall location and fall cause, drugs administered, post-fall care measures (P < 0.001), and the presence of companion were identified as risk factors for falling (P < 0.001) Older females, those without a companion, and those without post-fall care measures and with medication history were at a higher risk. Falls from bed were the prevalent type of fall (IRR = 1.65). Falls in the internal ward were lower than in other wards (IRR = 0.67). Conclusion The WP model is suggested as an appropriate model to predict fall risk factors. Fall rate may be reduced by combining information on risk factors with the strategies of training nurses or caregivers, or making possible changes in patients' environment.

关键词： Accidental fall Hospitalization Risk factors Poisson distribution linear model generalized linear models

来源：评论

学校读者我要写书评

暂无评论

Introducing a general class of species diversification models for phylogenetic trees

引用

STATISTICA NEERLANDICA 2020年第3期74卷 261-274页

作者： Richter, Francisco Haegeman, Bart Etienne, Rampal S. Wit, Ernst C. Univ Groningen Bernoulli Inst Math Comp Sci & Artificial Intelli Groningen Netherlands Univ Groningen Groningen Inst Evolutionary Life Sci Groningen Netherlands CNRS Theoret & Expt Ecol Stn Toulouse France Paul Sabatier Univ Toulouse France USI Inst Computat Sci Lugano Switzerland

Phylogenetic trees are types of networks that describe the temporal relationship between individuals, species, or other units that are subject to evolutionary diversification. Many phylogenetic trees are constructed from molecular data that is often only available for extant species, and hence they lack all or some of the branches that did not make it into the present. This feature makes inference on the diversification process challenging. For relatively simple diversification models, analytical or numerical methods to compute the likelihood exist, but these do not work for more realistic models in which the likelihood depends on properties of the missing lineages. In this article, we study a general class of species diversification models, and we provide an expectation-maximization framework in combination with a uniform sampling scheme to perform maximum likelihood estimation of the parameters of the diversification process.

关键词： EM algorithm generalized linear models importance sampling nonhomogeneous Poisson process phylogenetic trees

来源：评论

学校读者我要写书评

暂无评论

Analysis of the characteristics of some populations of Crambe tataria Sebe ′ok from Romania

引用

ACTA OECOLOGICA-INTERNATIONAL JOURNAL OF ECOLOGY 2022年第0期114卷 103810-103810页

作者： Chirila, Simona Dumitrita Alexandra Ioan Cuza Univ Iasi Fac Biol Carol I Blvd 20A Iasi 700505 Romania

Crambe tataria is a perennial species in the Brassicaceae family considered currently threatened. The identified causes of the decline of this species are overgrazing, use of fertilizers, mowing, invasive species, fires, abandonment of pastoral systems, artificial planting, agricultural and forestry activities, as well as recreational activities. In Romania, the species is declining due to overgrazing. The study aimed was to identify and describe the relationships between population characteristics and some environmental variables. Moreover, for the evaluation of the edaphic conditions of the populations of C. tataria, soil samples were collected and analyzed. The characteristics of the populations that were recorded in the plots of 100 m(2) were represented by morphological variables (the habitus of the species, the size of the leaves, and the flowering) and demographic variables (the proportion of flowering individuals and number of individuals/plot). Habitat characteristics were represented by topographic, climatic, soil chemical, anthropogenic data, and the structural characteristics of plant communities. The relationships between population characteristics and environmental variables were evaluated using generalized linear models (GLMs). A multivariate analysis (Principal Component Analysis) was performed. The results obtained showed that soil chemical variables are the best predictors of the characteristics of C. tataria populations. Analysis of the characteristics of C. tataria populations indicates that 80% of the populations present good status, 13.33% of the populations present poor status, and 6.66% of the populations present bad status. However, the decrease in population size and the proportion of individuals flowering in the regions of Transylvania and Muntenia indicate the establishment of active protection strategies.

关键词： Crambe tataria Population characteristics Environmental conditions generalized linear models Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

PipeArch: Generic and Context-Switch Capable Data Processing on FPGAs

引用

ACM TRANSACTIONS ON RECONFIGURABLE TECHNOLOGY AND SYSTEMS 2020年第1期14卷 1-28页

作者： Kara, Kaan Alonso, Gustavo Swiss Fed Inst Technol Syst Grp Dept Comp Sci Stampfenbachstr 114 CH-8092 Zurich Switzerland

Data processing systems based on FPGAs offer high performance and energy efficiency for a variety of applications. However, these advantages are achieved through highly specialized designs. The high degree of specialization leads to accelerators with narrow functionality and designs adhering to a rigid execution flow. For multi-tenant systems this limits the scope of applicability of FPGA-based accelerators, because, first, supporting a single operation is unlikely to have any significant impact on the overall performance of the system, and, second, serving multiple users satisfactorily is difficult due to simplistic scheduling policies enforced when using the accelerator. Standard operating system and database management system features that would help address these limitations, such as context-switching. preemptive scheduling, and thread migration are practically non-existent in current FPGA accelerator efforts. In this work, we propose PipeArch, an open-source project(1) for developing FPGA-based accelerators that combine the high efficiency of specialized hardware designs with the generality and functionality known from conventional CPU threads. PipeArch provides programmability and extensibility in the accelerator without losing the advantages of SIMD-parallelism and deep pipelining. PipeArch supports context-switching and thread migration, thereby enabling for the first time new capabilities such as preemptive scheduling in FPGA accelerators within a high-performance data processing setting. We have used PipeArch to implement a variety of machine learning methods for generalized linear model training and recommender systems showing empirically their advantages over a high-end CPU and even over fully specialized FPGA designs.

关键词： FPGA generic architecture programmable context-switch high-performance machine learning generalized linear models training matrix factorization data processing

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：