检索结果-内蒙古大学图书馆

Feasibility of aligning creatine kinase MB activity and mass data in multicentre trials using generalized additive modelling

引用

INTERDISCIPLINARY CARDIOVASCULAR AND THORACIC SURGERY 2024年第2期39卷 ivae138-ivae138页

作者： Hoenicka, Markus Vokshi, Arbresha Zhou, Shaoxia Liebold, Andreas Mayer, Benjamin Ulm Univ Med Ctr Dept Cardiothorac & Vasc Surg Albert Einstein Allee 23 D-89081 Ulm Germany Ulm Univ Med Ctr Dept Clin Chem Ulm Germany Ulm Univ Inst Epidemiol & Med Biometry Ulm Germany

OBJECTIVES Elevated serum creatine kinase isoenzyme MB (CK-MB) levels indicate myocardial ischaemia and periprocedural myocardial injury during treatment of heart diseases. We established a method to predict CK-MB mass from activity data based on a prospective pilot study in order to simplify multicentre trials. METHODS 38 elective cardiac surgery patients without acute myocardial ischaemia and terminal renal failure were recruited. CK-MB mass and activity were determined in venous blood samples drawn preoperatively, postoperatively, 6 h post-op, and 12 h post-op. Linear regression and generalized additive models (GAMs) were applied to describe the relationship of mass and activity. Influences of demographic and perioperative factors on the fit of GAMs was evaluated. The agreement of predicted and measured CK-MB masses was assessed by Bland-Altman analyses. RESULTS Linear regression provided an acceptable overall fit (r(2) = 0.834) but showed deviances at low CK-MB levels. GAMs did not benefit from the inclusion of age, body mass index and surgical times. The minimal adequate model predicted CK-MB masses from activities, sex and sampling time with an r(2) of 0.981. Bland-Altman analyses confirmed narrow limits of agreement (spread: 8.87 mu g/l) and the absence of fixed (P = 0.41) and proportional (P = 0.21) biases. CONCLUSIONS GAM-based modelling of CK-MB data in a representative patient cohort allowed to predict CK-MB masses from activities, sex and sampling time. This approach simplifies the integration of study centres with incompatible CK-MB data into multicentre trials in order to facilitate inclusion of CK-MB levels in statistical models.

关键词： Creatine kinase MB generalized additive models Statistical modelling Myocardial injury

来源：评论

学校读者我要写书评

暂无评论

Explainable generalized additive neural networks with independent neural network training (vol 34, 6, 2024)

引用

STATISTICS AND COMPUTING 2024年第5期34卷 1-11页

作者： Ortega-Fernandez, Ines Sestelo, Marta Villanueva, Nora M. Galician Res & Dev Ctr Adv Telecommun GRADIANT Carretera Vilar 56-58 Vigo 36214 Spain CITMAga Santiago De Compostela 15782 Spain Univ Vigo Dept Stat & OR SiDOR Res Grp Vigo 36310 Spain Univ Vigo Escola Enxenaria Telecomunicac Vigo 36310 Spain

Neural Networks are one of the most popular methods nowadays given their high performance on diverse tasks, such as computer vision, anomaly detection, computer-aided disease detection and diagnosis or natural language processing. While neural networks are known for their high performance, they often suffer from the so-called “black-box” problem, which means that it is difficult to understand how the model makes decisions. We introduce a neural network topology based on generalized additive models. By training an independent neural network to estimate the contribution of each feature to the output variable, we obtain a highly accurate and explainable deep learning model, providing a flexible framework for training generalized additive Neural Networks which does not impose any restriction on the neural network architecture. The proposed algorithm is evaluated through different simulation studies with synthetic datasets, as well as a real-world use case of Distributed Denial of Service cyberattack detection on an Industrial Control System. The results show that our proposal outperforms other GAM-based neural network implementations while providing higher interpretability, making it a promising approach for high-risk AI applications where transparency and accountability are crucial.

关键词： Interpretable deep learning generalized additive models Interpretable AI Neural network GAM Explainable AI

来源：评论

学校读者我要写书评

暂无评论

A noisy-input generalized additive model for relative sea-level change along the Atlantic coast of North America

引用

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES C-APPLIED STATISTICS 2024年第1期74卷 34-82页

作者： Upton, Maeve Parnell, Andrew Kemp, Andrew Ashe, Erica Mccarthy, Gerard Cahill, Niamh Maynooth Univ Hamilton Inst Dept Math & Stat ICARUS Maynooth Ireland Tufts Univ Dept Earth & Climate Sci Boston MA USA Rutgers State Univ Dept Earth & Planetary Sci New Brunswick NJ USA Maynooth Univ ICARUS Maynooth Ireland Maynooth Univ Dept Math & Stat ICARUS Maynooth Ireland

We propose a Bayesian, noisy-input, spatial-temporal generalized additive model to examine regional relative sea-level (RSL) changes over time. The model provides probabilistic estimates of component drivers of regional RSL change via the combination of a univariate spline capturing a common regional signal over time, random slopes and intercepts capturing site-specific (local), long-term linear trends and a spatial-temporal spline capturing residual, non-linear, local variations. Proxy and instrumental records of RSL and corresponding measurement errors inform the model and a noisy-input method accounts for proxy temporal uncertainties. Results highlight the decomposition of regional RSL changes over 3,000 years along North America's Atlantic coast. The physical process glacial isostatic adjustment prevailed before 1800 CE, with anthropogenic forcing dominating after 1900 CE.

关键词： Bayesian sea-level generalized additive models uncertainty

来源：评论

学校读者我要写书评

暂无评论

generalized additive models for functional data

引用

TEST 2013年第2期22卷 278-292页

作者： Febrero-Bande, Manuel Gonzalez-Manteiga, Wenceslao Univ Santiago de Compostela Dpt Stat Santiago De Compostela Spain Univ Santiago de Compostela OR Fac Math Santiago De Compostela Spain

The aim of this paper is to extend the ideas of generalized additive models for multivariate data (with known or unknown link function) to functional data covariates. The proposed algorithm is a modified version of the local scoring and backfitting algorithms that allows for the nonparametric estimation of the link function. This algorithm would be applied to predict a binary response example.

关键词： Functional data generalized additive models generalized linear models

来源：评论

学校读者我要写书评

暂无评论

Cross-realm transferability of species distribution models-Species characteristics and prevalence matter more than modelling methods applied

引用

ECOLOGICAL MODELLING 2025年 499卷

作者： Takolander, Antti Forsblom, Louise Hellsten, Seppo Ilmonen, Jari Jokinen, Ari-Pekka Kallio, Niko Koponen, Sampsa Vakeva, Sakari Virtanen, Elina Finnish Environm Inst Syke Latokartanonkaari 11 Helsinki 00790 Finland Metsahallitus Akselinkatu 8 Savonlinna 57130 Finland

Species Distribution models (SDMs) are frequently applied in ecological research, but geographic transferability of SDMs holds major uncertainties. Here, we assess the cross-realm (sea to lake) geographic transferability of four SDM methods: generalized Linear models (GLMs), generalized additive models (GAMs), Boosted Regression Trees (BRTs), and Bayesian additive Regression Trees (BARTs) predicting occurrences of freshwater macrophytes from brackish water sea area (Bothnian Bay) to a freshwater lake environment in Finland. We found that the SDM method applied did not affect model transferability, and majority of the variation in transferability performance was associated with species. For most species model transferability was low, but reasonably good on one third of the species modelled, which had similar prevalences in both marine and freshwater data. These were emergent species or species growing close to shoreline, which presumably share similar environmental niche in terms of growing depth and water turbidity between the two environments. Generally, models which had high interpolation performance, also had higher transferability, but this relationship was not dependent on the SDM method applied. Our results suggest that species prevalence and species-specific characteristics, such as growth form, life history traits and ecological niche, are main contributors to geographic transferability of SDMs.

关键词： Species distribution models Macrophytes Model extrapolation Geographic transferability Spatial modelling Prevalence generalized linear models generalized additive models Boosted regression trees Bayesian additive regression trees

来源：评论

学校读者我要写书评

暂无评论

Site characteristics determine the prevalence of extreme weather events affecting freshwater macroinvertebrate communities

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2024年 950卷 175436页

作者： Haubrock, Phillip J. Senckenberg Res Inst Dept River Ecol & Conservat Gelnhausen Germany Nat Hist Museum Frankfurt Gelnhausen Germany Univ South Bohemia Ceske Budejovice Fac Fisheries & Protect Waters South Bohemian Res Ctr Aquaculture & Biodivers Hyd Vodnany Czech Republic Gulf Univ Sci & Technol Ctr Appl Math & Bioinformat CAMB Kuwait Kuwait

Understanding the impacts of extreme weather events on freshwater ecosystems is imperative during a time when a multitude of challenges compromises these environments' health. Exploring how such events affect macroinvertebrate communities in rivers sheds light on the resilience of freshwater ecosystems, which is essential for human well-being and biodiversity conservation. In this study, long-term time series of benthic macroinvertebrate communities from four sites along three freshwater streams within the Rhine-Main-Observatory Long-Term Ecological Research site in Germany were analyzed. Each of them was sampled annually over a span of similar to 20 years to assess the impacts of extreme weather events (floods, droughts, and extreme heat) on macroinvertebrate communities. The findings reveal that the effects of extreme events are site-specific, suggesting that the impacts of an extreme event can vary based on several potential factors, including the life history traits of the organisms within the community and, among others, the hydrography of the site. Moreover, the analysis highlights that the cumulative impact of these events over time is more significant than the impact of a single event's magnitude, while following distinct temporal dynamics. This underscores the importance of considering both the temporal dynamics and the biological characteristics of communities when evaluating the consequences of extreme weather events on biodiversity, illustrating that the resilience of freshwater ecosystems and their biodiversity under such conditions depends on a complex interplay of factors rather than the severity of individual events.

关键词： Extreme events Biodiversity Climate change generalized additive models Long-term data

来源：评论

学校读者我要写书评

暂无评论

Towards Improved Heliosphere Sky Map Estimation with Theseus

引用

TECHNOMETRICS 2024年第2期66卷 208-226页

作者： Osthus, Dave Weaver, Brian P. Beesley, Lauren J. Moran, Kelly R. Stricklin, Madeline A. Zirnstein, Eric J. Janzen, Paul H. Reisenfeld, Daniel B. Los Alamos Natl Lab Stat Sci Grp Los Alamos NM 87545 USA Los Alamos Natl Lab Informat Syst & Modeling Los Alamos NM USA Los Alamos Natl Lab Space Sci & Applicat Grp Los Alamos NM USA Princeton Univ Dept Astrophys Sci Princeton NJ USA Univ Montana Dept Phys & Astron Missoula MT USA New Mexico Consortium Los Alamos NM USA

The Interstellar Boundary Explorer (IBEX) satellite has been in orbit since 2008 and detects energy-resolved energetic neutral atoms (ENAs) originating from the heliosphere. Different regions of the heliosphere generate ENAs at different rates. It is of scientific interest to take the data collected by IBEX and estimate spatial maps of heliospheric ENA rates (referred to as sky maps) at higher resolutions than before. These sky maps will subsequently be used to discern between competing theories of heliosphere properties that are not currently possible. The data IBEX collects present challenges to sky map estimation. The two primary challenges are noisy and irregularly spaced data collection and the IBEX instrumentation's point spread function. In essence, the data collected by IBEX are both noisy and biased for the underlying sky map of inferential interest. In this article, we present a two-stage sky map estimation procedure called Theseus. In Stage 1, Theseus estimates a blurred sky map from the noisy and irregularly spaced data using an ensemble approach that leverages projection pursuit regression and generalized additive models. In Stage 2, Theseus deblurs the sky map by deconvolving the PSF with the blurred map using regularization. Unblurred sky map uncertainties are computed via bootstrapping. We compare Theseus to a method closely related to the one operationally used today by the IBEX Science Operation Center (ISOC) on both simulated and real data. Theseus outperforms ISOC in nearly every considered metric on simulated data, indicating that Theseus is an improvement over the current state of the art.

关键词： Deconvolution Ensemble models generalized additive models Heliosphere Projection pursuit regression Regularization

来源：评论

学校读者我要写书评

暂无评论

Using eddy covariance data to detect nuclear reactor operational status

引用

JOURNAL OF ENVIRONMENTAL MANAGEMENT 2025年 373卷 123569页

作者： Kraklow, Vachel A. Thompson, E. Christi Stachelek, Jemma Casleton, Emily Sevanto, Sanna Dickman, L. Turin Junghans, Ann Los Alamos Natl Lab Earth & Environm Sci Div Los Alamos NM 87545 USA Los Alamos Natl Lab Comp Computat & Stat Sci Div Los Alamos NM 87545 USA Los Alamos Natl Lab High Performance Comp Div Los Alamos NM 87545 USA Los Alamos Natl Lab Nucl Engn & Nonproliferat Div Los Alamos NM 87545 USA

Monitoring nuclear reactor operations is vital for nuclear safeguards as it ensures that reactors are in compliance with international legal agreements. Validating nuclear facilities and activities, including potential clandestine activities, is currently accomplished by using remotely sensed data from satellites and aircrafts and on-site sampling. However, these techniques are temporally-limited as sampling and interpretation of environmental releases frequently involve labor-intensive, on-site collections. Here, we investigate whether remotely sensed data from eddy-covariance ecosystem monitoring networks, such as AmeriFlux, can be used to detect waste heat generated from four U.S.-based nuclear reactors, two pressurized water reactors (Callaway Nuclear Generating Station and Seabrook Nuclear Power Plant), and two boiling water reactors (Columbia Nuclear Generating Station and Enrico Fermi Nuclear Generating Station). Though both pressurized and boiling water reactors release latent and sensible heat into the environment in a similar way, we evaluated whether different signatures exist among the two types of nuclear facilities. Additionally, we evaluated whether different signatures exist among those reactors that release waste heat into the atmosphere via latent heat or into the ocean via sensible heat. To do this, we used logistic generalized additive models to investigate whether reactor operational status (i. e., on versus off) can be estimated from two environmental heat fluxes, latent and sensible heat. We also evaluated whether wind direction, seasonality and vegetation type influences potential latent and sensible heat signatures from reactors. Using a Dirichlet Process Means clustering analysis, we investigated whether certain weather conditions are more conducive to detecting reactor status. Our results suggest that eddy-covariance towers can detect waste heat flux signatures from nuclear reactors, particularly latent heat. Our results also suggest that

关键词： FLUXNET AmeriFlux Latent heat Sensible heat generalized additive models

来源：评论

学校读者我要写书评

暂无评论

Challenging the Performance-Interpretability Trade-Off: An Evaluation of Interpretable Machine Learning models

引用

BUSINESS & INFORMATION SYSTEMS ENGINEERING 2025年 1-25页

作者： Kruschel, Sven Hambauer, Nico Weinzierl, Sven Zilker, Sandra Kraus, Mathias Zschech, Patrick Univ Regensburg Chair Explainable AI Business Value Creat Bajuwarenstr 4 D-93053 Regensburg Germany Friedrich Alexander Univ Erlangen Nurnberg Chair Digital Ind Serv Syst Further Str 248 D-90429 Nurnberg Germany TH Nurnberg Georg Simon Ohm Professorship Business Analyt Hohfederstr 40 D-90489 Nurnberg Germany Univ Leipzig Professorship Intelligent Informat Syst & Proc Grimma Str 12 D-04109 Leipzig Germany

Machine learning is permeating every conceivable domain to promote data-driven decision support. The focus is often on advanced black-box models due to their assumed performance advantages, whereas interpretable models are often associated with inferior predictive qualities. More recently, however, a new generation of generalized additive models (GAMs) has been proposed that offer promising properties for capturing complex, non-linear patterns while remaining fully interpretable. To uncover the merits and limitations of these models, the study examines the predictive performance of seven different GAMs in comparison to seven commonly used machine learning models based on a collection of twenty tabular benchmark datasets. To ensure a fair and robust model comparison, an extensive hyperparameter search combined with cross-validation was performed, resulting in 68,500 model runs. In addition, this study qualitatively examines the visual output of the models to assess their level of interpretability. Based on these results, the paper dispels the misconception that only black-box models can achieve high accuracy by demonstrating that there is no strict trade-off between predictive performance and model interpretability for tabular data. Furthermore, the paper discusses the importance of GAMs as powerful interpretable models for the field of information systems and derives implications for future work from a socio-technical perspective.

关键词： Decision support Predictive analytics Interpretable machine learning generalized additive models Explainable artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Single-species quotas drive discards by multi-species trawlers in the Celtic Seas ecoregion when their relative abundance fluctuates

引用

ICES JOURNAL OF MARINE SCIENCE 2024年第9期81卷 1745-1763页

作者： Browne, Maria Calderwood, Julia Brophy, Deirdre Minto, Coilin Atlantic Technol Univ Marine & Freshwater Res Ctr Dublin Rd Galway H91T8NW Ireland

Our study investigated discarding patterns by bottom otter trawlers over 17 years prior to the full implementation of the Landing Obligation. A generalized additive modelling approach was applied to at-sea sampling data to examine the most important drivers of the discards per unit effort (DPUE) of cod, whiting, hake, and haddock in the Celtic Seas ecoregion from 2002 to 2018. Many operational, environmental, regulatory, and spatio-temporal factors were tested. Fish above and below the minimum conservation reference size (MCRS) were modelled separately to compare drivers of discarding of these categories of unwanted catch. In the full time period analysis, the three most important factors in determining DPUE were geographic location, an interaction between geographic location and year, and year interacting with month. Further analysis of a subset of the time series indicated that quota availability significantly impacted the DPUE for MCRS hake, while the quota allocated for one species often significantly influenced the DPUE of other species and size classes. Quota interacting with abundance had a significant impact for all >MCRS species and < MCR Shake. This indicates that changes in relative abundance compound discarding under quota constraints. Collectively, these results empirically demonstrate that single-species quotas majorly contribute to discards in a mixed-fisheries context .

关键词： fishing behaviour generalized additive models landing obligation management measures mixed fisheries unwanted catch

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：