检索结果-内蒙古大学图书馆

On generating random Gaussian graphical models

INTERNATIONAL JOURNAL OF APPROXIMATE REASONING 2020年 125卷 240-250页

作者： Cordoba, Irene Varando, Gherardo Bielza, Concha Larranaga, Pedro Univ Politecn Madrid Madrid Spain Univ Copenhagen Copenhagen Denmark

Structure learning methods for covariance and concentration graphs are often validated on synthetic models, usually obtained by randomly generating: (i) an undirected graph, and (ii) a compatible symmetric positive definite (SPD) matrix. In order to ensure positive definiteness in (ii), a dominant diagonal is usually imposed. In this work we investigate different methods to generate random symmetric positive definite matrices with undirected graphical constraints. We show that if the graph is chordal it is possible to sample uniformly from the set of correlation matrices compatible with the graph, while for general undirected graphs we rely on a partial orthogonalization method. (C) 2020 Elsevier Inc. All rights reserved.

关键词： Concentration graph Covariance graph Positive definite matrix simulation Undirected graphical model algorithm validation

来源：评论

学校读者我要写书评

暂无评论

Satellites for long-term monitoring of inland US lakes: The MERIS time series and application for chlorophyll-a

引用

REMOTE SENSING OF ENVIRONMENT 2021年 266卷 112685-112685页

作者： Seegers, Bridget N. Werdell, P. Jeremy Vandermeulen, Ryan A. Salls, Wilson Stumpf, Richard P. Schaeffer, Blake A. Owens, Tommy J. Bailey, Sean W. Scott, Joel P. Loftin, Keith A. NASA Goddard Space Flight Ctr Ocean Ecol Lab Greenbelt MD 20771 USA Univ Space Res Assoc USRA Columbia MD 21046 USA Sci Syst & Applicat Inc Lanham MD 20706 USA US EPA Off Res & Dev Res Triangle Pk NC 27711 USA NOAA Natl Ocean Serv Silver Spring MD 20910 USA Sci Applicat Int Corp Reston VA 20190 USA US Geol Survey Kansas Water Sci Ctr Lawrence KS 66049 USA

Lakes and other surface fresh waterbodies provide drinking water, recreational and economic opportunities, food, and other critical support for humans, aquatic life, and ecosystem health. Lakes are also productive ecosystems that provide habitats and influence global cycles. Chlorophyll concentration provides a common metric of water quality, and is frequently used as a proxy for lake trophic state. Here, we document the generation and distribution of the complete MEdium Resolution Imaging Spectrometer (MERIS;Appendix A provides a complete list of abbreviations) radiometric time series for over 2300 satellite resolvable inland bodies of water across the contiguous United States (CONUS) and more than 5,000 in Alaska. This contribution greatly increases the ease of use of satellite remote sensing data for inland water quality monitoring, as well as highlights new horizons in inland water remote sensing algorithm development. We evaluate the performance of satellite remote sensing Cyanobacteria Index (CI)-based chlorophyll algorithms, the retrievals for which provide surrogate estimates of phytoplankton concentrations in cyanobacteria dominated lakes. Our analysis quantifies the algorithms' abilities to assess lake trophic state across the CONUS. As a case study, we apply a bootstrapping approach to derive a new CI-to-chlorophyll relationship, Chl(BS), which performs relatively well with a multiplicative bias of 1.11 (11%) and mean absolute error of 1.60 (60%). While the primary contribution of this work is the distribution of the MERIS radiometric timeseries, we provide this case study as a roadmap for future stakeholders' algorithm development activities, as well as a tool to assess the strengths and weaknesses of applying a single algorithm across CONUS.

关键词： MERIS timeseries Inland waters Remote sensing algorithm validation Chlorophylla Water quality

来源：评论

学校读者我要写书评

暂无评论

Atrial fibrillation detection service validation tool

引用

SOFTWARE IMPACTS 2021年 10卷

作者： Faust, Oliver Kareem, Murtadha Lei, Ningrong Sheffield Hallam Univ Dept Engn & Math Howard St Sheffield S1 1WB S Yorkshire England Sheffield Hallam Univ Mat & Engn Res Inst Howard St Sheffield S1 1WB S Yorkshire England

We developed a software tool to validate a deep learning algorithm for an atrial fibrillation detection service with heart rate data from a clinical study. The deep learning algorithm analyses the measurement data and establishes an estimated atrial fibrillation probability for each heartbeat. The software tool displays both data and deep learning analysis results. Furthermore, the graphical user interface can be used by medical experts to detect atrial fibrillation periods in the data and establish a reference result which will be treated as ground truth in subsequent result analysis steps. Once both deep learning and expert results are available, a confusion matrix is produced and the algorithm performance is validated by establishing accuracy, sensitivity, specificity, and f1-score. The software tool was created in Python and the software incorporated a graphical user interface as well as functional elements for data display and deep learning. To establish the required functionality, we used three different parallel processing methods for: (1) user interface processing, (2) data handling, and (3) deep learning. This highlights the need for parallel processing methods even for projects with a low or mid-range complexity. We have learned that the functionality of individual components can be expressed elegantly in Python. However, the lack of parallel debugging support makes it rather difficult to integrate functional components to establish a working solution.

关键词： algorithm validation Deep learning Parallel processing Clinical data processing

来源：评论

学校读者我要写书评

暂无评论

validation of febrile seizures identified in the Sentinel Post-Licensure Rapid Immunization Safety Monitoring Program

引用

VACCINE 2019年第30期37卷 4172-4176页

作者： Kawai, Alison Tse Martin, David Henrickson, Sarah E. Goff, Ashleigh Reidy, Megan Santiago, Diana Selvam, Nandini Selvan, Mano McMahill-Walraven, Cheryl Lee, Grace M. Harvard Pilgrim Hlth Care Inst Dept Populat Med Boston MA USA Harvard Med Sch Boston MA 02115 USA US FDA Ctr Drug Evaluat & Res Silver Spring MD USA Childrens Hosp Philadelphia Div Allergy Immunol Philadelphia PA 19104 USA HealthCore Alexandria VA USA Humana Comprehens Hlth Insight Louisville KY USA Aetna Blue Bell PA USA Stanford Univ Sch Med Dept Pediat Palo Alto CA 94304 USA RTI Hlth Solut 307 Waverley Oaks RdSuite 101 Waltham MA 02452 USA

Background: The Sentinel Initiative was established in 2008 to monitor the safety of FDA-regulated medical products. We evaluated the positive predictive value (PPV) of ICD-9 codes for post-vaccination febrile seizures to identify optimal algorithms for use in post-market safety surveillance. Methods: We identified ICD-9 diagnosis codes for fever and seizures in the emergency department or inpatient setting after vaccinations of interest from July 1, 2010 to June 30, 2011. Medical record review was conducted to verify febrile seizure events. Results: Of 216 potential febrile seizures identified with one or more seizure codes (the broadest algorithm), 152 were chart-confirmed (i.e., documentation of fever within 24 h of seizure or clinician diagnosis of febrile seizure;PPV 70%, 95% CI 64, 76%). Two codes specific for febrile seizures produced the highest PPV (PPV 91%, 95% CI 85, 95%) and accounted for 140 confirmed febrile seizures. In the absence of febrile seizure codes, other seizure codes yielded much lower PPVs, regardless of the presence of fever codes. Conclusions: Our results indicate that ICD-9 diagnosis codes in the inpatient and emergency department settings have high predictive value for identifying febrile seizures within the Sentinel Distributed Database. While the PPV of the algorithm based on any diagnosis code for seizure is moderate, the algorithm limited to febrile seizure codes has a high PPV (>90%) and captures the vast majority of confirmed cases identified by the broadest algorithm, suggesting that the narrower algorithm limited to febrile seizure,codes may be preferred. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： Febrile seizures algorithm validation Vaccine safety

来源：评论

学校读者我要写书评

暂无评论

A global approach for chlorophyll-a retrieval across optically complex inland waters based on optical water types

引用

REMOTE SENSING OF ENVIRONMENT 2019年 229卷 159-178页

作者： Neil, C. Spyrakos, E. Hunter, P. D. Tyler, A. N. Univ Stirling Fac Nat Sci EPOC Biol & Environm Sci Stirling Scotland

Numerous algorithms have been developed to retrieve chlorophyll-a (Chla) concentrations (mg m(-3)) from Earth observation (EO) data collected over optically complex waters. Retrieval accuracy is highly variable and often unsatisfactory where Chla co-occurs with other optically active constituents. Furthermore, the applicability and limitations of retrieval algorithms across different optical complex systems in space and time are often not considered. In the first instance, this paper provides an extensive performance assessment for 48 Chla retrieval algorithms of varying architectural design. The algorithms are tested in their original parametrisations and are then retuned using in-situ remote sensing reflectance (R-rs(lambda), sr(-1)) data (n = 2807) collected from 185 global inland and coastal aquatic systems encompassing 13 different optical water types (OWTs). The paper then demonstrates retrieval performance across the full dataset of observations and within individual OWTs to determine the most effective model(s) of those tested for retrieving Chla in waters with varying optical properties. The results revealed significant variability in retrieval performance when comparing model outputs to in-situ measured Chla for the full in-situ dataset in its entirety and within the 13 distinct OWTs. Importantly, retuning an algorithm to optimise its parameterisation for each individual OWT (i.e. one algorithm, multiple parameterisations) is found to improve the retrieval of Chla overall compared to simply calibrating the same algorithm using the complete in-situ dataset (i.e. one algorithm, one parameterisation). This resulted in a 25% improvement in retrieval accuracy based on relative percentage difference errors for the best performing Chla algorithm. Improved performance is further achieved by allowing model type and specific parameterisation to vary across OWTs (i.e. multiple algorithms, multiple parameterisations). This adaptive framework for the dynamic selection

关键词： algorithm validation Chlorophyll-a Water quality Inland waters Case 2 waters Remote sensing Optical water type

来源：评论

学校读者我要写书评

暂无评论

The Role of the ACR Data Science Institute in Advancing Health Equity in Radiology

引用

JOURNAL OF THE AMERICAN COLLEGE OF RADIOLOGY 2019年第4期16卷 644-648页

作者： Allen, Bibb Dreye, Keith Grandview Med Ctr Dept Radiol 3690 Grandview Pkwy Birmingham AL 35243 USA ACR Data Sci Inst Reston VA USA Massachusetts Gen Hosp Dept Radiol Boston MA 02114 USA

Commercially available artificial intelligence (AI) algorithms outside of health care have been shown to be susceptible to ethnic, gender, and social bias, which has important implications in the development of Al algorithms in health care and the radiologic sciences. To prevent the introduction bias in health care AI, the physician community should work with developers and regulators to develop pathways to ensure that algorithms marketed for widespread clinical practice are safe, effective, and free of unintended bias. The ACR Data Science Institute has developed structured Al use cases with data elements that allow the development of standardized data sets for AI testing and training across multiple institutions to promote the availability of diverse data for algorithm development. Additionally, the ACR Data Science Institute validation and monitoring services, ACR Certify-AI and ACR Assess-AI, incorporate standards to mitigate algorithm bias and promote health equity. In addition to promoting diversity, the ACR should promote and advocate for payment models for AI that afford access to AI tools for all of our patients regardless of socioeconomic status or the inherent resources of their health systems.

关键词： Artificial intelligence algorithm bias structured AI use cases algorithm training algorithm validation

来源：评论

学校读者我要写书评

暂无评论

A synthetic dataset for Visual SLAM evaluation

引用

ROBOTICS AND AUTONOMOUS SYSTEMS 2020年第0期124卷 103336-000页

作者： Wang, Senbo Yue, Jiguang Dong, Yanchao He, Shibo Wang, Haotian Ning, Shaochun Tongji Univ Dept Control Sci & Engn 4800 Caoan Rd Shanghai Peoples R China Tongji Univ Dept Control Theory & Control Engn 4800 Caoan Rd Shanghai Peoples R China Tongji Univ 4800 Caoan Rd Shanghai Peoples R China

Vision-based self-localization methods are key functionalities for various research topics. Recent research results on related fields have catalyzed several accurate, versatile and reliable real-time Visual SLAM systems suitable for self-localization under a wide variety of environmental preconditions. These methods extend their functionalities from being only a good camera tracker to being able to recursively build up camera's surroundings. The fast development of Visual SLAM research has proposed demands on innovating evaluation methods for Visual SLAM systems. However, retrieving images and ground truth from various kinds of environments, estimating calibration parameters between several sensors and annotating useful labels all require cumbersome human labor and will introduce inevitable errors. In this paper, we propose a method that uses virtually established models to automatically generate photorealistic images with accurate ground truth and several kinds of pixel-level annotations useful for Visual SLAM development and evaluation. We build and render a challenging dataset in low-texture environments with large scale camera movement, multiple moving objects and varying luminance status. We also propose several new evaluation criteria that can fully take advantage of ground truth and annotations from synthetic datasets. Experiments are conducted using the proposed datasets and criteria with several state-of-the-art Visual SLAM methods to demonstrate the functionality of our datasets. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Synthetic dataset Computer graphic Visual SLAM algorithm validation Evaluation criteria

来源：评论

学校读者我要写书评

暂无评论

Collision Avoidance in Fixed-Wing UAV Formation Flight Based on a Consensus Control algorithm

引用

IEEE ACCESS 2018年 6卷 43672-43682页

作者： Zhang, Jialong Yan, Jianguo Zhang, Pu Kong, Xiangjie Northwestern Polytech Univ Sch Automat Xian 710129 Shaanxi Peoples R China Dalian Univ Technol Sch Software Key Lab Ubiquitous Network & Serv Software Liaoni Dalian 116620 Peoples R China

This paper addresses a collision avoidance problem for multiple unmanned aerial vehicles (UAVs) in the process of high-speed flight, thereby enabling UAV cooperative formation flight and effective mission completion. The main contribution is to propose a collision avoidance control algorithm for a multi-UAV system based on a bi-directional network connection structure. To effectively avoid collisions between UAVs and between UAVs and obstacles, the proposed consensus-based algorithm and a "leader-follower" control strategy are simultaneously applied for UAV formation control to ensure the convergence of the formation. Each of the UAVs has the same forward velocity and heading angle in the horizontal plane, and they maintain a constant relative distance in the vertical direction. This paper proposes a consensus-based collision avoidance algorithm for multiple UAVs based on an improved artificial potential field method. Simulation tests involving multiple UAVs were performed to validate the proposed control algorithm and to provide a reference for engineering applications.

关键词： Bidirectional network connection consensus -based control algorithm collision avoidance algorithm validation engineering application

来源：评论

学校读者我要写书评

暂无评论

A New algorithm for the Retrieval of Atmospheric Profiles from GNSS Radio Occultation Data in Moist Air and Comparison to 1DVar Retrievals

引用

REMOTE SENSING 2019年第23期11卷 2729-2729页

作者： Li, Ying Kirchengast, Gottfried Scherllin-Pirscher, Barbara Schwaerz, Marc Nielsen, Johannes K. Ho, Shu-peng Yuan, Yun-bin Chinese Acad Sci IGG State Key Lab Geodesy & Earths Dynam 340 Xudong Rd Wuhan 430077 Peoples R China Graz Univ Wegener Ctr Climate & Global Change WEGC Brandhofgasse 58010 Graz Austria Graz Univ Inst Phys Inst Geophys Astrophys & Meteorol Brandhofgasse 58010 Graz Austria Zentralanstalt Meteorol & Geodynam ZAMG A-381190 Vienna Austria DMI Lyngbyvej 100 DK-2100 Copenhagen Denmark NOAA NESDIS STAR SMCDCtr Weather & Climate Predict 5830 Univ Res CourtColl Pk College Pk MD 20740 USA

The Global Navigation Satellite System (GNSS) Radio Occultation (RO) is a key technique for obtaining thermodynamic profiles of temperature, humidity, pressure, and density in the Earth's troposphere. However, due to refraction effects of both the dry air and water vapor at low altitudes, retrieval of accurate profiles is challenging. Here we introduce a new moist air retrieval algorithm aiming to improve the quality of RO-retrieved profiles in moist air and including uncertainty estimation in a clear sequence of steps. The algorithm first uses RO dry temperature and pressure and background temperature/humidity and their uncertainties to retrieve humidity/temperature and their uncertainties. These temperature and humidity profiles are then combined with their corresponding background profiles by optimal estimation employing inverse-variance weighting. Finally, based on the optimally estimated temperature and humidity profiles, pressure and density profiles are computed using hydrostatic and equation-of-state formulas. The input observation and background uncertainties are dynamically estimated, accounting for spatial and temporal variations. We show results from applying the algorithm on test datasets, deriving insights from both individual profiles and statistical ensembles, and from comparison to independent 1D-Variational (1DVar) algorithm-derived moist air retrieval results from Radio Occultation Meteorology Satellite Application Facility Copenhagen (ROM-SAF) and University Corporation for Atmospheric Research (UCAR) Boulder RO processing centers. We find that the new scheme is comparable in its retrieval performance and features advantages in the integrated uncertainty estimation that includes both estimated random and systematic uncertainties and background bias correction. The new algorithm can therefore be used to obtain high-quality tropospheric climate data records including uncertainty estimation.

关键词： GNSS atmospheric sounding radio occultation moist air retrieval uncertainty propagation algorithm validation

来源：评论

学校读者我要写书评

暂无评论

A path to next-generation reproducibility in cheminformatics

引用

JOURNAL OF CHEMINFORMATICS 2019年第1期11卷 62-62页

作者： Clark, Robert D. Simulat Plus Inc 42505 10th St West Lancaster CA 93534 USA

Currently, the submission guidelines for the Journal of Cheminformatics say it will "only publish research or software that is entirely reproducible by third parties." They go on to specify that being reproducible means that anything essential to the conclusion of the paper be freely accessible and states that source code must be provided. I submit that this definition of reproducibility is too narrow-that a cheminformatics method can only truly be replicated by reimplementing it from a detailed, step-by-step high-level description to determine how reliably the algorithm per se does what it is intended to do.

关键词： Reproducibility Consilience Triangulation Replicability Reimplementation algorithm validation

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：