HW platform for BMS algorithm validation

2018 ◽  
Author(s):  
Luca Buccolini ◽  
Federico Garbuglia ◽  
Matteo Unterhorst ◽  
Massimo Conti
Keyword(s):  
Algorithm Validation

Operational snow monitoring on the Tibetan plateau by using SSM/I data and algorithm validation

2003 ◽  
Author(s):  
Feng Gao ◽  
Xin Li ◽  
R. L. Armstrong ◽  
Jiemin Wang ◽  
Tao Che ◽  
...  
Keyword(s):  
Tibetan Plateau ◽  
The Tibetan Plateau ◽  
Algorithm Validation

scholarly journals Towards a long-term dataset of ELBARA-II measurements assisting SMOS level-3 land product and algorithm validation at the Valencia Anchor Station

2015 ◽  
pp. 55
Author(s):  
R. Fernandez Moran ◽  
J. P. Wigneron ◽  
E. Lopez-Baeza ◽  
M. Miernecki ◽  
P. Salgado-Hernanz ◽  
...  
Keyword(s):  
Soil Moisture ◽  
Anchor Station ◽  
Ocean Salinity ◽  
Algorithm Validation ◽  
Level 3

La misión de SMOS (Soil Moisture and Ocean Salinity) se lanzó el 2 de Noviembre de 2009 con el objetivo de proporcionar datos de humedad del suelo y salinidad del mar. La principal actividad de la conocida como Valencia Anchor Station (VAS) es asistir en la validación a largo plazo de productos de suelo de SMOS. El presente estudio se centra en una validación de datos de nivel 3 de SMOS en la VAS con medidas in situ tomadas en el periodo 2010-2012. El radiómetro Elbara-II está situado dentro de los confines de la VAS, observando un campo de viñedos que se considera representativo de una gran proporción de un área de 50×50 km, suficiente para cubrir un footprint de SMOS. Las temperaturas de brillo (TB) adquiridas por ELBARA-II se compararon con las observadas por SMOS en las mismas fechas y horas. También se utilizó la inversión del modelo L-MEB con el fin de obtener humedades de suelo (SM) que, posteriormente, se compararon con datos de nivel 3 de SMOS. Se ha encontrado una buena correlación entre ambas series de TB, con mejoras año tras año, achacable fundamentalmente a la disminución de precipitaciones en el periodo objeto de estudio y a la mitigación de las interferencias por radiofrecuencia en banda L. La mayor homogeneidad del footprint del radiómetro ELBARA-II frente al de SMOS explica la mayor variabilidad de sus TB. Los periodos de precipitación más intensa (primavera y otoño) también son de mayor SM, lo que corrobora la consistencia de los resultados de SM simulados a través de las observaciones del radiómetro. Sin embargo, se debe resaltar una subestimación por parte de SMOS de los valores de SM respecto a los obtenidos por ELBARA-II, presumiblemente debido a la influencia que la pequeña fracción de suelo no destinado al cultivo de la vid tiene sobre SMOS. Las estimaciones por parte de SMOS en órbita descendente (6 p.m.) resultaron de mayor calidad (mayor correlación y menores RMSE y bias) que en órbita ascendente (6 a.m., momento de mayor humedad de suelo).

Algorithm Validation of the Current Profile Reconstruction of EAST Based on Polarimeter/Interferometer

2015 ◽  
Vol 17 (1) ◽  
pp. 75-79 ◽  
Author(s):  
Jinping Qian ◽  
Qilong Ren ◽  
Baonian Wan ◽  
Haiqin Liu ◽  
Long Zeng ◽  
...  
Keyword(s):  
Current Profile ◽  
Algorithm Validation ◽  
Profile Reconstruction

scholarly journals A new framework to map fine resolution cropping intensity across the globe: Algorithm, validation, and implication

2020 ◽  
Vol 251 ◽  
pp. 112095
Author(s):  
Chong Liu ◽  
Qi Zhang ◽  
Shiqi Tao ◽  
Jiaguo Qi ◽  
Mingjun Ding ◽  
...  
Keyword(s):  
Cropping Intensity ◽  
Algorithm Validation ◽  
Fine Resolution ◽  
New Framework

scholarly journals Artificial intelligence-enabled screening for diabetic retinopathy: a real-world, multicenter and prospective study

2020 ◽  
Vol 8 (1) ◽  
pp. e001596
Author(s):  
Yifei Zhang ◽  
Juan Shi ◽  
Ying Peng ◽  
Zhiyun Zhao ◽  
Qidong Zheng ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Diabetic Retinopathy ◽  
Interobserver Variability ◽  
Classification Performance ◽  
Early Screening ◽  
Algorithm Validation ◽  
Patients With Diabetes ◽  
Registration Number ◽  
Classification Images ◽  
Design And Methods

IntroductionEarly screening for diabetic retinopathy (DR) with an efficient and scalable method is highly needed to reduce blindness, due to the growing epidemic of diabetes. The aim of the study was to validate an artificial intelligence-enabled DR screening and to investigate the prevalence of DR in adult patients with diabetes in China.Research design and methodsThe study was prospectively conducted at 155 diabetes centers in China. A non-mydriatic, macula-centered fundus photograph per eye was collected and graded through a deep learning (DL)-based, five-stage DR classification. Images from a randomly selected one-third of participants were used for the DL algorithm validation.ResultsIn total, 47 269 patients (mean (SD) age, 54.29 (11.60) years) were enrolled. 15 805 randomly selected participants were reviewed by a panel of specialists for DL algorithm validation. The DR grading algorithms had a 83.3% (95% CI: 81.9% to 84.6%) sensitivity and a 92.5% (95% CI: 92.1% to 92.9%) specificity to detect referable DR. The five-stage DR classification performance (concordance: 83.0%) is comparable to the interobserver variability of specialists (concordance: 84.3%). The estimated prevalence in patients with diabetes detected by DL algorithm for any DR, referable DR and vision-threatening DR were 28.8% (95% CI: 28.4% to 29.3%), 24.4% (95% CI: 24.0% to 24.8%) and 10.8% (95% CI: 10.5% to 11.1%), respectively. The prevalence was higher in female, elderly, longer diabetes duration and higher glycated hemoglobin groups.ConclusionThis study performed, a nationwide, multicenter, DL-based DR screening and the results indicated the importance and feasibility of DR screening in clinical practice with this system deployed at diabetes centers.Trial registration numberNCT04240652.

scholarly journals Can Chemotherapy-Related Acute Care Visits Be Accurately Identified in Administrative Data?

2018 ◽  
Vol 14 (1) ◽  
pp. e51-e58 ◽  
Author(s):  
Monika K. Krzyzanowska ◽  
Katherine Enright ◽  
Rahim Moineddin ◽  
Lingsong Yun ◽  
Melanie Powis ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Emergency Department ◽  
Adjuvant Chemotherapy ◽  
Acute Care ◽  
Administrative Data ◽  
Validation Cohort ◽  
Early Stage ◽  
Early Stage Breast Cancer ◽  
Algorithm Validation ◽  
Ed Visits

Purpose: There is increasing interest in using administrative data to examine treatment-related complications that lead to emergency department (ED) visits or hospitalizations (H). The purpose of this study was to evaluate the reliability of billing codes for identifying chemotherapy-related acute care visits (CRVs) among women with early-stage breast cancer. Materials and Methods: The cohort was identified by using deterministically linked health databases and consisted of women who were diagnosed with early-stage breast cancer who started adjuvant chemotherapy between 2007 and 2009 in Ontario, Canada. A random sample of 496 patient cases was chosen as the validation cohort. Sensitivity (SN) and specificity (SP) were calculated for three scenarios: chemotherapy-related ED visit, chemotherapy-related H, and febrile neutropenia (FN)–related visit. For FN-related visits, three definitions were considered: general, moderate, and strict. Results: The administrative cohort consisted of 8,359 patients, 43.4% of whom had at least one ED or H, including 1,496 women who had multiple visits that resulted in 6,293 unique visits. Of these, 73.1% were considered CRVs. The algorithm performed well in identifying CRVs that included H either from ED (SN, 90%; SP, 100%) or directly from home (SN, 91%; SP, 93%), but less well for ED visits that did not result in H (SN, 65%; SP, 80%). Depending on which FN algorithm was used, 4.8% to 24% of visits were considered related. The moderate FN algorithm provided the best tradeoff between SN (69% to 97%) and SP (83% to 98%). Conclusion: Administrative data can be valuable in evaluating chemotherapy-related serious events. Algorithm validation in other cohorts is needed.

Issues impacting genetic network reverse engineering algorithm validation using small networks

2012 ◽  
Vol 1824 (12) ◽  
pp. 1434-1441 ◽  
Author(s):  
Nguyen Xuan Vinh ◽  
Madhu Chetty ◽  
Ross Coppel ◽  
Pramod P. Wangikar
Keyword(s):  
Reverse Engineering ◽  
Genetic Network ◽  
Algorithm Validation
Sign in / Sign up

Export Citation Format

Share Document