An empirical study into annotator agreement, ground truth estimation, and algorithm evaluation

TA Lampert, A Stumpf… - IEEE Transactions on …, 2016 - ieeexplore.ieee.org
Although agreement between the annotators who mark feature locations within images has
been studied in the past from a statistical viewpoint, little work has attempted to quantify the …

[HTML][HTML] Exploring the usefulness of downscaling free forecasts from the Warn-on-Forecast System

WJS Miller, CK Potvin, ML Flora… - Weather and …, 2022 - journals.ametsoc.org
Abstract The National Severe Storms Laboratory (NSSL) Warn-on-Forecast System (WoFS)
is an experimental real-time rapidly updating convection-allowing ensemble that provides …

An error recognition method for power equipment defect records based on knowledge graph technology

H Wang, Z Liu - Frontiers of Information Technology & Electronic …, 2019 - Springer
To recognize errors in the power equipment defect records in real time, we propose an error
recognition method based on knowledge graph technology. According to the characteristics …

Smartphone-based hard-braking event detection at scale for road safety services

L Liu, D Racz, K Vaillancourt, J Michelman… - … research part C …, 2023 - Elsevier
Road crashes are the sixth leading cause of lost disability-adjusted life-years (Daly s)
worldwide. One major challenge in traffic safety research is the sparsity of crashes, which …

Characterizing and identifying reverted commits

M Yan, X Xia, D Lo, AE Hassan, S Li - Empirical Software Engineering, 2019 - Springer
In practice, a popular and coarse-grained approach for recovering from a problematic
commit is to revert it (ie, undoing the change). However, reverted commits could induce …

[HTML][HTML] Diagnosing supercell environments: A machine learning approach

SA Shield, AL Houston - Weather and Forecasting, 2022 - journals.ametsoc.org
The importance of discriminating between environments supportive of supercell
thunderstorms and those that are not supportive is widely recognized due to significant …

Sensitivity and Specificity versus Precision and Recall, and Related Dilemmas

W Cullerne Bown - Journal of Classification, 2024 - Springer
Many evaluations of binary classifiers begin by adopting a pair of indicators, most often
sensitivity and specificity or precision and recall. Despite this, we lack a general, pan …

基于知识图谱技术的电力设备缺陷记录错误识别方法

H Wang, Z Liu, AH Wang, AZ Liu - Frontiers, 2019 - jzus.zju.edu.cn
为实时检测缺陷记录的录入错误, 提出一种基于知识图谱技术的电力设备缺陷记录错误识别方法
. 针对电力缺陷文本特点, 通过优化构建知识图谱的一般流程, 提出利用现有电力设备缺陷记录 …

Exploring the Usefulness of Downscaling Free Forecasts from the Warn-on-Forecast System

WJS Millera, CK Potvinb, ML Floraa, BT Galloa… - 2021 - journals.ametsoc.org
Abstract The National Severe Storms Lab (NSSL) Warn-on-Forecast System (WoFS) is an
experimental real-time rapidly-updating convection-allowing ensemble that provides …