scholarly journals Optimal Estimation of the Climatological Mean

2009 ◽  
Vol 22 (18) ◽  
pp. 4845-4859 ◽  
Author(s):  
Balachandrudu Narapusetty ◽  
Timothy DelSole ◽  
Michael K. Tippett
Keyword(s):  
Spectral Method ◽  
Spectral Methods ◽  
Cross Validation ◽  
Optimal Estimation ◽  
Sea Surface ◽  
Least Squares Fit ◽  
Straightforward Consequence ◽  
Independent Parameters ◽  
Special Case ◽  
Validation Experiments

Abstract This paper shows theoretically and with examples that climatological means derived from spectral methods predict independent data with less error than climatological means derived from simple averaging. Herein, “spectral methods” indicates a least squares fit to a sum of a small number of sines and cosines that are periodic on annual or diurnal periods, and “simple averaging” refers to mean averages computed while holding the phase of the annual or diurnal cycle constant. The fact that spectral methods are superior to simple averaging can be understood as a straightforward consequence of overfitting, provided that one recognizes that simple averaging is a special case of the spectral method. To illustrate these results, the two methods are compared in the context of estimating the climatological mean of sea surface temperature (SST). Cross-validation experiments indicate that about four harmonics of the annual cycle are adequate, which requires estimation of nine independent parameters. In contrast, simple averaging of daily SST requires estimation of 366 parameters—one for each day of the year, which is a factor of 40 more parameters. Consistent with the greater number of parameters, simple averaging poorly predicts samples that were not included in the estimation of the climatological mean, compared to the spectral method. In addition to being more accurate, the spectral method also accommodates leap years and missing data simply, results in a greater degree of data compression, and automatically produces smooth time series.

scholarly journals Towards computer-aided severity assessment via deep neural networks for geographic and opacity extent scoring of SARS-CoV-2 chest X-rays

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
A. Wong ◽  
Z. Q. Lin ◽  
L. Wang ◽  
A. G. Chung ◽  
B. Shen ◽  
...  
Keyword(s):  
Neural Networks ◽  
Monte Carlo ◽  
Lung Disease ◽  
Disease Severity ◽  
Deep Neural Networks ◽  
Cross Validation ◽  
X Rays ◽  
Computer Aided ◽  
Monte Carlo Cross Validation ◽  
Validation Experiments

AbstractA critical step in effective care and treatment planning for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the cause for the coronavirus disease 2019 (COVID-19) pandemic, is the assessment of the severity of disease progression. Chest x-rays (CXRs) are often used to assess SARS-CoV-2 severity, with two important assessment metrics being extent of lung involvement and degree of opacity. In this proof-of-concept study, we assess the feasibility of computer-aided scoring of CXRs of SARS-CoV-2 lung disease severity using a deep learning system. Data consisted of 396 CXRs from SARS-CoV-2 positive patient cases. Geographic extent and opacity extent were scored by two board-certified expert chest radiologists (with 20+ years of experience) and a 2nd-year radiology resident. The deep neural networks used in this study, which we name COVID-Net S, are based on a COVID-Net network architecture. 100 versions of the network were independently learned (50 to perform geographic extent scoring and 50 to perform opacity extent scoring) using random subsets of CXRs from the study, and we evaluated the networks using stratified Monte Carlo cross-validation experiments. The COVID-Net S deep neural networks yielded R$$^2$$ 2 of $$0.664 \pm 0.032$$ 0.664 ± 0.032 and $$0.635 \pm 0.044$$ 0.635 ± 0.044 between predicted scores and radiologist scores for geographic extent and opacity extent, respectively, in stratified Monte Carlo cross-validation experiments. The best performing COVID-Net S networks achieved R$$^2$$ 2 of 0.739 and 0.741 between predicted scores and radiologist scores for geographic extent and opacity extent, respectively. The results are promising and suggest that the use of deep neural networks on CXRs could be an effective tool for computer-aided assessment of SARS-CoV-2 lung disease severity, although additional studies are needed before adoption for routine clinical use.

scholarly journals Interclass Interference Suppression in Multi-Class Problems

2021 ◽  
Vol 11 (1) ◽  
pp. 450
Author(s):  
Jinfu Liu ◽  
Mingliang Bai ◽  
Na Jiang ◽  
Ran Cheng ◽  
Xianling Li ◽  
...  
Keyword(s):  
Classification Accuracy ◽  
Cross Validation ◽  
Selection Process ◽  
Interference Suppression ◽  
Generalization Ability ◽  
Suppression Effect ◽  
Binary Classifiers ◽  
The One ◽  
Fold Cross Validation ◽  
Validation Experiments

Multi-classifiers are widely applied in many practical problems. But the features that can significantly discriminate a certain class from others are often deleted in the feature selection process of multi-classifiers, which seriously decreases the generalization ability. This paper refers to this phenomenon as interclass interference in multi-class problems and analyzes its reason in detail. Then, this paper summarizes three interclass interference suppression methods including the method based on all-features, one-class classifiers and binary classifiers and compares their effects on interclass interference via the 10-fold cross-validation experiments in 14 UCI datasets. Experiments show that the method based on binary classifiers can suppress the interclass interference efficiently and obtain the best classification accuracy among the three methods. Further experiments were done to compare the suppression effect of two methods based on binary classifiers including the one-versus-one method and one-versus-all method. Results show that the one-versus-one method can obtain a better suppression effect on interclass interference and obtain better classification accuracy. By proposing the concept of interclass inference and studying its suppression methods, this paper significantly improves the generalization ability of multi-classifiers.

scholarly journals A Skillful Prediction Model for Winter NAO Based on Atlantic Sea Surface Temperature and Eurasian Snow Cover

2015 ◽  
Vol 30 (1) ◽  
pp. 197-205 ◽  
Author(s):  
Baoqiang Tian ◽  
Ke Fan
Keyword(s):  
Prediction Model ◽  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Snow Cover ◽  
Correlation Coefficient ◽  
Cross Validation ◽  
Sea Surface ◽  
Interdecadal Variability ◽  
Eurasian Snow Cover ◽  
Eurasian Snow

Abstract A new statistical forecast scheme, referred to as scheme 1, is developed using observed autumn Atlantic sea surface temperature (SST) and Eurasian snow cover in the preceding autumn to predict the upcoming winter North Atlantic Oscillation (NAO) using the year-to-year increment prediction approach (i.e., DY approach). Two predictors for the year-to-year increment are identified that are available in the preceding autumn. Cross-validation tests for the period 1950–2011 and independent hindcasts for the period 1990–2011 are performed to validate the prediction ability of the proposed technique. The cross-validation test results for 1950–2011 reveal a high correlation coefficient of 0.52 (0.58) between the predicted and observed NAO indices (DY of the NAO). The model also successfully predicts the independent hindcasts for the period 1990–2011 with a correlation coefficient of 0.55 (0.74). In addition, scheme 0 (i.e., anomaly approach) is established using the SST and snow cover anomalies during the preceding autumn. Compared with scheme 0, this new prediction model has higher predictive skill in reproducing the interdecadal variability of NAO. Therefore, this study provides an effective climate prediction scheme for the interannual and interdecadal variability of NAO in boreal winter.

Sea surface temperature from a geostationary satellite by optimal estimation

2009 ◽  
Vol 113 (2) ◽  
pp. 445-457 ◽  
Author(s):  
C.J. Merchant ◽  
P. Le Borgne ◽  
H. Roquet ◽  
A. Marsouin
Keyword(s):  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Optimal Estimation ◽  
Geostationary Satellite ◽  
Sea Surface

scholarly journals EvoMBN: Evolving Multi-Branch Networks on Myocardial Infarction Diagnosis Using 12-Lead Electrocardiograms

Biosensors ◽  
2021 ◽  
Vol 12 (1) ◽  
pp. 15
Author(s):  
Wenhan Liu ◽  
Jiewei Ji ◽  
Sheng Chang ◽  
Hao Wang ◽  
Jin He ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Cross Validation ◽  
Accurate Diagnosis ◽  
Fitness Evaluation ◽  
Flexible Architecture ◽  
Encoding Method ◽  
Fully Connected ◽  
Detection And Localization ◽  
Architecture Optimization ◽  
Validation Experiments

Multi-branch Networks (MBNs) have been successfully applied to myocardial infarction (MI) diagnosis using 12-lead electrocardiograms. However, most existing MBNs share a fixed architecture. The absence of architecture optimization has become a significant obstacle to a more accurate diagnosis for these MBNs. In this paper, an evolving neural network named EvoMBN is proposed for MI diagnosis. It utilizes a genetic algorithm (GA) to automatically learn the optimal MBN architectures. A novel fixed-length encoding method is proposed to represent each architecture. In addition, the crossover, mutation, selection, and fitness evaluation of the GA are defined to ensure the architecture can be optimized through evolutional iterations. A novel Lead Squeeze and Excitation (LSE) block is designed to summarize features from all the branch networks. It consists of a fully-connected layer and an LSE mechanism that assigns weights to different leads. Five-fold inter-patient cross validation experiments on MI detection and localization are performed using the PTB diagnostic database. Moreover, the model architecture learned from the PTB database is transferred to the PTB-XL database without any changes. Compared with existing studies, our EvoMBN shows superior generalization and the efficiency of its flexible architecture is suitable for auxiliary MI diagnosis in real-world.

scholarly journals Transfer-to-Transfer Learning Approach for Computer Aided Detection of COVID-19 in Chest Radiographs

AI ◽  
2020 ◽  
Vol 1 (4) ◽  
pp. 539-557 ◽  
Author(s):  
Barath Narayanan ◽  
Russell Hardie ◽  
Vignesh Krishnaraja ◽  
Christina Karam ◽  
Venkata Davuluru
Keyword(s):  
Transfer Learning ◽  
Cross Validation ◽  
Class Imbalance ◽  
Chest Radiographs ◽  
Training Dataset ◽  
Learning Approach ◽  
Computer Aided Detection ◽  
Computer Aided ◽  
Fold Cross Validation ◽  
Validation Experiments

The coronavirus disease 2019 (COVID-19) global pandemic has severely impacted lives across the globe. Respiratory disorders in COVID-19 patients are caused by lung opacities similar to viral pneumonia. A Computer-Aided Detection (CAD) system for the detection of COVID-19 using chest radiographs would provide a second opinion for radiologists. For this research, we utilize publicly available datasets that have been marked by radiologists into two-classes (COVID-19 and non-COVID-19). We address the class imbalance problem associated with the training dataset by proposing a novel transfer-to-transfer learning approach, where we break a highly imbalanced training dataset into a group of balanced mini-sets and apply transfer learning between these. We demonstrate the efficacy of the method using well-established deep convolutional neural networks. Our proposed training mechanism is more robust to limited training data and class imbalance. We study the performance of our algorithm(s) based on 10-fold cross validation and two hold-out validation experiments to demonstrate its efficacy. We achieved an overall sensitivity of 0.94 for the hold-out validation experiments containing 2265 and 2139 marked as COVID-19 chest radiographs, respectively. For the 10-fold cross validation experiment, we achieve an overall Area under the Receiver Operating Characteristic curve (AUC) value of 0.996 for COVID-19 detection. This paper serves as a proof-of-concept that an automated detection approach can be developed with a limited set of COVID-19 images, and in areas with scarcity of trained radiologists.

On wave breaking and the equilibrium spectrum of wind-generated waves

1969 ◽  
Vol 310 (1501) ◽  
pp. 151-159 ◽  
Keyword(s):  
Drag Coefficient ◽  
Wave Breaking ◽  
Low Frequency ◽  
Spectral Density Function ◽  
Sea Surface ◽  
Sea State ◽  
Wave Cycle ◽  
Equilibrium Spectrum ◽  
Special Case ◽  
Made In

A theoretical calculation is made of the loss of energy by wave breaking in a random sea state in terms of the spectral density function. In the special case of the equilibrium spectrum F(σ) = αg 2 σ -5 the proportion ɷ of energy lost per mean wave cycle is found to be given by ω ≑ e -1/8α irrespective of the low-frequency cut-off in the spectrum. Assuming that in the equilibrium state the loss of energy by breaking is comparable to that supplied by the wind, one can estimate the constant α in terms of the drag coefficient of the wind on the sea surface. It is found that α≑ -1/8/ln[1600C 3/2 ( ρ air/ ρ water)]. Taking a representative value of C one finds α ≑ 1.3 x 10 -2 , which falls within the range of observed values of α. The above equation for α is rather insensitive to the various assumptions made in the analysis. There is some evidence, derived from observation, that α may not in fact be quite constant, but may decrease slightly as the wave age ( gt/U ) or the non-dimensional fetch ( gx/U 2 ) is increased. It is suggested that the drag coefficient may behave similarly.

Chebyshev Collocation Spectral Methods for Coupled Radiation and Conduction in a Concentric Spherical Participating Medium

2009 ◽  
Vol 131 (6) ◽  
Author(s):  
Ben-Wen Li ◽  
Ya-Song Sun ◽  
Da-Wei Zhang
Keyword(s):  
Spectral Method ◽  
Spectral Methods ◽  
Discrete Ordinates ◽  
Conductive Heat ◽  
Discrete Ordinates Method ◽  
Chebyshev Collocation ◽  
Collocation Points ◽  
Collocation Spectral Method ◽  
Space Dependence ◽  
Very High

The Chebyshev collocation spectral method for coupled radiative and conductive heat transfer in concentric spherical participating medium is introduced and formulated. The angular dependence of the problem is discretized by conventional discrete ordinates method, and the space dependence is expressed by Chebyshev polynomial and discretized by collocation spectral method. Due to the exponential convergence of the spectral methods, very high accuracy can be obtained even using a small resolution (i.e., number of collocation points) for present problems. Comparisons between the solutions from Chebyshev collocation spectral–discrete ordinates method (SP-DOM) with available numerical or exact solutions in references indicate that the SP-DOM for the combination of radiation and conduction in concentric spherical participating medium is accurate and efficient.

Sign in / Sign up

Export Citation Format

Share Document