Leave-$p$ -Out Cross-Validation Test for Uncertain Verhulst-Pearl Model With Imprecise Observations

Background: β thalassemia is a common monogenic genetic disease that is very harmful to human health. The disease arises is due to the deletion of or defects in β-globin, which reduces synthesis of the β-globin chain, resulting in a relatively excess number of α-chains. The formation of inclusion bodies deposited on the cell membrane causes a decrease in the ability of red blood cells to deform and a group of hereditary haemolytic diseases caused by massive destruction in the spleen. Methods: In this work, machine learning algorithms were employed to build a prediction model for inhibitors against K562 based on 117 inhibitors and 190 non-inhibitors. Results: The overall accuracy (ACC) of a 10-fold cross-validation test and an independent set test using Adaboost were 83.1% and 78.0%, respectively, surpassing Bayes Net, Random Forest, Random Tree, C4.5, SVM, KNN and Bagging. Conclusion: This study indicated that Adaboost could be applied to build a learning model in the prediction of inhibitors against K526 cells.

Download Full-text

Leaf geometric morphometrics among populations of Dalbergia ecastaphyllum (L.) Taub.

Bioscience Journal ◽

10.14393/bj-v35n6a2019-39814 ◽

2019 ◽

Vol 35 (6) ◽

Author(s):

Daniel Vieira de Morais ◽

Lorena Andrade Nunes ◽

Vandira Pereira da Mata ◽

Maria Angélica Pereira de Carvalho Costa ◽

Geni da Silva Sodré ◽

...

Keyword(s):

Principal Component Analysis ◽

Geometric Morphometrics ◽

Cross Validation ◽

Abiotic Factors ◽

Principal Component ◽

Canonical Variate ◽

Validation Test ◽

Significant Difference ◽

Variate Analysis ◽

Geographical Distances

Leaves are plant structures that express important traits of the environment where they live. Leaf description has allowed identification of plant species as well as investigation of abiotic factors effects on their development, such as gases, light, temperature, and herbivory. This study described populations of Dalbergia ecastaphyllum through leaf geometric morphometrics in Brazil. We evaluated 200 leaves from four populations. The principal component analysis (PCA) showed that the first four principal components were responsible for 97.81% of variation. The non-parametric multivariate analysis of variance (NPMANOVA) indicated significant difference between samples (p = 0.0001). The Mentel test showed no correlation between geographical distances and shape. The canonical variate analysis (CVA) indicated that the first two variables were responsible for 96.77 % of total variation, while the cross-validation test showed an average of 83.33%. D. ecastaphyllum leaves are elliptical and ovate.

Download Full-text

Development of multistage 10-m shuttle run test for VO2max estimation in healthy adults

10.31083/jomh.2021.066 ◽

2021 ◽

Keyword(s):

Cross Validation ◽

Age Groups ◽

Healthy Adults ◽

Coefficient Of Determination ◽

Validation Test ◽

Uniform Distributions ◽

Gender And Age ◽

Run Test ◽

Shuttle Run ◽

Spatial Limitation

Background and objective: The disadvantage of the traditional 20-m multistage shuttle run test (MST) is that it requires a long space for measurements and does not include various age groups to develop the test. Therefore, we developed a new MST to improve the spatial limitation by reducing the measurement to a 10-m distance and to resolve the bias via uniform distributions of gender and age. Material and methods: Study subjects included 120 healthy adults (60 males and 60 females) aged 20 to 50 years. All subjects performed a graded maximal exercise test (GXT) and a 10-m MST at ﬁve-day intervals. We developed a regression model using 70% of the subject's data and performed a cross-validation test using 30% of the data. Results: The male regression model's coeﬃcient of determination (R2) was 58.8%, and the standard error of estimation (SEE) was 4.17 mL/kg/min. The female regression model's R2 was 69.2%, and the SEE was 3.39 mL/kg/min. The 10-m MST showed a high correlation with GXT on the VO2max (males: 0.816; females: 0.821). In the cross-validation test for the developed regression models, the male's SEE was 4.38 mL/kg/min, and the female's SEE was 4.56 mL/kg/min. Conclusion: Thus, the 10-m MST is an accurate and valid method for estimating the VO2max. Therefore, the 10-m MST developed by us can be used when the existing 20-m MST cannot be used due to spatial limitations and can be applied to both men and women in their 20s and 50s.

Download Full-text

A New Approach to Forecasting Typhoon Frequency over the Western North Pacific

Weather and Forecasting ◽

10.1175/2009waf2222194.1 ◽

2009 ◽

Vol 24 (4) ◽

pp. 974-986 ◽

Cited By ~ 67

Author(s):

Ke Fan ◽

Huijun Wang

Keyword(s):

Prediction Model ◽

North Pacific ◽

Western North Pacific ◽

Cross Validation ◽

Forecast Model ◽

Multilinear Regression ◽

New Approach ◽

Validation Test ◽

Operational Forecasting ◽

Close Fit

Abstract This paper presents a new approach for forecasting the typhoon frequency of the western North Pacific (WNP). The year-to-year increase or decrease in typhoon frequency is first forecasted to yield a net typhoon frequency prediction. Five key predictors for the year-to-year increment in the number of typhoons in the WNP have been identified, and a forecast model is established using a multilinear regression method based on data taken from 1965 to 2001. Using the forecast model, a hindcast of the typhoon frequency of the WNP during 2002–07 is made. The model exhibited a reasonably close fit for the period 1965–2007, including the larger anomalies in 1997 and 1998. It also accounted for the smaller variability of the typhoon frequency of the WNP during the validation period 2002–07 with an average root-mean-square error (RMSE) of 1.3 (2.85) during 2002–07 (1965–2001). The cross-validation test of the prediction model shows that the new approach and the prediction model demonstrate better prediction skill when compared to the models established based on typhoon frequency rather than the typhoon frequency increment. Thus, this new approach has the potential to improve the operational forecasting skill for typhoon frequency in the WNP.

Download Full-text

Differentiation of Five Species of Megachile (Hymenoptera: Megachilidae), based on Wing Shape

Journal of Apicultural Science ◽

10.1515/jas-2016-0015 ◽

2016 ◽

Vol 60 (2) ◽

pp. 41-50 ◽

Cited By ~ 1

Author(s):

Shahram Falamarzi ◽

Behzad Habibpour ◽

Mohammad S. Mossadegh ◽

Alireza Monfared

Keyword(s):

Geometric Morphometrics ◽

Cross Validation ◽

Principal Component ◽

Wing Shape ◽

Canonical Variate ◽

Effective Technique ◽

Validation Test ◽

Variate Analysis ◽

Clear Differentiation ◽

Respective Species

Abstract In the present work we used landmark-based geometric morphometrics to compare the wing shapes of five species of Megachile (belonging to three subgenera) to confirm whether this technique may be used reliably for differentiation of this group. Analyses of wing shape by the use of principal component analysis (PCA), and canonical variate analysis (CVA) led to a clear differentiation among species. We found a close phenotypic similarity in wing shape between M. albisecta (belonging to the subgenus Creightonella) and M. picicornis (belonging to the subgenus Eutricharaea). According to the results of UPGMA, a higher degree of divergence between M. farinosa (belonging to the subgenus Pseudomegachile) and species belonging to other subgenera, was detected. The results of a cross-validation test indicated that geometric morphometrics is an effective technique to use for distinguishing between Megachile species. The reliability rate of this technique was between 85.71-100%. Using only two submarginal cell landmarks for generating shape variables, the cross-validation test correctly assigned individuals to their respective species, with a 92.85-100% reliability rate. Significant differences in wing size were obtained among the analysed species.

Download Full-text

RFAmyloid: A Web Server for Predicting Amyloid Proteins

International Journal of Molecular Sciences ◽

10.3390/ijms19072071 ◽

2018 ◽

Vol 19 (7) ◽

pp. 2071 ◽

Cited By ~ 14

Author(s):

Mengting Niu ◽

Yanjuan Li ◽

Chunyu Wang ◽

Ke Han

Keyword(s):

Feature Extraction ◽

Acid Composition ◽

Extraction Method ◽

Cross Validation ◽

Protein Composition ◽

Amyloid Protein ◽

Feature Extraction Method ◽

Validation Test ◽

Fibrous Protein ◽

Fold Cross Validation

Amyloid is an insoluble fibrous protein and its mis-aggregation can lead to some diseases, such as Alzheimer’s disease and Creutzfeldt–Jakob’s disease. Therefore, the identification of amyloid is essential for the discovery and understanding of disease. We established a novel predictor called RFAmy based on random forest to identify amyloid, and it employed SVMProt 188-D feature extraction method based on protein composition and physicochemical properties and pse-in-one feature extraction method based on amino acid composition, autocorrelation pseudo acid composition, profile-based features and predicted structures features. In the ten-fold cross-validation test, RFAmy’s overall accuracy was 89.19% and F-measure was 0.891. Results were obtained by comparison experiments with other feature, classifiers, and existing methods. This shows the effectiveness of RFAmy in predicting amyloid protein. The RFAmy proposed in this paper can be accessed through the URL http://server.malab.cn/RFAmyloid/.

Download Full-text

A cross validation test of four models for quantifying multiattribute preferences

Marketing Letters ◽

10.1007/bf00994355 ◽

1993 ◽

Vol 4 (4) ◽

pp. 369-380 ◽

Cited By ~ 31

Author(s):

Paul E. Green ◽

Abba M. Krieger ◽

Manoj K. Agarwal

Keyword(s):

Cross Validation ◽

Validation Test

Download Full-text

Radiomic Analysis of the Heterogeneous Tumor and Surrounding Parenchyma Based on DCE-MRI Decomposition to Predict HER2 Expression in Breast Cancer

10.21203/rs.3.rs-638341/v1 ◽

2021 ◽

Author(s):

Peng Zhang ◽

Juan Yan ◽

Zhongqi Liu ◽

Xiangsheng Li ◽

Qianxiang Zhou

Keyword(s):

Breast Cancer ◽

Contrast Enhancement ◽

Cross Validation ◽

Test Group ◽

Her2 Expression ◽

Breast Cancer Patients ◽

Enhancement Pattern ◽

Dce Mri ◽

Validation Test ◽

Heterogeneous Tumor

Abstract Background Human epidermal growth factor receptor-2 (HER2) correlates with cancer heterogeneity, and the identification of HER2 expression is invasive immunohistochemistry in the clinic. To determine whether noninvasive predictors of HER2 expression are implied in the dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).Methods 189/47 breast cancer patients collected from The Cancer Imaging Archive (TCIA) were used as a cross-validation/test group. A convex analysis of mixtures (CAM) was conducted to decompose heterogeneous tissues inside and outside the tumor. Their DCE-MRI images were decomposed into relatively homogeneous subregions with different contrast enhancement patterns. The predictor of HER2 expression was composed of radiomic features acquired from intratumoural or peritumoural subregions. The area under the curve (AUC) of receiver operating characteristic (ROC) was used to assess the predictive power.Results The predictor formed in the undecomposed tumor was used as a baseline for comparison (AUC=0.691±0.072/0.625±0.056 in cross-validation/test group). The intratumoural subregion with a contrast enhancement pattern corresponding to the plateau of signal intensity formed a more robust predictor (AUC=0.816±0.059/0.785±0.067, P=0.0128/0.0389). Peritumoral parenchyma of <20 mm from the tumor margin was also researched (AUC=0.589±0.083/0.524±0.064). The peritumoural subregion with a contrast enhancement pattern corresponding to steady enhancement also formed a helpful predictor compared to the undecomposed parenchyma (AUC=0.702±0.068/0.681±0.042, P=0.0128/0.0389). The best predictor was formed when two predictors from subregions were fused together (AUC=0.851±0.057/0.812±0.045, P=0.0011/0.0397).Conclusions A subregion rather than a heterogeneous tumor itself provided a more accurate predictor of HER2 expression. Radiomic predictors from intratumoural and peritumoural subregions were complementary to each other.

Download Full-text

Testing the seismic quiescence hypothesis through retrospective trials of alarm-based earthquake prediction in the Kurile–Japan subduction zone

Earth Planets and Space ◽

10.1186/s40623-021-01418-z ◽

2021 ◽

Vol 73 (1) ◽

Author(s):

Kei Katsumata ◽

Masao Nakatani

Keyword(s):

Subduction Zone ◽

Cross Validation ◽

Large Earthquake ◽

Detailed Comparison ◽

Seismic Quiescence ◽

Validation Test ◽

Forecast Models ◽

Japan Subduction Zone ◽

The Cross ◽

Validation Tests

AbstractWe make trial binary forecasts for the Kurile–Japan subduction zone for the period 1988–2014 by hypothesizing that seismic quiescence (i.e., the absence of earthquakes of M ≥ 5 for a minimum period of Tq) is a precursor of a large (7.5 ≤ Mw < 8.5) earthquake in the coming period Ta within a radius R of the quiescence. We evaluate the receiver-operating-characteristic diagram constructed using a range of forecast models specified by (Tq, R, Ta). A forecast experiment targeting eight large earthquakes in the studied spacetime suggests that the risk of a large earthquake is modestly (probability gain G ~ 2) but significantly (p-value less than 5%) heightened for several years following a long quiescent period of Tq ≥ 9 years, within several tens of kilometers of the quiescence. We then attempt cross-validation, where we use half the data for training [i.e., optimization of (Tq, R, Ta)] and the remaining half for evaluation. With only four target earthquakes available for evaluation of the forecasts in each of the learning and evaluation periods, our forecast scheme did not pass the cross-validation test (with a criterion that the p-value is less than 5%). Hence, we cannot formally deny the possibility that our positive results for the overall period are a ghost arising from over-fitting. However, through detailed comparison of optimal models in the overall test with those in the cross-validation tests, we argue that severe over-fitting is unlikely involved for the modest G of ~ 2 obtained in the overall test. There is thus a reasonable chance that the presently tested type of quiescence will pass the cross-validation test when more target earthquakes become available in the near future. In the meantime, we find that G improves to ~ 5 when target earthquakes are limited to 8 ≤ Mw < 8.5, though we cannot say anything about the possible involvement of over-fitting because we have only three such very large target earthquakes.

Download Full-text