Study on learning effect prediction models based on principal component analysis in MOOCs

2018 ◽  
Vol 22 (S6) ◽  
pp. 15347-15356
Author(s):  
Wei Zhang ◽  
Shiming Qin ◽  
Baolin Yi ◽  
Peng Tian
Keyword(s):  
Principal Component Analysis ◽  
Learning Effect ◽  
Prediction Models ◽  
Principal Component ◽  
Component Analysis

Bankruptcy Prediction Using Principal Component Analysis Based Neural Network Models

2010 ◽  
pp. 138-156
Author(s):  
G. A. Rekha Pai ◽  
G. A. Vijayalakshmi Pai
Keyword(s):  
Neural Network ◽  
Principal Component Analysis ◽  
Prediction Models ◽  
Network Models ◽  
Principal Component ◽  
Component Analysis ◽  
Bankruptcy Prediction ◽  
Financial Ratios ◽  
Neural Network Models ◽  
The Individual

Industrial bankruptcy is a rampant problem which does not occur overnight and when it occurs can cause acute financial embarrassment to Governments and financial institutions as well as threaten the very viability of the firms. It is therefore essential to help industries identify the impending trouble early. Several statistical and soft computing based bankruptcy prediction models that make use of financial ratios as indicators have been proposed. Majority of these models make use of a selective set of financial ratios chosen according to some appropriate criteria framed by the individual investigators. In contrast, this study considers any number of financial ratios irrespective of the industrial category and size and makes use of Principal Component Analysis to extract their principal components, to be used as predictors, thereby dispensing with the cumbersome selection procedures used by its predecessors. An Evolutionary Neural Network (ENN) and a Backpropagation Neural Network with Levenberg Marquardt’s training rule (BPN) have been employed as classifiers and their performance has been compared using Receiver Operating Characteristics (ROC) analyses. Termed PCA-ENN and PCA-BPN models, the predictive potential of the two models have been analyzed over a financial database (1997-2000) pertaining to 34 sick and 38 non sick Indian manufacturing companies, with 21 financial ratios as predictor variables.

scholarly journals Lymphocyte–monocyte–neutrophil index: a predictor of severity of coronavirus disease 2019 patients produced by sparse principal component analysis

2021 ◽  
Vol 18 (1) ◽  
Author(s):  
Yingjie Qi ◽  
Jian-an Jia ◽  
Huiming Li ◽  
Nagen Wan ◽  
Shuqin Zhang ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Prediction Model ◽  
Disease Severity ◽  
Prediction Models ◽  
Principal Component ◽  
Component Analysis ◽  
Sparse Principal Component Analysis ◽  
Validation Data ◽  
Severity Prediction ◽  
Prediction Efficiency

Abstract Background It is important to recognize the coronavirus disease 2019 (COVID-19) patients in severe conditions from moderate ones, thus more effective predictors should be developed. Methods Clinical indicators of COVID-19 patients from two independent cohorts (Training data: Hefei Cohort, 82 patients; Validation data: Nanchang Cohort, 169 patients) were retrospected. Sparse principal component analysis (SPCA) using Hefei Cohort was performed and prediction models were deduced. Prediction results were evaluated by receiver operator characteristic curve and decision curve analysis (DCA) in above two cohorts. Results SPCA using Hefei Cohort revealed that the first 13 principal components (PCs) account for 80.8% of the total variance of original data. The PC1 and PC12 were significantly associated with disease severity with odds ratio of 4.049 and 3.318, respectively. They were used to construct prediction model, named Model-A. In disease severity prediction, Model-A gave the best prediction efficiency with area under curve (AUC) of 0.867 and 0.835 in Hefei and Nanchang Cohort, respectively. Model-A’s simplified version, named as LMN index, gave comparable prediction efficiency as classical clinical markers with AUC of 0.837 and 0.800 in training and validation cohort, respectively. According to DCA, Model-A gave slightly better performance than others and LMN index showed similar performance as albumin or neutrophil-to-lymphocyte ratio. Conclusions Prediction models produced by SPCA showed robust disease severity prediction efficiency for COVID-19 patients and have the potential for clinical application.

106 Assessment of fecal near infrared reflectance spectroscopy to detect and monitor the reproductive status of endangered Amur and Snow leopard females

2019 ◽  
Vol 31 (1) ◽  
pp. 179
Author(s):  
M. Santos-Rivera ◽  
L. Johnson-Ulrich ◽  
A. Graham ◽  
E. Willis ◽  
A. J. Kouba ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Infrared Spectra ◽  
Near Infrared ◽  
Prediction Models ◽  
Principal Component ◽  
Component Analysis ◽  
Chemometric Analysis ◽  
Reproductive Status ◽  
Fecal Samples ◽  
Near Infrared Spectra

Feces from captive and wild carnivores can yield valuable information about an individuals’ physiological and reproductive status, diet, and ecology. Near infrared spectroscopy (NIRS) is a rapid, noninvasive, cost-efficient technique widely used in the agricultural, pharmaceutical, and chemical industries that has gained traction in diagnostic and ecological field applications for herbivore species, such as wild deer, antelope, and giant panda. The aim of this study was to test the transferability of NIRS to measuring reproductive status in feces from 2 endangered carnivore species, the Snow (Panthera uncia) and Amur (Panthera pardus orientalis) leopards. Fecal near infrared spectra analysed with multivariate statistics were used to generate prediction models for estrone-3-glucuronide (E1G) and progesterone (P4). In the E1G NIRS model, fecal samples (n=93) were obtained from 5 female leopards (3 Amur, 2 Snow) at 5 different zoo facilities, whereas for the P4 NIRS model fecal samples (n=51) from only 1 pregnant Amur leopard was available. The hormones were extracted with methanol and quantified by enzyme-linked immunosorbent assays (C. Munroe), where the sample range for E1G was 0.20-2.17 μg/g and the range for P4 was 0.06-61.89 μg/g. The near infrared spectra (350-2500nm) were acquired with an ASD FieldSpec®3 portable spectrometer (Malvern Panalytical, Malvern, UK), and the chemometric analysis was realised using the Unscrambler® X v.10.4 (CAMO Software AS, Oslo, Norway). Hormone reference values were log transformed before chemometric analysis to account for the heterogeneity of variance. Spectral pretreatment of standard normal variate was applied to the truncated wavelength range 700-240 0nm in order to remove interference from the visible region (350-700nm) due to individual diets that can confer colour variants that alter spectral signatures. Initial principal component analysis for the E1G and P4 datasets models showed >95% of the variation was explained by 4 factors, with no separation of principal component analysis scores between species or reproductive status. Quantitative prediction models using partial least-squares regression on selected wavelength ranges yielded a coefficient of determination for E1G and P4 of 0.10-0.04 and 0.35-0.19 for calibrations and validations, respectively. These near infrared models require further mathematical processing and consideration of sample variation due to diet complexity in carnivores in order to accurately assess hormone levels and monitor reproductive cycles in these species. This work was supported by USDA-ARS Biophotonics Initiative grant #58-6402-3-018.

scholarly journals Research on prediction model of thermal and moisture comfort of underwear based on principal component analysis and Genetic Algorithm–Back Propagation neural network

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Pengpeng Cheng ◽  
Daoling Chen ◽  
Jianping Wang
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Principal Component Analysis ◽  
Prediction Model ◽  
Bp Neural Network ◽  
Prediction Models ◽  
Back Propagation ◽  
Principal Component ◽  
Component Analysis ◽  
Back Propagation Neural Network

AbstractIn order to improve the efficiency and accuracy of thermal and moisture comfort prediction of underwear, a new prediction model is designed by using principal component analysis method to reduce the dimension of related variables and eliminate the multi-collinearity relationship between variables, and then inputting the converted variables into genetic algorithm (GA) and BP neural network. In order to avoid the problems of slow convergence speed and easy falling into local minimum of Back Propagation (BP) neural network, this paper adopted GA to optimize the weights and thresholds of BP neural network, and utilized MATLAB software to program, and established the prediction models of BP neural network and GA–BP neural network. To verify the superiority of the model, the predicted result of GA–BP, PCA–BP and BP are compared with GA–BP neural network. The results show that PCA could improve the accuracy and adaptability of GA–BP neural network for thermal and moisture comfort prediction. PCA–GA–BP model is obviously superior to GA–BP, PCA–BP, BP, SVM and K-means prediction models, which could accurately predict thermal and moisture comfort of underwear. The model has better accuracy prediction and simpler structure.

Assessing and solving multicollinearity in sediment transport prediction models using principal component analysis

2019 ◽  
pp. 1-11 ◽  
Author(s):  
Mohd Sofiyan Sulaiman ◽  
Manal Mohsen Abood ◽  
Shanker Kumar Sinnakaudan ◽  
Mohd Rizal Shukor ◽  
Goh Qiu You ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Sediment Transport ◽  
Prediction Models ◽  
Principal Component ◽  
Component Analysis ◽  
Transport Prediction

scholarly journals Rapid quantification of rice (Oryza sativa) qualities based on adaptive near infrared spectroscopy

2021 ◽  
Vol 922 (1) ◽  
pp. 012020
Author(s):  
R Hayati ◽  
A A Munawar ◽  
A Marliah
Keyword(s):  
Principal Component Analysis ◽  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Prediction Models ◽  
Principal Component ◽  
Component Analysis ◽  
Partial Least Square ◽  
Rice Samples ◽  
Rapid Quantification

Abstract Determination of rice quality parameters is the key factor affecting sustainable agriculture practices. The main purpose of this present study is to develop prediction models based on adaptive near infrared spectroscopy (NIRS) for rapid quantification of rice qualities in form of protein content. Rice samples were obtained from several paddy field in Aceh province with different cultivars. Near infrared spectral data of rice samples were acquired and in wavelength range from 1000 to 2500 nm and recorded as diffuse reflectance spectrum. Prediction models were established using principal component analysis (PCA), principal component analysis (PCR) and partial least square regression (PLSR). The results showed that NIRS combined with PCA can classify rice samples based on their cultivars. Moreover, this approach with PCR and PLSR can also predicted and determined protein contents with satisfactory performance achieving maximum correlation coefficient (r) of 0.81 and ratio prediction to deviation (RPD) index of 2.84 for PCR and r of 0.90 and RPD of 3.19 for PLSR respectively. Based on achieved results, it may conclude that adaptive NIRS approach can be used to quantify rice qualities rapidly and non-destructively.

P191: Can principal component analysis be used to improve fetal weight prediction models?

2003 ◽  
Vol 22 (S1) ◽  
pp. 121-121
Author(s):  
W. Lee ◽  
R. L. Deter ◽  
R. Huang ◽  
J. Espinoza ◽  
L. F. Goncalves ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Prediction Models ◽  
Principal Component ◽  
Component Analysis ◽  
Fetal Weight ◽  
Weight Prediction
Sign in / Sign up

Export Citation Format

Share Document