Intrusion Detection Model Based on Support Vector Regression and Principal Components Analysis

2009 ◽  
Author(s):  
WenJie Tian ◽  
JiCheng Liu
Keyword(s):  
Intrusion Detection ◽  
Support Vector Regression ◽  
Principal Components Analysis ◽  
Principal Components ◽  
Support Vector ◽  
Detection Model ◽  
Model Based ◽  
Components Analysis

scholarly journals Avaliando aprendizado de máquina na previsão de curto prazo de séries temporais de energia solar

2021 ◽  
Vol 13 (2) ◽  
pp. 105-112
Author(s):  
Naylene Fraccanabbia ◽  
Viviana Cocco Mariani
Keyword(s):  
Neural Network ◽  
Support Vector Regression ◽  
Principal Components Analysis ◽  
Linear Model ◽  
Principal Components ◽  
Generalized Linear Model ◽  
Support Vector ◽  
Components Analysis

Fontes alternativas de energia estão se tornando cada vez mais frequentes, tendo como objetivo reduzir a poluição ambiental, além de serem ideais para superar a crise energética, logo, neste contexto, a energia solar se destaca por ser abundante. Devido ao alto nível de incerteza dos fatores que interferem diretamente na geração de energia solar, como temperatura e radiação solar, realizar previsões de energia solar com alta precisão é um desafio. Assim, o objetivo deste artigo é desenvolver um modelo de previsão por meio de séries temporais que possibilite prever a produção de energia solar, para 1, 3 e 6 passos à frente, enfatizando a potencialidade da rede neural, utilizando um banco de dados de uma usina fotovoltaica localizada no Uruguai. Para o desenvolvimento da proposta, técnicas de pré-processamento e os métodos de previsão regressão de vetores de suporte (Support Vector Regression, SVR), rede neural perceptron multicamadas com regularização bayesiana (Bayesian Regularized Neural Network, BRNN) e modelo linear generalizado (Generalized Linear Model, GLM) foram combinados. Por fim, tais combinações foram comparadas usando medidas de desempenho. Notou-se que a combinação da análise de componentes principais (Principal Components Analysis - PCA) e a Rede Neural Perceptron Multicamadas com Regularização Bayesiana obteve os melhores resultados, utilizando as três medidas de desempenho.

A Statistical Machine Learning Model to Predict Equivalent Circulation Density ECD while Drilling, Based on Principal Components Analysis PCA

2021 ◽  
Author(s):  
Ahmed AlSaihati ◽  
Salaheldin Elkatatny ◽  
Hani Gamal ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Machine Learning ◽  
Principal Components Analysis ◽  
Principal Components ◽  
Regularization Parameter ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Linear Kernel ◽  
Svm Model ◽  
Components Analysis ◽  
Testing Set

Abstract Mathematical equations, based on conservation of mass and momentum, are used to determine the ECD at different depths in the wellbore. However, such equations do not consider important factors that have a influence on the ECD such as: (i) bottom hole temperature, (ii) pipe rotation and eccentricity, and (iii) wellbore roughness. Thus, discrepancy between the calculated ECDs and actual ones has been reported in the literature. This paper aims to explore how artificial intelligence (AI) and machine learning (ML) could provide real-time accurate prediction of the ECD, to have more insight and management of wellbore downhole conditions. For this purpose, a supervised ML algorithm, support vector machine (SVM), based on principal components analysis (PCA), was developed. Actual field data of Well-1 including drilling surface parameters and ECDs, measured by downhole sensors, were collected to develop a classical SVM model. The dataset was split with an 80/20 training-testing data ratio. Sensitivity analysis with different SVM parameters such as regularization parameter C, gamma, kernel type (linear, radial basis function "RBF") was performed. The performance of the model was assessed in terms of root mean square error (RMSE) and coefficient of determination (R2). Afterward, PCA was applied to the dataset of Well-1 to develop an SVM model using the transformed dataset in PCA space. The performance of the model while using different numbers of principal components was evaluated. The results showed that the classical SVM with the linear kernel predicted the ECD with RMSE of 0.53 and R2 of 0.97 in the training set, while RMSE and R2 were 0.56 and 0.97 respectively in the testing set. The PCA-based SVM model, with the linear kernel and four principal components (93.53% variation of the dataset), predicted the ECD with RMSE 0.79 and R2 of 0.95 in the testing set.

A Comparison of Two Quantitative Methods of Analysing Thyroid Dynamic Studies in Nuclear Medicine

1979 ◽  
Vol 65 (1) ◽  
pp. 29-32
Author(s):  
A. S. Houston ◽  
N. R. Thorpe
Keyword(s):  
Nuclear Medicine ◽  
Principal Components Analysis ◽  
Principal Components ◽  
Quantitative Methods ◽  
Physiological Model ◽  
Small Sample ◽  
Good Separation ◽  
Model Based ◽  
Dynamic Studies ◽  
Components Analysis

AbstractTwo quantitative methods of analysing thyroid dynamic studies using 99mTc O-4 are compared for 33 patients (22 euthyroid, 8 hyperthyroid and 3 hypothyroid). A physiological model based on pertechnetate uptake by the thyroid is compared with principal components analysis. Both methods gave good separation between euthyroid and hvperthyroid in all but one case, while the separation between euthyroid and hypothyroid, although based on a small sample, appeared to be better for principal components analysis.

Sign in / Sign up

Export Citation Format

Share Document