Classification of Cotton Wool Spots Using Principal Components Analysis and Support Vector Machine

2018 ◽  
Author(s):  
Syna Sreng ◽  
Noppadol Maneerat ◽  
Khin Yadanar Win ◽  
Kazuhiko Hamamoto ◽  
Ronakorn Panjaphongse
Keyword(s):  
Support Vector Machine ◽  
Principal Components Analysis ◽  
Principal Components ◽  
Support Vector ◽  
Cotton Wool ◽  
Cotton Wool Spots ◽  
Components Analysis

Raman spectral analysis of nasopharyngeal carcinoma cell line CNE2 after microwave radiation

2013 ◽  
Vol 91 (2) ◽  
pp. 67-71 ◽  
Author(s):  
Yuhuang Ye ◽  
Yang Chen ◽  
Ying Su ◽  
Changyan Zou ◽  
Yangwen Huang ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Raman Spectroscopy ◽  
Nasopharyngeal Carcinoma ◽  
Microwave Radiation ◽  
Principal Components ◽  
Carcinoma Cell ◽  
Support Vector ◽  
Components Analysis ◽  
Raman Spectral ◽  
Radiation Time

This study aimed to study the effects of microwave radiation on the nasopharyngeal carcinoma cell line CNE2 by Raman spectroscopy. The cells were separated into a control group and radiated groups with radiation times of 2, 5, 10, and 25 min, respectively. Both principal components analysis and support vector machine were employed for statistical analysis of Raman spectra. The results show that the relative content of C-H deformation and amide I begin to change when the radiation time is over 10 min, and principal components analysis further confirms there are significant differences after 10 min of radiation. Moreover, support vector machine is simultaneously used to classify radiated samples from control samples. The classification accuracy is low until the radiation time reaches over 10 min. In conclusion, this study reveals the Raman spectral characteristics of CNE2 under different microwave radiation exposure timesand demonstrates Raman spectroscopy can be a potential method to explore cellular characterization after radiation. The final results may help in elucidating the mechanism by which microwave radiation interacts with tumor cells.

Bloodless Technique to Detect Diabetes using Soft Computational Tool

2015 ◽  
pp. 139-158
Author(s):  
Puspalata Sah ◽  
Kandarpa Kumar Sarma
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Support Vector Machine ◽  
Support Vector ◽  
Cotton Wool ◽  
Research Issue ◽  
Important Research ◽  
Cotton Wool Spots ◽  
Essential Components ◽  
Soft Computing Techniques

Detection of diabetes using bloodless technique is an important research issue in the area of machine learning and artificial intelligence (AI). Here we present the working of a system designed to detect the abnormality of the eye with pain and blood free method. The typical features for diabetic retinopathy (DR) are used along with certain soft computing techniques to design such a system. The essential components of DR are blood vessels, red lesions visible as microaneurysms, hemorrhages and whitish lesions i.e., lipid exudates and cotton wool spots. The chapter reports the use of a unique feature set derived from the retinal image of the eye. The feature set is applied to a Support Vector Machine (SVM) which provides the decision regarding the state of infection of the eye. The classification ability of the proposed system for blood vessel and exudate is 91.67% and for optic disc and microaneurysm is 83.33%.

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.

Quantitative Phenotyping and Discriminant Analysis Improve Scoring Classification in Late B-Lymphoproliferative Disorders.

Blood ◽  
2005 ◽  
Vol 106 (11) ◽  
pp. 1463-1463
Author(s):  
Georges Jung ◽  
Sylvie Thiebault ◽  
Jean-Claude Eisenmann ◽  
Eckart Wunder ◽  
Marie Haas ◽  
...  
Keyword(s):  
Discriminant Analysis ◽  
Principal Components Analysis ◽  
Principal Components ◽  
Scoring System ◽  
Low Grade ◽  
Surface Markers ◽  
Correct Classification ◽  
Chi Square ◽  
Components Analysis

Abstract Multivariate analysis classification of chronic lymphocytic leukemia (CLL) and lymphoma (non-CLL) disorders is investigated in 299 patients by an extended panel of surface markers, and compared with Matutes classical scoring proposal. Diagnosis was based on clinical features, cell morphology, node or bone marrow histology, and immunological scoring system. Results are obtained on directly labeled tumoral cells by flow cytometry gating. Patients included 154 CLL, 2 Richter transformation, and 143 lymphoma (26 follicular, 49 lymphocytic, 18 other low-grade, 7 Waldenström macroglobulinemia, 13 mantel, 11 diffuse large-cell, 6 Burkitt, 4 marginal zone-cell, 5 hairy-cell leukemia, 2 MALT, 1 prolymphocytic leukemia, 1 SLVL). For CD43, FMC7, CD23, CD5, CD79b (% stained cells) and CD20, CD22 surface antigen intensities Chi-Square values indicate very high probability of correct classification (varing from 621 to 94.9; p<0.0000). If, alternatively, % of CD22, CD20, CD19 and intensities of CD79b, CD5, CD19, CD43, CD23 and kappa/lamba chains are employed, Chi-Square yields values of lower significance (varing from 65 to 0.1; p<0.0000 to 0.6573). Using classical panel scoring with CD79b, 82.4 % of patients were correctly classified, compared to 84.5% after replacing CD79b by CD22 intensity. If CD43 is added, correct classification increased to 89.6% and 88.1% of patients, respectively; this improvement is due to better allocation of CLL. In discriminant analysis 91.3% of patients are correctly classified with the panel including CD79b, and 90.9% with CD22 intensity. CD43 enhances the allocation of either one to 94.3%. Using our previous discriminant analysis with CD79b (Jung G, et al. Br J Haematol.2003; 120:496–499), this blind analysis correctly classified the population in 87.1%, compared to 91.3% with the new one. By adding CD43, it moved from 92.4% up to 94.3%. In order to find the optimal combination of the selected best markers, a stepwise probit discrimination was performed. Using CD43 and FMC7 yields a correct classification of 90.3%; after addition of CD5, CD79b, CD23, and CD22 intensity, efficiency increased to 94.6%. Further added markers don’t improve classification. Efficiency of this panel was further confirmed by hierarchical cluster and principal components analysis. Cluster analysis with squared Euclidian distances separated CLL from non-CLL patients with low overlaps: 86.6% of cases are correctly identified. Separated points in the plot representing patients with CLL and non-CLL, obtained by principal components analysis of surface markers, confirm the high predictive potential of this panel. The same analysis of surface marker positions for non-CLL suggests use of: % of CD79b, FMC7, and CD22 intensity, and for CLL: % of CD5, CD23, CD43. So, the addition of CD43 improves as well the discriminant function as the scoring system. Our selected panel of best markers is useful in distinguishing CLL from non-CLL and offers a better distinction by discriminant analysis. Furthermore quantitative expression of each marker and its predictive value improve diagnosis and classification.

Application of Principal Components Analysis for Evaluation and Classification of Complex Emg Data

2002 ◽  
Vol 46 (13) ◽  
pp. 1147-1151
Author(s):  
Miguel A. Perez ◽  
Maury Nussbaum
Keyword(s):  
Principal Components Analysis ◽  
Principal Components ◽  
Injury Risk ◽  
Hypothesis Generation ◽  
Trunk Muscles ◽  
Lower Trunk ◽  
Biomechanical Models ◽  
Straightforward Method ◽  
Components Analysis

Many biomechanical models used to produce injury risk estimates for the lower trunk require lower trunk muscle forces as inputs. These forces are typically estimated through the use of surface electromyography (sEMG). The variability inherent in sEMG measurements can, and should, be analyzed to determine the possible presence and sources of excessive variation in the data. Principal components analysis (PCA) provides a robust and straightforward method for performing an analysis of the variability of complex sEMG datasets. This paper describes the results obtained from the application of PCA to a dataset consisting of activation levels for several lower trunk muscles. The results demonstrate the value of the technique in identifying clusters of observations in the data and in simplifying the multidimensional dataset. The use of PCA as a hypothesis generation tool is also explored.

Sign in / Sign up

Export Citation Format

Share Document