A comparative study of K-Nearest Neighbour, Support Vector Machine and Multi-Layer Perceptron for Thalassemia screening

Amendolia, S. R.; Cossu, Gianfranco; Ganadu, Maria Luisa; Golosio, Bruno; Masala, G. L.; Mura, Giovanni Maria

doi:10.1016/s0169-7439(03)00094-7

Cited by 147 publications

(73 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Primarily, the class models in SIMCA are calculated with the aim of describing variation within each class: when PCA is applied on each category, it finds the directions of maximum variance in the class space. Consequently, no attempt is made to find directions that 50(4) 2015 Identification of Edible vegetable oils by spectroscopy and chemometricseparate classes, on the opposite of, for example, partial least squares discriminant analysis (PLS-DA), which directly models the classes on the basis of the descriptors (Marengo et al, 2006) Support vector machines (SVMs) have been developed by Vapnik (Vapnik, 1998) and details about SVM classifier can be found in literature (Amendolia et al, 2003;Cristianini and Shawe-Taylor, 2000). SVM is also showing high performances in practical applications.…”

Section: Theorymentioning

confidence: 99%

See 1 more Smart Citation

ATR-FTIR spectroscopy and chemometric techniques for the identification of edible vegetable oils

Karim

Rana

et al. 2015

Bangladesh J. Sci. Ind. Res.

View full text Add to dashboard Cite

There is a large variety and trademarks of vegetable oils in Bangladesh. The oils have characteristics very similar to each other and often cannot be classified by the observation of color, odor or taste. This paper proposes a vibrational spectroscopic method like FTIR in association with chemometric techniques to classify vegetable oils like: sunflower, mustard, sesame, soybean, castor, olive and palm oils from different manufacturers. In the FTIR spectra of oil, as information about fatty acid composition is concentrated in the range of 4400-200 cm-1 principal component analysis (PCA) was applied on the standardized full FTIR spectral data of this region for vegetable oils to totally capture the FTIR spectral pattern; seven varieties of vegetable oils could be successfully classified from their PCA scores. PCA of FTIR spectra of different known vegetable oils is used to determine the identity of several unknown vegetable oils. The unknowns are then analyzed, plotted, and identified based on their proximity to the known in principal component space. For the multivariate analysis PCA and soft independent modeling of class analogy (SIMCA) and support vector machines (SVMs) were used. 85% and 14% variability of data was explained by PC1 and PC2 respectively. PC1 has strong positive correlation with soybean, sunflower, palm and olive oil while strong negative correlation with mustard, castor and sesame oil. Soybean oils are positively and sesame oils are negatively correlated with PC2. Unknown oil samples can be identified properly by used supervised methods i.e. SIMCA, SVM by developing model with the help of PCA. The major interest of this method using chemometric analysis of spectral data is in their rapidity, since no chemical treatment of samples is required.

show abstract

Section: Theorymentioning

confidence: 99%

“…Support vector machines map input vectors to a higher dimensional space where a maximal separating hyper plane is constructed (Amendolia et al, 2003;Cristianini and Shawe-Taylor, 2000). Two parallel hyper planes are constructed on each side of the hyper plane that separates the data.…”

Section: Theorymentioning

confidence: 99%

ATR-FTIR spectroscopy and chemometric techniques for the identification of edible vegetable oils

Karim

Rana

et al. 2015

Bangladesh J. Sci. Ind. Res.

View full text Add to dashboard Cite

show abstract

“…Amendolia e t al. [16] have compared k-NN, SVM and ANN for talasemi detection by using accuracy criterion. This test has been done for real data and the results obtained from the test show that ANN acts better than the other two methods.…”

Section: Related Work; Background and Motivationmentioning

confidence: 99%

“…Among the other criteria for comparing classification methods, G-means [14], RMSE [4,15] and Accuracy [6,16] can be mentioned.…”

Section: Introductionmentioning

confidence: 99%

An experimental investigation of the effect of discrete attributes on the precision of classification methods

Entezari‐Maleki

Iranmanesh

Minaei-Bidgoli

2009

2009 International Conference on Information and Communication Technologies

View full text Add to dashboard Cite

Abstract:In this paper, the precision of logistic regression, naïve-Bayes and linear data classification methods, with regard to the Area Under Curve (AUC) metric have been compared. The effect of the parameters including size of the dataset, kind of the independent attributes, number of the discrete attributes and their values have been investigated. From the results, it can be concluded that in datasets consisting of both discrete and continuous attributes, the AUC of the three mentioned classifiers are the same. With increasing the number of the discrete attributes, the AUC of logistic regression is increased and the precision related to this classifier become more than the other two classifiers. Also considering the impact of the discrete attributes it can be seen that with increasing the number of values in discrete attributes the AUC related to the logistic regression classifier increases and linear classifier's AUC decreases, but the AUC of the naïve-Bayes classifier remains constant. Therefore, the results of this research can help data miners in selecting the most efficient classifier by considering the characteristics of the datasets.

show abstract

“…Amendolia et al showed Thalassemia screening indicators by using the Principal Components Analysis (PCA) where the selected features are RBC, Hb, Ht and MCV. They compared the study of K-Nearest Neighbor, Support Vector Machine and Multi-Layer Perceptron for Thalassemia screening [9].…”

Section: Introductionmentioning

confidence: 99%

The Knowledge Discovery of β-Thalassemia Using Principal Components Analysis: PCA and Machine Learning Techniques

Paokanta¹

2011

IJEEEE

View full text Add to dashboard Cite

Abstract-Feature Selection plays an important role in many areas especially in classification tasks. It is also an important pre-treatment for every classification process and not only decreases the computational time and cost, but selecting an appropriate variable also increases the classification accuracy. In this research, the comparison of classification performance of machine learning techniques using Principal Components Analysis (PCA) for screening the genotypes of β-Thalassemia patients will be proposed.

show abstract

A comparative study of K-Nearest Neighbour, Support Vector Machine and Multi-Layer Perceptron for Thalassemia screening

Cited by 147 publications

References 7 publications

ATR-FTIR spectroscopy and chemometric techniques for the identification of edible vegetable oils

ATR-FTIR spectroscopy and chemometric techniques for the identification of edible vegetable oils

An experimental investigation of the effect of discrete attributes on the precision of classification methods

The Knowledge Discovery of β-Thalassemia Using Principal Components Analysis: PCA and Machine Learning Techniques

Contact Info

Product

Resources

About