Wyniki wyszukiwania - BazTech

1

Could k-NN classifier be Useful in tree leaves recognition?

Horaisová K.

Archives of Control Sciences

|

2014

|

Vol. 24, no. 2

177--192

EN

This paper presents a method for affine invariant recognition of two-dimensional binary objects based on 2D Fourier power spectrum. Such function is translation invariant and their moments of second order enable construction of affine invariant spectrum except of the rotation effect. Harmonic analysis of samples on circular paths generates Fourier coefficients whose absolute values are affine invariant descriptors. Affine invariancy is approximately saved also for large digital binary images as demonstrated in the experimental part. The proposed method is tested on artificial data set first and consequently on a large set of 2D binary digital images of tree leaves. High dimensionality of feature vectors is reduced via the kernel PCA technique with Gaussian kernel and the k-NN classifier is used for image classification. The results are summarized as k-NN classifier sensitivity after dimensionality reduction. The resulting descriptors after dimensionality reduction are able to distinguish real contours of tree leaves with acceptable classification error. The general methodology is directly applicable to any set of large binary images. All calculations were performed in the MATLAB environment.

2

Analysis of matrix metalloproteinases (MMPs) in cerebrospinal fluid of patients with amyotrophic lateral sclerosis (ALS)

Sokołowska B., Jóźwik A., Niebroj-Dobosz I., Janik P., Kwieciński H.

Journal of Medical Informatics & Technologies

|

2009

|

Vol. 13

147--150

EN

Matrix metalloproteinases (MMPs) are implicated in the pathogenesis of motor neuron degeneration in amyotrophic lateral sclerosis (ALS) and might be potential markers of diagnosis, prognosis and monitoring treatment effects. The aim of the present study was evaluation of the MMPs significance in cerebrospinal fluid (CSF MMPs) of patients with ALS in relation to severity of the disease. Metalloproteinases MT-MMP-1, MMP-2, MMP-9 and additionally age of subjects and disease duration were analyzed. The results demonstrate that the error of differentiation between healthy subjects and ALS patients (for MMP-2 feature) as well as between mild and severe ALS states (for CSF MMPs set) equalled to 0.033. In conclusion, the pattern recognition approach may be useful for differentation of ALS progressing on the basis of CSF MMPs features.

3

Pattern recognition approach to differentiation of disease severity in patients with amyotrophic lateral sclerosis

Jóźwik A., Sokołowska B., Niebroj-Dobosz I., Janik P., Kwieciński H.

Journal of Medical Informatics & Technologies

|

2008

|

Vol. 12

143--147

EN

A possibility of recognition of the clinical status of patients with amyotrophic lateral sclerosis (ALS) in relation to severity of the disease was investigated. Three groups: (i) healthy controls (n=15) and two subgroups of ALS patients (ii) mild (n=15) and (iii) severe (n=15) were considered as classes. Four features of the subjects: (i) their age (AGE) (ii) erythropoietin concentration in serum (SERUM), (iii) in cerebrospinal fluid (CSF), and (iv) duration time of the disease (Tdis) were used for classifier construction based on the k Nearest Neighbours (k-NN) rule, known from pattern recognition theory. The presented results demonstrate that the pattern recognition approach may be useful for the evaluation of the severity of the ALS disease.

4

Application of the k-NN classifier for mutagenesis tests. Recognition of wild type and defective in DNA repair bacterial strains on the basis of adaptive response to alkylating agents

Maciejewska A. M., Jóźwik A., Kuśmierek J. T., Sokołowska B.

Biocybernetics and Biomedical Engineering

|

2008

|

Vol. 28, no. 3

45-50

EN

The k-Nearest Neighbor classifier (k-NN) was applied to differentiate two bacterial strains, the wild type and its mug derivative. Bacterial cells were exposed to different concentrations of chloroacetaldehyde and studied under two different conditions, i.e. with and without induction of an adaptive response. We evaluated the influence of adaptation on the wt and mug strains by estimating the probability of misclassification to the class: no adaptation or adaptation. We have also checked differentiation between wt and mug, separately for adapted and non-adapted conditions. Our results confirm the usefulness of the k-NN classifier as a tool for statistical analysis of results of mutagenesis tests.

5

Application of k-NN classifier and Fisher-test in analysis of cells culture model

Jóźwik A., Faff L., Sokołowska B.

Journal of Medical Informatics & Technologies

|

2000

|

Vol. 1

CS 15--20

EN

The paper deals with determination of the LPS factor influence and the significance of Na+ -contained and Na+ -free HEPES solution on a behavior of microglial cells cultured in vitro. A behavior of microglial cells is characterized by 14 parameters. The dependence between these parameters and a presence of LPS factor or natrium ions has been studied by use of the “k nearest neighbor” (k-NN) rule taken from the pattern recognition theory. The obtained computational results were verified by the Fisher test.