scholarly journals Global and Non Parametric Classification Methods Using Mathematical Morphology: Application to DNA Ploidy Measurement of Archival Solid Tumors

1996 ◽  
Vol 7 (5-6) ◽  
pp. 477-484
Author(s):  
Christophe Boudry ◽  
Michel Coster ◽  
Paulette Herlin ◽  
Brigitte Sola ◽  
Jean-Louis Chermant
Keyword(s):  
Solid Tumors ◽  
Mathematical Morphology ◽  
Dna Ploidy ◽  
Classification Methods ◽  
Parametric Classification ◽  
Non Parametric

scholarly journals Automatic Morphological Sieving: Comparison between Different Methods, Application to DNA Ploidy Measurements

1999 ◽  
Vol 18 (4) ◽  
pp. 203-210
Author(s):  
Christophe Boudry ◽  
Paulette Herlin ◽  
Benoit Plancoulaine ◽  
Eric Masson ◽  
Abderrahim Elmoataz ◽  
...  
Keyword(s):  
Neural Network ◽  
Breast Carcinoma ◽  
Brain Tumour ◽  
Mathematical Morphology ◽  
False Positive ◽  
Dna Ploidy ◽  
Automatic Classification ◽  
Classification Methods ◽  
Automatic Methods ◽  
Automatic Elimination

The aim of the present study is to propose alternative automatic methods to time consuming interactive sorting of elements for DNA ploidy measurements. One archival brain tumour and two archival breast carcinoma were studied, corresponding to 7120 elements (3764 nuclei, 3356 debris and aggregates). Three automatic classification methods were tested to eliminate debris and aggregates from DNA ploidy measurements (mathematical morphology (MM), multiparametric analysis (MA) and neural network (NN)). Performances were evaluated by reference to interactive sorting. The results obtained for the three methods concerning the percentage of debris and aggregates automatically removed reach 63, 75 and 85% for MM, MA and NN methods, respectively, with false positive rates of 6, 21 and 25%. Information about DNA ploidy abnormalities were globally preserved after automatic elimination of debris and aggregates by MM and MA methods as opposed to NN method, showing that automatic classification methods can offer alternatives to tedious interactive elimination of debris and aggregates, for DNA ploidy measurements of archival tumours.

Who needs it? Variation in experiencer marking in Estonian ‘need’-constructions

2017 ◽  
Vol 53 (04) ◽  
pp. 789-822 ◽  
Author(s):  
LIINA LINDSTRÖM ◽  
VIRVE-ANNELI VIHMAN
Keyword(s):  
Classification Methods ◽  
Case Marking ◽  
Parametric Classification ◽  
The Subject ◽  
Non Parametric

In this paper, we tackle the twin issues of obligatoriness of semantic arguments and variation in their expression through a study of Estonian constructions denoting need. The variation under investigation consists in the choice of case-marking, between adessive and allative case, as well as the option to omit the oblique argument. We extracted and coded ‘need’-constructions from spoken and written corpora and used non-parametric classification methods for analysis. We found high rates of oblique experiencer omission in these constructions (nearly 60% across corpora). The most important predictors of overt expression of the experiencer in our models were participant-internal modality and the presence of nominal complements, meaning that both semantic and syntactic factors are relevant. The choice between two overt cases is affected by person, complement type, and referential distance. Topical experiencer arguments do not show the subject-like tendency to be omitted more often, but they are more likely to be marked with adessive case, suggesting that adessive is more grammaticalised as a structural, non-nominative, argument-marking case than the more semantic allative case. Our findings show that oblique, semantic arguments may be frequently omitted, and both semantic and syntactic factors may affect variation in case-marking.

Non-Parametric Classification of Remotely Sensed Multispectral Image Data by Means of Matrix Representation of Multidimensional Histograms

1994 ◽  
Vol 6 (1) ◽  
pp. 42-50
Author(s):  
Minoru Inamura ◽  
Keyword(s):  
Parametric Method ◽  
Image Data ◽  
Remotely Sensed ◽  
Multispectral Image ◽  
Likelihood Method ◽  
Classification Rate ◽  
The Matrix ◽  
Parametric Classification ◽  
Non Parametric

The computer framing of land use maps using remotely sensed multispectral image data is identical with pattern classification for spectral reflectance of objects on earth's surface. In particular, the classification by the maximum likelihood method is the most popular method because it theoretically gives the highest correct classification rate on the condition that the statistical distribution of the image data be normal. However, the histogram of real image data is not a normal distribution. Actual histograms show the proper distributions to classes. This fact means that a histogram gives a spatial property of the class statistically. This paper described a newly developed non-parametric method by means of the matrix representations of multidimensional histograms and subimages.

scholarly journals PERBANDINGAN ANTARA METODE CART (CLASSIFICATION AND EGRESSION TREE) DAN REGRESI LOGISTIK (LOGISTIC REGRESSION) DALAM MENGKLASIFIKASIKAN PASIEN PENDERITA DBD (DEMAM BERDARAH DENGUE)

2018 ◽  
Vol 15 (1) ◽  
pp. 98-107
Author(s):  
R Lestawati ◽  
Rais Rais ◽  
I T Utami
Keyword(s):  
Logistic Regression ◽  
Statistical Methods ◽  
Parametric Method ◽  
Parametric Methods ◽  
Classification Methods ◽  
Classification Result ◽  
The Status ◽  
Classification Table ◽  
Non Parametric

Classification is one of statistical methods in grouping the data compiled systematically. The classification of an object can be done by two approaches, namely classification methods parametric and non-parametric methods. Non-parametric methods is used in this study is the method of CART to be compared to the classification result of the logistic regression as one of a parametric method. From accuracy classification table of CART method to classify the status of DHF patient into category of severe and non-severe exactly 76.3%, whereas the percentage of truth logistic regression was 76.7%, CART method to classify the status of DHF patient into categories of severe and non-severe exactly 76.3%, CART method yielded 4 significant variables that hepatomegaly, epitaksis, melena and diarrhea as well as the classification is divided into several segmens into a more accurate whereas the logistic regression produces only 1 significant variables that hepatomegaly

Sign in / Sign up

Export Citation Format

Share Document