Adaptive classification of two-dimensional gel electrophoretic spot patterns by neural networks and cluster analysis

1997 ◽  
Vol 18 (15) ◽  
pp. 2749-2754 ◽  
Author(s):  
Jiří Vohradský
2018 ◽  
Vol 174 ◽  
pp. 04007 ◽  
Author(s):  
Tomasz Nowobilski ◽  
Irena Bagińska ◽  
Krzysztof Gawron

The article classifies Polish voivodeships into appropriate groups with a similar level of occupational safety in the construction industry. The basis for the adopted classification was statistical data published by the Central Statistical Office regarding population, employment in the construction industry, the value of construction production and the number of occupational accidents. The conducted research allowed a logical and correct, in terms of content, division of the Polish territory to be made, taking into account the aspect of occupational safety in the construction industry. Statistica software and cluster analysis were used to solve the problem.


2003 ◽  
Vol 57 (1) ◽  
pp. 14-22 ◽  
Author(s):  
Lin Zhang ◽  
Gary W. Small ◽  
Abigail S. Haka ◽  
Linda H. Kidder ◽  
E. Neil Lewis

Cluster analysis and artificial neural networks (ANNs) are applied to the automated assessment of disease state in Fourier transform infrared microscopic imaging measurements of normal and carcinomatous immortalized human breast cell lines. K-means clustering is used to implement an automated algorithm for the assignment of pixels in the image to cell and non-cell categories. Cell pixels are subsequently classified into carcinoma and normal categories through the use of a feed-forward ANN computed with the Broyden–Fletcher–Goldfarb–Shanno training algorithm. Inputs to the ANN consist of principal component scores computed from Fourier filtered absorbance data. A grid search optimization procedure is used to identify the optimal network architecture and filter frequency response. Data from three images corresponding to normal cells, carcinoma cells, and a mixture of normal and carcinoma cells are used to build and test the classification methodology. A successful classifier is developed through this work, although differences in the spectral backgrounds between the three images are observed to complicate the classification problem. The robustness of the final classifier is improved through the use of a rejection threshold procedure to prevent classification of outlying pixels.


2007 ◽  
Vol 38 (3) ◽  
pp. 303-314 ◽  
Author(s):  
K. Srinivasa Raju ◽  
D. Nagesh Kumar

The present study deals with the application of cluster analysis, Fuzzy Cluster Analysis (FCA) and Kohonen Artificial Neural Networks (KANN) methods for classification of 159 meteorological stations in India into meteorologically homogeneous groups. Eight parameters, namely latitude, longitude, elevation, average temperature, humidity, wind speed, sunshine hours and solar radiation, are considered as the classification criteria for grouping. The optimal number of groups is determined as 14 based on the Davies–Bouldin index approach. It is observed that the FCA approach performed better than the other two methodologies for the present study.


2021 ◽  
Vol 59 (4) ◽  
pp. 330-339
Author(s):  
M.D.C. Toro ◽  
M.A. Antonio ◽  
M.G. Alves Dos Reis ◽  
M.S. de Assumpcao ◽  
E. Sakano

Background: Chronic Rhinosinusitis is currently classified into eosinophilic and non-eosinophilic, according to the histologic quantification of the number of eosinophils in nasal mucosa biopsy. There is a lack of unanimous histopathologic criteria and methodology for this classification and no consensus regarding a cut-off point for Eosinophils per High power field. Methodology: A systematic electronic search was performed on BVS, PUBMED, PUBMED PMC, SCOPUS, WEB OF SCIENCE, EMBASE, COCHRANE and PROQUEST databases looking for studies that reported a cut point for classification of Eosinophilic Chronic Rhinosinusitis (eCRS), and data concerning methodology of classification was extracted. Results: We identified 142 studies that reported 29 different cut-off values for classification of eCRS, and different methods of histologic analysis. Out of these studies 13 reported their own methodology to establish the cut-off point, and used different reference standards as polyp recurrence, asthma and allergy, immunocytochemistry, quality of life index, standard deviation of the control population and cluster analysis. Conclusions: Further studies are needed to determine a precise cut-off point, especially international multicentered cluster analysis. Moreover, methodologic standardization of biopsy and analysis is needed to certify comparable results. Multiple biopsy sites, densest cellular infiltration area examination and oral steroids restriction at least four weeks before sampling are advisable.


Sign in / Sign up

Export Citation Format

Share Document